Weekly Seminar – April 18: Andrew Gelman (Columbia University), “How large is that treatment effect, really?”

Date: April 18th, 2024 (12:30 pm – 1:30 pm)

Speaker: Andrew Gelman

Paper Title: “How large is that treatment effect, really?”

Abstract: “Unbiased estimates” aren’t really unbiased, for a bunch of reasons, including aggregation, selection, extrapolation, and variation over time.  Econometrics typically focus on causal identification, with this goal of estimating “the” effect.  But we typically care about individual effects (not “Does the treatment work?” but “Where and when does it work?” and “Where and when does it hurt?”).  Estimating individual effects is relevant not only for individuals but also for generalizing to the population.  For example, how do you generalize from an A/B test performed on a sample right now to possible effects on a different population in the future?  Thinking about variation and generalization can change how we design and analyze experiments and observational studied.  We demonstrate with examples in social science and public health.

Bio:

Andrew Gelman (PhD, Harvard, 1990) is Higgins Professor of Statistics, Professor of Political Science, and director of the Applied Statistics Center at Columbia University. He has received the Outstanding Statistical Application award from the American Statistical Association, the award for the best article published in the American Political Science Review, and the Council of Presidents of Statistical Societies award for outstanding contributions by a person under the age of forty.

Professor Gelman’s research spans a wide range of topics, including why it is rational to vote; why campaign polls are so variable when elections are so predictable; why redistricting is good for democracy; reversals of death sentences; police stops in New York City; the statistical challenges of estimating small effects; the probability that one vote will be decisive; seats and votes in Congress; social network structure; arsenic in Bangladesh; radon in home basements; toxicology; medical imaging; and methods in surveys, experimental design, statistical inference, computation, and graphics.