Separate Ratio Estimator Using Calibration Approach for the Population mean in Stratified Random Sampling

In this paper we investigate the problem of estimation of finite population mean using auxiliary information. The aim of this paper is to modify a separate ratio estimator by using calibration approach for the population mean using stratified random sampling. We use the calibration approach to improve the precision of estimate of the population parameter by incorporating auxiliary information. We use the chi-square distance function to minimize the distance between the original design weight and the new design weight. We use two constraints called calibration equations to find the new calibration weights. We use the Taylor’s linearization technique to find the approximate mean square (MSE) of the proposed estimator up to the first degree of approximation. We conduct a simulation study to assess the efficiency of the proposed calibration estimator based on an artificially generated data set. An empirical study has also been conducted to judge the merits of the proposed estimator, which shows that the proposed estimator performs better than the proposed estimator [9] and the usual separate ratio estimator.