Enhancing efficiency of ratio-type estimators of population variance by a combination of information on robust location measures

Numerous ratio-type estimators of population variance have been proposed in the literature based on different characteristics of studies and auxiliary variables. However, the existing estimators are mostly based on the conventional measures of population characteristics and their efficiency is questionable in the presence of outliers in the data. This study presents improved families of variance estimators under simple random sampling without replacement (SRSWOR), assuming that the information on some robust non-conventional location parameters of the auxiliary variable, besides the usual conventional parameters, is known. The bias and mean square error of the proposed families of estimators were obtained and the efficiency conditions were derived mathematically. The theoretical results were supplemented with numerical illustrations by using real datasets, which indicated the supremacy of the suggested families of estimators. (C) 2020 Sharif University of Technology. All rights reserved.