On the second order local comparison between perturbed maximum likelihood estimators and Rao's statistic as test statistics

DOI10.1016/0047-259X(88)90048-6MaRDI QIDQ1109448zbMATH OpenFDO

Authors S. H. Smith

Publication date 1988

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0047-259X(88)90048-6

zbMATH Keywords

bias-adjusted maximum likelihood estimatorEdgeworth expansionEfron's curvaturelikelihood ratiolocal powerslocal unbiasednessRao's statistictwo-sided testing problemWald's statistic

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Asymptotic properties of parametric tests (62F05) Asymptotic properties of parametric estimators (62F12)

Review text

A bias-adjusted maximum likelihood estimator (MLE), which has been shown to possess certain optimality criteria as an estimate of \(\theta\) [see \textit{J. K. Ghosh}, \textit{B. K. Sinha} and \textit{S. N. Joshi}, Statistical Decision Theory and Related Topics III, Proc. 3rd Purdue Symp., West Lafayette/Indiana 1981, Vol. 1, 403--456 (1982; Zbl 0585.62062)] is compared with Rao's statistic as a test statistic for the standard two-sided testing problem. It is shown that Rao's statistic is locally superior to any bias-adjusted MLE in the sense of the first author and \textit{S. N. Joshi} [Sankhyā, Ser. A 45, 226--246 (1983; Zbl 0563.62018)]. A second interpretation of a conjecture of \textit{C. R. Rao} [Linear statistical inference and its applications. New York etc.: John Wiley and Sons (1965; Zbl 0137.36203)] is proposed and Rao's statistic is shown to be superior as a test statistic according to the new interpretation as well. The last fact provides an interesting supplement to the results of Chandra and Joshi. Furthermore, a partial reason for the inferiority of the likelihood ratio and Wald's statistic to Rao's statistic is supplied and certain regularity assumptions of the last paper are eliminated. Finally, the local powers of certain modified versions of Rao's and Wald's statistics are studied.

Recommendations

• scientific article; zbMATH DE number 3898014
• Publication:4947018
• scientific article; zbMATH DE number 706391
• scientific article; zbMATH DE number 3954035
• Comparison between the locally most mean power unbiased and Rao's tests in the multiparameter case

Cites work

• A second-order investigation of asymptotic ancillarity
• Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information
• Asymptotic expansions of the distributions of some test statistics
• scientific article; zbMATH DE number 3898014 (Why is no real title available?)
• scientific article; zbMATH DE number 3938277 (Why is no real title available?)
• scientific article; zbMATH DE number 3945055 (Why is no real title available?)
• scientific article; zbMATH DE number 3223275 (Why is no real title available?)
• scientific article; zbMATH DE number 3224089 (Why is no real title available?)
• Likelihood ratio and associated test criteria
• On the validity of the formal Edgeworth expansion
• The local power of the efficient scores test statistic

Cited in

(6)

• Adjustments of Rao's score test for distributional and local parametric misspecifications
• Second-order power comparison of tests
• scientific article; zbMATH DE number 3898014 (Why is no real title available?)
• Monte carlo comparison of wald's, likelihood ratio and rao's tests
• scientific article; zbMATH DE number 1423413 (Why is no real title available?)
• Bartlett-type modification for Rao's efficient score statistic

This page was built for publication: On the second order local comparison between perturbed maximum likelihood estimators and Rao's statistic as test statistics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1109448)