On Efficient Iterative Estimation Algorithm Using Sample Counterpart of the Searles’ Normal Mean Estimator with Exceptionally Large But Unknown Coefficient of Variation
by Winston A. Richards, Robin Antoine, Ashok Sahai, and M. Raghunadh Acharya
This paper addresses the issue of finding an optimal estimator of the normal population mean when the coefficient of variation is unknown but is expected to be exceptionally high, as per the pilot surveys of the population at hand. The paper proposes an “Efficient Iterative Estimation Algorithm Using Sample Counterpart of the Searles’ Normal Mean Estimator”. The estimators per this strategy have no close form, and hence are not amenable to an analytical study determining their relative efficiencies as compared to the usual unbiased sample mean estimator. Nevertheless, we examine these relative efficiencies of our estimators with respect to the usual unbiased estimator by means of an illustrative numerical empirical study. MATLAB 18.104.22.1681 (R2008b) is used in programming this illustrative ‘Simulated Empirical Numerical Study’.
MVUE, MMSE, Complete Sufficient Statistic, Numerical Study
Ashok Sahai, firstname.lastname@example.org
Winston A. Richards, email@example.com
Robin M. Antoine, firstname.lastname@example.org
Raghunadh M. Acharya, email@example.com
Ahmed H. Youssef, firstname.lastname@example.org
READING THE ARTICLE: You can read the article in
portable document (.pdf) format (291378 bytes.)
NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.
This page has been accessed 3089 times since APRIL 18, 2010.
Return to the Home Page.