Quantile Model-Assisted estimation approach for the estimation of a population total

Abstract

Abstract: A quantile model-assisted approach is used to estimate a finite population total. This estimator attempts to make efficient use of auxiliary Information under the presence of influential points. The approach consists in minimizing a weighted sum of the distances between fitted and observed values. Firstly, an estimator for population coefficients of a quantile regression is obtained, then a GREG-like estimator for the total Is presented. The performance of the proposed estimator is assessed empirically via simulation studies under scenarios such as: different distribution of the errors and distinct settings of extreme observations with a single auxiliary variable. The proposed estimator for the finite population total seems to have a good performance in terms of smaller bias and mean square error specially in skewed distribution, normal mixtures and in the presence of influential points.