When we have two groups with pre and post-test data, which test is better? One-way analysis of covariance (ANCOVA) or Repeated Measures Analysis of Variance (RM-ANOVA)? Why?
One would typically use a mixed 2 (between) x 2 (within) ANOVA in this case. In other words, you would use a 2-factorial ANOVA in which one factor is a between-subjects (group) factor and the other factor is a within-subjects (pre-post/repeated measures) factor. Each factor has two levels in your example.
Here's another article suggesting ANCOVA is a good choice--but note that it assumes the groups have been formed via random allocation.
Vickers A J, Altman D G. Analysing controlled trials with baseline and follow up measurements BMJ 2001; 323 :1123 doi:10.1136/bmj.323.7321.1123
https://www.bmj.com/content/323/7321/1123
if you have only two groups of data ( Pre and Post), the ANCOVA is better, but if you have several (Post groups) data recorded at different times the Repeated Measures Analysis of Variance should be your choice.
It seems like you would use a 2-factorial ANOVA in which one factor is a between-subjects (group) factor and the other factor is a within-subjects (time) factor.
What is your outcome variable?
Which software do you use?
If you are using SPSS, ANOVAs are good in this software.
If you are using Stata, the tendencies of this software are towards regressions instead of ANOVAs. Therefore, panel regression is suggested and better; because you can choose the family of distribution for outcome variable.
- Badges
- Science topic
- Similar topics
- Engineering
- Materials Engineering
- Powders