Maximum Likelihood Estimation in Random Coefficient Models

Abstract

Abstract Previous Monte Carlo studies examining properties of estimators in random coefficient models have been hindered in part by computational difficulties. In particular, determination of maximum likelihood estimators appears sensitive to the computational algorithm used. In a small Monte Carlo experiment, several distinctly motivated algorithms are examined with respect to accuracy and cost in searching for global and local maximum likelihood parameter estimates. A noncalculus oriented approach offers promise. When compared with other estimators, maximum likelihood estimators, so determined, appear to be statistically relatively efficient.