AmstatNews

Subscribe to AmstatNews feed
Updated: 41 min 50 sec ago

Notes from the Chair of the Section on Physical and Engineering Sciences

Thu, 03/01/2018 - 6:00am
Pete Hovey, 2018 SPES Chair

    I know it is a little late, but Happy New Year!

    I’ve been a SPES member for at least 20 years, and I still didn’t realize how active SPES is until I took on the role of chair this year. I am taking this opportunity to remind you of the many activities SPES sponsors and invite you to participate in at least one this year.

    Networking is vitally important in any career, and you can meet your colleagues in SPES at three conferences. First up is the 2018 Joint Research Conference on Statistics in Quality, Industry, and Technology. This is a joint meeting of the 25th Spring Research Conference on Statistics in Industry, which SPES jointly sponsors with the Institute of Mathematical Statistics, and the 35th Quality and Productivity Conference, which is sponsored by the ASA’s Section on Quality and Productivity (Q&P). The joint conference is being held June 11–14 in Santa Fe, New Mexico. This is a small regional conference that provides a great opportunity for new researches to get to know the SPES and Q&P communities. Send questions by email.

    The annual Joint Statistical Meetings (JSM) will be held in Vancouver, BC, Canada, this year from July 28 to August 2. SPES will host a variety of invited and contributed sessions during which you can learn about new statistical methods and applications to a variety of physical and engineering sciences. And don’t forget to attend the business meeting/mixer, which SPES usually cosponsors with other sections.

    The last SPES-sponsored conference of the year is the 2018 Fall Technical Conference being held October 3–5 in West Palm Beach, Florida. This conference is cosponsored by the ASQ Statistics Division and the ASA’s SPES and Q&P sections. The theme is “Statistics and Quality: Riding the Big Data Wave.”

    A continuing SPES program is the Marquardt Memorial Industrial Speakers Program, which is funded by a generous endowment made by Margaret Marquardt in memory of her late husband, Donald Marquardt, who was an ASA Fellow and former ASA president. The program’s objective is to familiarize students with the role of statisticians in industry, an application area to which students often are not exposed. The program seeks to fill this gap by bringing experienced industrial statisticians to campus to talk directly with students about their work and industrial experiences. If you would like to have a speaker visit your campus or if you would like to tell the world about life as an industrial statistician, contact the program’s chair, Vaneeta Grover.

    We are also interested in new initiatives to provide services to our members. Currently, the ASA is promoting an initiative to improve mentoring in the statistical profession. If you have an interest in mentoring and would be willing to help SPES develop a mentoring program, send me a note.

    SPES is open to any type of career development programs you think would be useful. If you have an idea, please contact me or any of the officers to see what we can do to help implement it. Also, if you want to add a leadership role to your résumé, please consider running for a SPES office. The jobs don’t require an excessive amount of time and you get the chance to meet some interesting and enthusiastic colleagues.

    Alicia Laura Carriquiry

    Thu, 03/01/2018 - 6:00am

    Affiliation
    President’s Chair in Statistics (2016-)
    Distinguished Professor of Liberal Arts and Sciences (2010-)
    Director, Center for Statistics and Applications in Forensic Evidence (2015-)

    Previous Positions
    Professor of Statistics, Iowa State University (2000–2009)
    Associate Provost, Iowa State University (2000–2004)
    Associate Professor, Iowa State University (1996–2000)
    Assistant Professor, Iowa State University (1990–1995)

    Educational Background
    Iowa State University: PhD, Statistics/Animal Genetics (1989)
    Iowa State University: MSc, Statistics (1986)
    University of Illinois, Urbana: MSc, Animal Genetics (1985)
    Universidad de la Republica: BS, Agricultural Engineering (1982)

    About Alicia
    Alicia Carriquiry was born in Montevideo, Uruguay, in 1957. She earned a BS in agricultural engineering from the Universidad de la Republica (at the time, the only university in Uruguay) in 1982. She truly hated her first job, and this motivated her to pursue a graduate degree in an area of interest to her. The opportunity arose soon after she graduated from college, when a professor from the University of Illinois who was visiting Uruguay offered her an RA in his animal breeding program.

    Carriquiry completed an MSc in animal breeding and genetics in Urbana-Champaign in 1985. Also that year, a professor from statistics at Iowa State University approached her with an offer to join his group. Carriquiry moved to Ames and earned her doctoral degree in 1989. In Ames, she also met her husband of 30 years, Wolfgang Kliemann, who was an assistant professor in mathematics at the time. So that ISU would not lose him, Carriquiry was hired in 1990 for a tenure-track assistant professor position, half in statistics and half in agricultural economics. She was promoted to associate professor with tenure in 1996 (and moved to statistics full time), to professor in 2000, and to distinguished professor in 2010. Carriquiry was the first woman to become full professor in statistics at Iowa State and the first Latina/o to become distinguished professor at ISU. Between 2000 and 2004, Carriquiry was associate provost at ISU, in charge of research.

    Carriquiry’s research has always focused on Bayesian methods and their application in various disciplines. She has worked extensively with human nutritionists on problems as diverse as survey design to measurement error modeling and density estimation. More recently, Carriquiry was principal investigator on a large award from the National Institute of Standards and Technology that helped establish the Center for Statistics and Applications in Forensic Evidence, which she directs. Carriquiry has been a prolific writer (more than 130 peer-reviewed papers) and has raised more than $35 million in research funding. Her proudest achievement is the 20 doctoral students who have already completed (or are in the process of completing) their doctoral work under her mentorship.

    Carriquiry is an elected member of the National Academy of Medicine and a Fellow of the American Association for the Advancement of Science, American Statistical Association, Institute of Mathematical Statistics (IMS), International Society for Bayesian Analysis (ISBA), and International Statistical Institute. She was a member of the board of trustees of the National Institute of Statistical Sciences, president of ISBA, vice-president of the ASA, and executive secretary of IMS. She has participated in multiple national and international panels and committees and currently advises governments in Asia, South America, and North America.

