RESEARCH OVERVIEW

My lab and I develop statistical methods, theory, and algorithms for high-dimensional data analysis problems. From a variety of directions, we are currently working on a comprehensive framework to carry out statistical inference on high-dimensional data consisting of binary, count, or continuous measurements that are influenced by both known and unknown (latent) sources of variation. Most of our statistics research is directly motivated by and applied to problems in genomics and other areas of modern high-throughput quantitative biology. Examples include studies involving genome sequences of individuals from structured populations, genome-wide gene expression profiling measurements from next generation sequencing, and complex clinical genomics studies.

Specific projects in the lab include:

• Large-scale inference of high-dimensional data involving dependence and latent structure
• Statistical methods developed for and applied to:
  • gene-environment interaction studies involving gene expression
  • genome sequences of individuals from structured populations
  • high-throughput gene expression profiling studies
  • quantitative profiling experiments by next-generation sequencing technologies
• Quantitatively-driven experimental approaches to the genetic and molecular dissection of "complex traits" in yeast

Please see some of our recent publications to learn more about our research.