Multiple imputation and ANOVA

Posted by Joost van Ginkel on Feb 19, 2014; 8:48am
URL: http://spssx-discussion.165.s1.nabble.com/Multiple-imputation-and-ANOVA-tp5724566.html

Dear list,

In the past I've seen many posts from people trying to do an ANOVA on multiply imputed data sets and not being able to combine the results into one pooled analysis. Many people have emailed me with the same question. Because of all the questions I got and the posts I’ve read here, I decided to write an article on this which is now available online. The reference to this paper is

Van Ginkel, J.R. & Kroonenberg, P.M. (2014). Analysis of variance of multiply imputed data. Multivariate Behavioral Research, 39, 78-91. doi: 10.1080/00273171.2013.855890

Not only does it describe how the results of ANOVA to multiply imputed data sets may be combined from a theoretical point of view, but also does it give the reader guidelines for how to do in several software packages, including SPSS, using an SPSS macro that is available on my personal page (the link is given in the paper).
I hope this paper will help people carry out their ANOVAs on multiply imputed data sets, and maybe it will stimulate SPSS to implement the described procedure in future releases.

Best,

Joost van Ginkel