    Rachel Schutt

    Thu, 03/01/2018 - 6:00am

    Affiliation
    Managing Director at BlackRock where she leads Data Science together with Sherry Marcus.

    Educational Background
    Columbia University: PhD, Statistics (2009)
    New York University: Master’s Degree, Mathematics (2003)
    Stanford University: Master’s Degree, Engineering-Economic Systems and Operations Research (1999)
    University of Michigan: Bachelor’s Degree, Honors Mathematics (1997)

    About Rachel
    Rachel Schutt was the Chief Data Scientist of News Corp where she oversaw the company-wide data strategy as an executive on the senior technology leadership team. There she established the company’s first data science team for Dow Jones, the Wall Street Journal, and other brands. Schutt was named a World Economic Forum Young Global Leader in 2015 and is on the 2014 Crain’s New York Business 40 under 40 list.

    She has also been at the forefront of data science education. While working at Google Research (2009–2012), she recognized an emerging skill set (hybrid software engineer-statistician) was required. This skill set was not being taught in universities because it spanned traditional departmental lines and represented a new space of engineering, computational, and statistical problems coming out of technology companies. So to train the next generation of data scientists, Schutt proposed, designed, and taught the first Introduction to Data Science course at Columbia University (and one of the first such courses in the country). This course became the basis for the book she co-authored with Cathy O’Neil, Doing Data Science, published in 2013. Other university curricula now reflect the initial structure and content of her course. She is a founding member of the Education Committee for the Data Science Institute at Columbia.

    While at Google Research, Schutt was part of the machine learning group in New York and holds patents based on her work in social networks, large data sets, experimental design, and machine learning.

    Schutt is on the advisory board for Harvard’s Institute for Applied Computational Science (IACS).

    She was born in Boston, Massachusetts, in 1976 and grew up in Cambridge, England, and Princeton, New Jersey. She was interested in math starting at a young age and found solving problems and puzzles fun and calming. When she was five years old, her father realized the girls at her primary school were being directed to practice knitting while the boys solved math problems. He intervened and came to the class to teach set theory to the girls. Schutt’s interest in math persisted throughout college, where she studied theoretical math. She worked for several years in a variety of jobs, and then—after having a chance conversation with Andrew Gelman—she returned to earn her PhD in statistics. Gelman became her adviser at Columbia along with Regina Dolgoarshynnikh. Schutt’s thesis work was on the spread of contagious processes in networks.

    Susan A. Murphy

    Thu, 03/01/2018 - 6:00am

    Photo by Eliza Grinnell

    Affiliation
    Harvard University

    Educational Background
    Louisiana State University, Baton Rouge: BS, Mathematics (1980)
    The University of North Carolina at Chapel Hill: PhD, Statistics (1989)

    About Susan
    Susan Murphy is a professor of statistics and computer science at the Harvard John A. Paulson School of Engineering and Applied Sciences and Radcliffe Alumnae Professor at the Radcliffe Institute, Harvard University. Prior to joining Harvard in September 2017, she was the H.E. Robbins Distinguished University Professor of Statistics, professor of psychiatry, and research professor at the Institute for Social Research—all at the University of Michigan.

    Susan’s present research focuses on causal inference and sequential decision-making. She works on both data analysis and design of experiments to inform the sequencing of treatments, as well as how online algorithms can be used both in experimental designs and in treatment design in mobile health.

    Susan is a member of the National Academy of Sciences and National Academy of Medicine, both of the US National Academies. In 2013, she was awarded a MacArthur Fellowship for her work on experimental designs to inform sequential decision-making. She is a Fellow of the College on Problems in Drug Dependence, a member of the International Statistical Institute, a Fellow of the American Statistical Association (2000), and a Fellow of the Institute of Mathematical Statistics. She is also a former co-editor of the Annals of Statistics and delivered the IMS Wald Lectures in 2015.

    Susan grew up in southern Louisiana and, as an adolescent and college student, always found mathematics to be beautiful and accessible. While attending Louisiana State University, she realized mathematics could be a career (!) and, better yet, she could use mathematics to improve our society via the field of statistics. Since then, she has never looked back!

    Michelle C. Dunn

    Thu, 03/01/2018 - 6:00am

    Affiliation
    Co-Founder and Chief Technology Officer, Data Collaboratory

    Educational Background
    Carnegie Mellon University: PhD, Statistics (2005)
    Carnegie Mellon University: MS, Statistics (1996)
    Harvard University: AB, Applied Math (1995)

    About Michelle
    Michelle Dunn is CTO and co-founder of Data Collaboratory, a technology company that builds data science tools. Data Collaboratory’s flagship product is GRANTED!, a tool that uses data science to guide researchers to the most appropriate funding opportunities. GRANTED! builds on Michelle’s years of experience in federal funding at the National Institutes of Health (NIH).

    She started working at the National Cancer Institute (NCI), a part of the NIH, in 2009 as a program director who advocated for the funding of grants to develop statistical methodology. In this position, she advised applicants from across the country about appropriate funding opportunity announcements. GRANTED! automates this function by scraping FOAs from publicly available sources and using text-mining techniques to match them with a researcher’s interests.

    Next to building a data science company from the ground up, Michelle is proudest of her contributions to developing and leading the NIH Big Data to Knowledge (BD2K) Initiative. She was instrumental in conceiving and implementing a collection of programs aimed at nurturing a biomedical workforce capable of analyzing data and developing new methods for analyzing data. The BD2K Initiative provided funding for statisticians, informaticians, and other biomedical scientists to do research and receive training in data science.

