SMU SOE Online Seminar (Mar 1, 2021, 9am-10.30am): Linear Programming Approach to Nonparametric Inference under Shape Restrictions: with an Application to Regression Kink Designs

Please click here if you are unable to view this page.

ABSTRACT We develop a novel method of constructing conﬁdence bands for nonparametric regression functions under shape constraints. This method can be implemented via a linear programming, and it is thus computationally appealing. We illustrate a usage of our proposed method with an application to the regression kink design (RKD). Econometric analyses based on the RKD often suﬀer from wide conﬁdence intervals due to slow convergence rates of nonparametric derivative estimators. We demonstrate that economic models and structures motivate shape restrictions, which in turn contribute to shrinking the conﬁdence interval for an analysis of the causal eﬀects of unemployment insurance beneﬁts on unemployment durations. Keywords: Linear programming, regression kink design, shape restriction, nonparametric inference, conﬁdence band. JEL Codes: C13, C14, C21. Click here to view the paper. Click here to view the CV.		This seminar will be held virtually via Zoom. A confirmation email with the Zoom details will be sent to the registered email by 26 February 2021.
		PRESENTER Yuya Sasaki Vanderbilt University
		RESEARCH FIELD Econometrics
		DATE: 1 March 2021 (Monday)
		TIME: 9.00am - 10.30am