Does anyone have any SPSS syntax to decompose a 4-way interaction from a mixed ANOVA with 2 repeated factors?
Right now, we have a significant 4-way interaction that needs decomposition. Rather than conducting a series of ever-shrinking ANOVAs to decompose it, I was wondering if anyone had a something available to test that, e.g., MMATRIX, LMATRIX.
Don't worry, we're sufficiently powered.
Perhaps the 3-way ANOVA examples on the UCLA page linked below can be adapted for your design. When using LMATRIX, I recommend that you start by entering the contrast coefficients needed to produce each of the cell means in Excel. You can then easily do the subtractions (in Excel) needed to produce the contrasts you really want.
FWIW, interaction contrasts are quite a bit easier in Stata, if you have access to it. Michael Mitchell's nice book has plenty of examples (2nd link below). UCLA's IDRE website has several Stata examples too (3rd link).
HTH.
https://stats.idre.ucla.edu/spss/faq/how-can-i-use-the-lmatrix-subcommand-to-understand-a-three-way-interaction-in-anova/
https://www.stata.com/bookstore/interpreting-visualizing-regression-models/
https://stats.idre.ucla.edu/stata/faq/everything-you-always-wanted-to-know-about-contrasts-but-were-afraid-to-ask/
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS