The performance of the partially overlapping samples t-tests at the limits

TL;DR

This paper evaluates the effectiveness of partially overlapping samples t-tests when test elements are at their extremes, especially in cases with only one sample having independent observations.

Contribution

It provides an assessment of the test's performance at the limits, highlighting scenarios with extreme data and partial independence.

Findings

Performance varies at the extremes of data

Partially overlapping tests have limitations with independent observations

Guidelines for applying the test in boundary cases

Abstract

This note includes an assessment of the partially overlapping samples t-tests in scenarios where elements of the test are at their extremes, including where only one sample contains independent observations