Econometrics of Insurance Models with Multidimensional Types
49 Pages Posted: 22 Jun 2017 Last revised: 9 Jul 2019
Date Written: July 2019
In this paper we address the identification and estimation of insurance models where insurees have private information about their risk and risk aversion. The model includes random damage and allows for several claims, while insurees choose from a finite number of coverages. We show that the joint distribution of risk and risk aversion is nonparametrically identified despite bunching due to multidimensional types and a finite number of coverage. Our identification strategy exploits the observed number of claims as well as an exclusion restriction and a support assumption. Our results apply to any form of competition. We propose a novel and computationally friendly estimation method combining kernel regression and density estimation as well as inverse Fourier transforms.
Keywords: Insurance, Identification, Nonparametric Estimation, Multivariate Adverse Selection
JEL Classification: C10, C57, L89
Suggested Citation: Suggested Citation