Quasi Random Resampling Designs for Multiple Frame Surveys

Abstract

In this paper, we present two new algorithms that use the shuffled Sobol sequence to generate the bootstrap resampling designs in multiple frame surveys. We investigate the performance of the proposed algorithms in a simulation study using a three-overlapping frame setup design. The samples were selected independently from the frames using a stratified simple random sampling design. The performance of the proposed methods is comparable with the already established ones such as the Lohr-Rao bootstrap methods for multiple frame surveys in terms of relative percentage bias, coefficient of variation, and empirical coverage probabilities of 95 percent confidence interval.