Hi all, Welcome back to another semester of Applied Stats. We will continue to meet every Wednesday from 12-1:30PM throughout the semester in CGIS Knafel, Room K354. The schedule for the semester is below: Jan 29: Jason Anastasopoulos (University of Georgia) Feb 5: Gary King (Harvard University) Feb 12: Adam Kapelner (Queens College) Feb 19: Asya Magazinnik (MIT) Feb 26: Shusei Eshima (Harvard University) Mar 4: Jamie Robins (Harvard University) Mar 11: Reagan Mozer (Bentley University) Mar 25: Weihua An (Emory University) Apr 1: Soichiro Yamauchi (Harvard University) Apr 8: Alexander MacKay (Harvard University) Apr 15: Briana Stephenson (Harvard University) Apr 22: Kosuke Imai (Harvard University) Apr 29: TBC Our first meeting wiill be Wednesday January 29 where Jason Anastasopoulos will present research on 'Principled Estimation of Regression Discontinuity Designs' (Paper attached). Abstract: The regression discontinuity design (RDD) has become a popular method for making causal inferences with observational data under minimal assump- tions. Local average treatment effects (LATE) for RDDs are typically estimated using local linear regressions with pre–treatment covariates added to increase the efficiency of treatment effect estimates. In political science applications where there are typically few observations around the cutpoint, covariate selec-tion can have a large impact on treatment effect and standard error estimates. In this paper, I propose a principled, efficiency-maximizing approach for selecting covariates to include in RDDs. This approach allows researchers to combine substantive insights with regularization via a novel adaptive LASSO algorithm. When combined with currently existing robust estimation methods, this approach improves the efficiency of LATE RDD with pre–treatment covariates. All are welcome and lunch will be provided. I look forward to seeing you all next week! Georgie