    Michelle grew up in Memphis, Tennessee, and enjoyed math from an early age. She first learned about statistics on the drive from Memphis to Cambridge, Massachusetts, for the start of classes at Harvard. All freshman had to take a quantitative reasoning test based on a booklet containing essentially a “Stat 101” course. After reading that booklet, Michelle realized why math is important. At Harvard, she was fortunate to find professors and graduate students who encouraged her to pursue her studies in statistics. From Harvard, she went to Carnegie Mellon University (CMU) for a master’s, worked in government for a while, and then returned to CMU for a PhD.

    Michelle’s thesis adviser, Jay Kadane, was supportive not only of her choice of dissertation topic, but also of her choice to be a stay-at-home mom following the completion of her dissertation. This choice could have ended her statistical career had it not been for an open-minded statistician and hiring manager at NCI, Brenda Edwards. Brenda strove to create family-friendly working conditions because she had witnessed the hardships women and working mothers had endured during her career.

    Brenda is Michelle’s hero; she is a statistician who is dedicated to making the world a better place, not just through her work measuring the burden of cancer, but through her leadership of people and projects. Leadership requires taking calculated risks, making sometimes unpopular decisions, and communicating a vision and road map for concerted action. Michelle’s goal is to continue to put into action what she has learned about leadership from Brenda.

    Four Win Student Travel Awards to Conference on Statistical Practice

    Thu, 02/01/2018 - 6:00am

    Student winners will receive registration and travel support to attend CSP 2018.

    John J. Bartko Award

    Strakbein

    Stephanie Strakbein completed a dual degree Bachelor of Science in Veterinary Science and Bachelor of Arts in Spanish at the University of Arizona and is currently pursuing a Master of Science in Biostatistics at Oregon Health & Science University (OHSU-PSU School of Public Health). She also works as a teaching assistant for graduate biostatistics courses and as a graduate research assistant to Thuan Nguyen. At present, she is assisting Nguyen’s research in the USRDS database by extracting data relevant to questions of interest identified by their collaborator, Al-Uzri, the clinical director of pediatric nephrology at OHSU. Together, their goal is to submit an abstract to the Pediatric Academic Society. In the long run, Strakbein and Nguyen will use this database for testing Nguyen’s developing method, called classified mixed model prediction, with the hope of publishing this work in an applied statistical/biostatistical journal. Strakbein also serves as president of the Portland ASA Student Chapter. Outside of academia, she enjoys hiking, spending time with her dogs, and traveling internationally.

    Lester R. Curtin Award

    Montag

    Samantha Montag earned both her bachelor’s degree (biology, science in human culture) and master’s degree (epidemiology and biostatistics) from Northwestern University in Chicago, Illinois. She has worked in the Department of Preventive Medicine at Northwestern University since graduating in 2015 and collaborated with researchers studying sleep, cardiovascular disease, and organ transplantation. Montag specializes in data cleaning, data visualization, and survival methods and is fluent in SAS and R. She enjoys teaching and regularly is a teaching assistant for graduate courses in epidemiology and biostatistics. In her spare time, Montag cooks and plays board games. ​

    Winkel

    Munir Winkel is a PhD candidate in statistics at North Carolina State University. While earning his master’s in statistics at the University of Georgia, he worked with researchers at the Rollins School for Public Health at Emory University. In addition to working on his dissertation, which uses a Bayesian approach for design of experiments, he is collaborating with researchers at the US Centers for Disease Control and Prevention. Winkel especially enjoys bringing the tools of statistics to help address researchers’ questions.

    Lingzi Lu Memorial Award

    Lyu

    Lingzi Lu Memorial Award Winner Lingyun Lyu is a second-year master’s student in biostatistics at the University of Pittsburgh. Before studying at the University of Pittsburgh, she earned an MS in pharmaceutical science from China Pharmaceutical University and worked as a pharmacist at Nanjing, China. Lingyun is a self-motivated and vibrant student. She is not only the top performer in class, maintaining a GPA of 4.0/4.0, but also actively engages in the application of statistics to real-life research studies. Previously, she worked as a team member on a proteomics project; a paper from this work is under review at Proteomics. Working as a SAS programmer and analyst at the Department of Health Policy and Management, Lyu gained experience in big data management and Medicare data analysis. In addition, she is working on her thesis project, addressing imperfect compliance in clinical trials with noninferiority designs. Recently, she was selected as a graduate student researcher in the school of nursing and appointed as teaching assistant in the department of biostatistics. Lyu’s career goal is to improve public health and well-being as a biostatistician at a health care–related institution.

    Nominations Sought for 2018 Roger Herriot Award

    Thu, 02/01/2018 - 6:00am

    Nominations are sought for the 2018 Roger Herriot Award for Innovation in Federal Statistics.

    The award consists of a $1,000 honorarium and a framed citation, which will be presented at a ceremony during the Joint Statistical Meetings in August 2018. The Washington Statistical Society may also host a seminar given by the winner on a subject of his or her choosing.

    The committee may consider nominations made in prior years, but it encourages resubmission of those nominations with updated information. Completed packages must be received by April 1. Electronic submissions to Mary Batcher, chair of the 2018 Roger Herriot Award Committee, as Word or PDF files are strongly encouraged.

    For more information, read the announcement in the last issue of Amstat News.

    Highlights of the November 17–18, 2017, ASA Board of Directors Meeting

    Thu, 02/01/2018 - 6:00am

    The ASA Board, led by 2017 President Barry Nussbaum, met at the ASA headquarters in Alexandria, Virginia, for its final meeting of 2017. The board was joined by the incoming members elected to serve in 2018–2020. Highlights of the meeting follow.

