Samartsidis, P., "Bayesian estimation of heterogeneous policy effects from time-series data"

Title: "Bayesian estimation of heterogeneous policy effects from time-series data"

Speaker: Senior Research Associate Pantelis Samartsidis, University of Cambridge

Host:  Assistant Professor Alexopoulos Angelos, Department of Economics, Athens University of Economics and Business

Time: 15.30 -17.00

Room:  76, Patission Str., Antoniadou Wing, 3rd floor, Room A36

Abstract:  Assessing the effect of intervention (or policy/treatment) on a set of outcomes of interest using observational time-series data is a problem that arises frequently in the fields of public health, economics and political science, among others. Often, intervention effects exhibit great heterogeneity across units (e.g. hospitals or geographical regions) and time. In such cases, average treatments effects are not necessarily informative, and we are instead interested in alternative causal estimands including individual treatment effects (ITEs) or conditional average treatment effects (CATEs). The latter describe the dependence of causal effects on unit characteristics, or modifiers.