Does anyone know if there is any way of conducting a MANOVA when you have both categorical IVs or DVs? Or is this just not possible?
I'm wondering if there is some sort of post-hoc test that will help in the interpretation that is specific for if you're using a MANOVA analysis for categorical IVs and DVs.
Otherwise, what test would people suggest I use? The reason I had originally chosen a MANOVA was that I was comparing groups and had multiple (more than 2) DVs to do this with. Therefore, I thought a MANOVA would be the correct test to use!
Thanks in advance :)
MANOVA is usually used to determine whether there are any differences between independent groups on more than one continuous dependent variable (but the independent variable must be categorical). But there is also MANOVA for categorical data too.
See: Handbook of Statistics, Volume 1, 1980, Pages 343–387, Chapter11: ANOVA and MANOVA: Models for categorical data.
Otherwise, you can transform your categorical data. But also, make sure there is no autocorrelation, no outliers, and that the data fulfils normal assumptions.
I hope this helps :)
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS