vix.ing · top · new · best · stats · spec

Linear programming approach to nonparametric inference under shape\n restrictions: with an application to regression kink designs

2021/02/12 by Harold D. Chiang, Kengo Kato, Chiang, Harold D. +5
Economics, Econometrics and Finance · Mathematics · #Advanced Causal Inference Techniques #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #Methodology (stat.ME) #Monetary Policy and Economic Impact #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2102.06586

openalex publication_date 2021/02/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We develop a novel method of constructing confidence bands for nonparametric\nregression functions under shape constraints. This method can be implemented\nvia a linear programming, and it is thus computationally appealing. We\nillustrate a usage of our proposed method with an application to the regression\nkink design (RKD). Econometric analyses based on the RKD often suffer from wide\nconfidence intervals due to slow convergence rates of nonparametric derivative\nestimators. We demonstrate that economic models and structures motivate shape\nrestrictions, which in turn contribute to shrinking the confidence interval for\nan analysis of the causal effects of unemployment insurance benefits on\nunemployment durations.\n

Related