Article ID Journal Published Year Pages File Type
1150089 Journal of Statistical Planning and Inference 2007 10 Pages PDF
Abstract

This paper presents a method for constructing confidence intervals for the median of a finite population under unequal probability sampling. The model-assisted approach makes use of the L1L1-norm to motivate the estimating function which is then used to develop a unified approach to inference which includes not only confidence intervals but hypothesis tests and point estimates. The approach relies on large sample theory to construct the confidence intervals. In cases when second-order inclusion probabilities are not available or easy to compute, the Hartley–Rao variance approximation is employed. Simulations show that the confidence intervals achieve the appropriate confidence level, whether or not the Hartley–Rao variance is employed.

Related Topics
Physical Sciences and Engineering Mathematics Applied Mathematics
Authors
,