Abstract
We provide several methods to compare two Gaussian distributed means in the two sample location problems under the assumption of partially dependent observations. Simulation studies indicate that our test procedure is frequently more powerful than other methods depending on the ratio of the unpaired data and the strength and direction of the correlation between the two variables. The tests used in our comparative study are illustrated with an example based on data from a small gynecological study.
Original language | English |
---|---|
Pages (from-to) | 109-117 |
Number of pages | 9 |
Journal | Journal of Applied Statistics |
Volume | 41 |
Issue number | 1 |
DOIs | |
State | Published - Jan 2014 |
Scopus Subject Areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
Keywords
- corrected z-test
- partially dependent observation
- power of the test
- weighted t-tests
- weighted z-test