DID YOU KNOW? DTIC has over 3.5 million final reports on DoD funded research, development, test, and evaluation activities available to our registered users. Click HERE
to register or log in.
Simple BAN Estimators of Correlations for Certain Multivariate Normal Models with Known Variances.
FLORIDA STATE UNIV TALLAHASSEE DEPT OF STATISTICS
Pagination or Media Count:
It is well-known that in certain multivariate normal models with known variances, maximum likelihood estimation of correlations is arithmetically cumbersome. For many of these models, the author gives a technique to obtain estimators which are relatively simple functions of the sufficient statistics and are BAN. The procedure makes use of the fact that many of the likelihood equations for these models are essentially cubic equations. For the associated cubic equation, an explicit solution is found which is consistent for the parameter to be estimated. The author is then able to show that this solution has the appropriate asymptotic efficiency and normality properties. Considered in detail are the intraclass, autoregressive, and moving average models.
APPROVED FOR PUBLIC RELEASE