Resampling methods for labour force survey

Abstract

Labor force survey is one of the most important surveys carried out in all countries. Its main purpose is to estimate quantities such as the unemployment rate and the number of people in work. Labor force survey is focused both in estimates at a given time and in changes between two successive time period. However, it is essential to know the precision of the estimates and their corresponding variances. In order to estimate the variance in a complex survey, where the sample is reweighted to match some known marginal quantities based on age, sex and geographical location, we apply the resampling methods.

This paper reviews the resampling methods for the analysis of labour force survey that have been proposed in the literature—the jackknife, balanced repeated replication and the bootstrap and discuss the extent to which they are useful. Although the resampling methods may be useful in solving of some problems, there is no evidence that they are generally useful techniques for the analysis of labour force surveys