Maximum Simulated Likelihood Estimation of Random-Effects Dynamic Probit Models with Autocorrelated Errors

Abstract

This paper investigates using maximum simulated likelihood (MSL) estimation for random-effects dynamic probit models with autocorrelated errors. It presents and illustrates a new Stata command, redpace, for this estimator. The paper also compares using pseudorandom numbers and Halton sequences of quasirandom numbers for MSL estimation of these models.