AmstatNews

Subscribe to AmstatNews feed
Updated: 10 min 22 sec ago

Beyond AP Statistics Workshop Held in Conjunction with JSM

Sun, 10/01/2017 - 7:00am
Rebecca Nichols, ASA Director of Education, and Roxy Peck, BAPS Program Chair

    The American Statistical Association/National Council of Teachers of Mathematics Joint Committee on Curriculum in Statistics and Probability sponsored a Beyond AP Statistics (BAPS) workshop at the annual Joint Statistical Meetings in Baltimore August 3. The BAPS workshop is offered for experienced AP Statistics teachers and consists of enrichment material just beyond the basic AP curriculum.

    This year, 29 teachers came to Baltimore for a full-day workshop designed to strengthen and expand teachers’ statistics backgrounds. The brainchild of former ASA/NCTM Joint Committee Chair Jim Matis, BAPS has been offered at JSM for nearly two decades.

    This year’s BAPS workshop, organized by Roxy Peck of Cal Poly, was divided into four sessions led by the following statisticians:

    • Tom Short of West Chester University
      Analysis of Variance (ANOVA)
    • Allan Rossman and Beth Chance of Cal Poly, San Luis Obispo
      Probability Models
    • Jessica Utts of the University of California, Irvine
      Multiple Regression
    • James Cochran of the University of Alabama
      Teaching with Cases

    ASA Executive Director Ron Wasserstein and ASA Vice President Kathy Ensor welcomed the workshop participants. Washington Statistical Society president Linda Young and other chapter members also welcomed the BAPS attendees and spent time networking with them during breakfast and lunch.

    Participants were given a pass to attend the exhibit hall at the Joint Statistical Meetings and a certificate of participation from the American Statistical Association certifying professional development hours. Optional 0.5 graduate credit hours was also available through Adams State University. Some BAPS participants opted to also attend the high-school sessions of the Meeting Within a Meeting Statistics Workshop for Math and Science Teachers on August 2.

    Chapters and members are encouraged to connect with local AP Statistics teachers and middle- and high-school mathematics and science teachers. Questions should be directed to Rebecca Nichols, ASA director of education.

    Professional Development: What Does the ASA Offer?

    Fri, 09/01/2017 - 7:00am
    Rick Peterson, ASA Professional Development and Chapters & Sections Manager

      You have an idea for a website. You spend hours upon hours on design, navigation, and content. Finally, after all your work, you think the website is ready for public consumption and it goes live. What happens shortly thereafter? The website starts becoming obsolete. Unless the content of the website is consistently updated, people will no longer return because they see no reason to.

      The same is true of your career in statistics. Unless you are keeping up to date with new knowledge, skills, and personal qualities to be successful in the practice of statistics through professional development (PD), you will become obsolete, too. If you’re not moving forward, you’re falling behind.

      The ASA offers many PD programs to help advance your career. The most prominent of these are the conferences the ASA sponsors. The Joint Statistical Meetings (JSM) is one of the largest statistical events in the world, featuring 3,000 individual presentations on just about any topic one can think of. In addition to the technical sessions, there are around 30 continuing education short courses and a dozen computer technology workshops. Short courses are also offered at the Conference on Statistical Practice (CSP), the ASA Biopharmaceutical Section Regulatory-Industry Statistics Workshop, the Women in Statistics and Data Science Conference, and the International Conference on Establishment Surveys.

      If you prefer that PD comes to you, ASA chapters organize conferences and workshops all over North America, including the Council of Chapters’ traveling courses. Don’t want to leave the house or office? The ASA hosts 20–30 web-based seminars each year on a variety of topics.

      An often overlooked component of professional development are personal skills related to being a professional statistician. Effective communication, collaboration, leadership, and influence can be as vital as technical skills to one’s career. Since 2014, the ASA has offered personal skills development courses and workshops at the Joint Statistical Meetings and Conference on Statistical Practice. Emphasis is placed on interacting and communicating with nonstatisticians such as clients and decisionmakers in an organization. As ASA President Barry Nussbaum likes to say, “It’s not what we said, it’s not what they heard, it’s what they say they heard.”

      For a more personalized approach, don’t forget about the ASA’s mentoring programs. There are mentoring programs at conferences such as JSM and CSP and through ASA sections and chapters.

      Professional development details can be found under the “Your Career” tab of the ASA website.

      Interview with Dennis Pearl

      Fri, 09/01/2017 - 7:00am
      Allan Rossman, Cal Poly

        This interview with Dennis Pearl, conducted by Allan Rossman of Cal Poly, originally appeared in the open-access Journal of Statistics Education, volume 25, issue 1. Read it in its entirety.

        Dennis Pearl is professor of statistics at The Pennsylvania State University and director of the Consortium for the Advancement of Undergraduate Statistics Education (CAUSE). He is a fellow of the American Statistical Association. This interview took place via email November 18–29, 2016.

        AR: Thanks very much, Dennis, for agreeing to this interview for the Journal of Statistics Education (JSE). Let’s start with the 18-year-old version of you. Where were you then, and what were your thoughts about education and career goals at that point?

        DP: That would be 1969. I was a sophomore at Berkeley, protesting the Vietnam War and discovering I was no longer the smartest guy in the class like I was used to being in high school. I had a terrific AP calculus teacher in high school and figured I’d be a math major, go on to graduate school, and become a math professor. Unfortunately, I had a pretty boring instructor in my linear algebra class at Berkeley, and the same guy was going to teach the next course in the series, so I decided to shop for something else. My brother was a senior there and convinced me to take an introductory statistics class with him taught by Erich Lehmann. By the second week, I was hooked! My math classes were about understanding elegance, while statistics was about understanding evidence, and it just seemed the world needed more people who could do the latter.

        At that point, I didn’t think much about education except noting which qualities I liked in an instructor and which I didn’t. I liked organized professors like Lehmann, witty professors like Elizabeth Scott, professors who kept their class involved in discussions like David Freeman, professors who had the class construct their own knowledge like Jerzy Neyman, and friendly professors like Kjell Doksum. Then, there was David Blackwell, who was in a class by himself, as the quintessential explainer of complex things and who also had all of the traits mentioned above. The Berkeley Statistics Department had a lot of great teachers, and all of them gave me a feel for the relevance of the subject. I had the opposite feelings about the math instructors I encountered and so I became a statistics major.

        AR: My, that’s quite a list of professors you had as an undergraduate. What did you do after you earned your bachelor’s degree, and how did you make that decision?

        Back Row: George Cobb, Allan Rossman, Roger Hoerl; Middle Row: Beth Chance, Mary Parker, Deb Rumsey, Jeff Witmer, Bill Notz, Gale Rex Bryce; First Row: Joan Garfield, Paul Stephenson, Dennis Pearl, Rog Woodard

        DP: Oops—I only had Neyman as a grad student—but his teaching style was unique. He just stayed seated and asked random students to go to the board and work things out. If you were lost, he called on someone else—but after a few sessions, every student worked like crazy to be prepared!

        At the end of spring quarter in 1971, I had the units to graduate and I had no doubt I was going to grad school in statistics—but felt like I needed to slow down and possibly take some time off (I had only just turned 20 years old.). So, I postponed my graduation until after fall quarter and luckily was selected to take part in a National Science Foundation (NSF)-supported research program organized by an engineering professor, which turned out to be a life-changing experience.

        It involved eight senior undergrads: two from math, two from statistics, two from engineering, and two from ecology. Our task was to model fire and its effects. We had access to four farmers in California who were doing controlled burns on their property. The math students worked out differential equations on how the fire might spread; my teammate and I in statistics designed the experiments to collect data, and then worked to analyze it; the engineering students devised the instrumentation to measure stuff; and the ecology students made predictions about the effects on the non-plant organisms in the burn area.

        At the end of the summer, I was picked to go to the national AAAS meetings in Philadelphia to present our findings, where I heard talks by Carl Sagan and met Margaret Mead. That summer, I stopped thinking about statistics as a branch of mathematics and realized that what I wanted in life was a career as a statistical scientist, with the emphasis on science.

        In my final quarter as an undergrad (fall 1971), I asked David Blackwell if he would supervise me in a reading course to attempt to model the spread of fire using ideas from game theory, so I was able to continue that experience with my teaching idol. From January until grad school started for me in September 1972, I spent a little time working to have enough money to travel around Europe, and I met my wife in Jerusalem (so my second life-changing experience in one year).

        AR: That was quite a year! I hope you haven’t averaged two life-changing experiences per year since then, because that would probably be too much change. You stayed at Berkeley for graduate school, right? Did you consider going elsewhere?

        DP: Yes—I stayed in Berkeley for another 10 years and never considered anyplace else for grad school. I was a T.A. for Freeman, Pisani, and Purves (2007) as they wrote their classic introductory text. I became involved in studies of molecular evolution when the field was just new. I worked on a congressionally mandated study of the effects of ozone depletion on human health (my dissertation was about a stochastic model of skin cancer), on studies of law school admission policies toward women and minorities, and on studies of the workings of the subconscious brain.

        ResearchGate.net tells me I’m at about 7,500 citations now, and probably a good quarter of them came from my work as a grad student. So things were pretty interesting in my teaching, research, and collaborative work, while—during those years—our three children were born and my wife and I were reasonably active politically. I guess I slowed down to averaging perhaps a little under one life-changing event per year!

        AR: Was teaching a strong interest of yours at that point or just something you had to do in addition to your research? Did you have opinions about the FPP text/course then; did you have input into its development?

        DP: Well, I loved teaching and wanted to be better at it, but I wasn’t really thinking systematically about it. We would have weekly TA meetings and Freeman, Pisani, and Purves—but especially Freeman—would talk about the big ideas of the week and tell us how to remove the mathematics and just relay the core concepts of the discipline in English. I participated in the discussions, but I was just learning from them and not really contributing. After I taught the class once, I started speaking up more—about the details of the logistics of running the recitation sessions—to let the new TAs know what seemed to be working for me. It wasn’t really until I got to Ohio State and was coordinating TAs of my own that I started to take a more scholarly approach to teaching.

        AR: Did you go to Ohio State directly from Berkeley? Did you also consider nonacademic opportunities?

        DP: Yep—straight to Ohio State. OSU Statistics had been given five new positions and the chair of the department, Jagdish Rustagi, was visiting Berkeley and Stanford. He offered me a position based only on the recommendation of my adviser (Elizabeth Scott) and a 10-minute conversation with me. I never thought about nonacademic opportunities and the OSU position sounded great, so we moved to Columbus without so much as an onsite interview. Things worked differently then.

        AR: I assume research was the top priority for new faculty, but what were your teaching assignments in the first few years, and how did you approach them?

        DP: For my first couple of years at OSU, my teaching centered on graduate courses in discrete data, probability courses for engineers, and coordinating the large FPP-based intro course. For the first two, I worked hardest at developing examples that would engage the students and trying to make classroom discussions go beyond the same four or five top students. For the intro course, I worked hardest at coordinating the TAs, holding regular meetings with them, developing activities for them to do in recitation, and being sure they had what they needed to do a good job. By 1984, I started to work on changing from a lecture/recitation format to a lecture/lab format. I created an “honors” section of the course and wrote a lab activity manual for it. I wrote a grant to start the first computer lab for teaching in the arts and sciences at OSU and won that, so I was doing computer labs starting in 1985. Paul Velleman had just created DataDesk, and I wanted to use it a bit for exploratory analyses, but mostly for doing simulations to illustrate concepts.

        Consortium for the Advancement of Undergraduate Statistics Education (CAUSE)

        AR: I’d like to ask directly about a topic we’ve skirted thus far: your serving as director of the Consortium for the Advancement of Undergraduate Statistics Education (CAUSE). How did you come to take on this role, and what appealed to you about it? (I suspect readers are expecting to see “this was another Dick Scheaffer project” in your response.)

        DP: Actually, it was Joan Garfield and Deb Rumsey who received funding from the ASA (but that was when Dick Scheaffer was ASA president, so the theme continues!) to hold a series of meetings about starting some kind of national undergraduate statistics education effort. We decided on a basic structure, with a director overseeing the organization and three sub-components (research, professional development, and resources), each supervised by separate associate directors. Deb was going to be the director, Joan would be the associate director for research, and Beth Chance and you [Allan Rossman] would share the role as associate director for professional development. Also, we hadn’t settled on an associate director for resources, though Jackie Dietz (who had just finished her successful stint as founding editor of the JSE) was considering taking on the job. As things turned out, Deb had a new baby and Jackie declined, so new team members were needed for those responsibilities. Joan called and asked if I would take on the role of director, since I had been active at the meetings. I agreed to try and work out a plan to do that and make it feasible to move the organization forward. I asked Rog Woodard, who was then at OSU and working closely with me on the Buffet project, to be the associate director for resources and asked Doug Wolfe, as chair of OSU Statistics, if the department could provide a course relief for Rog and I to take on those jobs. Everyone agreed, and we began to work.

        AR: What were some of the early challenges, and also some of the early successes, for CAUSE?

        DP: The challenge to me was to put together the financial and staff resources to get things done. I was confident I could do that—but my biggest fear was that I wouldn’t be able to get people interested in working on projects. Happily, there was lots of good will toward CAUSE in the statistics education community and I had an ace in the hole—Joan Garfield. Joan knew everyone and was respected by everyone. She gave me the names of folks to ask for help and, for the research-oriented things, she asked them herself. To my amazement, almost everyone said yes. Now, at that point, Lee Zia at NSF had created a wonderful vision for a National Science Digital Library (NSDL) that would be a repository of resources for teaching and learning in the STEM disciplines. So, I worked with Rog Woodard in putting together a proposal for CAUSE to operate the statistics education NSDL and CAUSEweb was born, with Rog as the editor, Ginger Rowell as the associate editor, and Justin Slauson as our web programmer. The NSF reviewers said the editorial board we assembled from Joan’s recommendations was a “Who’s Who of Statistics Education.” I agreed.

        We also had a couple of other big successes in our first five years that helped propel things to the next level. Working with Tom Short, we received a major workshop grant (the CAUSEway program) enabling us to provide a series of about 30 multi-day workshops that were free to the participants. Then, working with Deb Rumsey, we launched the NSF-funded CAUSEmos program that supported three USCOTS conferences, provided funds for eight faculty-learning communities, and allowed us to hire Jean Scott as our program coordinator to handle the logistics of it all. Jean really became the face of CAUSE over the next eight years.

        AR: I suspect this will be the most softball question of the interview: For someone who has never been to the CAUSE website or participated in a CAUSE-sponsored activity, how would you recommend they get involved, and why should they want to get involved? But let me make this question a bit harder by asking you to address three different groups: those for whom statistics teaching is their primary professional activity, undergraduate instructors in other disciplines such as mathematics or social sciences who occasionally teach statistics, and education researchers interested in statistics education.

        DP: If you are a nonstatistician teaching undergraduate classes that involve statistical concepts, go to CAUSE to find a unique collection of songs, cartoons, well-researched quotes, and other fun items for teaching elementary statistical concepts, or find ways to connect your teaching to real-world applications though Chance News hosted on CAUSEweb.

        If you are an education researcher interested in getting involved in statistics education research, go to CAUSEweb to find a searchable annotated index to the literature; national reports providing guidelines for programs, research topics, and methods; and links to appropriate assessment items and inventories in statistics education research.

        If your career is in teaching statistics, then come to CAUSEweb to hear recordings of nearly 200 webinars and 100 hours of archived virtual conference sessions on the teaching and learning of statistics; come to share your own teaching tips and browse links to collections of online and hands-on activities and technological resources for teaching; find out how your students can take part in national undergraduate research competitions (USPROC) or in monthly cartoon caption contests; come to add your name to the map of people in statistics education and find others in your area; come to find out about how to implement new ideas in pedagogy like teaching statistical inference using simulation.

        If you are in any of these groups, then come to CAUSEweb to sign up for our eNEWS, which will keep you informed about professional development opportunities like webinars, workshops, and conferences about teaching statistics and activities of the latest statistics education projects funded by NSF. And this is just a sampling. CAUSEweb is meant to be both a portal for anyone interested in the teaching and learning of statistics at the undergraduate level and a link to a great community of like-minded people.

