I am a graduate student in the Department of Statistics at the University of Wisconsin-Madison. I earned my Masters in Statistics in Spring 2009. I am a member of the Wahba-Keles Thursday Working Group, which studies statistical genomics and affiliated machine learning problems. I was the department graduate student leader (2008-2009) and have organized the department's student seminar in the past.

I am from Buffalo, NY and received my Sc.B. from Brown University where I wrote a thesis on trial designs for diagnostic tests. I studied statistical methods for determining tumor clonality in the Department of Epidemiology and Biostatistics at Memorial Sloan Kettering Cancer Center before entering the graduate program at Wisconsin.

Research Work

Clustering, Linear models, Gene Expression Microarrays. We have studied extensions of clustering of regression models which have both time and species factors. These models isolate signal attributable to each factor and allow the estimation of the mean signal as well as the dependence structure. Clustering puts genes with similar mean and variance patterns into distinct groups whose biological characteristics can be further investigated.

• Eng KH, Keles S, Wahba GW. (2008) "A Linear mixed effects clustering model for multi-species time course gene expression data." Technical Report #1143. Dept of Statistics, UW-Madison.


• Eng KH, Kvitek D, Wahba G, Gasch A, and Keles S. (2007). "Exploratory statistical analysis of multi-species time course gene expression data." Proceedings of the 56th Session of the International Statistical Institute. Invited Paper.

Phylogenetic Estimation with Gene Expression. High resolution arrays potentially offer a large amount of information on the dependence structure across distantly or closely related species. We are studying the estimation of the tree structured correlation from continuous gene expression traits in order to characterize the observed dependence and compare it to the predicted dependence under the usual sequence based models. Under a relative mutation rate framework, we produce comparative models for neutral evolution which allow the estimation of deviations attributable to selection forces.

• Corrada Bravo H, Eng KH, Wahba GW, Keles S, Wright S. (2008) "Estimating Tree-Structured Covariance Matrices via Mixed-Integer Programming with an Application to Phylogenetic Analysis of Gene Expression." Technical Report #1142. Dept of Statistics, UW-Madison.


• Eng KH, Corrada Bravo HC, Wahba GW, Keles S. (2008) "A Phylogenetic Mixture Model for the Evolution of Gene Expression." Technical Report #1144. Dept of Statistics, UW-Madison.

Functional Estimates with Political Boundaries. With Marc Ratkovic, I am beginning to study the incorporation of political boundaries (discontinuities) in smooth functional estimates.

• Ratkovic MT, Eng KH. (2009) "Finding Jumps in Otherwise Smooth Curves: Identifying Critical Events in Political Processes" Political Analysis (To appear).
• Eng KH, Ratkovic MT (2009) "Likelihood based criterion for model selection in mixed-effects models" (In preparation).