This question already has an answer here:

I am currently working on pooling F- and p-values from the ANOVA tables in SPSS regression output. While I tried using various aspects miceadds, it proved to be quite complicated. I recently came across a couple of resources that said that I could run the analysis in SPSS, and then pool the F-values in R using the micombine.F function, as follows:

library(miceadds) Fvalues <- c( 6.76 , 4.54 , 4.23 , 5.45 , 4.78, 6.76 , 4.54 , 4.23 , 5.45 , 4.78, 6.76 , 4.54 , 4.23 , 5.45 , 4.78, 6.76 , 4.54 , 4.23 , 5.45 , 4.78 ) micombine.F(Fvalues, df1=4)

This provided seemingly appropriate output, but I am wondering if this is an acceptable way to pool F values? While I realize that it is tedious, I am content to use this approach if it gets the job done. Thank you!


marked as duplicate by Noah, Peter Flom Aug 1 at 10:53

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.

  • $\begingroup$ Yes, that was the answer that led me to this procedure. But I want to ensure that this is an acceptable procedure. It seems quite simple, which strikes me as odd given that all resources I have encountered on pooling ANOVA in R for MI are quite complex. $\endgroup$ – cwfrs Jul 31 at 18:11