Biostatistics and Epidemiology
Faculty and Staff
Samprit Banerjee, PhD, MStat, is an Assistant Professor of Biostatistics in Public Health at the Weill Medical College of Cornell University. He received a bachelor’s and master’s degree in statistics from Indian Statistical Institute, Kolkata, India and obtained a PhD in Biostatistics from the University of Alabama at Birmingham.
Dr. Banerjee’s research interest in statistical methodology is primarily in Bayesian methods for high dimensional data. He has developed a Bayesian multivariate regression framework performing variable selection on a large number of independent variables with applications to statistical genetics (QTL mapping). He has also worked on the estimation of high dimensional covariance matrices. His other interests include Markov Chain Monte Carlo methods, Bayesian and non-Bayesian variable selection, generalized linear models and mixed models and categorical data analysis.
Dr. Banerjee’s applied research in biomedical sciences has broadly been in computational genomics (particularly in cancer), public health research (health services and comparative effectiveness research) and clinical trials in Geriatric Psychiatry. He has worked extensively on gene expression data from various platforms, genome-wide association studies of SNPs and copy number variants, enrichment of molecular pathways, impact of structural variants in the evolution of pathways and next generation sequencing data. He has developed computational methods to detect copy number variants from array data that was applied in genome-wide association study of germline CNVs on prostate cancer (published in PNAS in 2012). He has also worked on detecting mutations by a Bayesian hierarchical measurement error model on next-generation sequencing data.
Dr. Banerjee’s interest in public health research spans health services research and comparative effectiveness of medical devices, especially in orthopedics. In a study evaluating the comparative effectiveness of different bearing surfaces (of implants used in hip-replacement surgeries), Dr. Banerjee developed a method to meta-analytically combine survival probabilities in linear mixed model framework to perform Network meta-analysis to estimate indirect evidence. He is also involved in a study which investigates the use of electronic health records across different medical specialties from survey data in longitudinal generalized linear model for complex surveys.Dr. Banerjee is also collaborating with researchers in Geriatric Psychiatry in multi-center randomized clinical trials for older patients with bipolar disorder studying the tolerability and efficacy of two popular drugs. A salient feature of clinical trials with older patients is high attrition rate, and the loss to follow-up is often related to outcome or treatment. Dr. Banerjee is studying appropriate statistical methods to model this missing data pattern and overcome the resulting bias in estimates.
- Division Office
- (646) 962-8020