Estimation of the Non-Centrality Parameter of a Chi-Square Distribution
CLEMSON UNIV SC DEPT OF MATHEMATICAL SCIENCES
Pagination or Media Count:
The non-central chi-square distribution arises in various statistical analyses. The estimation of the non-centrality parameter of the distribution is of importance in some problems. In this paper it is shown that the maximum likelihood estimator is inadmissible with respect to the squared error loss function. It is trivially minimax since all estimators have unbounded maximum risk. A class of estimators is given which are admissible and minimax for a modified loss function.
- Statistics and Probability