I am a Postdoctoral researcher working with Prof. Hans-Georg Müller, who is also my PhD advisor, and Prof. Jane-Ling Wang in the Department of Statistics at University of California, Davis. I finished my PhD in June 2019. Prior to this, I received a Bachelor of Statistics in 2012 and a Master of Statistics in 2014 from the Indian Statistical Institute, Kolkata.
My research centers around developing statistical methods for nonEuclidean data, examples being distribution and network valued data. Here is a link to my CV.
I love to sketch. In my spare time I sometimes go on sketchcrawls. I also love hiking.
I am interested in developing broadly applicable statistical methods for analyzing nonEuclidean data, popularly called object data. Such data often arise in many real applications, examples being brain imaging data, traffic network data, genetics and microbiome data. In my first project as a graduate student, I worked on a k-sample test for samples of metric space valued data which can be used for testing samples of distributions or samples of networks. In a subsequent paper, we extended this approach to carry out change point detection in a sequence of metric space data. Here is a recent poster about this that I presented at WHOA-PSI 2019 and my defense slides.
I am also interested in functional and longitudinal data analysis, with focus on studying samples of dynamic object data. I am privileged to have presented my recent work in this area in the Research Section Discussion Meeting of the Royal Statistical Society.
My research motivation is drawn from challenges in analyzing different kinds of emerging data forms in modern applications, many of which are high dimensional and present theoretical challenges. Broadly I am interested in nonparametric modeling and inference for such data.
Recently I am also interested in online learning problems, specifically contextual multi-armed bandit problems with unconventional contexts.
Publications and Preprints
P. Dubey, H.G. Müller. Fréchet Change Point Detection. (Under Revision in Annals of Statistics).
P. Dubey, H.G. Müller. Functional Models for Time Varying Object Data. Journal of Royal Statistical Society: Series B (to appear with discussion).[pdf]
P. Dubey, H.G. Müller. Fréchet Analysis of Variance for Random Objects. Preprint available as arXiv:1710.02761. Biometrika (to appear), winner of Best Paper Awards at JSM, 2018 (Section of Nonparametric Statistics) and 2018 IISA International Conference on Statistics. [pdf]
P. Sur, G. Shmueli, S. Bose, and P. Dubey. Modeling bimodal discrete data using Conway- Maxwell-Poisson mixture models. Journal of Business and Economic Statistics, Volume 33, 2015 - Issue 3.
S. Bose, G. Shmueli, P. Sur, and P. Dubey. Fitting COM-Poisson mixtures to bimodal count data. Proceedings of the 2013 International Conference on Information, Operations Management and Statistics (ICIOMS 2013), winner of Best Paper Award.
I have been teaching assistants for several courses during my time as a graduate student. I was also associate instructor for an introductory level Statistics course (STA 13) and an upper undergraduate level course (STA 131A).
As Teaching Assistant
STA 13 (Elementary Statistics)
STA 100 (Applied Statistics for Biological Sciences)
STA 103 (Applied Statistics for Business and Economics)
STA 206 (Statistical Methods for Research I)
STA 141A (R for Data Science)
STA 131B (Introduction to Mathematical Statistics)
STA 13 (Elementary Statistics)
STA 131A (Introduction to Probability Theory)
A few accolades
Peter Hall Graduate Research Award 2019, awarded for outstanding graduate research
SF Bay Area Chapter of ASA Travel Award for Joint Statistical Meetings 2019 for "Modeling Time Varying Object Data"
Student Paper Award, International Indian Statistical Association Conference, 2018 and Best Paper Award, Section on Nonparametric Statistics, Joint Statistical Meetings, 2018 for "Fréchet Analysis of Variance for Random Objects"
UC Davis and Humanities Graduate Research Award, 2018
UC Davis Graduate Studies Travel Award, 2018
Summer Statistics Research Fellowship, UC Davis, 2015-2017
Get in Touch
Department of Statistics
Mathematical Sciences Building 1131
399 Crocker Lane
University of California, Davis
One Shields Avenue
Davis, CA 95616