An Iterative Algorithm for Efficient Estimation of Normal Variance Using Sample Coefficient of Variation

by Miodrag M Lovric & Ashok Sahai.

Abstract: This paper addresses the issue of finding an optimal estimator of the normal population variance when the coefficient of variation is unknown. Searls & Intarapanich (1990) found the MMSE [Minimum Mean Squared Error Estimator] of the normal population variance. The paper proposes an “Efficient Iterative Estimation Algorithm exploiting sample coefficient of variation for the efficient Normal variance estimation”. 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 variance estimator S2. Nevertheless, we examine these relative efficiencies of our estimators with respect to the usual unbiased estimator S2 by means of an illustrative numerical empirical study. MATLAB (R2008b) is used in programming this illustrative ‘Simulated Empirical Numerical Study’.

Key Words: MMSE, Sample Coefficient of Variation, Numerical Simulation Study

Ashok Sahai,
Miodrag M Lovric,

Editor: . A.M. Abd-Elfattah,

READING THE ARTICLE: You can read the article in portable document (.pdf) format (449777 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 1499 times since MAY 1, 2011.

Return to the InterStat Home Page.