Another Look at the Identification of Dynamic Discrete Decision Processes: An Application to Retirement Behavior

Abstract

This article deals with the estimation of behavioral and welfare effects of counterfactual policy interventions using dynamic structural models where all the primitive functions are nonparametrically specified (i.e., preferences, technology, transition rules, and distribution of unobserved variables). It proves the nonparametric identification of agents’ decision rules, before and after the policy intervention, and of the change in agents’ welfare. Based on these results, I propose a nonparametric procedure to estimate the behavioral and welfare effects of a class of counterfactual policy interventions. The nonparametric estimator can be used to construct a test of the validity of a parametric specification. I illustrate this method using a simple model of labor force retirement, panel data with information on public pension wealth, and a hypothetical reform that delays by three years the eligibility ages of the public pension system in Sweden.