FORMAL BAYES ESTIMATION WITH APPLICATION TO A RANDOM EFFECTS ANALYSIS OF VARIANCE MODEL.
STANFORD UNIV CALIF DEPT OF STATISTICS
Pagination or Media Count:
Techniques of formal Bayes estimation are discussed and applied to the estimation of the components of variance in the one way layout random effects ANOVA model. Invariant formal Bayes estimators are presented and proved to be admissible in certain classes of invariant rules and also minimax. To do this a general sufficient condition for admissible in certain multiparameter problems is given and applied to the ANOVA problem. Numerical calculations of mean squared errors of various estimators are also presented, and these results help justify the recommendation of the formal Bayes estimators. Author
- Statistics and Probability