Professor of Biostatistics
Department of Biostatistics
Harvard School of Public Health & Dana-Farber Cancer Institute
Parsing variability and detecting signal in disease epigenetic studies
Epigenome-wide association studies (EWAS) of human disease and other quantitative traits are becoming increasingly common. We describe statistical approaches to parse out variance due to measurement error, biological variability, batch effects and other latent variables such as cell composition. We also describe approaches to detecting differentially methylated regions in cancer and how to attach uncertainty measures to these findings.