A modified regression-cum-ratio estimator of population mean of a sensitive variable in the presence of non-response in simple random sampling

Abstract

A generalized class of estimators has been proposed for finite population mean of a sensitive study variable in the presence of non-response under a Simple Random Sampling Without Replacement design (SRSWOR) using the Randomized Response Technique (RRT) in two phase sampling . Auxiliary information from a positively correlated non-sensitive variable is used. The expressions for MSE of the proposed estimator are derived. The performance of the proposed estimator is evaluated both theoretically and empirically in comparison to some of the existing estimators.