    Discussion Items
    • Led by Paul Gallo, 2018 chair of the ASA Committee on Fellows, the board discussed aspects of the ASA Fellows program. The committee was interested in the board’s interpretation of portions of the requirements for ASA Fellow. No changes are planned for 2018, but further discussion is likely.
    • The board conducted its annual review of the ASA Strategic Plan. Since the plan was thoroughly revised during 2016, no changes were recommended.
      Action Items
    • After hearing reports from Steve Pierson, ASA director of science policy; Jerry Reiter, chair of the ASA Scientific and Public Affairs Advisory Committee; and Jake Bournazian, chair of the ASA Privacy and Confidentiality Committee, the board formally endorsed the report of the Commission on Evidence-Based Policymaking, titled “The Promise of Evidence-Based Policymaking.”
    • The board adopted a statement titled, “Drawing Voting Districts and Partisan Gerrymandering: Preparing for 2020.” The statement, which may be issued jointly with the American Mathematical Society, notes that existing requirements for districts generally do not prevent partisan gerrymandering; that it has become easier to design district plans that strongly favor a particular partisan outcome; and that modern mathematical, statistical, and computing methods can be used to identify district plans that give one of the parties an unfair advantage in elections. Reiter and Pierson were instrumental in the development of this paper.
    • The board adopted in principle a position paper on appropriate ways of evaluating academic faculty in statistics and biostatistics in a collaborative working environment. The paper was developed by a large group of statisticians led by William Bridges and Bruce Craig. Small editorial changes were recommended, which, once made, will lead to the paper’s formal adoption by the Executive Committee of the Board.
    • The board also agreed in principle (conditional on minor changes) to the creation of a new ASA award to recognize excellence in the statistical use of administrative records and alternative data sources in government statistics. The award is being created in honor of statisticians Connie Citro, Robert Groves, and Fritz Scheuren.
    • The board formed a task force on sexual harassment and assault, to be chaired by Leslie A. McClure of Drexel University.
    • The board allocated funds to engage a consultant to assist the board in collecting data and preparing for a discussion at its next meeting about how the ASA should position itself with respect to data science.
    Reported Items
    • Associate Executive Director and Director of Operations Steve Porzio updated the board on ASA financials for 2017. He said net revenue for 2017 is expected to be positive.
    • ASA Treasurer Amarjot Kaur reported on the ASA’s investments. She said the market value of ASA investments was about $20 million as of September 20. She noted the Finance Committee had met with our investment advisers and that no change in investment policy was recommended at this time.
    • Nancy Potok, chief statistician of the United States, updated the board on matters related to the federal statistical system and the report of the Commission on Evidence-Based Policymaking. She was a member of that commission.
    • John Thompson, director of the Council of Professional Associations on Federal Statistics (COPAFS) and former director of the Census Bureau, updated the board on the activities and goals of COPAFS.
    • The Council of Chapters Governing Board (COCGB) and the Council of Sections Governing Board (COSGB) reported on their recent activities. The COSGB has been working with interest groups to provide funding. The COSGB has created a “Getting Started” guide for people interested in starting an interest group. Two new interest groups have recently formed: Statistical Auditing and History of Statistics. The COCGB highlighted the success of its “chapter stimulus funding” program, which the board extended for an additional two years.
    • ASA Vice President Rob Santos reported on the 2017 activities of the Education Council and the plans of the various council entities. Council reports are a key way the board and committees stay in contact with one another.
    • Amanda Malloy, ASA director of development, updated the board on the development program. She reported the outcome of a recent benchmarking study involving the development programs of associations belonging to the Joint Policy Board on Mathematics (JPBM) and Consortium of Social Science Associations (COSSA). Malloy said the study was encouraging, showing us to be about where we should expect to be relative to other societies with respect to the age of the development program. She also reported that 2017 fundraising is going well and the recent matching campaign has been a success.
    • Executive Director Ron Wasserstein reported that the ASA will be ready in early 2018 to launch its “Count on Stats” campaign. The ASA, in partnership with other organizations in the statistical community, is promoting and defending the federal statistical system and its important work through a public outreach initiative to enhance awareness of the importance, reliability, and trustworthiness of government data. Count on Stats is designed to elevate the public discourse about government data and the value of the system.
    • The board reviewed the interim report of the AAPOR-ASA Task Force on Improving the Climate for Surveys. The task force is chaired by former AAPOR President Peter Miller and former ASA Board member Cynthia Clark. (AAPOR is the American Association for Public Opinion Research.) The board noted that many of the recommendations of the task force dovetail with the goals of the ASA’s Count on Stats campaign.
    • Director of Science Policy Steve Pierson reported on the ASA’s recent efforts to support funding for statistical agencies and research, to track the report of the Commission on Evidence-Based Policymaking and the resulting legislation, and to continue support of former head of the Greek statistical system, Andreas Georgiou. Pierson said he is also monitoring the administration’s efforts to defund forensic science activities at the National Institute of Standards and Technology and to terminate the National Commission for Forensic Science at the Department of Justice.

    Nussbaum thanked the ASA staff for its work and for supporting him so well. He also expressed appreciation for the board’s commitment to the ASA and its active participation at the board meetings and throughout the year. He said these are what make the ASA run well.

    The board meets again April 13–14, 2018, at ASA headquarters.

    2018 Board of Directors
    • Lisa LaVange, President
    • Karen Kafadar, President-elect
    • Barry Nussbaum, Past-President
    • Kathy Ensor, Third-Year Vice President
    • David Williamson, Second-Year Vice President
    • Katherine Monti, First-Year Vice President
    • Paula Roberson, Third-Year Council of Chapters Representative
    • Julia Sharp, Second-Year Council of Chapters Representative
    • Don Jang, First-Year Council of Chapters Representative
    • Eileen King, Third-Year Council of Sections Representative
    • Jim Lepkowski, Second-Year Council of Sections Representative
    • Katherine Halvorsen, First-Year Council of Sections Representative
    • Cynthia Bocci, International Representative
    • Scott Evans, Publications Representative
    • Amarjot Kaur, Treasurer
    • Ron Wasserstein, Executive Director and Board Secretary

    Five Lessons Learned Implementing a School Drought Survey in Somalia

    Thu, 02/01/2018 - 6:00am
    Monica Dashen

      Somalia is experiencing a drought that has affected the educational system, leading to high dropout rates among children, a low number of teachers, and school closures. Data are needed to track the effects of the drought on school-aged children and help foreign aid workers coordinate food supplies.

