Afternoon Plenary Lecture I
A Statistician's Journey Through the 'Bayesian' Path
Professor and Co-Director of Graduate Programs,
Department of Statistics,
NC State University
Abstract: What is the chance of rain tomorrow given that past five days were dry? What is the chance an athlete didn't use doping given that s/he had a positive test? How would you compare two clinical treatments if they were never compared in a direct study? How would you increase the likelihood of finding the wreck of a sunken battleship lost in an ocean? The Bayesian statistical methods often provide straightforward solutions to several practical problems occurring in the field of astronomy to zoological sciences. Often these methods are based on the modern computationally-intensive techniques that help researchers and practitioners easily implement these methods using commonly used software (e.g., matlab, R and SAS). Unlike classical frequentist statistics, which attaches repeated-sampling frequencies to test hypotheses, Bayesian approaches directly describe uncertainty about unknown statistical parameters with a probability distribution. With this foundation, much of the Bayesian statistics follows from basic rules of probability theory. This talk presents the essential concepts of Bayesian statistics with a particular focus on the practical aspects of Bayesian methods: how conclusions are drawn, how they can provide answers by combining multiple studies, and what are their strengths and limitations. Using a wide variety of real data examples, this talk will illustrate some key features of Bayesian inference, including the meta-analytic methods.
Biosketch: Professor Sujit Kumar Ghosh earned a Ph.D. in Statistics from the University of Connecticut in 1996 and is currently a tenured faculty member at the rank of full professor in the Department of Statistics at North Carolina State University (NCSU). He has over 15 years of experience in conducting, applying, evaluating and documenting statistical analysis of biomedical and environmental data. Prof. Ghosh is actively involved in supervising and mentoring graduate students at the doctoral and master levels. He has supervised over 25 doctoral graduate students at NCSU. He has served as a statistical consultant for over 20 different research projects funded by various leading private industries and federal agencies (e.g., GSK, BAYER, U.S.EPA, CDC, NIH, NSF, USDA etc.). Prof. Ghosh has published over 80 refereed journal articles in the area of survival analysis, biomedical and environmental models and multivariate analysis and co-edited a popular book entitled "Generalized Linear Models: A Bayesian perspective." Prof. Ghosh has been regularly invited by peer institutions and conference organizers to present talks. He has given over 100 invited seminars and lectures at national and international meetings. Prof. Ghosh was elected to the prestigious position of Fellow of the American Statistical Association (ASA) in 2009 and he also was the recipient of the 2008 International Indian Statistical Association (IISA) Young Investigator Award. He currently serves as the project director of a training program for undergraduates funded by the National Science Foundation (NSF) (with a budget over $0.75 million dollars) entitled "CSUMS: NC State University Computation for Undergraduates in Statistics Program." Since July 2010, he has assumed the role of the co-director of graduate programs in Statistics at NCSU and manages over 150 graduate students.