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

This paper investigates the use of Maximum Simulated Likelihood estima-tion for random effects dynamic probit models with autocorrelated errors. It presents a new Stata command, redpace, for this estimator and illustrates its usage. The paper also compares the use of pseudo-random numbers and Halton sequences of quasi-random numbers for the MSL estimation of these models.