Test Statistics for the Comparison of Means for Two Samples That Include Both Paired and Independent Observations

Authors

Ben Derrick, University of the West of EnglandFollow
Bethan Russ, Office for National StatisticsFollow
Deirdre Toher, University of the West of EnglandFollow
Paul White, University of the West of EnglandFollow

Abstract

Standard approaches for analyzing the difference in two means, where partially overlapping samples are present, are less than desirable. Here are introduced two test statistics, making reference to the t-distribution. It is shown that these test statistics are Type I error robust, and more powerful than standard tests.

DOI

10.22237/jmasm/1493597280

Recommended Citation

Derrick, B., Russ, B., Toher, D., & White, P. (2017). Test statistics for the comparison of means for two samples that include both paired and independent observations. Journal of Modern Applied Statistical Methods, 16(1), 137-157. doi: 10.22237/jmasm/1493597280