Stephen McAteer

Logo

Father of two, husband of one. PhD in mathematical physics. Lead data scientist at the Victorian Auditor-General's Office. Long suffering Essendon supporter.

LinkedIn - GitHub - email

14 October 2019

Bootstrap for finite populations

I find bootstrapping to be one of the most general and useful statistical techniques in my toolbox. In the paper below, the method is extended to finite populations (roughly the bootstrapping equivalent of moving from a binomial to a hypergeometric distribution in proportion estimation).

I have yet to apply this technique in anger …

A survey of bootstrap methods in finite population sampling

Author: Zeinab Mashreghi

Abstract: We review bootstrap methods in the context of survey data where the effect of the sampling design on the variability of estimators has to be taken into account. We present the methods in a unified way by classifying them in three classes: pseudo-population, direct, and survey weights methods. We cover variance estimation and the construction of confidence intervals for stratified simple random sampling as well as some unequal probability sampling designs. We also address the problem of variance estimation in presence of imputation to compensate for item non-response.

Statistics Surveys, Vol. 10 (2016) 1–52, ISSN: 1935-7516, DOI: 10.1214/16-SS113

https://projecteuclid.org/euclid.ssu/1458047831

tags: bootsptap - statisitcs - parameter estimation - nonparametric statistics