        AR: You mentioned “fun” items such as cartoons in this response. You’ve done a good bit of work (although that seems like an odd word choice here) to incorporate “fun” into teaching statistics. Can you summarize what you’ve done and learned on this topic?

        DP: Yes—I’ve “worked” with Larry Lesser from The University of Texas at El Paso since the start of CAUSEweb in 2003 on the development of our collection of fun resources for teachers. Then, as part of a CAUSE faculty learning community on teaching with fun, we met John Weber from Perimeter College of Georgia State and started to do more systematic research in the area. We received an NSF grant in 2012 (project UPLIFT) to do randomized experiments of the effect of fun teaching on learning and student anxiety and also to remove some barriers that instructors had in using the resources in the CAUSEweb collection (e.g., providing high-quality recordings of songs). Results from our randomized trial were recently published in JSE (Lesser, Pearl, and Weber, 2016). It showed that students who were asked to listen and sing along with songs illustrating specific learning objectives got the correct answer on test items about those objectives an average of 7.7% more often than students who learned without the songs. Also, just last year, we received another NSF grant (project SMILES) that we are quite excited about. We are creating a large group of interactive that we are testing in new experiments. The interactive songs work kind of like MadLibs, where students are asked questions and then the words they use in their answers become part of the song via a synthetic voice. We hope the increased student engagement required will boost the learning gains provided by songs.

        AR: Of all of your activities and accomplishments in statistics education, which one are you most proud of?

        DP: I guess that would have to go to building up CAUSE, since that has had the most effect.

        30 Years of Teaching Behind Her, Roxy Peck Says There Are No Mistakes

        Fri, 09/01/2017 - 7:00am
        Jill Talley, ASA Public Relations Manager
          Roxy Peck is professor emerita of statistics at California Polytechnic State University, where she served as chair of the statistics department for six years and as associate dean of the college of science and mathematics for 13 years. A fellow of the American Statistical Association, she also is an elected member of the International Statistical Institute. She has received numerous awards throughout her career, including the ASA Founders Award and the Lifetime Achievement Award in Statistics from the US Conference on Teaching Statistics. She also has served as past chair of the Joint ASA/NCTM Committee on Curriculum in Probability and Statistics for Grades K–12 and the ASA Section on Statistical Education. There are no mistakes, only lessons.

          That commentary rings true with Roxy Peck, professor emerita of statistics at California Polytechnic State University (Cal Poly), who credits her students with reminding her of the value in trying. “The most important thing I have learned from students is that it is okay to make mistakes, as long as you learn from them.”

          Wanting to equip students with knowledge is a passion shared by teachers of any discipline. But, Peck, armed with 30 plus years of teaching experience, notes it’s when educators change things up that they can change a life. “Experimenting in class and trying different things is not only acceptable, it’s how we make improvements and become better teachers. I’ve found that students respect that if they know you really care and have their best interests at heart.”

          Even in her childhood, Peck was familiar with change. The daughter of a reporter who advanced up the corporate ladder to bigger newspapers in larger cities, she moved around often, living in the suburbs of Cleveland, Chicago, New York City, and finally Los Angeles, where she attended high school and has lived ever since. The first person in her family to graduate from college, Peck majored in social science. “It was the ’60s,” she chides, “and everyone I knew was majoring in political science or sociology or psychology. I obviously didn’t get very good advice when I was in high school!”

          It wasn’t until her senior year of college that she was introduced to statistics, and even then only as a requirement for graduation. “I really enjoyed it, and later took a second class that was offered by F.N. David called ‘Games, Gods, and Gambling’.” David was the chair of the statistics department at the University of California, Riverside, at the time, and Peck credits both the instructor and the course for shaping her career. “That was what made me decide that statistics and probability were really interesting and started me on the path to where I am today.”

          Two years after graduating, she decided to pursue additional education. Initially thinking she’d earn a second bachelor’s degree in statistics, she instead went on to earn a master’s degree in mathematics and PhD in applied statistics over the next five years.

          Throughout her career, Peck established a nationally recognized presence as a leader in statistics education. Remembering what life was like as a student—the demands, adapting to different teaching styles, and workload—she’s been active in initiatives that aim to improve and expand statistics education for both students and teachers.

          Along with educators from across the country and officials at the U.S. Census Bureau, she helped launch Statistics in Schools in 2000, a nationwide program to introduce statistics activities and resources into K–12 classrooms. “If you use artificial and contrived examples, students don’t really get the sense that it [statistics] really is useful and used to answer important questions that could impact their lives,” she said in an interview last December with the San Luis Obispo News Times.

          “Statistics is still poorly taught in some places that still focus on the procedural aspect of the subject. But now there are many good textbooks and professors and high-school teachers who provide more of an emphasis on statistical thinking and conceptual understanding, and this is a really good thing.” In addition to authoring textbooks on introductory statistics, Peck is a co-editor of Statistical Case Studies: A Collaboration Between Academe and Industry and a member of the editorial board for Statistics: A Guide to the Unknown, 4th Edition.

          Serving as the chief reader for the Advanced Placement (AP) Statistics Exam from 1999–2003, she led efforts to make subject-matter decisions during the exam-construction process and guided hundreds of teachers through the grading procedure. And, when the College Board began redesigning the SAT in 2014—a move critics and even many academic test reviewers argue negatively affected English Language Learners (ELL) and other disadvantaged groups—Peck was outspoken about some of the changes. She noted that specific changes could lead to confusion, as some problems were either not mathematically sound, had incorrect answers, or were unrealistic.

          Though college entrance exams have changed formats over the years, higher education institutions continue to place value on them, a tactic in which Peck has seen both pros and cons. “If you had asked me several years ago if colleges would begin to place less weight on standardized test results, I would have said that we would see less emphasis on admissions tests because they didn’t always successfully measure the right things and were not always very good predictors of student success in college. But, I think the new revised SAT does a much better job of this, and so maybe it will be more useful in making admissions decisions at competitive institutions.”

          As time will tell how teaching techniques and exams evolve, so too will it generate a new crop of savvy students and thought-provoking teachers, who—focusing on statistics as a scientific discipline—can continue to expand awareness of the value of statistics education. Peck looks forward to this and believes “perhaps in another 10 years, we won’t hear students say statistics was their worst class in college.”

          The Importance of Teaching Ethics in Statistical Consulting Courses

          Fri, 09/01/2017 - 7:00am
          This column is written for anyone engaged in or interested in statistical consulting. It includes articles ranging from what starting a consulting business would entail to what could be taught in a consulting course. If you have ideas for articles, contact the ASA’s Section on Statistical Consulting’s publications officer, Mary Kwasny.

          Alan Elliott is the director of the Statistical Consulting Center at Southern Methodist University within the department of statistical science. Previously, he served as a statistical consultant in the department of clinical science at The University of Texas Southwestern Medical Center at Dallas for 30 years.

          Editor’s Note: A version of this article originally appeared in The American Statistician in March 2017.

          An important component in any statistical consulting course is the topic of ethics. There are at least two reasons to include a study of ethics within this course. First, universities may require ethics as part of a degree requirement, as is the case at the university where I teach. Second, practicing statisticians should be aware of how the ethical guidelines adopted by their own professional organization can help them orient themselves to the profession. This article is primarily about how the ASA Ethical Guidelines for Statistical Practice is an important component to the training of future statisticians. As stated in the guidelines:

          The Ethical Guidelines aim to promote accountability by informing those who rely on statistical analysis of the standards that they should expect. The discipline of statistics links the capacity to observe with the ability to gather evidence and make decisions, providing a foundation for building a more informed society. Because society depends on informed judgments supported by statistical methods, all practitioners of statistics, regardless of training and occupation or job title, have an obligation to work in a professional, competent, and ethical manner and to discourage any type of professional and scientific misconduct.

          Science enables discovery of how the natural world works through the collection and study of observable physical evidence. Statisticians/data analysts play a key role in the scientific analysis and interpretation of results, using appropriate techniques. When scientists follow professional guidelines, science advances. When data analysts sidestep statistical ethics, the profession loses respect and those who should have benefited may suffer undesirable consequences instead.

          We live in a data-centric age. Today’s statistical profession encompasses a variety of careers described with terms such as applied statistician, data scientist, data analyst, and business analyst. This sudden and expanding need for the search for meaning within Big Data adds to the challenges that already exist in the world of data analysis.

          A desire to establish ethical guidelines for the use of statistics is not new. The first committee recommendation for a code of ethical practice was in 1949. Various other stages of the ethical code took place in the ensuing decades, culminating in the formation of an ad hoc Committee on a Code of Conduct in 1977. A code was adopted in 1981, and a permanent Committee on Professional Ethics (CoPE) was formed in 1986. The ASA Ethical Guidelines for Statistical Practice were adopted in 1999 and revised in 2016.

          The importance of the ASA guidelines, and a reason each student of statistics needs to be aware of them, is that they define ethical—consensus-based—standards on how to use and communicate the results of statistical methods in a manner that maintains scientific and professional integrity. In addition, the profession benefits from the dissemination of these guidelines because they help provide credibility and recognition for the value of our profession.

          Whenever, and by whomever, statistics are misused, it reflects badly on the entire statistical community. It degrades the profession and forces statisticians to become defensive about the value of their own career. It is therefore imperative that curricula help students establish successful careers by including training in professional guidelines that protect the profession and provide transparent principles of conduct for the practitioner, client, and collaborator.

          The practicing statistician has a unique role among scientists. Unlike most scientists, whose careers are focused on a field of study within a particular scientific discipline, a statistician often works across disciplines. A consulting statistician may work on topics that range from clinical science to factory efficiency. The ASA guidelines can serve as an important tool in helping the statistician navigate potential challenges in working in an interdisciplinary role.

          Rather than teaching these ASA guidelines as a body of knowledge to be learned and memorized, the challenge is to mentor students into a lifelong practice of responsible scientific conduct. Moreover, the ASA ethical guidelines may be most useful in providing professional response options to the statistician in the face of decisions made by others that might conflict or lead to conflicts with these guidelines.

          The guidelines are organized into the following eight topics. Each topic includes general guidelines on standards to be followed by an “ethical statistician.” They do not address all ethical issues, and they do not answer specific ethical questions. Rather than policing or offering specific rules for conduct, they are designed generally to “help statistics practitioners make and communicate decisions ethically.”

            1. Professional Integrity and Accountability
            2. Integrity of Data and Methods
            3. Responsibilities to Science, Public, and Client
            4. Responsibilities to Research Subjects
            5. Responsibilities to Research Team Colleagues
            6. Responsibilities to Other Statisticians
            7. Responsibilities Regarding Allegations of Misconduct
            8. Responsibilities of Employers

          CoPE continues to look at ways to disseminate relevant information and help instructors train students in ethical practice. This includes a current effort to collect case studies that can serve as teaching tools.

          We have both an opportunity and a responsibility to include ethical training as we prepare students for professional practice with statistics. In particular, this training should include substantial discussions about how the ASA guidelines provide a template for ethical behavior in our profession. This provides students with the tools to become more successful scientists and leaders and helps our profession create and contribute to a better world through ethical science.

          Martha Aliaga: The Charismatic Teacher

          Fri, 09/01/2017 - 7:00am
          Val Nirala, ASA Publications Coordinator

            When asked about Martha Aliaga, the word that comes to mind for most people is “teacher.” It seems everyone who knew her has a story to tell illustrating her special charisma and passion for teaching.

            Roxy Peck—emerita associate dean of the college of science and mathematics and professor of statistics emerita at California Polytechnic State University, San Luis Obispo—recalls this story:

            “Let Me Tell You About My Daughter” is my favorite Martha classroom demonstration. She would say, “Let me tell you about my daughter,” and then she would say she wanted to sew a blouse for her daughter using the fabric pictured on the cover of her book [Interactive Statistics]. She would hold up a large piece of that fabric and say she didn’t want to buy a lot of it before she was sure her daughter would like it, and she wondered how much she should buy as a sample to show her daughter. She would hold up a tiny swatch that clearly wasn’t enough to capture the pattern, and everyone would say, “No, no that isn’t enough.” Then she would hold up a slightly bigger piece—still not enough. And another—still not big enough. But then she would hold up a piece that was about 5 inches by 5 inches, and every one would say, “Yes, that’s enough.”

            Students got the idea of a sample being representative of a larger piece. But then (and this is what I think is the brilliant part of the lesson, because it addresses a common student misconception), she would say, “Well, I only need 1 yard of fabric for the blouse, but I think I may also want to make some curtains for my daughter’s room out of the same fabric. To do that, I will need 10 yards of the fabric, so if I am going to show my daughter a sample, I had better get a sample piece that is 10 times as big.”

            Students clearly saw this wasn’t necessary and would often argue with her, saying she didn’t need a bigger piece of fabric for her sample. She was then able to explain that the size of a sample needed to get a good sense of a population doesn’t really depend on the size of the population, if the sample is well chosen.

            That was typical of the way she challenged students to think about statistical concepts—by relating them to everyday things they could relate to.

            Martha Aliaga and Rebecca Nichols in Slovenia, 2010

            In Their Own Words
            Knowing Martha Aliaga meant having stories to tell. Here, colleagues relay experiences with her that continue to make them smile.

            Rebecca Nichols, ASA Director of Education

            I was particularly excited to go with her [Aliaga] to the International Conference on Teaching Statistics in Slovenia in 2010, which was my first international conference. We met at Reagan National airport and were all set to board our flight when something happened with the plane and they had to cancel the flight. They scrambled and got us on another flight to Amsterdam, leaving instead out of Dulles, that would get us there in time to catch our connection to Slovenia. It was going to be tight, so we jumped in a taxi and headed for Dulles.

            We didn’t have any bags to check, but had to wait in a huge line to get our new boarding passes. It was looking like we just weren’t going to make our flight and would then miss our international connection when Martha chanted, “I’m from Argentina!”

            She proceeded to work her magic as only Martha could by cutting in front of the huge line without making people mad, showing her special United card, and kindly working it out with the agent so we could quickly get our tickets and barely make our flight.

            She had to do something similar for the other legs of the trip, because part of her ticket was mistakenly cancelled when they changed our tickets. She managed to get us where we needed to be. We made it to Slovenia just fine, and she did a great presentation, as always.

            Rick Peterson, ASA Professional Development and Chapters and Sections Manager

            We had launched the Census at School website and Martha and Rebecca [Nichols] planned a series of Saturday workshops for high-school teachers in the Washington, DC, area at the ASA office. These workshops were to introduce the teachers to Census at School, give advice on how to collect data, and provide exercises the teachers could use in their own classrooms.

            It was Friday afternoon before the first workshop and I could hear Martha and Rebecca in the office next door going over logistics. I looked up from my monitor and saw Martha and Rebecca in my doorway looking, for lack of a better word, sheepish.

            My name is Rick, but when Martha said my name in her Argentinian accent, it always sounded like Rēk. So, Martha said, “Rēk, Rebecca and I have a favor to ask you.” I already knew what the question was, and I knew I would capitulate because it was Martha after all, so I replied, “Martha, what time would you like me to be here tomorrow morning?”

            Already a longtime member of the ASA, Aliaga joined the staff in August of 2003 after a distinguished career at the University of Michigan. While at Michigan, she won the First Prize in Statistics for Innovative Programs Using Technology and two awards for excellence in teaching. She also coauthored Interactive Statistics and was elected an ASA Fellow.

            Aliaga’s tenure at the ASA brought about the ASA’s Educational Ambassadorship Program, which Aliaga and the Committee on International Relations in Statistics launched in 2005. Within the program, an ambassador attends continuing education courses during the Joint Statistical Meetings and then returns to his or her country to teach the new subject matter. This way of passing statistics education forward has allowed statisticians to reach students in every corner of the world.

            Martha also believed in starting statistics education early and was a tireless advocate for K–12 curriculum in statistics. Now under the direction of the ASA/NCTM Joint Committee on Curriculum in Statistics and Probability, she created the Meeting Within a Meeting Statistics Workshop for K–12 math and science teachers and STEW, a peer-reviewed repository of lesson plans. She also introduced Census at School in the United States and created the K–12 statistics education webinar program. All these initiatives deliver training to K–12 teachers or provide resources for their success.

            Jerry Moreno, assistant professor emeritus of statistics at John Carroll University, says, “Behind her incredibly warm smile, was a mind continuously thinking of new ways to help students and teachers learn statistics. I recall when she was formulating STEW that I had some reservations about it. But she would listen and then reframe the project. Her insights far exceeded mine, as STEW has become a useful resource of lesson plans in statistics for teachers.”

            Martha was also a strong supporter of women and minorities and served as president of the Caucus for Women in Statistics in 2002. Additionally, she participated as the only instructor for a National Science Foundation program for middle-school minority girls in Ann Arbor, Michigan, and was invited to give workshops in many countries.

            Current ASA Director of Education Rebecca Nichols says, “I always loved going to statistics education conferences with Martha because she seemed to know everyone and it was like she was introducing me to her family. Martha was a master teacher who could explain complex ideas with simple, clever, and often witty examples. She loved teaching, loved students, and loved people.”

            Rick Peterson, ASA professional development and chapters and sections manager, says, “Working with Martha was probably the fondest time of my professional career. Her drive and passion for statistics education was infectious. I remember the Meeting Within a Meeting and Census at School programs when they were just preliminary ideas Martha had. But once she decided these were programs we were going to implement, there was no stopping her.”

            Aliaga passed away in October of 2011; however, the programs she imagined continue. STEW was integrated into Statistics Teacher, an online journal for statistics educators published by the ASA/NCTM Joint Committee on Curriculum in Statistics and Probability. Meeting Within a Meeting was held for the 11th time and the 12th Educational Ambassador made it to JSM in Baltimore, Maryland, this year. And last but not least, US Census at School just released a random sampler that generates samples from the entire messy U.S. database for teachers who wish to provide their students with messy data to clean and investigate. All these programs and more can be found on the ASA’s website.

            Teaching Statistical Literacy to Non-STEM Majors: Challenges and Opportunities

            Fri, 09/01/2017 - 7:00am

            Michelle Everson is a professor and program specialist of statistics at The Ohio State University and former editor of the Journal of Statistics Education. Since earning her PhD in 2002, she has been teaching introductory and intermediate statistics courses. She is particularly interested in distance education and ways to actively engage students in online learning environments.

             

            Ellen Gundlach has been teaching and coordinating several introductory-level courses since 2002. She co-authored a probability book with Mark Daniel Ward and has also won several teaching awards. She is an associate editor of the Journal of Statistics Education.

             

            We teach statistical literacy to non-STEM majors in public mid-western universities using large-lecture traditional, fully online, and flipped teaching methods. Between 500 and 1,100 students enroll in our courses each semester, and we both not only teach sections of these courses, but we also serve as the course coordinators (with valuable assistance from many talented graduate teaching assistants (GTAs) who lead recitation sessions and sometimes serve as lecturers).

            Our students are more likely to be consumers of statistical information than producers of statistics. As such, we want them to be able to develop the necessary skills to reason carefully through statistical information to better understand important issues in society today, such as whether to vaccinate their children, whether the American Community Survey is a good use of our tax dollars, how Big Data is something to be both excited and cautious about, how to interpret medical test results, and whether to panic when a local news station suggests there may be a cancer cluster in the community./

            GAISE Guidelines

            The 2005 Guidelines for Assessment and Instruction in Statistics Education (GAISE) College Report and the recently revised GAISE College Report have had a profound effect on our thoughts about how to best structure and teach our statistical literacy courses. The GAISE College Report recommends teachers of first courses in statistics (1) teach statistical thinking; (2) focus on conceptual understanding; (3) integrate real data with a context and purpose; (4) foster active learning; (5) use technology to explore concepts and analyze data; and (6) use assessments to improve and evaluate student learning.

            Given that our courses are designed to help students become critical and thoughtful consumers of statistical information, there is a strong emphasis in our classrooms on learning the language of statistics and understanding the big ideas.

            Technology—often in the form of applets and statistical software such as JMP—is used to illustrate different ideas and concepts (such as distributions of sample statistics or correlation), to graph data, and to perform calculations. Whenever possible, we attempt to use real data that has been gathered from our students or that comes from published research. We use this data to better illustrate the investigative nature of statistics. We want our students to know that data, if gathered under the right conditions, can help us answer important questions. We also want our students to appreciate the need to ask critical questions when they are trying to make sense of data.

            To determine if students are meeting the learning objectives in our courses, we use a variety of formative and summative assessments, including clicker questions, weekly homework assignments and lab activities, projects, and exams.

            What to Teach

            Topics That Work

            Our students appreciate daily connections to current events so they can see immediate relevance of statistical literacy to their daily lives. This can be accomplished through a “statistics in the news” segment incorporated into each lecture or with whole lectures written to explain a particular hot topic.

            For example, during election season, understanding how pre-election polls could vary from each other and the final election outcome allowed us to discuss sampling variability, sample size, margin of error, sampling design, response bias, undercoverage, and nonresponse. When the Affordable Care Act was being debated by Congress, we talked about how the Law of Large Numbers is important to the business plans of insurance companies. A few years ago, Facebook announced results from an experiment it performed on hundreds of thousands of users without explicit permission, and this led to discussions about exactly what informed consent means and whether Facebook is considered a “public space” that would allow some exemptions from usual informed consent rules.

            We’ve enjoyed sharing and discussing news articles about topics we think our students will relate to and find interesting. For example, we’ve talked about whether Facebook use has a negative effect on GPA, whether dogs like to be hugged, if college students will literally “text through anything,” if using electronic devices during class affects learning, the typical cost of a wedding, the best day of the week to weigh yourself, the best excuse to give if you ever need to call in sick to work, whether the outcome of a coin toss can predict the winner of a football game, and the calorie content of Chipotle burritos.

            We also frequent YouTube and share many video clips in our classrooms. Videos from the “Colbert Report,” “Saturday Night Live,” “Bill Nye the Science Guy,” Neil deGrasse Tyson’s “Cosmos,” TED talks, and, of course, Hans Rosling’s “The Joy of Stats” all enliven explanations and discussions while showing the wide-ranging relevance of statistics.

            Topics That Don’t Work

            Many of our students have math anxiety, or at least a strong dislike for anything math-related, so we carefully plan our courses to build confidence and show students many examples with step-by-step guidance and ample opportunities to practice alone and in groups. We make it clear how statistics and math are different, and we attempt to emphasize that we use math as one of our tools to understand what is happening in the world. About one-third of our topics are taught primarily with words instead of numbers. Proofs are not as important for students as understanding what the results of their data explorations mean and how to communicate these results to others.

            How to Teach

            Active Learning

            We attempt to incorporate many opportunities into our courses for students to play an active role in the learning process. Although we both teach in large lecture halls, we use clickers to engage our audience and give as many students as possible the opportunity to be part of class discussion. This has allowed us to sometimes gather data from our students that we can incorporate into future class discussions to illustrate particular ideas or concepts. Clickers also allow us to gauge whether our students have read assigned course readings or whether they have misconceptions or misunderstandings. At The Ohio State University, students have free access to a system called Top Hat that allows them to use their cell phones as clickers, therefore turning a device that sometimes distracts students into a valuable educational tool.

            Whenever possible, we try to bring as much activity and discussion as we can into the lecture hall. One favorite activity involves trying to conduct a horrible experiment with students by simply dividing the lecture hall in half and asking each half of the room to try to remember a different list of words read aloud by the instructor. Many lurking variables are built into the experiment, and, because students are active participants in the experiment, they often have much to say about the shortcomings of the experiment and how a better experiment could be designed to assess memory for words. Our hope is that this exercise will be more powerful than simply describing what an experiment is and telling students about the terms and ideas related to experimental design.

            Helpful Resources for Planning Courses

            While some of our best ideas come from talking to colleagues or paying attention to what is in the news, here are some other resources we have found especially helpful:

            Consortium for the Advancement of Undergraduate Statistics Education (CAUSE)

            This site has been compiled by statistics educators for more than a decade, beginning with a National Science Foundation grant. We especially like the webinars (Teaching & Learning, Activities, and Journal of Statistics Education author talks), but there are labs, projects, jokes, songs, data, lesson plans, quotes, and many other resources.

            United States Conference on Teaching Statistics (USCOTS) and Electronic Conference on Teaching Statistics (eCOTS),

            These conferences (in person for USCOTS, online for eCOTS) are wonderful ways to connect with the statistics education community. Having conversations over meals at USCOTS is ideal, but even looking through the resources posted on the CAUSE website once the conferences have ended can be inspiring. Many big changes in the statistics education field such as teaching hypothesis testing through simulation were born and nurtured at these conferences.

            Journal of Statistics Education (JSE)

            This free online journal contains excellent scholarly articles about research in statistics education, interesting data sets with suggestions for how they can be used in the classroom, interviews with leaders in the field, and summaries of interesting articles in other journals that could be relevant to teaching statistics.

            Multimedia Educational Resource for Learning and Online Teaching (MERLOT),

            This is a collection of online resources such as applets and modules that can be used as part of lab activities, lecture demonstrations, or at-home practice for students.

            Science Daily

            We both signed up for the daily email newsletter, which updates us on many new scientific articles published in a wide variety of fields. Almost every day, we can find a good experiment or observational study to bring to our students from this newsletter.

            Assessment Resource Tools for Improving Statistical Thinking (ARTIST)

            This is a collection of assessment resources for first courses in statistics. Over the years, we’ve used many of the assessment items from this site and been inspired to create course projects based on sample projects included here.

            When students are not in our lecture halls, they are in smaller recitation sections in which they work through lab activities with their peers under the guidance of our GTAs. Many of these activities involve wrestling with problems in which students need to apply what they have learned through lecture and course readings. Students are encouraged to work through these problems with peers and use technology to arrive at solutions. We attempt to structure each lab activity around a question that students need to answer, often with real data.

            As an example, in our first recitation activity (inspired by a webinar from the Consortium for the Advancement of Undergraduate Statistics Education [CAUSE], we break students into groups of three and give each group two small rubber pigs from the game Pass the Pigs. We tell students to imagine they are trying to gather information to be used to design a game that will incorporate the pigs. We also tell students that each pig can land in one of six possible ways, and we ask each group to come up with and execute a plan to gather enough data to determine how often a pig would be expected to land in each of the six positions. Each group is then asked to summarize their data and share it with their peers.

            We start our semester with this activity because we’ve found it to be a good way to introduce the idea of statistics as an investigative problem-solving process, and we also find that we can use it to illustrate and foreshadow many of the topics that will be covered in the course.

            For instance, students have to think carefully about what it means to “summarize” a data set, and it’s always interesting for us to see what kinds of summaries they choose to share. We can question students about the sample size they choose and what they think might happen if they were to increase the sample size. We can ask them if they would feel comfortable generalizing their results to a larger population, and we can ask them if they think factors such as how they tossed the pigs and the surfaces they tossed the pigs onto might have had an effect on their results. We can even present a claim to them about how the pigs should land, and we can ask them if they think they have found evidence in support of or against this claim.

            For all these reasons, we find this to be a rich activity to which we can refer many times to better help students see the connections among different topics in the course. It also tends to be a fun way to start a new semester and break the ice with our students.

            Other recitation activities have involved exploring data on movies to determine if a movie’s budget affects the revenue it generates, using Zener cards to determine if students have ESP (to illustrate important ideas of hypothesis testing), playing games (such as those developed by Shonda Kuiper ) to better understand the principles of experimental design, and examining the distributions of colors in M&M candies to illustrate the idea of the sampling distribution.

            We have also tried to use different projects in our course. One group project (inspired by work presented at the Electronic Conference on Teaching Statistics (eCOTS) involved finding an advertisement that uses data to make a claim about a product and then doing research to determine if that claim is credible. Another project involved asking students to keep track of data from their daily lives (e.g., number of steps taken per day, minutes spent texting per day, calories consumed per day, etc.) for several days and then use technology to explore the data. Yet another project involved asking students to keep a journal of news reports they were seeing that involved statistics in some way (e.g., poll results, graphical displays of data, descriptions of research studies, etc.).

            Big Data is a hot topic in the news, and while our students might not have the skills and technology to analyze Big Data, they are contributing to Big Data with daily activities online, so another project asks them to keep a 24-hour data diary in which they record everything they do within a 24-hour period where data could be collected from them, investigate two privacy policies, write a “Big Data privacy bill of rights,” and share an exciting use of Big Data in a field that interests them.

            One other favorite project we have used is an online discussion and investigation into the research on one of a student’s own good or bad habits. This gives our students the chance to talk with each other about a topic of personal interest to them, and students seem to enjoy the chance to get to know each other and critique research that has immediate implications for how they behave each day. Details about several of these projects were shared through a CAUSE webinar.

            Finding Ways to ‘Hook’ Students During the First Lecture

            First impressions are important, and we constantly strive to put our best foot forward on Day 1 of every new semester. We know our students are often not happy to be taking a statistics course, and we sometimes question if they see the relevance of it. We want our students to walk away from our courses with a new appreciation for the fact that data are all around them all the time and there are many decisions they will make in their lives that will require a careful and mindful synthesis of statistical information. We want to provide students with the tools to critically evaluate the statistical information we know they will be bombarded with on a regular basis outside our classrooms. We also want them to appreciate the active nature of our courses.

            A typical first day might involve asking students to meet and greet some of their peers. Students are given a few minutes to meet as many of their classmates as they can and gather information from each classmate. This activity, and the information gathered, can then be used to illustrate several of the new terms students will read about in the first two chapters of their textbook. We’ve found the activity works even in large lectures halls.

            We also like to spend the first day sharing several snippets from the news. For instance, we will compile several recent stories that include the results of a study or survey aimed at answering a particular research question. We’ll share the research questions with students and ask them to tell us what they think the answers are. We will then tell students what the news stories actually claim the answers to be. Many of these stories are ones we’ll come back to at different times during the semester to introduce different concepts, and some of the stories have flaws we will eventually critique as a class. Our hope is that sharing these stories right away will better illustrate the relevance of the course content and the usefulness of the content in navigating daily life.

            We also try, as much as possible, to not spend a great deal of time talking about the syllabus on Day 1; instead, we might have a syllabus quiz or a syllabus scavenger hunt activity for students to work on outside of class.

            Learn About Student Interests and Incorporate Them into Their Work

            It’s critical, particularly because we teach large courses, for us to get to know our students and learn about their backgrounds, interests, and concerns. Students from many departments take our courses, and this makes for a great deal of diversity in our classrooms. We might have students who are brand new to college or students who have put off our courses until the end of college and are just about to graduate.

            The majority of our students are taking our course because they must to fulfill a general education requirement, and this is not necessarily a course they would have chosen on their own. Some students might have negative attitudes or misconceptions about the course content. As soon as we can, we attempt to gather information from our students to help ease their concerns and find out more about what they are passionate about.

            During our first lectures, we often accomplish this by handing out index cards and asking the students to write down answers to questions about themselves. We then collect the cards and spend time reading through and responding to them. We might notice, for example, several students from similar majors, or several students who enjoy athletics or are involved in athletic programs on campus, and this might give us ideas for examples we can share during future class discussions. We can also reassure the students who have anxiety about math that this is a course designed for people exactly like them, and we are happy to help them along the way.

            Traditional, Online, Flipped Delivery Formats

            We both teach our courses in multiple formats, and this gives our students more opportunities to choose a format they think will work best for them or fit best into their schedule. In addition to teaching in a traditional, face-to-face setting, we also teach sections almost completely online (with the exception of exams that students must take in proctored settings). At Purdue, there is also a flipped section that presents the lectures online but has the students meet weekly to solve problems or do hands-on activities to reinforce the material. We have found the attitudes, learning, and performance of students in all three types of section to be fairly similar, but the students appreciate having an opportunity to choose.

            What We Want

            We both enjoy the challenge of explaining the importance of statistics to an audience that might not have an appreciation for this discipline before taking our class. We want to send our students into the world as informed citizens who are curious and willing to challenge speakers, reporters, politicians, medical care providers, advertisers, and others about where their data and conclusions come from. We are not trying to create cynics, but we do want to empower our students to ask questions and think critically, rather than simply accept what they are hearing and reading at face value. We want our students to appreciate logic and good investigative procedures. We want them to understand the quality of their sources of information, and we want them to appreciate how much information the right graph can convey, what sampling variability is, and how a properly selected sample can represent a much larger population. We know our students will leave our classrooms and be expected to make sense of a world filled with data, and, most of all, we want to make sure they have the tools to get them started on their journeys.

            Q&A With Educators

            Fri, 09/01/2017 - 7:00am

            We interviewed a handful of statistics teachers to find out who inspired them, where they get their best teaching tools, and what they think is the most challenging part of being a teacher.

            Amy Hogan

            Statistics and Math Teacher
            Math for America Master Teacher
            Twitter: @alittlestats
            Blog: A Little Stats

             

            What level of education do you teach?
            I teach AP Statistics and other math classes in a specialized public high school.

            Where do you teach?
            Brooklyn Technical High School in Brooklyn, NYC.

            What or who inspired you to become a teacher?
            When I was a math major in college, I said I never wanted to teach, but I changed my mind once I got a taste. Prior to teaching, I worked as an actuarial analyst. I took on a training role in my company and quickly realized I really enjoy helping other people learn.

            Can you describe your day-to-day life as a teacher?
            An average teaching day for me: subway to work, teach AP Statistics classes, meet with colleagues for mentoring or common planning, coach my math team, grade and/or lesson plan after school, subway home, go to Pilates class, and then relax with a nice dinner at home.

            What has been your most satisfying teaching experience?
            The greatest reward, in general, is when my former students tell me about the math and statistics they’re learning in college or doing in their careers. Recently, a former student visited and said, “This semester in college, I derived the Central Limit Theorem using a Fourier transform. So cool.”

            What is the most challenging part of being a teacher?
            The politics. The negative impact of reduced budgets, changing curricula, and outside influences are becoming more and more of a reality for public high-school math teachers, especially.

            How is teaching today different than it was when you first started?
            The biggest difference I see is the growing number of open source and open access materials. The increased availability of these resources is especially helpful for public school teachers because it means they can do more with their often-limited resources. Less reliance on cost-prohibitive materials is a win for everyone, sure, but it’s imperative to increase equity in math and statistics education.

            What advice would you offer someone who is just starting their teaching career?
            New teachers should make sure to find a community of teachers, in their school or elsewhere. I would not be where I am today without the help of very supportive colleagues.

            What do you enjoy doing in your spare time?
            I am learning R/RStudio, and it’s been a lot of fun. I also love to travel. I enjoy finding great local places to eat and drink in my travels as well as at home in New York City.

            You have a great blog, A Little Stats, that offers resources for statistics teachers. Do you recommend any other blogs or books?
            Too many to list here! You can see my stats faves on my blog. In general, one of the best resources for AP Statistics teachers is the AP Statistics Teacher Community

            Where do you get your favorite lesson plan ideas? What is your favorite teaching resource?
            My favorite source of statistics teaching ideas comes from other statistics teachers and professors. The network of stats teaching friends via the AP Statistics community, conferences, and Twitter is an endless source of inspiration for me.

             

            Michelle Everson

            Professor and program specialist of statistics at
            The Ohio State University

             

            What level of education do you teach?
            I teach at the college level.

            Where do you teach?
            I teach in the department of statistics at The Ohio State University.

            What or who inspired you to become a teacher?
            My biggest inspiration to become a teacher was Joan Garfield. I started working as a teaching assistant for Joan during the second year in my PhD program at the University of Minnesota, and that experience changed my life.

            I wasn’t sure at that time what I wanted to do once I completed my degree. I was shy and introverted. The thought of being a teacher and standing up and talking in front of other people on a daily basis scared me to death. Joan opened my eyes to a world I was unfamiliar with, and her support and encouragement gave me a much-needed boost in confidence. She showed me that activity and discussion have a place in the statistics classroom, and she changed my ideas about teaching and learning. She introduced me to research and scholarship in statistics education and to a whole community of statistics educators.

            Joan was one of my biggest cheerleaders while I was a graduate student, and she continued to be a mentor to me after I received my degree.

            Can you describe your day-to-day life as a teacher?
            Typically, I teach one face-to-face section of our statistical literacy course, and I also teach the online section. I also serve as the coordinator for the course, and this involves supervising 12 or more graduate teaching assistants and lecturers per semester. I’m ultimately responsible for all the students and teaching staff who work with the course, and we often have between 900 and 1,100 students taking the course per semester.

            I would say a good chunk of my day-to-day life involves trying to keep up with email! On a daily basis, I generally receive several messages from students, teaching assistants, or lecturers about various course-related issues. I have a weekly meeting with our teaching assistants to talk about what is going on in the course and to plan ahead for future assignments and activities, and it’s not uncommon for teaching assistants to stop by my office at various times each day to ask questions or share some of their experiences. There are two days each week when I have regular office hours, and students from our course might stop in then as well to get extra help or talk about concerns.

            I always like to try new things each semester and revise my course materials, and that takes some time each day. I update my lectures with new and timely examples, and I make adjustments to lab activities and homework assignments based on how these assignments worked during the previous semester.

            Sometimes, I might attempt a new activity from scratch if we begin to notice our students are struggling with particular ideas and need extra practice with certain concepts. I would love to get to a point where I have all assignments and lectures ready to go at the start of the semester, but I’m usually tinkering with things a little at a time throughout the semester.

            If I’m not in the classroom or checking in with my online students, I’m usually planning ahead and trying to stay on top of things. Another part of my job involves handling some of the staffing in our Mathematics and Statistics Learning Center (MSLC). This is a place where students can go throughout the week to get extra help from our graduate teaching assistants with the content in many of our statistics courses, and there are often little things I have to take care of on a regular basis related to the MSLC.

            This coming autumn, I will also be serving as a faculty mentor in a special OSU program called the Second-Year Transformational Experience Program (STEP). Through this program, I will work with and meet regularly with a cohort of approximately 15 second-year students, and I’m excited to be able to learn more about their interests and concerns and help guide them through part of their college journey.

            What has been your most satisfying teaching experience?
            I think I get the most satisfaction when former students get in touch with me, out of the blue, to tell me about experiences they’ve had that remind them of content they learned in my course or to tell me about how much they are using information they learned in the course.

            Just recently, a former student stopped by my office to talk about his plans for graduate school, and he told me he is now seeing a lot of what we talked about in our statistics course in journal articles he is reading in his field of study. Another former student sent me a bad graphical display she noticed in a news report because she thought I would appreciate it (and it was a good one).

            For me, it is such a wonderful feeling when I can tell students are seeing the value in what we are trying to share with them, even if they might not totally get it until well after the course ends.

            What is the most challenging part of being a teacher?
            The older I get, the more out of touch I sometimes feel where my students are concerned. I gasp each year when I read the new Mindset List from Beloit College, because the world our students are now living in seems so different from the world I grew up in. I don’t always know what interests my students have, or what types of obstacles they are facing as college students, and I am constantly trying to figure this out so I can do a better job when it comes to engaging and motivating these students.

            I teach a course that students have to take, and many of the students don’t necessarily want to be taking the course or see the point of the course. I honestly think that is one of the biggest hurdles I face as a teacher. I work hard to try to get to know my students and find out more about them so I can bring more engaging and relevant examples into the classroom. Finding new and innovative ways to excite and inspire students is definitely a challenge, but it’s one I’ve enjoyed trying to tackle.

            How is teaching today different than it was when you first started?
            I personally think one of the biggest differences relates to technology and how it has changed what we can do and how we can interact with each other. When I first started teaching, we were not offering online courses, and I had no experience ever being an online student. When we were able to develop our first online courses at the University of Minnesota, in 2004, I was still using a dial-up connection at home, and this greatly affected what I felt I could do in my courses. I didn’t want to share resources my students would not be able to easily download, and I was limited in terms of what I could easily upload from my home computer. There was no YouTube, Twitter, or Facebook when I first started teaching, and students were not spending several hours per day texting.

            Now, I find the possibilities to be endless in terms of what we can do within our online classrooms, and I love that it is so easy for us to find and share great YouTube clips with our students. I’ve even experimented with course assignments that capitalize on students’ fascination with social media. I love being able to easily communicate with my students via email, and I like that my interactions with students are not bound to certain hours each week within my office.

            I also find that students appear more comfortable now with technology, and savvier when it comes to using technology, and that opens the door for us to use technology in different ways in our classrooms.

            What advice would you offer someone who is just starting their teaching career?
            I would advise trying to find at least one other person you can collaborate with or share ideas with. If you don’t have someone at your institution, there are so many wonderful people all over the world who are passionate about statistics education. The Isolated Statisticians discussion list is a great place to connect with other educators.

            I would also advise trying to go to at least one conference that focuses on statistics education. One of the best ones is the United States Conference on Teaching Statistics (USCOTS). This conference takes place every odd-numbered year. During the even-numbered years, there is the Electronic Conference on Teaching Statistics (eCOTS).

            The statistics education community is incredibly warm and welcoming, and I know my own career has been enriched by having opportunities to network with and get to know others in this community.

            What do you enjoy doing in your spare time?
            When I am not on campus, I’m very happy spending time working around our house. My husband and I have a small hobby farm where we raise sheep, pigs, and chickens. I’ve also recently developed an interest in repurposing old furniture, and I love reading true-crime novels.

            Name one or two favorite blogs or books you have read and would recommend to others.
            A few years ago, my good friend Ellen Gundlach suggested I read the book My Freshman Year: What a Professor Learned by Becoming a Student, by Rebekah Nathan, and I just recently re-read this book. It’s all about a college professor who decides to apply to college, as a freshman, and live for a year among other freshmen in order to better understand why college students behave as they do. The book is probably slightly out of date now—it was written in 2005—but I was fascinated by what I learned about the modern-day college student, and it definitely gave me some insights as to why some of my own students might act as they do.

            Another book I am currently reading is called Cheating Lessons: Learning from Academic Dishonesty, by James M. Lang. It’s filled with ideas about how we can re-think our classroom assessments to extrinsically motivate our students (and, hopefully, in the process, cut down on academic dishonesty).

            Where do you get your favorite lesson plan ideas? What is your favorite teaching resource?
            Honestly, I get lots of ideas from reading news reports and listening to news radio! I have a long commute to campus, and I often listen to the news as I’m driving. Several news stories have made their way into my lectures and assignments.

            I have also found lots of great ideas on the website for the Consortium for the Advancement of Undergraduate Statistics Education (CAUSE) and within the Journal of Statistics Education and the journal Teaching Statistics. Other great resources are my peers; lots of lesson ideas have been born simply by bouncing ideas off of colleagues.

             

            Katherine Halvorsen

            Professor, Smith College,
            Northampton, Massachusetts

             
             

            What or who inspired you to become a teacher?
            My mother and her aunt were both teachers. It felt to me like the “family business.”

            Can you describe your day-to-day life as a teacher?
            Teaching classes, meeting with students, serving on committees—both at the college and for the ASA—and working on research projects—alone and with students.

            What have been your most satisfying teaching experiences?
            Watching students develop mastery in my courses and reading a student’s comment that projects are so much easier when they hand in intermediate reports on a regular schedule, rather than do everything in the last few weeks of the course!

            What is the most challenging part of being a teacher?
            Teaching students the importance of planning ahead for getting their work done, of showing up prepared, and of working out a plan with me when they can’t do these things.

            How is teaching today different than it was when you first started?
            Statistics is now a required course for almost all STEM students and many liberal arts majors. It was not a required course when I started teaching. Only curious math majors and some adventurous biology majors took the course.

            What advice would you offer someone who is just starting their teaching career?
            Join the Statistical Education Section of the ASA and become a grader for AP Statistics. Both groups offer a lot of help to newcomers and experienced teachers.

            What do you enjoy doing in your spare time?
            Reading, hiking, and traveling.

            Name one or two favorite blogs or books you have read and would recommend to others.
            James Lang’s Small Teaching: Everyday Lessons from the Science of Learning.

            Where do you get your favorite lesson plan ideas? What is your favorite teaching resource?
            I read a lot and talk to other teachers.

             

            Mark Ward

            Associate Professor of Statistics
            Associate Director of Actuarial Science
            Undergraduate Chair, Purdue University

             

            What level of education do you teach? Where do you teach?
            I have been the undergraduate chair in statistics at Purdue University since 2008. Purdue has one of the largest undergraduate programs in statistics in the United States. I am also associate director for actuarial science and the faculty adviser for Purdue’s ASA Student Chapter. I am the PI for the NSF-funded Statistics Living Learning Community. I have an active research program that includes both graduate students and undergraduate students.

            What or who inspired you to become a teacher?
            My mom recently retired from a career as an elementary school teacher. Her work with students always inspired me. When I was in middle school, I spent a significant amount of time reading to my peers who couldn’t read. I experienced the joy of helping others learn, so I decided to devote my life to learning and helping others learn.
            I first learned about probability and statistics from Ron Selby, my high-school mathematics teacher. He had an inspiring style of conveying ideas about mathematics. My college professors Don Bonar and Joan Krone were particularly motivating mentors.

            I also am inspired by my wife, Laura. Our children learn at home, rather than going to school. I love seeing how my wife and children interact with each other. I learn a great deal from Laura and our children, and I feel fortunate to be married to the smartest person I know.

            Can you describe your day-to-day life as a teacher?
            I spend a great deal of time with undergraduate students. Last year, I requested to move to the academic advising floor in our building because I talk with students and their advisers a lot. Students are constantly hanging out in my office. I try to maintain a comfortable research environment, where students can ask questions and push themselves to learn more than they might on their own.

            I am a morning person, so I like to arrive early to campus, have my courses and seminars in the early morning, and go home to my family in time for dinner.

            What has been your most satisfying teaching experience?
            The Statistics Living Learning Community (STAT-LLC) has been the most satisfying experience for me. Twenty sophomore undergraduate students participate per year. They take their probability theory, statistical theory, and data analysis courses together as a cohort. They all live together on the same floor of the same residence hall, and I am their faculty fellow (a mentor role). They all have a full 12 months of research as sophomores.

            We also have professional development seminars, visits with alumni, travel to conferences, etc. Quite a few of them came with me to JSM in Baltimore this summer. Our first cohort of students just graduated from Purdue this spring, and I miss them already.

            The STAT-LLC has afforded me the opportunity to learn a great deal from our sophomores. In particular, I am always trying to better understand how to connect the disparate parts of their time spent on a college campus. I encourage my colleagues to do many things with students outside the classroom and office.

            Every year, for instance, my wife, kids, and I go camping with the students, and we also feed them in our home. The students get a better understanding of the lifestyle of a faculty member as a result. I also eat with the students in their dining courts on a daily basis.

            I think the more students know about the statistics profession, the more they are prepared to experience the joys and benefits of spending one’s life working in this area.

            What is the most challenging part of being a teacher?
            I am not a fan of assessment. I prefer to focus on learning, rather than assessing.

            How is teaching today different than it was when you first started?
            Many learning environments include online components and group work. This will be my fourth year in which I conduct all my own courses in an “active learning” style.

            The students in my probability theory course learn by working on problems in groups, rather than listening to me lecturing in class. I have created hundreds of videos, notes, and exercises with solutions to aid them in learning the material in between class sessions. The students in my data analysis course learn by working on data-driven projects, also in group settings.

            I find that active learning promotes better long-term understanding. It also affords the opportunity for students to go deeper in their learning. By not spending a class session lecturing, I have more time to talk with students individually or in a group. It enables us to connect with the material in a more meaningful way.

            What advice would you offer someone who is just starting their teaching career?
            Be open minded with the learning environment you offer to students. Try to adopt your favorite methods from the peers you respect the most and find the way you and your students enjoy interacting the most.

            Students appreciate faculty who wholeheartedly devote time to learning. Students also love to do research with faculty members. Research offers a great way to convey one’s appreciation of the field to a student. Research and learning with students can make the life of a professor a sheer pleasure all the time. It doesn’t feel like work when you truly love what you do.

            What do you enjoy doing in your spare time?
            Most of my time away from Purdue is consumed by time with my family. We particularly enjoy camping at Indiana state parks, as well as playing board games together. My hobbies including playing guitar (and occasionally harmonica) at our church. I also enjoy reading poetry.

            Name one or two favorite blogs or books you have read and would recommend to others.
            I recommend the blog Stats + Stories. My favorite book is True Love, by Robert Fulghum. It was published 20 years ago, when I was in college. I love how it describes the real-world aspects of love in its many forms.

