Raji Balasubramanian

Raji Balasubramanian

Professor of Biostatistics

Metabolomic studies, pediatric HIV studies, measurement error in self-reported outcomes, study design, high-dimensional data and analysis of biological networks.

Location

Arnold House

715 North Pleasant Street
Amherst, MA 01003
United States

405 Arnold House

My research is motivated by studies of complex disorders in large epidemiological studies such as the Women’s Health Initiative. My interests are in methods for biomarker discovery in metabolomics studies, biological network analysis and measurement error models.

Personal website:

Raji Balasubramanian Lab Website

Education

  • Postdoctoral, Harvard University
  • ScD, Harvard University, 2002
  • BA, Mount Holyoke College, 1996

Key Publications

Xu, H.*, Qian, J.*, Paynter, N. P., Zhang, X., Whitcomb, B. W., Tworoger, S. S., Rexrode, K. M., Hankinson, S. E., Balasubramanian, R. (2018): Estimating the area under the Receiver Operating Characteristic (ROC) curve in matched case control studies, Statistics in Medicine, accepted.

*equal contribution.

Xu, H., Gu, X., Tadesse, M. G., Balasubramanian, R. (2018). A modified Random Survival Forests algorithm for high dimensional predictors and self-reported outcomes, Journal of Computational and Graphical Statistics, in press.

Balasubramanian, R., Fowler, M.G., Dominguez, K., Lockman, S., Tookey, P. A., Huong, N. N. G., Nesheim, S., Hughes, M. D., Lallemant, M., Toswill, J., Shaffer, N., Sherman, G., Palumbo, P., Shapiro, D. E. (2017). The Association Of Prophylactic Maternal And Infant Antiretroviral Regimen With The Time To Positive HIV-1 DNA Polymerase Chain Reaction In Non-Breastfed Infants Infected Primarily With Non-B Subtype HIV-1 – A Multi Cohort Analysis, AIDS, 31(18), 2465-2474.

Gu, X., Balasubramanian, R. (2016). Study design for non-recurring, time to event outcomes in the presence of error-prone diagnostic tests or self-reports, Statistics in Medicine, 35(22), 3961-3975. PMCID: PMC5012924

Gu, X., Ma, Y., Balasubramanian, R. (2015). Semi-parametric time to event models in the presence of error-prone, self-reported outcomes - with application to the Women’s Health Initiative, Annals of Applied Statistics, 9 (2), 714-730. PMCID: PMC4729390