Area of Interest
Our methodological research is focused on the statistical analysis of high dimensional data. This includes exploratory analysis (clustering, biclustering, correlation mining), variable selection in genome wide association studies, and multi-tissue eQTL analysis. Our research is driven in part by biomedical problems arising in the study of cancer and toxicology, with the broad goal of developing statistical methods that can help provide insight into disease etiology and treatment. The work is being carried out as part of a cross disciplinary effort involving UNC researchers from the Lineberger Comprehensive Cancer Center, the Department of Biostatistics, and the Department of Environmental and Health Sciences.
Of particular interest to us are data sets based on measurements of gene (and micro-RNA) expression, copy number variation, and genotype. Although they are motivated by biomedical data, our methods have application to other high dimensional problems, including the analysis of social and political networks. Research in these related areas is ongoing.
Awards and Honors
1986- Churchill Scholar, Cambridge University
1992-1995 - Beckman Institute Fellow
2002- Lucent Distinguished Lecture, Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor.
2008- Fellow of the Institute of Mathematical Statistics