      To fill this gap, a Somali official and I constructed a school drought survey whereby school officials will be asked to report the number of school closings, student absences, meals delivered, and educational supplies received. We also drafted a supplementary survey involving parents of school-aged children to confirm the school officials’ reports. Parents will be asked about their children’s health and dietary habits, school status, and aid received.

      Monica Dashen, who retired early from the federal government, recently worked on a Somali civil worker gender survey. Contact her if you have questions or would like to know more.

      When designing and implementing a survey in a crisis situation, a survey methodologist may find standard tasks to be more challenging (particularly in developing countries). For example, trained and experienced interviewers may not be readily available at the time of implementation, and the methodologist will have to take time to train a group of novice interviewers and vet their English-speaking skills. To obtain an interviewer job, for example, candidates may say they speak and understand English better than they actually do. Here are five lessons I learned while trying to implement a school drought survey:

      1. Asking foundational questions about sanitation is important.

      A survey designer should not limit questions to aid distribution, student enrollment, and school status. Instead, the designer must paint a broader picture of the crisis and ask about the school toilets and water source functionality. Unclean water is often the source of cholera and other diseases. In Somalia, the drought may eliminate clean water sources and force people to drink unclean water.

      Likewise, sanitation habits and bleach availability are important topics to assess. For instance, in rural areas, cholera is difficult to treat, as it requires truckloads of intravenous (IV) fluid for those patients who suffer from severe dehydration. Rural clinics simply do not have a ready supply of IV fluid for a large number of patients. Also, the roads leading to these clinics are in poor condition, thereby limiting access to large trucks. Such roads and distances make prevention all the more critical, and clean water and good sanitation habits are preventative methods.

      The US Centers for Disease Control and Prevention recommends bleach—a water treatment—be available in every village, as bleach is easy and cheap to produce in any country. (In many American homes, water is chlorinated at the source and does not need to be purified at the tap.)

      2. Asking gender-specific questions is important.

      The survey designer should ask about the number of boys and girls enrolled by grade level. In Somalia, boys, who are viewed as “future bread winners,” are encouraged to pursue their education more so than girls. Typically, more boys attend secondary school than girls. To encourage more Somali girls to attend school, an NGO recommends providing scholarships, solar lanterns for night time studying, sanitary kits, job-training skills, and a greater number of female instructors. A survey designer may consider inquiring about incentives used to keep the children (particularly girls) in school during the drought.

      The survey designer may also want to collect data on the number of single-gender toilets per school. Not only are toilets a sanitation issue, but toilets are a school enrollment issue, too. Girls drop out of school due to the lack of single-sex toilets. Some girls have experienced violent attacks in a mixed-gender bathroom. When an NGO or government official installs a single-gender bathroom in a school, for example, the teachers may use it for themselves while the girls continue using the unisex bathroom.

      3. Designing the questionnaire can be trickier than expected.

      The designer may find some questions to be seemly straight forward to draft, but require multiple rewrites. The “change in dietary habits after a crisis” question is one such example. Asking about the number of meals eaten per day, or whether one has eaten enough, is ineffective. Rather, the type of food eaten and how it differs after the drought is key, along with where the food was obtained. The designer should find out whether the food is home-grown, donated, or store-bought. Likewise, the designer may find it difficult to ask people about their job and income. For example, farmers who are unable to grow food may still report working after a disaster. Once a farmer, always a farmer.

      4. Obtaining a detailed map of drought-affected areas is difficult.

      Unlike a hurricane that strikes in a clear location, the Somali drought is gradually spreading throughout the country. Some areas are more affected than others. To the best of my knowledge, detailed maps depicting the drought severity of villages or towns are difficult to obtain or nonexistent. As a result, the team and I had to rely on the villagers to tell us about the severity of the drought. Interestingly, simply asking the people about the last time it rained did not provide a full picture of the drought. Instead, we asked people to describe the (1) rate of rain fall—sheets or drizzle, (2) soil moisture, and (3) last time it rained. Another way involves physically analyzing the ground water.

      5. Implementing a survey has security risks.

      Having a security guard accompany the team in the field is prudent after any disaster. That is, the act of asking people about aid after a disaster and how they are doing can enrage them, particularly if they are hungry and homeless. Likewise, a methodologist should be present at the time of implementation to make sure the interviewers follow proper survey protocol. With the political unrest in certain areas of Somalia and lingering anti-American sentiment, it is difficult for a non-Somali like me to be present at implementation. For example, the team’s visits to schools around Mogadishu would require an SUV, security team of three persons, guide, and driver, so it was unclear whether the interviewers and I would find a seat in this SUV.

      To extend our reach outside of Mogadishu and the state capitals, the team and I could conduct a phone survey of school officials listed in the national registry. Somalia has about 50% phone coverage, and people don’t have to pay to receive a phone call. However, our reach would be limited for three reasons. First, phone coverage is lower in rural areas than urban. Second, people do not always keep their phones “on” so as to save power. And third, people sometimes do not have the money to pay their phone bills. Providing phones along with phone credit to survey participants is a “work around” practiced by other researchers, but it comes with its own problems (e.g., the participants sell their phones for cash).

