Abstract
This article provides to the survey practitioner some guidance about the problem of variance estimation for equal probability single-start systematic samples. An investigation of eight alternative estimators of the variance of the sample mean is presented. In the first half of the investigation, the theoretical properties of the estimators are compared using several superpopulation models; in the second half, the comparison is empirical, based on several real populations. Recommendations are made about the appropriateness of the various estimators.

This publication has 0 references indexed in Scilit: