HEC Research Papers Series,
HEC Paris

Abstract: We study the estimation of dynamic economic models for which some of the state variables are observed only occasionally by the econometrician—a common problem in many fields, ranging from marketing to finance to industrial organization. If such occasional state observations are serially correlated, the likelihood function of the model becomes a potentially high-dimensional integral over a nonstandard domain. We propose a method that generalizes the recursive likelihood function integration procedure (RLI; Reich, 2018) to numerically approximate this integral. We prove consistency and asymptotic normality of our (approximate) estimator and demonstrate its high efficiency in several well-understood examples from finance and industrial organization. In extensive Monte Carlo studies, we compare the performance of our approach to a recently suggested method of simulated moments. In all our demonstrations, we identify all model parameters with high efficiency, and we find that the additional variance of our estimator when going from full to occasional state observations is small for the parameters of interest.

Keywords: Maximum likelihood estimation; occasional state observations; recursive likelihood function integration; interpolation; numerical quadrature; Markov models; dynamic discrete choice models; long-run risk models

JEL-codes: C13; C49; C63

62 pages, July 22, 2020

Full text files

papers.cfm?abstract_id=3638618 HTML file Full text

Download statistics

• HEC Paris
• Ordering Working Papers
• Home page for this series

Questions (including download problems) about the papers in this series should be directed to Antoine Haldemann ()
Report other problems with accessing this service to Sune Karlsson ().

RePEc:ebg:heccah:1380This page generated on 2024-09-13 22:19:53.