            Where do you get your favorite lesson plan ideas? What is your favorite teaching resource?
            Ellen Gundlach and I wrote a book on probability together. She is a constant source of ideas for problems and activities students will love. We worked hard to create hundreds of exercises in our book that would be motivating for students. I also give her all the credit for introducing me to the concept of “active learning” and helping me transition all my own courses to this model.

             

            Chris Olsen

            Visiting Professor
            Grinnell College

             
             

            What level of education do you teach? Where do you teach?
            After four years in middle school and 35 years in high school (interrupted by a stint as an “assessment specialist” in Cedar Rapids, Iowa), I am now teaching statistics at Grinnell College in Grinnell, Iowa.

            What or who inspired you to become a teacher?
            My inspiration was a terrific math teacher, Mr. Larsen, in high school. A wonderful person and a wonderful man. When I went to college, I thought I wanted to be an engineer and build bridges in South America. I knew nothing about engineering, bridges, or South America, but all my friends were going to college, so I figured I should also. A quick discovery of a singular inability to do engineering graphics (by hand in those pre-computer days) led to a quick decision—I wanted to be like Mr. Larson.

            Can you describe your day-to-day life as a teacher?
            My day-to-day life as a teacher begins on my commute, listening to National Public Radio and catching up with the world. I have pen and paper at hand in case there is a story about some new study that might be a good example of statistics. If there is one, I try to track it down when I get to the office; with any luck, it will reinforce my classroom assertion that statistics is not only relevant, it is constantly relevant!

            My day in the office starts with checking email from students to see what problems have developed in the interim and getting ready for the day’s classes (think caffeine here).

            The best part of the day is my classes and the excitement interacting with young people. Between classes, I do the usual teacher things: prepare for the next class, re-write lessons and activities that I am—as they say in Casablanca—shocked(!) to discover need improvement. Then, at the end of the day, I head home with NPR (see above).

            What has been your most satisfying teaching experience?
            My most satisfying teaching experience occurs when the expressions on the faces of my students evolve from quizzical uncertainty to tentative understanding to (finally) that smiling countenance that says, “I have this nailed.” As can be imagined, this transition is not universal and does not necessarily happen in one day.

            To change the question a bit, my most heartwarming teaching experience occurs when I hear from former students who have discovered (sometimes with much surprise) they actually use statistics in their day-to-day professional lives.

            What is the most challenging part of being a teacher?
            For me, the most challenging aspect occurs when a student is struggling and I need to find a way to present the material differently, not just louder. I get stuck on those phrases that make sense to me, but don’t translate well to those just beginning their journey through statistics. Different words? Different pictures? Different analogies? Different examples? I suppose variability is the heart and soul of statistics, but variability in students’ understanding is a challenge indeed!

            How is teaching today different than it was when you first started?
            The salient difference is due to technology. The ready availability of calculator and computer has revolutionized what we can do, perhaps without a companion revolution in our understanding of what we should do. The graphic capability of these tools is breathtaking. It allows us to bring statistics to a much larger audience, and that larger audience to better utilize statistics. The power of statistical software has eliminated the drudgery of calculation and graphing, but cannot speak to the important issues of sampling on the front end and enlightened analysis on the back end.

            I have always tried to find statistically interesting data sets from a variety of fields, but now I think it is increasingly important to discuss the non-computation non-graphical aspects of wrenching knowledge from data: What is the source of the data, and what meaning and insight can be gained from the results presented by the software?

            What advice would you offer someone who is just starting their teaching career?
            Read in journals outside the realm of statistics and digest both what and where statistics are used. Be prepared (and appreciate) that many of your students in elementary classes know more about their fields of study than you do. Learning is a lifelong activity, and your students will help keep you up to speed about that world beyond theoretical statistics.

            What do you enjoy doing in your spare time?
            Spare time. Hmm. I’ll have to look into that concept. I mostly enjoy reading (plugging those vast holes in my knowledge) and computer programming (my “hobby”).

            Name one or two favorite blogs or books you have read and would recommend to others.
            Most of my casual reading is cheap, trashy murder mysteries, but occasionally, by chance, I stumble into some more literary tomes. I can’t decide on one or two, so I will offer three.

            The Lost: The Search for Six of the Six Million, by Daniel Mendelsohn, is a fascinating weaving of Old Testament brother-brother relationships and his search
            for information about his family lost in the holocaust.

            To everyone I see recently, I have been recommending Killers of the Flower Moon: The Osage Murders and the Birth of the FBI, by David Grann. That title says it all; I could not put it down.

            In the fiction category, it would be tough to beat Louise Erdrich’s The Last Report on the Miracles at Little No-Horse. Not to give anything away, long story short, it is a tale about a woman who assumes a priest’s identity and functions in that role for many years at a Native American reservation. These three are the best I have read since Catch-22.

            Where do you get your favorite lesson plan ideas? What is your favorite teaching resource?
            My favorite ideas basically come from (a) NPR, (b) The New York Times Tuesday Science section, and (c) trolling libraries and JSTOR to find real data for real students.

            Truth be told, I enjoy reading about our fascinating world and I’m lucky to be able to claim I’m “planning” when on these little excursions into what we used to refer to as the stacks.

            Expectations and Skills for Undergraduate Students Doing Research in Statistics and Data Science

            Fri, 09/01/2017 - 7:00am

            Jo Hardin is a professor in the department of mathematics at Pomona College. Her work involves analysis of different types of high-throughput genetic data that don’t conform to the usual assumptions needed for statistical analyses.

            As more statistics undergraduates participate in summer and capstone research projects, it becomes paramount for teachers to prepare them adequately for the experiences. Indeed, the most successful research students are those with both a strong understanding of foundational statistical methods and a fluent ability to wrangle data.

            Undergraduate research has long been considered one of the strongest high-impact educational practices. However, there are myriad paths to successful undergraduate research, and there is scant information about how to link successful research practices to the undergraduate curriculum.

            In recent years, the statistics and data science communities have come together to propose curriculum guidelines for undergraduate programs (GAISE, Statistics Guidelines, Data Science Guidelines). The suggestions are well thought out and meant to balance competing demands of time/units, student background, and existing curricular structure. The guidelines have been written to encourage modernization of standard curricula to catch up with new ideas being developed for the statistics and data science classroom.

            Of course, one important aspect of any curriculum is to set goals for the graduates of that program. That is, what skills are necessary for students coming out of a specific statistics or data science program who will enter either the workforce or a graduate program?

            Less common in current curriculum guidelines are details about how the pieces of the curriculum work together. In particular, we are concerned with how the course assignments and structure can support undergraduate research projects in statistics and data science.

            Almost every summer since I began my faculty position, I have worked with students on projects related to my own research areas. Often, those projects extend into year-long senior thesis projects or repeated summer projects. I have published with my students as first author or substantial contributors in Statistical Applications in Genetics and Molecular Biology, BMC Bioinformatics, Briefings in Bioinformatics, Environmental and Ecological Statistics, Computational Geosciences, and CHANCE. Certainly, some projects have been more successful than others; indeed, there are plenty of projects that did not result in a peer-reviewed publication. A project’s success often depends on factors unrelated to the curriculum (e.g., how conducive the project is to undergraduate exploration, whether the student is interested in the work, etc.) But most of the success of the project does come directly from the experiences the student has prior to starting the research.

            Skills

            As we all know, doing research takes myriad skills. The skills below are all taught to some degree within a standard curriculum. I submit, however, that many skills which typically get less attention are among the most valuable for research.

            Making an Argument

            The most important skill for successful research is the ability to make a convincing argument. Making an argument requires there to be a novel idea and a method by which to argue the point. Students can often approach the problem in different ways: theoretically (e.g., mathematical proof), simulation, or via a literature review. Knowing that any given idea can be argued in different formats is surprising/illustrative for students. By understanding there are different creative ways to solve a problem, they are given the freedom to harness their own skills and comfort with the research project.

            One of my recent projects involves creating prediction intervals for a random forest model. The novelty comes from the derivation of the appropriate standard error. There are a handful (not many) of papers on the topic, a few very theoretical papers, and a few that approach the problem in a different applied way. My student and I have had to work through how our ideas add to the literature and how those ideas can be synthesized into an argument. Our conversations circle back repeatedly to “what are we trying to argue, and how can we argue that effectively?”

            The classroom is an ideal place to demonstrate that there is almost never only one solution or argument to a problem. A simple comparison of mean versus median hypothesis testing shows two tests can address the same underlying scientific hypothesis. Simulation studies (e.g., to determine coverage rates for different bootstrapped confidence intervals) give a way of understanding a theoretical outcome.

            The curricular aspect to making an argument relies on the professor continuing to ask a student “how do we know that?” or “how can we argue that one test is better than another?” Students are often so caught up in the weeds of learning the techniques that they fail to reflect on the process by which the method was developed or by which it has become popular.

            Engaging with Theory

            The theoretical underpinnings of statistics have long been a cornerstone of most undergraduate programs. Certainly, my most productive research experiences have been those done with students who have strong knowledge of undergraduate topics such as probability theory, distribution theory, maximum likelihood, and regression modeling. And although some of my projects have built on those theoretical constructs, it is the intuitive theoretical grounding of core principles in statistics (e.g., sampling distributions, interactions) that are imperative to a successful research project. Indeed, whether a student can derive a particular moment-generating function is much less important than whether they understand that knowing every single moment of a distribution uniquely defines that distribution.

            A solid theoretical background builds not only strong intuition, but also an ability to read the literature and place the research in a larger framework of knowledge. With undergraduates, I do not try to prove results with measure theoretic tools. Instead, I often work with the students to simulate scenarios and gain an understanding of what others have done within that more theoretical framework. For the students to have new insights, they must be able to understand the general structure in which their work resides.

            A recent project used canonical correlation analysis to identify correlated pairs of linear combinations of variables. The setting is sufficiently complicated that it would be difficult to find the theoretical distribution underlying each correlated linear combination (keeping in mind that each pair is also correlated with other pairs), but the analysis is not useful unless there is a way for the practitioner to know whether a large correlation is actually statistically significant. We were able to derive a permutation algorithm to define significance (the method also doubled as a way to measure false positive and false negative rates). The permutation method, however, was not trivial to implement, and it required the students to understand how the distributional aspects are determined by both the linear combinations and the complex correlation structures.

            I suggest that many theoretical statistics and data science courses are already providing the needed background to make a student researcher successful. However, when teaching, for example, the Neyman-Pearson lemma, the intuition behind how we know what we know (and why it matters) is vastly more fundamental for the students’ future research capabilities than the detailed steps of the proof.

            Working Independently

            There is likely no question that a student’s ability to work independently is imperative for a successful research project. As busy advisers, a needy student can be an inordinate drain on our time. And if we are providing guidance at every step, then we might as well be doing the research ourselves. (One way to cut down on contact hours is for a pair or trio of independent students, who can be even more successful than an individual, to work together on a successful research project.)

            While absolutely important, one might argue that a student’s ability to work independently is not something that can be taught in a standard curriculum. I disagree. By providing the student with both practice working independently and time to reflect, all students can learn to generate their own ideas in a productive way.

            I encourage all upper division (and I dare say lower division) statistics and data science courses to contain project-based assignments with some degree of autonomy. That is, the project should have as one of the assigned tasks a directive for the student to do something independent (e.g., teach themselves a twist on a topic already covered in the course). Admittedly, projects can be time consuming to grade, especially in large classes. However, there are structures and tools to make projects more attractive for the instructor. For example, working in groups cuts down on the number of projects to grade, and peer assessment gives the students a sense of what other students have created. Also, such an assignment has the added benefit of allowing you to use it on letters of recommendation. I sometimes provide details about the topic a student has learned and communicated independently.

            GitHub and GitHub Classroom are resources that streamline both group work and assessment and are nevertheless valuable skills for statistics and data science students. Additionally, Jenny Bryan has put together Git resources that are streamlined and easy to follow.

            Along with doing the project, another aspect to developing independent research is providing structure for the student to reflect on their work. For any assignment (project or other), the student should be able to express what they did, why they did it, and what the next step should be. Reflecting on what they still do not understand can be incredibly valuable. One professor I know requires his students to reflect via a Google form with a mechanism running in the background to inform him if they don’t do it!

            A quick reflection on a notecard or as part of the end of the assignment teaches the student to deliberate on what they have done and to think about the next steps in the process. A strong research student will come to your meetings with both work accomplished and ideas for moving forward. The process by which they generate ideas for moving forward is not innate and can be learned through repeated practice.

            Wrangling Data

            I have included data wrangling as a core skill because it is increasingly important to almost every research project I see (in my group and in others). Indeed, even the theoretical projects on which I am involved often use examples that require substantial data wrangling. Additionally, I continue to see data wrangling as a core tenet that is overlooked in many curricula.

            Working with data is the only way to get good at working with data. Our students should be graduating with a fluency in programs like the dplyr R package. It is not only a vital aspect of having a successful research project, but it is the key to a successful career in any data-related field.

            Practice in data wrangling should come early and often, and the swirl R package and DataCamp platform use interactive tools to get students started. Requiring good data wrangling skills in your courses will benefit you and your students in the long run.

            Successful Research(ers)

            I’ve structured this article to focus on the learning goals associated with curricular choices to produce strong researchers (and new members of the workforce who can deal with the complex challenges they will face in a world full of data). There are many other choices a student makes along the way that can contribute to a successful research project. For example, engagement in a field outside of statistics and data science can generate excitement for solving a particular applied research project. Or working with new software programs (e.g., the quo function in dplyr version 0.7.1 as of June 22, 2017) can give the student a sense of being part of a larger community of statisticians and data scientists.

            Alas, the most important aspect of successful research is the degree to which you are excited about the project. If you love what you are doing, the student will sense that and be just as engaged. So, if there is something you want to work on, I implore you to assign an undergraduate student to the project, regardless of their background or the curriculum from which they come.

            Further Reading

            Curriculum Guidelines
            High-impact educational practices suggested by the Association of American Colleges and Universities

            GAISE Guidelines for Assessment and Instruction in Statistics Education (GAISE) Reports,

            Curriculum Guidelines for Undergraduate Programs in Statistical Science

            Data Science Guidelines

            Working Independently
            Projects that are a high-impact practice as defined by the Association of American Colleges and Universities

            Resources for Both Group Work and Assessment
            GitHub

            GitHub Classroom

            Jenny Bryan’s Git resources

            Practicing Data Wrangling
            Dplyr R package

            Swirl R package

            DataCamp platform

            Statistical Literacy and Journalism: The Road Less Traveled

            Fri, 09/01/2017 - 7:00am

            Trevor Butterworth is executive director of Sense About Science USA, a nonprofit organization that advocates for scientific and statistical literacy and communication. He is also a visiting fellow at Cornell University’s Alliance for Science. Butterworth is a former journalist who has written for The New Yorker online, Harvard Business Review, The Financial Times, and The Wall Street Journal. He attended Trinity College Dublin, Georgetown, and Columbia University’s Graduate School of Journalism.

             

            My first issue as editor of the college newspaper was met with a needling sneer from a rival publication, which, perhaps softened by a horizon of almost three decades, went something like this: “Trinity News is all stats; doesn’t Trevor Butterworth know that journalism is about words?”

            In retrospect, the review is amusingly prophetic and precisely the kind of detail that makes for a perfect introduction—or lede as one would say in journalese—to a just-so story about how a journalist became evangelical about the necessity and vitality of statistics to his profession. But at the time, I was stung. One didn’t become a writer to write about numbers.

            Despite Joseph Pulitzer’s conviction—advanced in his 1904 plea for the professionalization of journalism (The College of Journalism)—that there was “romance, human interest, humor, and fascinating revelations” in statistics—the truth of which should be discernible to the properly trained journalist—the American press did not, in the main, trust its audience with numbers, in part because it did not trust its journalists to report them correctly.

            As Jeffrey Dvorkin noted in 2004 during his tenure as National Public Radio’s ombudsman:

            One of the rarely admitted secrets about journalists is that many of us are functional “innumerates”—another way of saying “mathematically illiterate.” Oh sure, we can add and subtract reasonably well, but with some exceptions, journalists generally don’t know, understand, or are interested in numbers. As for more complex subjects such as statistics and probability, well … many journalists would be hard pressed to tell the difference between “average” and “mean.”