      To determine where in Somalia the team and I could go with a reduced security risk, I looked at what other researchers did. I learned we could simply go to Somaliland, an autonomous region to the north of Mogadishu. This region has been fairly stable and even has its own currency. There is also a World Health Organization contact there. A census pre-count was done in this region, along with work on mobile money usage, reasons for piracy, and opinions toward the new government. Still, security precautions are needed, given the drought.

      Know of Any Late-Breaking Developments? Please Share!

      Thu, 02/01/2018 - 6:00am
      JSM Late-Breaking Proposals Due April 16 Christian Léger, JSM 2018 Program Chair

        Are you tired of winter? I invite you to think about summer. Vancouver. The 2018 Joint Statistical Meetings! The 181 invited sessions have been scheduled and, in the next few weeks, we will organize the contributed abstracts into sessions. When you consult the online program, I am sure you will find exciting sessions to attend from Sunday afternoon through Thursday morning and you will want to join us to “#LeadWithStatistics” at JSM 2018.

        Preparing such a big program requires much advanced planning, so the invited session proposal deadline is in early September. Of course, much can happen in the ensuing 11 months, which is why there is a call for proposals for late-breaking sessions. A late-breaking session must cover one or more technical, scientific, or policy-related topics that have arisen during the one-year period prior to JSM.


        A late-breaking session must cover one or more technical, scientific, or policy-related topics that have arisen during the one-year period prior to JSM.

        To give you an idea of the type of sessions that have been selected in the recent past, here is a handful of late-breaking session titles:

        • National Governments, Coerced Narratives, Creative Language, and Alternative Facts
        • Hindsight Is 20/20 and for 2020: Lessons from 2016 Elections
        • Invest in What Works: First Steps Toward Establishing Evidence-Based Policymaking Clearinghouse
        • Data Journalism and Statistical Expertise: An Urgent Need for Writers, Bloggers, and Journalists to Be Statistically Savvy
        • The VA Secretary Bans a Statistics Book
        • Meeting the Challenges of a Pandemic: The Statistical Aspects of Dealing with Ebola
        • Statistical Science and the President’s BRAIN Initiative
        • Recent Concerns About Reproducibility and Replicability: The Statistical Aspects

        Proposals for late-breaking sessions should be emailed to JSM 2018 program chair, Christian Léger, with a copy to the ASA meetings department by April 16. The competition is open to any member or organization of a partner society.

        Proposals will be judged on statistical and scientific quality, timeliness, significance and impact, potential audience appeal, and completeness. Up to two late-breaking sessions will be selected from the proposals received by the deadline (subject to approval by the ASA Committee on Meetings). The proposal must include the following:

        • Session description—including a title, summary of statistical and scientific content, and explanation of the subject’s timeliness and significance—and comments about the intended target audience
        • Format of the session (e.g., a chair and four panelists, 2–3 speakers and a discussant, etc.)
        • Names, affiliations, and contact information for the session organizer, chair, and all participants (speakers, panelists, discussants)
        • A title for each presentation in the session
        • Web links to relevant technical reports or news reports, if applicable

        Organizers should make sure the participants agree to participate before the proposal is submitted. The JSM participation guidelines state that a speaker can give a main presentation and participate in a late-breaking session at the same meeting, so previous commitment to a regular session does not preclude participation.

        We look forward to reading your proposals!

        ThisIsStatistics Challenges Students to Apply Stats Skills for Greater Good

        Thu, 02/01/2018 - 6:00am

        The ASA’s public education campaign, ThisIsStatistics, expanded its educational footprint in 2017 on “all things statistics” with high-school and undergraduate students in today’s increasingly digital and mobile world.

        Police Data Challenge

        In the Police Data Challenge, students helped make communities safer by analyzing emergency call data from metropolitan police departments in Baltimore, Cincinnati, and Seattle. The ASA joined forces with the Police Data Initiative in this unique partnership to provide students with open and publicly accessible data sets on emergency calls, giving them an opportunity to apply their savvy statistical skills to an important cause and providing major cities with a better understanding of the value and use of statistics in public safety. Hundreds of students from across the United States participated, and the following winners were recently announced:

        Best Overall Winners
        • Undergraduate: Jimmy Hickey, Kapil Khanal, and Luke Peacock – Winona State University (Sponsored by Silas Bergen)
        • High School: Catalina Bartholomew, Sophie Mason, Grace Ding, and Allie Restani – Valley Christian High School, San Jose, California (Sponsored by Claudia Smith)
        Best Visualization Winners
        • Undergraduate: Julia Nguyen, Katherine Qian, Youbeen Shim, and Catherine Sun – University of Virginia (Sponsored by Jordan Rodu)
        • High School: Alex Lapuente, Ana Kenefick, and Sara Kenefick – Charlotte Latin School, Charlotte, North Carolina (Sponsored by Donna Minnig)
        Best Use of External Data Winners
        • Undergraduate: Luke Zheng, Qianyu Liu, Scott Lai, Sicheng Chu, and Xi He – University of Wisconsin (Sponsored by Karl Rohe)
        • High School: Alaina Cerro, Sean Conroy, and Elise Bermudez – Bethel Park High School, Bethel Park, Pennsylvania (Sponsored by Lee Cristofano)
        What’s Going On in This Graph?

        Teaming up with The New York Times Learning Network, ThisIsStatistics developed a unique exercise, titled “What’s Going On in This Graph?” Spearheaded by ASA member Sharon Hessney, this partnership is modeled after the Times’s popular series, “What’s Going On in This Picture?” and is intended to inspire students to examine graphs, charts, or maps via a rich and robust supply of the Times’s infographics.

        Each month, a different New York Times graph will be published on a topic suitable for a variety of subjects across the curriculum. Students will then be asked to use math and statistics thinking skills to answer the following questions:

        • What do you notice?
        • What do you wonder?
        • What’s going on in this graph?

