Statistics and Data Sciences
University of Texas at Austin
  Abhra Sarkar
  • Home
  • Research
  • Teaching
  • Software
  • CV

Overview

    My research interests center around the development of novel statistical approaches that aid in the study of complex real world phenomena and provide new insights into related scientific queries. I enjoy, in particular, developing sophisticated Bayesian semi and nonparametric methods that accommodate a wide range of data generating processes, adapting to different levels of data complexity and potentially automating various aspects of the analysis, including feature extraction, variables selection, uncertainty quantification, and hypotheses testing. These methods have appealing practical advantages and theoretical properties, exhibiting substantial gains in performance compared with existing approaches under wide range of scenarios.

    My research is often application-driven, the overarching goal being the development of novel statistical methods that improve results and practices in an initial motivating area while having much broader general utility. In such pursuits, I am often drawn to scientific problems that lack substantial coverage in the statistics literature. Such application-driven philosophy has led me to a wide range of methodological interests, as outlined below. Over the years, I have been successful in introducing many novel ideas that address long-standing challenges and gaps in the literature.

Measurement Error Models
With Applications in Nutritional Epidemiology
  1. Ho, B. N.*, Ramdas, V.* and Sarkar, A. (2024+). HEI analysis of NHANES dietary data: Exploring the diet quality of Americans with R package heiscore. [* equal contributions] (under revision).
  2. Roy, A. and Sarkar, A. (2023). Bayesian semiparametric multivariate density deconvolution via stochastic rotation of replicates. Computational Statistics and Data Analysis, 182: 107706. [link]
  3. Sarkar, A. (2022). Bayesian semiparametric covariate informed multivariate density deconvolution. Journal of Computational and Graphical Statistics, 31, 1153–1163. [link]
  4. Sarkar, A., Pati, D., Mallick, B. K., and Carroll, R. J. (2021). Bayesian copula density deconvolution for zero inflated data in nutritional epidemiology. Journal of the American Statistical Association, 116, 1075-1087. [link]
  5. Sarkar, A., Pati, D., Chakraborty, A., Mallick, B. K., and Carroll, R. J. (2018). Bayesian semiparametric multivariate density deconvolution. Journal of the American Statistical Association, 113, 401-416. [link]
  6. Sarkar, A., Mallick, B. K. and Carroll, R. J. (2014). Bayesian semiparametric regression in the presence of conditionally heteroscedastic measurement and regression errors. Biometrics, 70, 823-834. [link]
  7. Sarkar, A., Mallick, B.K., Staudenmayer, J., Pati, D. and Carroll, R.J. (2014). Bayesian semiparametric density deconvolution in the presence of conditionally heteroscedastic measurement errors. Journal of Computational and Graphical Statistics, 24, 1101-1125. [link]


(Higher Order) (Nonhomogeneous) (Hidden) Markov (Renewal) (Mixed) Models
With Applications in Neuroscience of Vocal Communication / Climatology
  1. Wu, Y. and Sarkar, A. (2024+). BMRMM: An R package for Bayesian Markov (renewal) mixed models. To appear in the R Journal.
  2. Sarkar, A. and Dunson, D. B. (2024+). Bayesian higher order hidden Markov models. (under revision). [link to arXiv preprint]
  3. Wu, Y., Jarvis, E. D. and Sarkar, A. (2024). Bayesian Markov renewal mixed models for analyzing vocalization syntax. Biostatistics, 25, 648-665. [link]
  4. Wang, H., Asefa, T., and Sarkar, A. (2021). A novel non-homogeneous hidden Markov model for simulating and predicting monthly rainfall. Theoretical and Applied Climatology, 143, 627-‌638. [link]
  5. Sarkar, A., Chabout, J., Macopson, J. J., Jarvis, E. D. and Dunson, D. B. (2018). Bayesian semiparametric mixed effects Markov models with application to vocalization syntax. Journal of the American Statistical Association, 113, 1515-1527. [link]
  6. Chakraborty, M., Fridel, E.E., Chen, L., Klein, M. E., Senft, R., Sarkar, A. and Jarvis, E. D. (2017). Over-expression of human NR2B receptor subunit in LMAN causes stuttering and song sequence changes in adult zebra finches. Scientific Reports, 7, 1-18. [link]
  7. Sarkar, A. and Dunson, D. B. (2016). Bayesian nonparametric modeling of higher order Markov chains. Journal of the American Statistical Association, 111, 1791-1803. [link]
  8. Chabout, J., Sarkar, A.*, Patel, S.*, Raiden, T., Dunson, D. B., Fisher, S. E. and Jarvis, E. D. (2016). A Foxp2 mutation implicated in human speech deficits alters sequencing of ultrasonic vocalizations in adult male mice. [* equal contributions] Frontiers in Behavioral Neuroscience, 10, 1-18. [link]
  9. Chabout, J., Sarkar, A., Dunson, D. B. and Jarvis, E. D. (2015). Male song syntax depends on contexts and influences female preferences in mice. Frontiers in Behavioral Neuroscience, 9, 1-19. [link]
  10. Sarkar, A., Bhadra, A. and Mallick, B. K. (2011). Nonparametric Bayesian approaches to nonhomogeneous hidden Markov models. (unpublished technical report).


