Estimation of the Finite Population Mean in Stratified Random Sampling under Non-response

In this paper we have considered the problem of estimating the population mean using auxiliary information in presence of non-response. This situation is examined under two cases; Case I: when non-response occurs both on study variable and auxiliary variable and population mean of the auxiliary variable is known; Case II: when non-response occurs only on study variable, complete information on auxiliary variable and population mean of auxiliary variable is known. Mathematical properties of proposed estimators such as bias, mean square error and minimum mean square error are separately obtained for both the cases of all the proposed estimators up to the first order of approximation. The proposed estimators have been compared theoretically with the Hansen and Hurwitz (1946) estimator and some other existing estimators. The conditions for which proposed estimators are most efficient are obtained. Moreover, numerical illustrations shows that the proposed estimators perform better than existing estimators in terms of mean square error.