We recently came across a 2019 blog post, “OPM team develops new tool for improving power calculations”, by Michale Binci and Paul Jasper of Oxford Policy Management. The post describes a tool that Binci, Jasper, and their colleague Virginia Barberis developed to calculate the ideal sample size for an impact evaluation.
The power calculation command that the OPM team developed is designed to be effective for complex evaluation designs, including quasi-experimental designs and stratified/cluster sampling. The command “allows users to account for a larger and more comprehensive range of design parameters than most available power commands, including difference-in-differences and regression discontinuity settings, clustering, inter-temporal correlation, variance, and finite population corrections, amongst others.”
To learn more about the OPM power calculation command, and to listen to a brief audio discussion by the authors, check out the full blog post.