(Local Inference with) Longitudinal / Time Series (Functional) (Mixed) Models
With Applications in Public Health / Social Sciences / Climatology / Metabolomics
  1. Sarkar, A., Cominetti, O., Martin, F. P., Montoliu, I. and Dunson, D. B. (2024+). Bayesian semiparametric inference in longitudinal metabolomics data: the EarlyBird study. (submitted).
  2. Paulon, G., Mueller, P. and Sarkar, A. (2024+). Bayesian semiparametric hidden Markov tensor partition models for longitudinal data with local variable selection. To appear in Bayesian Analysis. [link]
  3. Fan, J. and Sarkar, A. (2024). Bayesian semiparametric local clustering of multiple time series data. Technometrics, 66, 282-294. [link]


Drift-Diffusion Models for Decision Making / Category Learning
With Applications in Neuroscience of Auditory Processing
  1. Mukhopadhyay, M., McHaney, J., Chandrasekaran, B. and Sarkar, A. (2024). Bayesian semiparametric longitudinal inverse-probit mixed models for category learning. Psychometrika, 89, 461-485. [link]
  2. Roark, C. L., Rebaudo, G., Paulon, G., McHaney, J. R., Sarkar, A. and Chandrasekaran, B. (2024) Individual differences in working memory impact decision processes during speech category learning. PLOS One, 19, e029791. [link]
  3. Roark, C. L., Paulon, G., Sarkar, A. and Chandrasekaran, B. (2021). Comparing artificial perceptual category learning across modalities in the same individuals. Psychonomic Bulletin & Review, 28, 898-909. [link]
  4. Paulon, G., Llanos, F., G., Chandrasekaran, B. and Sarkar, A. (2021). Bayesian semiparametric longitudinal drift-diffusion mixed models for tone learning in adults. Journal of the American Statistical Association, 116, 1114-1127. [link]
  5. Paulon, G., Reetzke, R., Chandrasekaran, B. and Sarkar, A. (2019). Functional logistic mixed effects models for learning curves from longitudinal binary data. Journal of Speech, Language and Hearing Research, 62, 543-553. [link]


Precision Factor Analysis / Vector Autoregressive Models for Graphs
With Applications in Neuroscience of Auditory Processing / Genomics / Finance
  1. Fan, J., Sitek, K., Chandrasekaran, B. and Sarkar, A. (2024+). Bayesian tensor decomposed vector autoregressive models for inferring Granger causality from high-dimensional multi-subject panel neuroimaging data. (being revised to be resubmitted)
  2. Chandra, N. K.*, Sitek, K.*, Chandrasekaran, B. and Sarkar, A. (2024). Functional connectivity across the human subcortical auditory system using an autoregressive matrix-Gaussian copula graphical model. [* equal contributions] Imaging Neuroscience, 2, 1–23. [link]
  3. Chandra, N. K., Mueller, P. and Sarkar, A. (2024+). Bayesian scalable precision factor analysis for Gaussian graphical models. To appear in Bayesian Analysis.
  4. Zhang, L., Sarkar, A. and Mallick, B. K. (2016). Bayesian sparse covariance matrix decomposition with a graphical structure. Statistics and Computing, 26, 493-510. [link]


Other Miscellaneous Interests
With Applications in Neuroimaging / Neuroscience of Auditory Processing / Genomics / Clinical Trials
  1. Rebaudo, G., Llanos, F., Chandrasekaran, B. and Sarkar, A. (2024+). Bayesian mixed multidimensional scaling for auditory processing. (submitted)
  2. Chandra, N. K., Sarkar, A., de Groot, J. F., Yuan, Y. and Mueller, P. (2023). A Bayesian semiparametric approach to accelerating clinical trials with synthetic controls. Journal of the American Statistical Association, 118, 2301-2314. [link]
  3. Mueller, P., Chandra, N. K. and Sarkar, A. (2023). Bayesian approaches to include real world data in clinical studies. Philosophical Transactions of the Royal Society A, 381: 20220158. [link]
  4. Zoh, R., Sarkar, A., R. J. Carroll, and Mallick, B. K. (2018). A powerful Bayesian test for equality of means in high dimensions. Journal of the American Statistical Association, 113, 1733-1741. [link]



Research
Last updated in Aug, 2024