Wanting to get further insights into the practicality of combining Mann Whitney U, Krustall Wallis & Chi square tests along with Spearman Correlation. I wondered if this is repetitious since the first three can still be used to test hypothesis?
Thanks in advance.
Itodo
Dear Itodo, I'm not sure why you would want to combine these tests or what exactly you mean by combining them. They are each have different test designs. Mann Whitney and Spearman should only be used when the equivalent parametric test is inappropriate. Combining tests sounds more like general linear models - a more advanced parametric design.
Dear Peter,
Thanks for the feedback. Mann Whitney U and Krustall Wall will be used to test hypotheses. I was hoping to get some clarifications if the Spearman correlations test would strengthen the former or it's okay to stop there, still reading around this, was hoping a second opinion would aid a better insight.
Thanks,
Itodo.
Dear Itodo,
Although each one of these tests has different applications, In some cases you may need to use almost all of them to prove your point.
Chi-Square is used for goodness of fit test.
Spearman for testing correlations.
And Mann Whitney and Krustall wall for testing independent measures. When you have only two conditions, you may use Mann Whitney. otherwise, for more than two conditions, Krustall Wall test is suggested.
Good luck
- Badges
- Science topic
- Similar topics
- Psychology