        Under Hessney’s leadership, an ASA team will help select graphs to use each month, moderate discussion, engage students, and provide a ‘reveal’ at the end of the week-long session that incorporates the graph’s original title and caption and related statistical concepts and vocabulary to help students transform the data into information.

        What’s Next?

        Stay tuned this winter and spring for Statistics Is for Everyone, the latest video showcasing professionals from a variety of occupations demonstrating that everyone is connected to statistics at some point and the field can be applied to a diverse group of professions. Included in the video are the following:

        • Hillary Parker, data scientist, Stitch Fix
        • Dawn Eash, associate director, Berkeley Research Group
        • Dave Robinson, data scientist, Stack Overflow
        • Alexander Oftelie, analytics subject matter expert, IBM
        • Matthew Krachey, data scientist, HomeAway

        Statsketball returns to see who can score big and best predict the winner and brackets for March Madness. The website and social media platforms will launch as the college basketball season heats up.

        With graduation inching closer, check out ThisisStatistics for more dynamic education tools and resources, including data about statistics degrees and career projections from the Bureau of Labor Statistics, to help foster statistical literacy and excitement in the next generation of critical thinkers.

        Nominations Wanted for International Representative to ASA Board

        Thu, 02/01/2018 - 6:00am

        The ASA is searching for individuals to stand for election in spring 2019 for the International Representative to the Board for the period 2020–2022.

        To be eligible, the person must have been an ASA member continuously since January 1, 2015, and reside outside the United States.

        Send your nominations via email to ASA Executive Director Ron Wasserstein by March 5.

        Biometrics Section News for February

        Thu, 02/01/2018 - 6:00am
        Zheyu Wang, Biometrics Section Publications Officer

          The Chronic Kidney Disease Biomarkers Consortium (CKD BioCon) is accepting applications to fund pilot and feasibility studies focused on the discovery, validation, or qualification of chronic kidney disease (CKD) biomarkers. As part of this program, applications proposing the development and/or evaluation of new statistical methods relevant to biomarker research specifically related to CKD biomarkers will be accepted.

          CKD BioCon was established by the National Institute of Diabetes and Digestive and Kidney Diseases to promote the discovery, evaluation, and validation of biomarkers to advance CKD research.

          The deadline for preliminary applications is March 16.

          The full funding opportunity announcement can be found at the Chronic Kidney Disease Biomarkers Consortium website.

          San Francisco Bay Area Chapter Hosts Career Development Panel

          Thu, 02/01/2018 - 6:00am
          Jeremy Gu, San Francisco Bay Area Chapter Vice President

            Speakers and ASA San Francisco Bay Area Chapter volunteers meet for a careers event in December. View more photos of the event.

            Speakers and ASA San Francisco Bay Area Chapter Volunteers

            Chapter officers Second row (from left):

            • Chris Barker Program committee member
            • Jeremy Gu Chapter vice president
            • Kathy Zhang Chapter president
            • Ron Yu Chapter vice president
            • Ruixiao Lu Council of Chapters representative
            • Li Zhang Chapter president-elect

            Speakers First row (from left):

            • Deepak Agarwal Vice president of engineering at LinkedIn
            • Anirban Biswajit Deb Data science manager at Uber
            • Imola K. Fodor Deputy global head of oncology biostatistics for gRED and breast/GYN franchise of Genentech/Roche
            • Annette Molinaro Professor of neurosurgery, epidemiology, and biostatistics at the University of California, San Francisco
            • Tara Maddala Head of biostatistics and data management at GRAIL
            • Brad Klingenberg Vice president of data science at Stitch Fix
            • Jizhou Fu Data science manager at Uber
            • The San Francisco Bay Area Chapter of ASA (SFASA) invited a group of panelists to speak December 7, 2017, about career development for data scientists, statisticians, and students interested in the careers of data science, machine learning, business analytics, and biostatistics. Speakers came from diverse backgrounds and provided the audience—made up of ASA members and the public—with guidance on various perspectives.

              When the discussion began, each of the speakers gave a self-introduction and described how they started their career. Annette Molinaro, a professor at the University of California, San Francisco, talked about how she decided to join academia. Deepak Agarwal, vice president of engineering at LinkedIn, shared his path toward artificial intelligence and recommendation systems after earning his PhD in statistics. Imola K. Fodor, deputy global head of oncology biostatistics for gRED and breast/GYN franchise of Genentech/Roche, and Tara Maddala, head of biostatistics and data management at GRAIL, discussed their interests in statistics and research when they were studying as undergrads. Finally, Brad Klingenberg, vice president of data science at Stitch Fix; Jizhou Fu, data science manager at Uber; and Anirban Biswajit Deb, data science manager at Uber, shared their experiences working as data science managers in fast-growing startups.

              The questions raised by the audience concerned preparing for job interviews, applying to graduate schools, deciding between master’s degrees and PhD degrees, and gaining the qualifications of a data scientist in current job markets. The panel members addressed the importance of statistical knowledge in boosting their careers, advised how to be successful in a data science career, and described work challenges—such as time planning and business communication with nonstatisticians.

              After the discussion, the speakers and audience members had about an hour to chat one-on-one.

              The panel speakers and audience members agreed statistics is the foundation of data science and people cannot work effectively in data science without statistical skills.

              Since 2015, SFASA has successfully hosted panel discussions about career development and plans are in place to continue in 2018.

            Obituaries for February 2018

            Thu, 02/01/2018 - 6:00am
            James Thompson

            James Thompson, Noah Harding Emeritus Professor of Statistics and statistician at Rice before there was a statistics department, died December 4 at age 79.

            Thompson taught statistics at Indiana University and Vanderbilt before joining Rice University in 1970. He retired just last year, after 46 years as a member of the faculty. In 1987, statistics moved from under the mathematics science department to the school of social sciences and became a separate department with Thompson as the founding chair. The department moved to the George R. Brown School of Engineering in 1990.

            “Jim taught me skepticism,” said John Dobelman, who Thompson advised in 2004 while he was earning his doctorate and is now professor in the practice of statistics. “He was brutally honest. He often stepped in and, besides providing the technical and academic guidance I needed, provided family and mentorship.”

            Thompson was a fellow of the American Statistical Association, Institute of Mathematical Statistics, and International Statistical Institute. He was the recipient of the Army’s Wilks Medal and the ASA’s Don Owen Award for his work in quality control.

            He directed 17 doctoral students and authored or co-authored 14 books, including Models for Investors in Real World Markets and Empirical Model Building: Data, Models, and Reality.

            Read a memoriam written by Patrick Kurp.

            Data for Good—On the Job!

            Thu, 02/01/2018 - 6:00am
            This column is written for those interested in learning about the world of Data for Good, where statistical analysis is dedicated to good causes that benefit our lives, our communities, and our world. If you would like to know more or have ideas for articles, contact David Corliss.

            With a PhD in statistical astrophysics, David Corliss works in analytics architecture at Ford Motor Company while continuing astrophysics research on the side. He serves on the steering committee for the Conference on Statistical Practice and is president-elect of the Detroit Chapter. He is the founder of Peace-Work, a volunteer cooperative of statisticians and data scientists providing analytic support for charitable groups and applying statistical methods to issue-driven advocacy in poverty, education, and social justice.

            As we explore different opportunities for Data for Good (D4G) projects, it is important to mention one avenue becoming more widespread today: statistical volunteering through work. Companies often encourage employees to volunteer in the community where they work, with many offering time off for teams or individuals volunteering for local organizations.

            Common projects include cleaning up parks, volunteering at a school for a day, working in community food banks, and participating in construction projects for Habitat for Humanity. While supported by the employers, which provide critical infrastructure and logistics, individual projects are usually proposed and led by individual employees. This makes Data for Good a project many of us can consider for the next team-building service project where we work.

            Often, employee-led community service projects in D4G can spring from existing activities with favorite charities at your company. The membership and volunteer study for a local Habitat for Humanity group described in the November issue started when two work colleagues, one of them a statistician, volunteered for the same organization. Likewise, the food pantry where you volunteer now might need a seasonal analysis. Science fairs need judges who understand statistics. The school partnering with your company might benefit from a data dive to better understand their changing demographics and forecast changes.

            Opportunities

            With the start of a new year, this month’s Data for Good opportunities include many organizations looking for people to start new projects. Kaggle would like volunteers to host Data for Good events. Also in February, the ASA’s Conference on Statistical Practice is featuring several D4G papers, and I’ll be leading a data dive on hate speech in social media. Hope to see you there!

            Many companies engaged in data science and technology have sponsored projects in which groups of employees apply the same skills they use on the job to support important causes on a pro bono basis. Well-known employers supporting statistical volunteering include Cloudera, which recently sponsored a hackathon to compile data on the spread of the Zika virus. Also, DataKind has partnered with Teradata, Pivotal, Informatica, and others. The number of companies supporting the D4G movement with volunteer opportunities continues to grow.

            Company volunteer programs usually have a particular set of ground rules. Projects and the organizations receiving support should be approved through the HR department or, in the case of smaller companies, the operations lead. Projects must not interfere with or delay regular work for company customers. Companies will often choose the cause they want to support, and then seek employees to volunteer, generally preferring activities that support important needs in the community. As the company will want to let others know about the good they are doing, communication with HR or operations, an employee newsletter, and even the outside press might be a requirement. Employee volunteer projects often serve as team-building activities, so it’s a good chance several co-workers will be involved. Many companies will give a limited, specified amount of time off for volunteering through work, often one day a year or sometimes two. As the company is performing the work as a charitable activity, careful documentation is needed for tax purposes. This is usually done by a team captain who submits a request for an employee volunteer activity, helps recruit volunteers, records attendance in hours for each participating employee, and reports to HR or operations about how everything went.

            One advantage of volunteering through work is the company often makes available analytic resources and software volunteers use every day. The familiar analytic environment at work usually becomes the platform for pro bono projects, as well, maximizing the efficiency and effectiveness of statistical volunteering.

            Microsoft’s MySkills4Afrika is an excellent example of a D4G program created by a large tech corporation relying on employee volunteers. Established in 2013, MySkills4Afrika offers Microsoft employees from around the world the opportunity to develop practical and affordable technology in developing African nations. The Microsoft program partners with governments, NGOs, commercial enterprises, and schools and universities.

            Characteristic of MySkills4Afrika projects is the opportunity to use advanced skills normally applied only at work in service to others on a volunteer basis. Many MySkills4Afrika projects involve longer-term consulting projects in which volunteers work virtually with Africans. Microsoft also sponsors 1–2-week hands-on projects in Africa.

            One project developed a team of subject matter experts to partner with the Rwanda Ministry of Education. Months of preparation—all done as volunteers in addition to work—culminated in a two-week trip to Rwanda to train professionals and small business owners in emerging technologies. At the same time, the employee team worked with Rwanda education officials to establish an ongoing program so they could continue the good work.

            Employee volunteering is supported by many companies, but not all have started projects using analytics and data science. If there are not volunteer opportunities on the Data for Good projects where you work, contacting someone in your HR department might be a good place to start.

            All these opportunities and many more share a quality commonly found in Data for Good projects: An organization has data about its activities and the people it supports, but doesn’t have—and can’t afford—the statistical expertise needed to make their important work in the community even more effective. At the same time, companies both small and large are looking for opportunities to build team spirit by working together on projects that benefit the community. D4G projects through work are a perfect opportunity to use the science we love to make a difference in our communities and around the world. I would love to hear about the D4G projects you have done through work.

            Pages