dootika *at* iitk.ac.in
I am an Assistant Professor in the Department of Mathematics and Statistics at the Indian Institute of Technology, Kanpur. Before moving to Kanpur, I was an NSF Postdocotoral fellow with Prof. Gareth Roberts. My PhD was from the School of Statistics at the University of Minnesota, Twin-Cities working with Prof. Galin Jones.
I work in the general area of Bayesian computation and specifically focus on Markov chain Monte Carlo. My collaborators and I develop theoretically founded and practically relevant tools for MCMC output analysis (see software tab). I am also interested in the theoretical properties of Markov chain samplers including rates of convergence.
Students: If you’re interesed in working with me, see students tab.
- June 24-26, EcoSta 2021 (Virtual)
|Dec 6, 2020||Our work on “Batch size selection for variance estimators in MCMC” has been accepted in Methodology and Computing in Applied Probability! Co-authors: Ying Liu and James Flegal.|
|Sep 19, 2020||Our work on “Revisiting the Gelman-Rubin diagnostic” has been accepted in Statistical Science! Co-author: Christina Knudson and R package is here.|
|Sep 4, 2020||Our work on “Assessing and visualizing simultaneous simulation error” has been accepted in JCGS! Co-authors: Nathan Robertson, James Flegal and Galin Jones.|
|Sep 3, 2020||Medha Agarwal and I proposed globally-centered autocovariances for multiple Markov chains. The new ACF plots are remarkably improved! Paper, Webpage, and R package.|
|Aug 30, 2020||Ayush Agarwal completed his Google Summer of Code project under my mentorship. The qbld R package implements a Bayesian quantile regression model for binary longitudinal data.|