Statistical inference with paired observations and independent observations in two samples

Derrick, Ben

Abstract

A frequently asked question in quantitative research is how to compare two samples that include some combination of paired observations and unpaired observations. This scenario is referred to as `partially overlapping samples'. Most frequently the desired comparison is that of central location. Depending on the context, the research question could be a comparison of means, distributions, proportions or variances. Approaches that discard either the paired observations or the independent observations are customary. Existing approaches evoke much criticism. Approaches that make use of all available data are becoming more prominent. Traditional and modern approaches for the analyses for each of these research questions are reviewed. Novel solutions for each of the research questions are developed and explored using simulation. Results show that proposed tests which report a direct measurable difference between two groups provide the best solutions.

• Thesis Type: Thesis
• Deposit Date: Oct 1, 2019
• Publicly Available Date: Mar 12, 2020
• Public URL: https://uwe-repository.worktribe.com/output/3429190
• Award Date: Mar 12, 2020