Rank-Based Inference for Survey Sampling Data

Abstract

For regression models where data are obtained from sampling surveies, the statistical analysis is often based on approaches that are either non-robust or inefficient. The handling of survey data requires more appropriate techniques, as the classical methods usually result in biased and inefficient estimates of the underlying model parameters. This article is concerned with the development of a new approach of obtaining robust and efficient estimates of regression model parameters when dealing with survey sampling data. Asymptotic properties of such estimators are established under mild regularity conditions. To demonstrate the performance of the proposed method, Monte Carlo simulation experiments are carried out and show that the estimators obtained from the proposed methodology are robust and more efficient than many of those obtained from existing approaches, mainly if the survey data tend to result in residuals with heavy-tailed or skewed distributions and/or when there are few gross outliers. Finally, the proposed approach is illustrated with a real data example.