Two New Undergraduate Degrees in Data Science
Beginning in fall 2023, UConn students will be able to pursue a Bachelor of Science (BS) in Statistical Data Science and a Bachelor of Arts (BA) in Applied Data Analysis.
Academic Programs
The Department of Statistics provides outstanding undergraduate and graduate education to students at UConn, preparing them for successful careers in academia, industry, government, and beyond.
Quick Links

Undergraduate Advising
Our advisors help students navigate their requirements, select courses, and make the most of their academic experience.

Graduate Education
The Department of Statistics welcomes applicants to our Master of Science (MS) and Doctor of Philosophy (Ph.D.) programs.

Outreach and Engagement
Through events and outreach initiatives, we share our expertise with students and scholars at UConn and beyond.
News and Announcements
Featured Story
Dipak Dey Nominated Candidate for President of American Statistical Association
The UConn Board of Trustees Distinguished Professor of Statistics has been nominated to serve as president of the American Statistical Association (ASA) for the 2025 term.
Upcoming Events
-
Mar
29
STAT Colloquium, Jing Qin4:00pm
STAT Colloquium, Jing Qin
Wednesday, March 29th, 2023
04:00 PM - 05:00 PM
Storrs Campus Virtual Event
Jing Qin, PhD
National Institute of Allergy and Infectious Diseases
A shape restricted propensity score matching method in casual inference
(joint work with Yukun Liu, East China Normal University)
Propensity score matching (PSM) is a pseudo-experimental method that uses statistical techniques to construct an artificial control group by matching each treated unit with one or more untreated units of similar characteristics. To date, the problem of determining the optimal number of matches per unit, which plays an important role in PSM, has not been adequately addressed. We propose a tuning-parameter-free PSM method based on the nonparametric maximum-likelihood estimation of the propensity score under the monotonicity constraint. The estimated propensity score is piecewise constant, and therefore automatically groups data. Hence, our proposal is free of tuning parameters. The proposed estimator is asymptotically semiparametric efficient for the univariate case, and achieves this level of efficiency in the multivariate case when the outcome and the propensity score depend on the covariate in the same direction.
We conclude that matching methods based on the propensity score alone cannot, in general, be efficient.
Bio: Jing Qin is a Mathematical Statistician at Biostatistics Research Branch in National Institute of Allergy and Infectious Diseases. He earned his Ph.D. from University of Waterloo (1992) and then became an assistant Professor at University of Maryland, College Park. Before moving to National Institute of Health (2004), he worked at Memorial Sloan-Kettering Cancer Center for 5 years. Dr. Qin’s research interests include empirical likelihood method, case-control study, biased sampling problems (now called covariate shift or prior probability shift problems in machine learning literature), survival analysis, missing data, causal inference, genetic mixture models, generalized linear models, survey sampling and microarray data analysis. He was elected as an American Statistical Society Fellow, 2006. Dr. Qin published a monograph on "Biased sampling, over-identified parametric problems and beyond" in 2017 (Springer, ICSA book series in statistics).
DATE: Wednesday, 3/29/23
TIME: 4:00 PM
PLACE: Virtual
Webex link: https://uconn-cmr.webex.com/uconn-cmr/j.php?MTID=m636152ee63a668032e47201fadcb0a90Contact Information: tracy.burke@uconn.edu
More