Improved chain-ratio type estimator for population total in double sampling

Abstract

Chain-ratio estimators are often used to improve the efficiency of the estimation of the population total or the mean using two auxiliary variables, available in two different phases. An improved chain-ratio estimator for the population total based on double sampling is proposed when auxiliary information is available for the first variable and not available for the second variable. The bias and the mean square error of this estimator are obtained for a large sample. Empirical evaluations using both model-based and design-based simulations show that the proposed estimator performs better than the ratio, the regression, and the difference estimators.