A class-cum-class estimators for population ratio in poststratified sampling over two occasions

Abstract

Onyeka (2002) proposed two estimators of the second occasion population ratio, R2 , in poststratified sampling over two occasions along the line of Tripathi and Sinha (1976) and Okafor (1985). The estimators are a ratio-cum-product type (d1) estimator and a product-cum-ratio type (d2) estimator. The present study provides a generalization of the estimators, d1 and d2 , proposed by Onyeka (2002). This generalization is in the form of a class-cum-class estimators, d, for the second occasion population ratio, R2 , in poststratified sampling over two occasions. The proposed class-cum-class estimators, d, do not assume knowledge of the first occasion population ratio, R1 . Conditions under-which some of the estimators in the proposed class perform better than the others (in terms of having smaller mean square errors) are obtained for repeated samples of fixed sizes.



Keywords: Successive sampling, poststratified sampling, ratio estimation, matching (or replacement) fraction, repeated samples

[Global Jnl Mathematical Sci Vol.2(1) 2003: 65-72]