Efficient Likelihood Estimators
作者:
E.L. Lehmann,
期刊:
The American Statistician
(Taylor Available online 1980)
卷期:
Volume 34,
issue 4
页码: 233-235
ISSN:0003-1305
年代: 1980
DOI:10.1080/00031305.1980.10483036
出版商: Taylor & Francis Group
关键词: Maximum likelihood;Consistency;Asymptotic efficiency;One-step approximation;Multiparameter exponential family;Multivariate normal distribution
数据来源: Taylor
摘要:
IfX1, …,Xnare identically and independently distributed, then asnŕ ∞, 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.
点击下载:
PDF (275KB)
返 回