            That Dvorkin could conceive of innumeracy as a secret only “rarely admitted” is delightfully ironic; many journalists have made similar claims. As one journalism professor once put it to me, innumeracy was an open wound for everyone to see, allowing all manner of rotten claims to fester and go unchecked. It was evident in the howlers that any mathematically minded reader could spot the “massive” (percentage) increases that came from one per thousand turning into two per thousand, the replacement of precise quantification with portentous adjectives that turned laughable risks into certain causalities, the magic number that turned a discrete example into a trend (three).

            Sense About Science USA is a nonprofit organization that advocates for an evidence-based approach to science and technology and for clinical trial transparency.

            The original Sense About Science (SAS)—begun in the United Kingdom—established guiding principles for promoting scientific understanding and defending scientific integrity in the United Kingdom and Europe. A separate, legal entity to SAS UK, Sense about Science USA is committed to improving communication, transparency, and the use of evidence in the sciences.

            To be fair, journalists had periodically rebelled into numeracy. In 1989, The Washington Post’s Victor Cohn published a gem-like book, News and Numbers, with the rallying cry that, “We can be better reporters if we understand how the best statisticians—the best figurers—figure.”

            In the 1970s, “precision journalism” turned the news media into pollsters (thereby requiring stories about the margin of error every electoral season), while the rise of computer-assisted reporting revealed how coding and data could sometimes deftly, sometimes naively, reveal new ‘truths’ about society (foreshadowing the rise of data science and data journalism). Pulitzer would surely have been delighted to see the prize bearing his name finally going to stories that appeared to find the truth in statistics, if not necessarily with statistics.

            But these were minority pursuits. In the main, the conclusions of James Tankard and Paul Ryan, academics who studied how the media covered science in the 1970s and ’80s, held true: “Most journalists seem unable to judge whether numbers are really meaningful or accurate. Consequently, they either trust all figures or they trust none. And they tend to focus exclusively on a report writer’s conclusions, while ignoring specific numbers and data collection techniques.”

            I once belonged to that cohort that swung between avoidance and credulity, until one day—faced with a vertiginous plunge into unemployment—I hesitantly accepted an offer to take over a moribund project called STATS.

            Intellectually, I had been shaped by a preoccupation with language—both literary criticism and philosophy of language—and, ironically, it was close textual reading—the kind one did in the manner of I.A. Richards or ‘deconstruction’ in English class—that led me to think about the role numbers were playing in a story. I’m not suggesting this was particularly deep or required signing up to a theory of metaphysics; one simply imagined numbers as agents in a story and then tried to figure out what they were doing behind all those adjectives and elisions and bold proclamations. “When you say there is an increased risk of boils from eating bananas, how many boils and how many bananas are you talking about?” That sort of thing. The secret was understanding you didn’t need to be able to figure out the answer to these questions yourself; that was something a mathematician or a statistician could do for you.

            This is hardly revelatory—and, of course, it only marks a first basecamp in the ascent toward understanding statistics and the role statistics plays in so many facets of knowledge. But almost 15 years since I began, tentatively, asking these questions, much has changed in journalism and society. A generation marinated in the cultural prestige and economic value of data has entered journalism—and it increasingly understands that if journalism is to hold this world accountable, words are not enough.

            STATS, too, has changed dramatically to respond to this demand for statistical insight (which is evident in the number of journalists using our free statistical help service and the responses from those who attend our workshops). If we take the next logical step and develop the right visualized and interactive tools to help these journalists “see” statistical concepts in action in the kinds of stories they typically cover, then this generation will change journalism—accomplishing what Joseph Pulitzer imagined a century ago in ways he could not have imagined.

            Updated Guidelines for Statistics Education: The GAISE 2016 College Report

            Fri, 09/01/2017 - 7:00am

            Megan Mocko is a master lecturer at the University of Florida. Her focus is teaching introductory statistics in multiple formats: face-to-face, hybrid, and online. She studies techniques to improve learning for students with learning disabilities and students in the online learning environment, as well as teaching with technology.

            Michelle Everson is a professor and program specialist of statistics at The Ohio State University and former editor (2015) of the Journal of Statistics Education. Since earning her PhD in 2002, she has been teaching introductory and intermediate statistics courses. She is particularly interested in distance education and ways to actively engage students in online learning environments.

             

            In July 2016, the revised Guidelines for Assessment and Instruction in Statistics Education (GAISE) 2016 College Report was endorsed by the ASA Board. The GAISE revision committee consisted of 11 members, and these individuals surveyed the larger statistics education community, led panel discussions at the United States Conference on Teaching Statistics (USCOTS) and JSM, and delivered various webinars to gather information to inform the writing of GAISE.

            The updated report includes the same six recommendations for teaching introductory statistics at the college level as can be found in the original 2005 GAISE College Report with two emphases added to the first recommendation. Important changes in wording also were made across these recommendations:

            • Teach statistical thinking.
            • Teach statistics as an investigative process of problem solving and decision making.
            • Give students experience with multivariable thinking.
            • Focus on conceptual understanding.
            • Integrate real data with a context and purpose.
            • Foster active learning.
            • Use technology to explore concepts and analyze data.
            • Use assessments to improve and evaluate student learning.

            In addition to the inclusion of these new emphases, the original goals for students in introductory statistics courses were re-written in the form of learning objectives and two goals were added. The nine goals in the revised report are as follows:

              1. Students should become critical consumers of statistically based results reported in popular media, recognizing whether reported results reasonably follow from the study and analysis conducted.

              2. Students should be able to recognize questions for which the investigative process in statistics would be useful and answer questions using the investigative process.

              3. Students should be able to produce graphical displays and numerical summaries and interpret what graphs do and do not reveal.

              4. Students should recognize and be able to explain the central role of variability in the field of statistics.

              5. Students should recognize and be able to explain the central role of randomness in designing studies and drawing conclusions.

              6. Students should gain experience with how statistical models, including multivariable models, are used.

              7. Students should demonstrate an understanding of, and ability to use, basic ideas of statistical inference, both hypothesis tests and interval estimation, in a variety of settings.

              8. Students should be able to interpret and draw conclusions from standard output from statistical software packages.

              9. Students should demonstrate an awareness of ethical issues associated with sound statistical practice.

            The last two goals are new. They align with the increasing importance of these topics in statistical practice and public discourse. To make room for these new topics, a list of topics to omit or reduce in a first course was added to the main body of the document. In addition, the report has expanded appendices that provide multiple resources and examples to help instructors meet the GAISE recommendations and goals. The appendices focus on the following:

            • Evolution of introductory statistics and emergence of statistics education resources
            • Multivariable thinking
            • Activities, projects, and data sets
            • Examples of using technology
            • Examples of assessment items
            • Learning environments

            Read the full report.

            Following the ASA endorsement of the report, the GAISE revision committee has focused on sharing the report with the larger community of statistics educators. Allan Rossman delivered a presentation at the November 2016 American Mathematical Association of Two-Year Colleges (AMATYC) meeting, and an ASA webinar presented by three members of the revision committee took place in December 2016.

            At the 2017 USCOTS, five members of the revision committee led two breakout sessions in which participants were given the opportunity to experience active learning with real data as part of a mini data fest. Each breakout session was broken into five groups, and each group worked with a different data set. The data sets focused on youth health, airline flights, lacrosse, missing children, and highway fatalities. Each group was asked to explore multivariate relationships within the data set and come up with examples of multivariate relationships that could be used in an introductory course. Participants used many platforms to explore the data, including R, SAS, Minitab, iNZight, Statcrunch, and TinkerPlots.

            The five data sets used (including data dictionaries) and an overview slide for the breakout sessions can be found on the Consortium for the Advancement of Undergraduate Statistics Education (CAUSE) website.

            On May 22, three members of the revision team and four panelists from community colleges (Monica Dabos, Joe Gerda, and Kathy Kubo from College of Canyons and Rebecca Wong from West Valley College) presented a joint webinar with AMATYC. The panelists answered questions such as “What do our current students need to be productive members in the workforce?” “How did the panelists get started making changes?” and “How can the new GAISE report help with change?” View the webinar and a copy of the slides.

            An upcoming article in CHANCE magazine gives more insight into the process of revising the GAISE College Report, includes more discussion about the key recommendations, and ends with some challenges for the community.

            GAISE Committee Members
            Robert Carver, Stonehill College
            Michelle Everson (co-chair), The Ohio State University
            John Gabrosek, Grand Valley State University
            Ginger Holmes Rowell, Middle Tennessee State University
            Nicholas Horton, Amherst College
            Robin Lock, St. Lawrence University
            Megan Mocko (co-chair), University of Florida
            Allan Rossman, Cal Poly San Luis Obispo
            Paul Velleman, Cornell University
            Jeffrey Witmer, Oberlin College
            Beverly Wood, Embry-Riddle Aeronautical University

            Slip Slidin’ to the Mean

            Tue, 08/01/2017 - 7:00am
            Lyric © 2017 Lawrence M. Lesser, reprinted with permission

            Lawrence Lesser of The University of Texas at El Paso repurposed Paul Simon’s 1977 top-five hit “Slip Slidin’ Away” to teach regression to the mean.

            CHORUS: Slip slidin’ to the mean,
            slip slidin’ to the mean:
            when there’s imperfect correlation,
            you know you’re slip slidin’ to the mean.

            Well parents have daughter or son—
            their heights were all observed by England’s Francis Galton:
            extreme parents he did see
            had kids that regressed toward mediocrity!
            (Repeat Chorus)

            And I know a teacher who gave high praise
            to the students whose midterms were the highest A’s;
            those failing badly received rebuke—
            but the next test showed those extremes were a partial fluke!
            (Repeat Chorus)

            And I know a rookie who made the All-Star team
            and the cover of Sports Illustrated magazine.
            You can imagine what the coach thinks
            when the star has sophomore slump as if there was a jinx!
            (Repeat Chorus)

            JBES Highlights: Editor’s Introduction: Regime Switching and Threshold Models

            Tue, 08/01/2017 - 7:00am
            Kung-Sik Chan of the University of Iowa, Bruce E. Hansen of the University of Wisconsin-Madison, and Allan Timmermann of the University of California, San Diego

            This special issue of the Journal of Business & Economic Statistics (April) on regime switching and threshold models is motivated by the mounting empirical evidence of important nonlinearities in regression models commonly used to model the dynamics in macroeconomic and financial time series. Commonly cited examples include the very different behavior of second moments for many macroeconomic time series before and after the Great Moderation in the early eighties, the different behavior of U.S. interest rates during the Federal Reserve’s Monetarist Experiment from 1979–1982, and the behavior of a variety of risk indicators during the more recent global financial crisis. These are episodes that can be difficult to model in the context of standard linear regression models.

            The key difference between Markov switching models and threshold models is that the former assume that the underlying state process that gives rise to the nonlinear dynamics (regime switching) is latent, whereas threshold models commonly allow the nonlinear effect to be driven by observable variables but assume the number of thresholds and the threshold values to be unknown. However, it is often overlooked that the general formulation of the threshold model includes the Markov switching model. Thus, these two classes of models share many common features. From an econometric perspective, both classes of models are affected by the presence of unidentified parameters under the null, which poses challenges to inference, including the number of thresholds (or regimes) and their location. Empirically, both types of models can, by design, allow for discrete, nonlinear effects.

            The papers brought together in this special issue highlight both similarities and differences for threshold- and regime-switching models, offering many novel insights along methodological, computational, and empirical lines.

            Luc Bauwens, Jean-Francois Carpantier, and Arnaud Dufays, in “Autoregressive Moving Average Infinite Hidden Markov Switching Models,” study a class of Markov switching models in which regime switches only affect some parameters, while other parameters remain the same across regimes. Limiting regime switches to a subset of the parameters can lead to simpler models with fewer unknown parameters and better out-of-sample forecasting performance. In particular, the authors propose to decouple the regime switching dynamics for the mean and variance parameters.

            The methodology—developed by Bauwens, Carpantier, and Dufays—allows the number of regimes to be determined as part of the estimation process and so has no need to use extraneous criteria for selecting the number of regimes. Detailed empirical applications to quarterly U.S. GDP growth and monthly U.S. inflation show that the new class of “sticky infinite hidden Markov switching autoregressive moving average” models can lead to better forecasts than more conventional models. These findings are corroborated on a set of 18 additional macroeconomic variables.

            In their paper “Forecasting Macroeconomic Variables Under Model Instability,” Davide Pettenuzzo and Allan Timmermann compare a range of methods in common use in macroeconomic forecasting for handling parameter instability. Specifically, the paper focuses on comparing and contrasting approaches that assume small but frequent changes to the model parameters (time-varying parameter models) versus models that assume rare, but large (discrete) breaks to the model parameters. The paper considers breaks in the parameters of both the first and second moments of the modeled process and studies their impact using predictive accuracy measures that focus on either the conditional mean or the entire probability distribution of the outcome.

            In an empirical out-of-sample forecasting exercise for U.S. GDP growth and inflation, the authors find that models that allow for parameter instability generate more accurate density forecasts than constant-parameter models. Conversely, such models fail to produce better point forecasts. Overall, a model specification that allows for both time-varying parameters and stochastic volatility is found to perform best. Model combination methods also deliver gains in the performance of density forecasts, but fail to improve on the predictive accuracy of the time-varying parameter model with stochastic volatility. These results suggest that accounting for model instability can deliver better probability forecasts for key macroeconomic variables, whereas gains in predictive accuracy for traditional point forecasts are harder to come by.

            Jesus Gonzalo and Jean-Yves Pitarakis, in “Inferring the Predictability Induced by a Persistent Regressor in a Predictive Threshold Model,” introduce a predictive regression model with threshold effects and use it to construct tests that have power to detect episodic predictability arising from a persistent predictor. The null hypothesis being tested in the paper is one of no predictability versus the alternative of predictability triggered by threshold effects associated with a particular predictor variable. The tests developed are easy to implement and robust to possible threshold effects for auxiliary predictors not of interest to the forecaster. Moreover, the proposed test statistic is robust to the presence of certain unidentified nuisance parameters. An empirical application to predictability of stock market returns by means of valuation ratios finds evidence that the predictive power of these variables is stronger around recessions and reveals state-dependence in return predictability.

            Kung-Sik Chan, in “Testing for Threshold Diffusion,” studies continuous time diffusion processes that assume piece-wise linear drift and diffusion terms and develops a test for threshold nonlinearities in the drift of the process. In particular, Chan develops a quasi-likelihood test under the assumption that the diffusion term is constant, thus side-stepping the problem that, in general, the functional form of the diffusion term is unknown. A test for a single threshold is shown to have an asymptotic null distribution, which is a distribution of a functional of centered Gaussian processes. Chan develops ways to efficiently compute the p-value of the test statistic by bootstrapping its asymptotic null distribution. He also shows that the test statistic is consistent, derives its local power function, and extends the test to allow for multiple thresholds. Finally, simulations and empirical analysis of the term structure of U.S. interest rates are used to demonstrate the performance and usage of the test statistic.

            Bruce Hansen, in “Regression Kink With an Unknown Threshold,” develops methods for estimation and inference in regression kink models that can have an unknown threshold. The class of regression kink models explored are threshold regressions required to be everywhere continuous, but can have a kink at an unknown threshold. Hansen develops a toolkit for inference and estimation, including ways to test for the presence of the threshold and for estimating model parameters and conducting inference on the regression parameters and, more broadly, on the regression function. Inference on the regression function is shown to be non-standard due to the nondifferentiability of the regression function with respect to the model parameters. Empirically, the paper applies its methods to the study of the possibly nonlinear (threshold) relationship between growth and debt using a long-span time-series for the United States.

            Young-Joo Kim and Myung Huan Seo develop a procedure for testing for jumps in smooth transition processes in the paper, “Is There a Jump in the Transition?” The null model under the proposed test methodology is a threshold regression, while the alternative model is a smooth transition model. To conduct the test, the authors develop the asymptotic distribution of a quasi-Gaussian likelihood ratio statistic. The asymptotic distribution is defined as the maximum of a two-parameter Gaussian process that has a non-zero bias term. Kim and Seo show that asymptotic critical values can be tabulated and these depend on the transition function employed. Empirical critical values can be computed through simulations. The authors evaluate the finite sample performance of the test by means of Monte Carlo simulations and provide an empirical illustration through a model for the dynamics of racial segregation within cities across the United States.

