Efficient Likelihood Estimators |
| |
| Authors: | E. L. Lehmann |
| |
| Affiliation: | University of California , Berkeley , CA , 94720 , USA |
| |
| Abstract: | If X 1, …, X n are identically and independently distributed, then as n ? ∞, there exists under suitable regularity conditions a sequence of solutions of the likelihood equation that is consistent and asymptotically efficient. However, this consistent solution is not necessarily the maximum likelihood estimate. Likelihood estimation should therefore emphasize the determination of a consistent sequence of solutions of the likelihood equations rather than maximizing the likelihood. The issues are illustrated on some examples. |
| |
| Keywords: | Maximum likelihood Consistency Asymptotic efficiency One-step approximation Multiparameter exponential family Multivariate normal distribution |
|
|
