Improving the Limited Information Maximum Likelihood Estimator When the Disturbances are Small

Abstract

The limited information maximum likelihood (LIML) estimator is shown to be inadmissible in terms of asymptotic expansions of the distributions of the estimators. The LIML estimator is improved by combining it linearly with the two-stage or the ordinary least squares estimator.

Key Words:

• Econometrics
• Simultaneous equations
• Reduced bias
• Reduced MSE
• Asymptotic expansions
• Small-disturbance asymptotics