            The paper, “Sharp Threshold Detection Based on Sup-Norm Error Rates in High-Dimensional Models,” by Laurent Callot, Mehmet Caner, Anders Bredahl Koch, and Juan Anders Riquelme develops a high-dimensional threshold regression model. The authors propose a new threshold-scaled Lasso estimator suitable for this class of models. The authors’ main theoretical contribution is a new sup-norm bound on the estimation error. This bound can be used to provide sharper insights into variable selection properties. The authors also provide an empirical investigation into the impact of debt on GDP growth using a multi-country data set.

            The paper, “Status Traps,” by Steven Durlauf, Andros Kourtellos, and Chih Ming Tan is an empirical application of threshold regression methods to study intergenerational mobility. The authors explore nonlinearities in children’s outcomes based on parental education and skills. The uncovered threshold processes imply persistent dynastic effects, which are interpreted as “status traps.” The empirical investigation is conducted with three distinct U.S. data sets (the PSID, NLSY, and administrative data), and the consistent findings across these data sets indicate the threshold effects are quite robust.

            Biqing Cai, Jiti Gao, and Dag Tjostheim, in “A New Class of Bivariate Threshold Cointegration Models,” study nonlinear cointegration effects in the context of cointegrated vector autoregressive processes with threshold effects. The paper only imposes cointegration between the processes outside a compact region and shows cointegrating parameters converge at the conventional rate (T). In addition, the authors establish a faster convergence rate for the estimators of the remaining in the cointegrated region (T1/2) than in the non-cointegrated region (T1/4). The authors study the finite sample properties of the estimators in a Monte Carlo simulation. In an empirical application to a two-state bivariate model consisting of the federal funds rate and the three-month treasury bill rate, the authors show the cointegrating coefficients are identical across regimes, while the coefficients determining the short-run dynamics differ across regimes.

            In “On Mixture Double Autoregressive Time Series Models,” Quodong Li, Qianqin Zhu, Zhao Liu, and Wai Keung Li study a class of mixture double autoregressive models whose mixing probabilities are allowed to vary over time. Double autoregressive processes allow autoregressive dynamics to affect both the conditional mean and the conditional variance as the heteroscedasticity of such processes are driven by past squared values of the process. Such processes resemble autoregressive models with ARCH dynamics. Li, Zhu, Liu, and Li establish stochastic properties for this class of processes, including conditions guaranteeing the existence of their moments. Further, they discuss methods for maximum likelihood estimation and inference with particular attention to the logistic mixture double autoregressive model. A simulation study and empirical example are used to illustrate the properties of the proposed model.

            In the paper, “Inference for Heavy-Tailed and Multiple-Threshold Double Autoregressive Models,” Yaxing Yang and Shiqing Ling develop methods for conducting inference on a class of multi-threshold double autoregressive models that can have heavy tails. Specifically, the authors establish consistence and convergence properties of the estimators of the thresholds. Other (nonthreshold) parameter estimators are shown to be asymptotically normal. Methods for determining the number of thresholds and diagnostic tools are developed in the paper. Finally, Yang and Ling illustrate their approach in an empirical application for daily crude oil prices.

            In “Threshold Estimation via Group Orthogonal Greedy Algorithm,” Ngai Hang Chan, Ching-Kang Ing, Yuanbo Li, and Chun Yip Yau develop a computationally efficient algorithm for estimating a self-exciting threshold autoregressive model with known autoregressive order and delay, but unknown number of thresholds. It is a three-step procedure that first uses a group orthogonal greedy algorithm (GOGA) to compute a solution path for screening potential thresholds, then applies a new high-dimensional information criterion and trimming procedure to eliminate spurious thresholds. The proposed method is shown to achieve consistent estimation of the thresholds at the rate of convergence, where is the sample size. Simulation experiments reported in the paper indicate the GOGA outperforms the group LASSO for estimating the thresholds. The authors illustrate their approach by revisiting the analysis of the U.S. real GNP data.

            2017 Causality in Statistics Award Winner Announced

            Tue, 08/01/2017 - 7:00am

            The American Statistical Association will award the fifth Causality in Statistics Education Prize to Ilya Shpitser, John C. Malone Assistant Professor of Computer Science at The Johns Hopkins University, at the 2017 Joint Statistical Meetings in Baltimore.

            Judea Pearl

            Ilya Shpitser

            2017 Prize Committee Members

            Onyebuchi Arah, University of California, Los Angeles
            Maya Petersen, University of California, Berkeley
            Dennis Pearl (co-chair), Penn State University
            Judea Pearl (co-chair), University of California, Los Angeles
            Felix Elwert, University of Wisconsin-Madison
            Daniel Kaplan, Macalester College
            Michael Posner, Villanova University
            Arvid Sjölander, Karolinska Institutet
            Tyler VanderWeele, Harvard School of Public Health

            Established in 2013 to “encourage the teaching of basic causal inference methods in introductory statistics courses” from a donation by Judea Pearl—recipient of the 2012 Turing Award and professor of computer science and statistics at the University of California, Los Angeles—the annual award recognizes the work of an individual or team that enhances the teaching and learning of causal inference in introductory statistics coursework. This year, the $5,000 award is being funded by Microsoft Research and Google.

            “While the study and practice of statistics is growing in popularity and demand in both academia and professional occupations, there remains a glaring gap when it comes to causal inference,” said Pearl, who is co-chair of the prize-selection committee. “Even with the recent development of causal inference tools, which are currently sweeping new insights and application areas, most statistics educators and textbooks do not provide any information on these tools,” he continued. “In giving this award, we not only recognize the dynamic efforts of renowned scholars, but also show other researchers and scientists that teaching causal inference can be fun and formative.”

            Ilya Shpitser has developed master’s-level graduate course material that takes causal inference from the ivory towers of research to the statistics student with a machine learning and data science background. It combines techniques of graphical and counterfactual models and provides both an accessible coverage of the field and excellent conceptual, computational, and project-oriented exercises for students.

            The winning materials of previous Causality in Statistics Education Award winners are available to download. The materials from this year’s winner will be available online in the early fall. Nominations for the 2018 award are being accepted until February 15, 2018.

            Update from the Division of Mathematical Sciences

            Tue, 08/01/2017 - 7:00am
            Michael Vogelius, DMS Director; Tie Luo, DMS Deputy Director; and Henry Warchall, DMS Senior Advisor

            With this article, the management team of the Division of Mathematical Sciences (DMS) at the National Science Foundation would like to provide an update about recent program activities from DMS and an outlook for the future. DMS plays a critical role in providing about 64 percent of all U.S. federal support for basic research at the frontiers of discovery in the mathematical sciences. DMS also supports training through research involvement of the next generation of mathematical scientists, conferences and workshops, and a portfolio of national mathematical sciences research institutes.

            Here we call attention to four recent funding opportunities we find particularly newsworthy. Two are calls for development of large-scale interdisciplinary research centers/institutes that involve collaboration between mathematical scientists and researchers from other scientific areas, and two are calls for activities to enhance and broaden graduate education in the mathematical sciences.

            Transdisciplinary Research in Principles of Data Science

            The Transdisciplinary Research in Principles of Data Science (TRIPODS) program aims to bring together the statistics, mathematics, and theoretical computer science communities to develop the theoretical foundations of data science through integrated research and training activities. Phase I will support the development of small collaborative institutes. Phase II (to be described in an anticipated future solicitation, subject to availability of funds) will support a smaller number of larger institutes, via a second competitive proposal process. All TRIPODS institutes will involve significant and integral participation by all three communities.

            The TRIPODS program is a part of the NSF initiative “Harnessing Data for 21st-Century Science and Engineering,” one of the “Ten Big Ideas for Future NSF Investments.” The TRIPODS program is co-funded equally by the NSF Division of Computing and Communication Foundations (CCF) and DMS. These investments are augmented by funds from the initiative “Growing Convergent Research at NSF” and the Office of Multidisciplinary Activities of the Mathematical and Physical Sciences Directorate.

            It is the hope of DMS that the TRIPODS program will emphasize to academic institutions forming programs in data science that such efforts naturally involve computer scientists, mathematicians, and statisticians. The TRIPODS Phase I proposals are under review, and it is anticipated that up to 12 three-year awards of approximately $500,000 per year will be made.

            NSF-Simons Research Centers for Mathematics of Complex Biological Systems

            The NSF-Simons Research Centers for Mathematics of Complex Biological Systems is a new program that expects to fund centers of five-year duration from a one-time call for proposals.

            The program focuses on research to understand emergent properties in biological systems. It welcomes proposals to establish centers at which sustained collaborations are facilitated between mathematical scientists and biologists to develop novel mathematical, computational, and statistical approaches to advance fundamental understanding of how and why emergent properties arise in molecular, cellular, and organismal systems. The program strongly encourages projects aimed at developing predictive frameworks for understanding phenotype.

            Projects are expected to include plans for significant effort in cross-disciplinary training of cohorts of future scientists, such as postdoctoral research associates, graduate students, and/or undergraduates from mathematical sciences and the areas of the biological sciences that are the focus of this activity. Each center also is envisaged to conduct convening activities, including short-term and/or long-term visitors’ programs, workshops, and/or outreach activities.

            The NSF-Simons Research Centers for Mathematics of Complex Biological Systems program is part of the NSF initiative “Understanding the Rules of Life: Predicting Phenotype,” another of the “Ten Big Ideas for Future NSF Investments.” The program is co-funded equally by the Simons Foundation and NSF, with 30% of the total investment furnished by DMS and 20% furnished by the NSF Directorate for Biological Sciences.

            Letters of intent and proposals are due August 10 and September 29, respectively. It is anticipated that three centers devoted to collaboration between mathematicians, statisticians, and biologists will be funded. Each center will be funded for a five-year duration with an annual budget of $2 million.

            Mathematical Sciences Graduate Internships

            By means of this activity, DMS aims to provide opportunities to enrich the training of doctoral students in the mathematical sciences through summer research internships in nonacademic settings. DMS has partnered with the Oak Ridge Institute for Science and Education (ORISE), which is managed by Oak Ridge Associated Universities (ORAU) for the Department of Energy, to establish the Mathematical Sciences Graduate Internships program.

            The immediate goal of the program is to arrange and support internships for approximately 40 students annually, primarily at the U.S. National Laboratories. The program is intended to introduce doctoral students in the mathematical sciences to important applications of mathematical or statistical theories outside of academia. The internships are aimed at students who are interested in learning about such applications, regardless of whether they plan to pursue an academic or nonacademic career.

            Not only will interns gain experience in the diverse uses of advanced mathematical tools at national laboratories, they will also become aware of the additional skills required for success in employment outside the traditional academic setting. The program is equally intended for students in pure and applied areas. It is planned to continue this collaboration with ORISE in 2018.

            Improving and Supporting the Transition to Graduate School in the Mathematical Sciences

            The NSF Directorate for Education and Human Resources (EHR) and DMS in collaboration invite proposals for projects designed to encourage and prepare U.S. students to pursue and succeed in graduate doctoral study in the mathematical sciences. Particular emphasis is placed on broadening participation of students from under-represented populations, including racial/ethnic groups under-represented in mathematics and statistics, individuals with disabilities, and women.

            The activity aims to support projects that are scalable to serve large numbers of students without large increases in cost and that are sustainable, that is, have continued impact without ongoing large influxes of grant funding. Projects are expected to involve mathematical sciences research as part of student training and/or educational research that produces new knowledge to help the community understand for whom and under what circumstances proposed activities are effective in preparing a diverse population of students to be successful in graduate school.

            About These New Initiatives

            DMS considers the first two activities to be parts of the DMS research institutes portfolio, which constitutes approximately 12% of the annual DMS investment. These new opportunities represent the continued evolution of the DMS institute portfolio, which the division aims to keep current, dynamic, and responsive to emerging needs of the mathematical sciences community. Both new programs were developed in close consultation with the communities involved, in particular through workshops that provided insight into current activity in these areas and perceived future needs. Both new programs are centered on an intellectual partnership between the mathematical sciences and another discipline, matched by significant financial investment from the other disciplinary partner. This arrangement reflects the worth of the interdisciplinary activity from a scientific viewpoint, in that it certifies the importance of these activities to both disciplines, and it also greatly leverages DMS investments.

            DMS considers the last two activities to be parts of the DMS workforce program portfolio, which constitutes approximately 10% of the annual DMS investment. These new opportunities address two distinct community needs in support of the development of the next generation of mathematical scientists.

            First, employment data show the majority of mathematical sciences PhD recipients take employment other than conventional academic tenure-track positions, yet many U.S. graduate programs in the mathematical sciences do not provide students with needed information about potential nonacademic career paths. The Mathematical Sciences Graduate Internships program is an early step toward raising doctoral students’ awareness of potential rewarding nonacademic careers.

            Second, despite substantial efforts by the mathematical sciences community and investment by funding agencies, current data indicate both the percentage of women and percentage of students from under-represented groups entering doctoral programs and receiving doctoral degrees in the mathematical sciences have remained relatively constant since 2004, and these levels are well below the representation of these groups in the general population. The activity in Improving and Supporting the Transition to Graduate School in the Mathematical Sciences aims to catalyze cost-effective community projects based on proven techniques to address this under-representation.

            Outlook for the Future

            The congressional appropriation for the fiscal year 2017 budget had not been finalized. The expected fiscal year 2017 budget for DMS is $233,512,000, which represents a small decrease of approximately $400,000 from the 2016 level. The president’s fiscal year 2018 budget request to Congress for the NSF will result in a decrease in the DMS budget of approximately $24,000,000, roughly a 10% reduction. The highest priorities for DMS in this challenging budgetary climate are to maintain, to the extent possible, investments in its core activities, namely the disciplinary programs that fund unsolicited proposals for research by individual investigators and the research institutes portfolio.

            Looking further into the future, the Mathematical Sciences Research Institutes program will hold an open competition [in fiscal year 2019]. Proposals are invited for new institute projects from U.S. sites, as well as renewal proposals from any of the currently supported U.S.-based Mathematical Sciences Research Institutes. Awards from this competition are anticipated to begin in fiscal year 2020. DMS is committed to maintaining investment in its research institutes portfolio at a level of 12–14% of the total DMS investment over the long term.

            ASA Census at School Program Exceeds 50,000 Students

            Tue, 08/01/2017 - 7:00am

            The American Statistical Association’s U.S. Census at School program—a free international classroom project that engages students in grades 4–12 in statistical problem solving using their own real data—has exceeded the milestone of 50,000 students.

            The program began in the United Kingdom in 2000 to promote statistical literacy in school children and has included participants from the UK, New Zealand, Australia, Canada, South Africa, Ireland, Japan, and the United States. The U.S. component of Census at School launched in 2010 and is hosted by the American Statistical Association. It has now reached 57,103 students with 2,119 registered teachers from all 50 states, plus the District of Columbia, Puerto Rico, the Virgin Islands, and Guam.

            Census at School is a web-based project. Under the direction of his or her teacher, each student anonymously completes an online survey. Only the teacher can download the class census data via a password, though others can take random samples of other participating students. Together, the students analyze their class data and compare those results with results from random samples of other participating students.

            Random Samplers Offer Clean and Messy Data
            Census at School New Zealand now hosts the random sampler for the international Census at School data, New Zealand data, and cleaned U.S. data. The online random sampler allows students and teachers to take random samples up to size 1,000 from the international, New Zealand, or U.S. database and either download the data or start up the free online iNZight Lite software with the data already loaded and ready for analysis. The international database includes data from Australia, Canada, New Zealand, the United Kingdom, and the United States.

            U.S. Census at School also provides a random sampler to generate a sample from the entire messy U.S. database. Some teachers prefer to take samples of messy data to provide their students with practice cleaning and investigating uncleaned data. For other teachers, taking a random sample of clean U.S. data from the international random sampler makes the program more accessible for their students, especially in the younger grades.

            For more information about the international random sampler, accessing cleaned U.S. data, or downloading data into iNZight Lite, read “Technology Insights” in Statistics Teacher.

            The online survey consists of 13 questions common to children in every participating country and a few questions specific to children in each country. The common questions are related to measurement—length (height, arm span, foot length), travel time to school, reaction time to an online applet, time to complete an online memory test—and category—favorite sport or activity. The U.S. questionnaire has additional questions about text messaging, hours of sleep, technology usage, future plans, allergies and preferences (i.e., foods, music, school subject, their ideal super power). All questions lead to a variety of categorical and quantitative responses teachers can use in teaching statistics concepts and students can explore.

