Department of Biostatistics, School of Public
Health and Medicine, Tulane University,
New Orleans, Louisiana
Indian Host Institution:
Institute of Bioinformatics and Applied
Duration of Grant & Start Date :
Duration: 6 months
Professor Sudesh Srivastav is a Professor of biostatistics and bioinformatics at Tulane University. He received his MSTAT and M.S. degrees in statistics and applied mathematics from Indian Statistical Institute, New Delhi, and New Jersey Institute of Technology, respectively. He received his Ph.D. from Old Dominion University. He is trained in the field of experimental statistical designs. He was an honorary fellow at the center of mathematical sciences at the University of Wisconsin, Madison in summer 2000, and also a visiting fellow at the department of statistics at Stanford University during the summer of 2001. He collaborated with several investigators at the University of California, San Francisco and Tulane University. In 2005, he was awarded the Excellence in Intercampus Collaborative Research, from the Tulane University Health Sciences Center. He served as the chair of the Scientific Review Committee for the Louisiana Cancer Research Consortium, New Orleans. In 2009, he was a recipient of the Undergraduate Public Health Studies Research and Teaching Award Grant, Tulane University Health Sciences Center, New Orleans. He is also Program Co-Director for the Building Interdisciplinary Research Careers in Women's Health (BIRCWH) at Tulane University. Dr. Srivastav has published numerous papers in experimental designs in both theoretical and applied statistical journals. His research interests are focused on both analyses as well as methodology development within the area of experimental design and bioinformatics. He is actively involved in research related to re-sampling techniques associated with micro-array gene expression data patterns for comparing drug treatments, temporal factors, biological conditions, and tissue types.
The goal of Professor Srivastav's Fulbright-Nehru research is to construct statistically efficient/optimal microarray experimental designs to be used as tools in biomedical research. These designs help in the analysis of gene expression patterns for comparing drug treatments, temporal factors, biological conditions, and tissue types. In particular, statistical optimality criteria will be investigated for the well-known classes of microarray designs such as reference designs, dye-swap designs, and loop designs to provide greater flexibility in planning microarray experiments. Furthermore, re-sampling techniques such as exact sampling with replacement and bootstrap methods used to identifying differential expression genes will also be explored.