Professional Summary
Bhramar Mukherjee is an Associate Professor in the Department of Biostatistics, joining the department in September 2006, after spending four years as an Assistant Professor in the Department of Statistics at the University of Florida. Bhramar completed her Ph.D. in 2001 from Purdue University. She has held visiting scholar positions at Stanford, Purdue, The Indian Statistical Institute, Victoria University (New Zealand), and the National Cancer Institute over the last four years. Bhramar did her doctoral work on optimal designs for estimating functionals of a random process, but then developed research interest in application of Bayesian methods to problems in epidemiology. She is currently serving as the principal investigator on an NSF and an NIH grant on developing Bayesian methods for studying the synergism of gene and environment. She was also awarded an Young Investigator Grant awarded by the National Security Agency in 2005 on developing Bayesian design and inference methods for complex epidemiological studies. Her current research focuses on modeling missingness in exposure, capturing unmeasured heterogeneity due to stratification, studies of gene-environment interaction under matched and unmatched case-control sampling design. Bhramar has successfully used Bayesian semiparametric techniques to achieve robust inference in applications in epidemiology. She is involved as a co-investigator in several R01s led by faculty in Internal Medicine and Environment Health sciences at UM.
Courses Taught
BIOSTAT695: Analysis of Categorical Data
Syllabus (PDF)
BIOSTAT699: Analysis of Biostatistical Investigations
Education
Ph.D., Statistics, Purdue University, 2001
M.S., Mathematical Statistics, Purdue University, 1999
M.Stat., Applied Statistics and Data Analysis, Indian Statistical Institute, 1996
B.Sc., Statistics, Presidency College, 1994
Research Interest & Projects
In terms of statistical methods, my research interests are Bayesian semiparametric methods, experimental design, statistical methods for case-control and other outcome-dependent sampling schemes, studies of gene-gene and gene-environment interaction, missing data and measurement error in case-control studies. The central theme in my research program has been to illustrate the advantage of using Bayesian techniques for flexible, hierarchical modeling of epidemiological data. Epidemiology is a science which progresses by accumulation of evidence, and the Bayesian paradigm offers many natural solutions to complex problems encountered in modern epidemiology. Currently, I am working on case-control studies of gene-environment interaction and family based case-control studies. I am interested in Bayesian nonparametric techniques, especially involving the Dirichlet process prior. Foundational issues related to any choice based sampling scheme is another area which interests me greatly.
Selected Publications
Mukherjee, Bhramar and Liu, Ivy (2008). A characterization of bias for fitting multivariate generalized linear models under choice-based sampling. Accepted in Journal of Multivariate Analysis.
Mukherjee, Bhramar, Ahn, Jaeil, Liu, Ivy and Sanchez, Brisa (2008). On elimination of nuisance parameters in stratified proportional odds model by amalgamating conditional likelihoods. Statistics in Medicine.
Mukherjee, Bhramar, Ahn, Jaeil, Rennert, Gad, Gruber, Stephen, Moreno, Victor and Chatterjee, Nilanjan (2008). Testing gene-environment interactin from case-control data: A novel study of Type-1 error, power and designs. Genetic Epidemiology.
Mukherjee, Bhramar and Chatterjee, Nilanjan (E-Pub: 2007). Exploiting gene-environment independence for analysis of case-control studies: An empirical-Bayes type shrinkage estimator to trade off between bias and efficiency. Biometrics.
Zhang Li, Mukherjee, Bhramar, Ghosh, Malay, Gruber, Stephen and Moreno, Victor. (E-Pub: 2007). Misclassification of exposures in case-control studies of gene-environment interaction, Statistics in Medicine., Online Publication.
Dorazio, Robert M. , Mukherjee, Bhramar, Zhang, Li, Ghosh, Malay, Jelks,Howard and Jordan, Frank (E-Pub: 2007). Modeling Unobserved Sources of Heterogeneity in Animal Abundance Using a Dirichlet Process Prior. Biometrics.
Mukherjee,Bhramar, Liu, Ivy and Sinha, Samiran (2007). Analysis of Matched case-control data with ordinal disease states: possible choices and comparisons Statistics in Medicine, 26, No 17, 3240--3257.
Mukherjee,Bhramar, Zhang, Li, Ghosh,Malay and Sinha, Samiran (2007). Bayesian semiparametric analysis of case-control data under conditional gene-environment independence Biometrics, 63, No 3, 834-844.
Sinha, Samiran, Mukherjee, Bhramar,Ghosh, Malay, Mallick, Bani K. and Carroll, Raymond J. (2005). Bayesian semiparametric analysis of matched case-control studies with missing exposure. Journal of the American Statistical Association, Vol 100, No. 470, pp 591-601.
Sinha, Samiran, Mukherjee, Bhramar,Ghosh, Malay (2004). Bayesian analysis of matched case-control studies with multiple disease states. Biometrics , Vol 60, No. 1, pp 41-49.
|
Site Menu
back to top