            Students engage in statistical problem solving using Census at School by formulating questions that can be answered with the data, collecting and selecting the appropriate data, analyzing the data, and making appropriate conclusions in context.

            The Census at School program is self-contained and includes detailed instructions, instructional webinars, a PowerPoint presentation, lesson plans, and other resources. Teachers comfortable with statistical concepts, problem solving, and data analysis can begin using the program in their classes immediately.

            Getting Involved

            The ASA is seeking champions to expand the U.S. Census at School program. Champions can be teachers who use the program in their classes or statisticians and statistics educators who assist teachers who are not yet comfortable with statistics and statistical problem solving. There are a variety of ways to get involved, including sharing information about the program with local schools, writing lesson plans, and teaching local workshops for teachers. For those interested in teaching local workshops, the ASA will provide materials.

            The ASA also is building online Census at School resources and seeking those interested in writing new U.S. Census at School lesson plans or adapting international Census at School lesson plans for U.S. data. Those teaching grades 4–12 pre-service teachers might consider encouraging them to create lesson plans using U.S. Census at School data and submit them to the Statistics Education Web (STEW), an online bank of peer-reviewed lesson plans for K–12 teachers.

            STEW lesson plans relating to Census at School will be published on the Census at School website in the resources area. Lessons or potentially related articles also may be published in Statistics Teacher, an online journal published by the ASA/NCTM Joint Committee on Curriculum in Statistics and Probability for Grades K–12.

            Educators teaching or advising undergraduate or graduate statistics students might consider encouraging or requiring them to get involved in service learning by working with grades 4–12 teachers and students to incorporate Census at School and enhance their statistical problem-solving skills.

            Other ideas to enhance and expand the program are welcome. Contact Rebecca Nichols, ASA director of education, about these or any efforts regarding service learning or other activities.

            Summertime and the Living Is …

            Tue, 08/01/2017 - 7:00am

            Roll out those lazy, hazy, crazy days of summer
            Those days of soda and pretzels and beer.

            It’s August, but despite what Nat King Cole may have thought, the days are hardly lazy for the statistics profession. Of course, the main event for me is the huge assemblage of statisticians at the Joint Statistical Meetings in Baltimore. I suspect you will be reading this either in the middle of, or just after the conclusion of, JSM.

            I hope it is, or was, a truly rewarding experience.

            While the agenda is full of technical sessions, continuing education courses, workshops, committee meetings, section meetings, mixers, receptions, and more, it serves as the golden opportunity for me to interact with others in the field. This is the time when those people you have heard of, read about, purchased books by, or listened to are there in person. Meet the person, match the name with the face, discuss ideas, and forge ahead with new collaborations.

            Of course, you can make a vacation around JSM. My late wife and I used to do exactly that. We would fly the three kids to Chicago, where their aunt and uncle would spoil them. I would attend JSM sessions, and Debbie would sight see (okay, me too.) It was truly a win-win-win situation.

            This gathering, with all its different topic areas, always reminds me of John Tukey’s famous line about the statistician getting to play in everyone’s sandbox. This also reminds me of Lenore Skenazy’s delightful opinion piece in the June 21 Wall Street Journal, “If You’re a Kid, the Experts Want You to Have a Fun-Free Summer.” She cites Karl Neuman of the American Academy of Pediatrics, who said, “… [T]he risk of illness increases … digging wet sand.” However, he adds, “Dry sand presents problems, too.” The article also notes that the website KidsTravelDoc.com states that only with a lot of do’s and don’ts is frolicking in the sand a healthy activity. This is attributed to the U.S. Environmental Protective (sic) Agency. So in addition to messing up summer and mangling the name of the EPA, they attribute this incorrectly to the EPA—my former workplace for more than 40 years. By the way, neither Skenazy nor I could find the EPA’s caveats on sandbox activities. I’ll stick with Tukey.

            But back to JSM, I am reminded of a former Environmental Protection Agency (EPA) colleague, Ron Shafer. A few weeks before JSM 1993 in San Francisco, I was telling Ron this would be a huge assembly of thousands of statisticians. What would occur if the unthinkable happened: a major earthquake? (Just four years earlier, the World Series was interrupted by the major Loma Prieta earthquake moments before the third game was to start.) Without a moment’s hesitation, Ron responded, “Ah, a return to certainty!”
            I remember taking one of the courses offered, Rank Set Sampling. What impressed me was not only the quality of the instruction (Thank you, Dick Gilbert and Bimal Sinha.), but also the questions and interaction from the enrollees in the course. It was truly an interactive affair. Fondly, I also remember taking a metadata course from the late Ingram Olkin. Wasn’t it wonderful how this elderly scholar was full of energy and so proficient in this new and burgeoning field?

            I also remember the standing-room-only session regarding sports statistics with a speaker who had stalked general managers of several Major League Baseball teams to get a job doing statistical analysis for the club. Yes, this was the golden age of Moneyball. If you follow this column, you know my thoughts about statistics and baseball from the April issue. Incidentally, because I can’t resist, The Wall Street Journal carried a story on the “new” strategy of the Houston Astros. Apparently from 2012 through 2016, the Astros had more strikeouts than any other team—and by quite a margin. This year, with some acquired new players, they are last in strikeouts. So, what is the difference? The Astros now tell their players to hit a pitch if it looks good, thereby contradicting the conventional wisdom of working the counts and trying to tire out the pitchers. (This worked for the kind of ball I played where the pitchers were not that good, so waiting for a base on balls was not a bad suggestion.) But back to the majors, I could never really understand that conventional strategy since the relief pitchers are generally pretty good at what they do, so exhausting the starter may not yield much. Looks like it is working. As I write this, the Astros are also leading the majors in home runs.

            I also want to throw a pitch (Catch the segue?) to activity in JSM committees and sections. In prior years, I have served as both the program chair and general chair of the Statistics and the Environment Section. I also served five years as chair of the Statistical Partnerships Among Academe, Industry, and Government (SPAIG) Committee. It is quite true that the more you put into ASA efforts, the more you get out. It is truly rewarding to be an active participate in the activities of the sections, chapters, and committees. So, get involved and help your profession grow!

            As you might imagine, arranging and coordinating all the activities of JSM require considerable work. Hats off to the ASA staff who does this so well year after year. There are an awful lot of i’s to dot and t’s to cross, and the meetings staff stay on top of it all. My thanks to them for all these efforts.

            But it is not just the ASA that keeps busy in summer. I have been fortunate enough to travel to various campuses to see firsthand some excellent activities that go on during the (not so) off time. In June, I visited the University of Iowa and addressed the Iowa Summer Institute in Biostatistics. This is a research education program funded by the National Institutes of Health with the goal of exposing undergraduate and graduate math majors to the field of biostatistics. The program involves having students from universities that may not even have formal statistics departments come to Iowa City to be exposed to biostatistics topics that spur their interest. I understand there are similar NIH-supported programs at five other universities.

            I also attended a STEM boot camp at George Mason University. The students were high-school graduates with analytical aptitude about to enter their undergraduate studies at Mason. The boot camp exposed them to a glimpse of what exciting areas exist in the STEM fields. It was my personal pleasure to present some of the areas in which proper statistical analysis made an impact on health. I hope I won over some students in the statistical direction.

            At a recent trip to Purdue University, I observed the Statistics Living-Learning Community program, which is geared toward undergraduate sophomores. One told me he can hardly wait for summer so he will have more time for research. Hmmm, why let course time bog you down? Clearly, priorities have changed since my sophomore summer. Although I was a waiter that summer and suspect I learned more about people and human nature than could ever be taught in a class or by doing research. Hardly a wasted summer for me!

            And, of course, many of you may have attended the International Statistical Institute meeting in Marrakech, Morocco. As I write this, I am preparing to go there, but as you read this, I will already have been there! So what tense do you use to describe this?

            Enjoy summer, but keep busy.

            Roll out those lazy, hazy, crazy days of summer
            Dust off the sun and moon and sing
            a song of cheer

            Jeff Wu Receives 2017 Box Medal from ENBIS

            Tue, 08/01/2017 - 7:00am

            Georgia Tech’s Stewart School of Industrial & Systems Engineering (ISyE) announces that Coca-Cola Chair in Engineering Statistics and Professor Jeff Wu has received the 2017 Box Medal Award from ENBIS, the European Network for Business and Industrial Statistics.

            Jeff Wu

            The Box Medal is named after George Box, the late British-American statistician who is considered one of the greatest statistical minds of our time. Box was extremely influential on Wu’s work during his formative years as a young academic at the University of Wisconsin, Madison, where Box was also a professor.

            In a 2015 interview with professor Hugh Chapman of Acadia University and professor Roshan Joseph of ISyE, Wu affirmed that Box was a tremendous influence: “[Box] was a great scholar and a great lecturer. His opinions and passion for work were contagious. … I respected him a lot.”

            According to the ENBIS website, the Box Medal honors the legacy of George Box and is awarded each year to “an extraordinary statistician who has remarkably contributed with his work to the development and the application of statistical methods in European business and industry.”

            The ENBIS press release announcing Wu as this year’s Box Medal recipient stated that “with the medal, the link between two great statisticians is strengthened even further.”

            The press release also specified that Wu was chosen for his many contributions to the study of statistics, as well as “his ability to clearly explain complex concepts … and for systematically passing on his knowledge.” Wu has supervised 45 PhD students in the course of his career, many of whom are active researchers in the statistical sciences.

            Wu will accept the Box Medal at the ENBIS conference, held from September 9–14, in Naples, Italy. While there, he will also deliver a keynote speech on September 12.

            Wu earned a bachelor of science in mathematics from National Taiwan University in 1971 and a PhD in statistics from the University of California, Berkeley in 1976. He has been a faculty member at the University of Wisconsin, Madison; the University of Waterloo; and the University of Michigan.

            He is known for his work on the convergence of the EM algorithm; resampling methods; nonlinear least squares; and sensitivity testing and industrial statistics, including design of experiments, robust parameter design, and computer experiments. He also has been credited for coining the term “data science” as early as 1997.

            Wu has received several awards, including the COPSS Presidents’ Award (1987), the Shewhart Medal (2008), the R. A. Fisher Lectureship (2011), and the Deming Lecturer Award (2012). He is an elected member of Academia Sinica (2000) and the National Academy of Engineering (2004) and has received many other awards and honors, including an honorary doctorate from the University of Waterloo.

            He has published more than 170 peer-reviewed articles and two books. He was the second editor of Statistica Sinica.

            Biopharmaceutical Symposium on Tap for October in Savannah

            Tue, 08/01/2017 - 7:00am

            The 24th meeting of the Biopharmaceutical Applied Statistics Symposium (BASS XXIV) will be held October 23–27 at the Hotel Indigo Savannah Historic District in Savannah, Georgia.

            One-hour tutorials on diverse topics pertinent to the research, clinical development, and regulation of pharmaceuticals will be presented October 23–25 by speakers from academia, the pharmaceutical industry, and the U.S. Food and Drug Administration.

            For the first time, BASS will offer a poster session. Also, two parallel two-day short courses will be presented October 25–27.

            Popular features of BASS are the keynote address, reception dinner, and FDA/industry/academia session.

            BASS is a nonprofit entity established to support graduate studies in biostatistics. It has supported more than 50 master’s or doctoral students in biostatistics. For more information, contact the BASS registrar at rewhitworth@gmail.com or BASS chair, Tony Segreti.

            Getting Paid: How to Determine Your Fee

            Tue, 08/01/2017 - 7:00am
            Stephen Simon This column is written for anyone engaged in or interested in statistical consulting. It includes articles ranging from what starting a consulting business would entail to what could be taught in a consulting course. If you have ideas for articles, contact the ASA’s Section on Statistical Consulting publication’s officer, Mary Kwasny.

            Stephen Simon is a part-time independent statistical consultant and part-time faculty member in the department of biomedical and health informatics at the University of Missouri-Kansas City. He writes about statistics, evidence-based medicine, and research ethics.

            If you are an independent statistical consultant, one of the earliest choices you must make is how to bill for your services. You can either bill by the hour or bill by the project. There are trade-offs between the two approaches.

            I like billing by the hour. It doesn’t require a lot of up-front planning. You don’t have to worry about clients sneaking extra work in by changing the scope of the project. In fact, you are hoping your work is so impressive your client will want you to do even more.

            A survey published in a 2006 newsletter of the Statistical Consulting Section (v23.1) put the median consulting rate at $130 per hour. In 2017, you should ask for more, especially if you have advanced degrees and/or specialized experience.

            It is okay for you to add the time you travel to and from meetings with your clients to your total bill. I’ll charge for travel if it is more than 15 minutes, but not if I can stop by easily on the way to or from my regular job.

            General professional development is on your own dime. You can, however, charge for the time you spend learning new software and new statistical techniques if those are specifically required by your client and your client is aware of this and this is but a small fraction of your total hours. Don’t use your client to get a head start on that data science certificate you want.

            Your clients may not like the open-ended nature of billing by the hour, and you may end up having to place an upper bound on the number of hours you will need to complete the project. This combines the worst of hourly billing and flat billing. If you exceed your cap, you eat the cost, but if you finish early, you don’t get a bonus.

            I push for a soft ceiling, where I promise to not exceed a certain number of hours without checking first. It also helps to show your clients regular evidence of your progress so they don’t think they’re throwing money down a black hole.

            You don’t have to charge the same amount for each client. I offer a break for graduate students because I remember how tight money was when I was slaving away on my own PhD. You can also offer discounts for clients who bring you a lot of business, because one client with 20 billable hours per week is a lot less work than 10 clients with two billable hours per week apiece.

            You can also charge more for clients who make special demands. If your client insists on owning any programming code you produce or requires you to use a software program they love and you hate, a 25–50 percent hike in your standard consulting rate is not unreasonable.

            Take some time at the beginning of each new year to think about increasing your hourly rate. Like a fine wine that gets better with age, the consulting you do gets more valuable as you acquire more experience. You might need a bit of negotiating with current clients. Or you can tell them they are getting a “long-term customer” discount and only charge the increased rate for new clients.

            Billing by the project is more work up front, but you can make a lot more money this way if you play your hand well. Charging by the project encourages your client to perceive your services in terms of the value you provide.

            It also doesn’t hurt that your clients are likely to overestimate the amount of time they think you will need to do the work because they are thinking in terms how much time it would take them to do this work. You do become more efficient as you gain experience, so if you charge the same flat fee for a succession of similar projects, you are actually getting a pay raise with each project.

            If you bill by the project, you must define the scope of your work in writing. This includes specifying reasonable expectations of the quality of data they deliver to you. When your client wants to add on, you need to renegotiate your fee.

            You can probably get a good sense of the scope of a project after the first meeting. If you need to spend more time understanding all the requirements of a project, ask for that time, but put a cap (maybe five or 10 hours) on the amount of time you need to produce an accurate estimate of your fee.

            The biggest risk to billing by the project is underestimating the amount of work required. It can’t hurt to ask for more money if you realize halfway through the project you’re in way over your head. Explain the unexpected developments that caused the extra work and hope for the best. You may just have to swallow your losses and try to estimate better in the future. Don’t cry too much. Unless all your estimates are too optimistic, the money lost on projects where you underestimate your effort will be more than compensated by the projects in which you finish earlier than you expected.

            When billing by the project, you do not have to wait until the project is complete before getting paid. Negotiate for some of the money before you start the work (50% is not unheard of) and more as you complete key intermediate steps in the analysis.

            There’s an ethical concern with billing by the hour that has a flipped ethical concern with billing by the project. If you bill by the hour, you might be tempted to pad the analysis with unnecessary work just to get a few extra bucks. If you bill by the project, you might be tempted to finish early by skipping some of the quality checks and assessments of assumptions your client deserves to have. Your clients will often not recognize when you are padding or cutting corners, so you must be honest with yourself about the proper amount of work to put in.

            One final word. You will find clients who expect you to work for an outrageously small rate. Please say no. When statistical consultants work at substandard rates, it is bad for the entire profession. If money is not important to you, consider pro bono work instead with a group like Statistics without Borders.

            Pages