General Departmental Seminar Series
Meta-Analysis of High-Throughput Genomic Data
Debashis Ghosh, PhD,
Department of Biostatistics
University of Michigan
November 12, 2004, 12 - 1 pm in room 1210 Medical Sciences Center (1300 University Ave.)
An increasing number of studies have profiled tumor specimens using distinct microarray platforms and analysis techniques. With the accumulating amount of microarray data, one of the most challenging tasks is to develop robust statistical models to integrate the findings. In this talk, we outline the issues associated with combining different genomic datasets. We discuss a two-stage approach for meta-analysis of data from microarrays using a mixture model- based data transformation technique. The methods are applied to validate and integrate independent findings from four microarray studies in breast cancer. If time permits, we will also discuss some recent work in studying false discovery rate estimation procedures under dependence.
Return to seminar list