Why stratification may hurt, & how much
Methodology
2008-02-15 v1
Abstract
There are circumstances under which stratified sampling is worse than simple random sampling, even if the allocation of the sample sizes is optimal. This phenomenon was discovered more than sixty years ago, but is not as widely known as one might expect. We provide it with lower and upper bounds for its badness as well as with an explanation.
Cite
@article{arxiv.0802.2087,
title = {Why stratification may hurt, & how much},
author = {Chris A. J. Klaassen and Andries J. Lenstra},
journal= {arXiv preprint arXiv:0802.2087},
year = {2008}
}
Comments
11 pages