Which test: Compare MORE THAN TWO DEPENDENT groups (Paired, Matched, Same respondent groups)
When the research objective is to compare more than two dependent groups, which means they are paired, matched, and thus the same respondent groups in a pre- post-test, we have a choice among different statistical procedures, depending on the following variable characteristics:
Number of variables:
[Unless where otherwise indicated] One dependent variable and one independent categorical variable (more than two levels or groups)
Examples:
- Are the means / frequencies (on the dependent variable) of the same respondents over more than two different time periods significantly different such as in a pre- mid- post- test (e.g. 3 waves test)?
- Are there significant differences (on the dependent variable) in the way the same respondents evaluated more than two different variables or objects measured at the same time such as their evaluation of product A on variable 1, variable 2 and variable 3, or their evaluation of product A, B and product C on variable 1?
When the dependent variable is BINOMIAL / BINARY / DICHOTOMOUS
- Cochran’s Q test
- Repeated measures logistic regression
When the dependent variable is NOMINAL
- Repeated measures logistic regression
When the dependent variable is ORDINAL / RANK-DATA
- Friedman Repeated test
- Kendall’s W
When the dependent variable is INTERVAL and passed the assumption of normality (parametric data)
- One-way Repeated-measures ANOVA
- Factorial Repeated-measures ANOVA (for more than one independent variable)
- Can also add a repeated measure of MANOVA, MANCOVA, and Mixed designs (for more than one dependent and independent variables)
When the dependent variable is INTERVAL but failed the assumption of normality (non-parametric data)
- Friedman Repeated test
- Kendall’s W
______________________________________________________
/zza59