Estimation of Current Population Variance in Two Successive Occasions

Abstract

The problem of estimation of the population variance for the current occasion based on the samples selected over two successive occasions has been considered. Expressions for the Optimum estimator and its variance have been derived for both the occasions. Also the expression has been derived when no information has been collected on the first occasion. Expression for the Optimum fraction of unmatched observations has been derived. The values of Optimum matched and unmatched fractions have been tabulated. The gain in efficiency of the proposed estimator is compared to the estimator without using the information collected on the first occasion. An empirical study has also been conducted to study the performance of the proposed strategy.