Hi everyone,
My dataset contains 2 IVs, manipulated within-subjects.
I'd like to run a repeated-measures ANOVA; the problem is that the two IVs are not balanced; i.e., I did not collect data in some of the IV combinations.
Suggestions on how to proceed with the analysis?
Thanks in advance,
Yaron
Use a mixed model approach coding "individual" as random factor.
You may test the direct effect of each IV on dependent variables with different samples. However, if you would like to test the interaction between 2 IVs, you can use only the complete sets of data (i.e.., using the cases where both IVs are manipulated with subjects).
To expand on Jochen's point - this is one of the main advantages of multilevel models (also known as linear mixed models or hierarchical linear models). Software such as R, SAS, SPSS, Stata etc. should all be able to run this.
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA