Statistical Engineering Division SeminarStatistical Methods for Differential Expression Identification
Yinglei Lai, Ph.D. Abstract Microarrays enable us to monitor expressions of thousands of genes simultaneously. They have been widely used for various biological and medical studies. One important issue is to efficiently identify differential expressions. The traditional rank based test statistics are not efficient, since sample sizes of microarray experiments are usually small. Based on certain prior biological information, the traditional t/F-statistics can be generalized to achieve more powerful identification of differential expressions. In this presentation, I discuss several statistical methods proposed in recent years. Most of them are generalized t/F-statistics based on shrinkage approaches, such as SAM or regularized t-tests. Other approaches, such as a likelihood based approach and some correlation based approaches, are also discussed. Author Bio Yinglei Lai received the B.S degrees in Information & Computation Sciences and Business Administration in 1999 from the University of Science of Technology of China, and the Ph.D degree in Applied Mathematics in 2003 from the University of Southern California. After the postdoctoral training during 2003-2004 at Yale University School of Medicine, he joined The George Washington University as an Assistant Professor of Statistics. His research interests are statistical aspects in the fields of bioinformatics, computational biology and statistical genetics. NIST Contact: John Lu, (301) 975-2846.
Date created: 11/14/2006 |