VARIANCE ESTIMATION IN PRESENCE OF RANDOM NON-RESPONSE
The goal of the paper is to advocate the problem of estimating the population variance of the study variance of the study variable using information on certain known parameters of the auxiliary variable in the presence of non-response. The proposed estimator is considered under two situations: i) when random non-response on study as well as auxiliary variable and population variance of auxiliary variable is known, and ii) when random non response on study variable and information on auxiliary variable is known with known population variance. Asymptotic expressions for bias and mean squared error of the proposed estimator have been obtained. Comparison of the proposed estimators with usual unbiased estimator has been carried out.