Congratulations to the O'Bayes Poster Winners! - Department of Statistics - Purdue University Skip to main content

Congratulations to the O'Bayes Poster Winners!

06-17-2005

Professor Bhramar Mukherjee, a former Purdue Department of Statistics Ph.D. student and current Purdue University Department of Statistics Visiting Assistant Professor from University of Florida, and Surya Tapas Tokdar, Department of Statistics Ph.D. graduate student advised by Professor Jayanta K. Ghosh, were poster winners at the Fifth International Workshop on Objective Bayes Methodology, June 4-8, 2005, in Branson, Missouri, USA.

Professor Bhramar Mukherjee with her winning poster.
Professor Bhramar Mukherjee with her winning poster.

Title: "Bayesian Semiparametric Analysis of Case-Control Data under Gene-Environment Independence and Population Stratification."

Abstract: Many common human diseases are a result of the complex interplay of genetic factors and environmental exposures. In case-control studies of gene-environment association with disease, when genetic and environmental exposures can be assumed to be independent in the underlying population, one may exploit the independence in order to derive more efficient estimation techniques for main effects and gene-environment interaction than the traditional logistic regression analysis (Chatterjee and Carroll, 2005, Biometrika). It is often possible that genetic susceptibility factors and environmental exposures, unlikely to be causally related at an individual level, may be correlated at a population level due to their dependence on certain other variables that stratify the population, such as age, ethnicity and alike. We provide a semiparametric Bayesian approach to model the effect of stratification variables under the assumption of gene-environment independence conditional on the stratification variables in studying the etiology of a rare disease. The results reflect that the semiparametric Bayesian model offers a flexible, robust alternative when standard parametric model assumptions for the distribution of the genetic and environmental exposure do not hold and provides a superior choice when compared with several other competing methods. This is joint work with Li Zhang and Malay Ghosh at University of Florida and Samiran Sinha at Texas A & M University.

Surya Tokdar and his award winning poster at the Fifth International Workshop on Objective Bayes Methodology
Surya Tokdar and his award winning poster at the Fifth International Workshop on Objective Bayes Methodology

Title: "Real Time Bayesian Density Estimation using Gaussian Process."

Abstract: A novel method is proposed to compute the posterior under a Gaussian process prior for density estimation problems. The method gains speed from a combination of imputation and MCMC. This would be of interest to many since recent studies have shown that a Gaussian process prior sits on a large space of densities and achieves posterior consistency.

Purdue Department of Statistics, 150 N. University St, West Lafayette, IN 47907

Phone: (765) 494-6030, Fax: (765) 494-0558

© 2024 Purdue University | An equal access/equal opportunity university | Copyright Complaints | DOE Degree Scorecards

Trouble with this page? Accessibility issues? Please contact the College of Science.