Combination rules for multiply imputed datasets in SPSS

[Joost van Ginkel]

Dear listers,

 

The people who have read my earlier posts on this list in the past may know me as someone who's expertise is multiple imputation, more specifically, combination rules. I regularly publish papers in which I either propose new combination rules for statistical techniques for which previously no combination rules had been defined, or draw people's attention to existing combination rules for which it is not widely known that they exist and can be applied to specific statistical analyses. Although nowadays I do most of my work in R, I was doing my master at a time when R was not yet widely used and SPSS had a large role in the master's program. For this reason I still regularly think from an SPSS framework, and let my work on combination rules mostly be inspired by what is currently not implemented in SPSS. In this way I have written papers on combination rules for PCA (Van Ginkel & Kroonenberg, 2014a; Van Ginkel & Kiers, 2011), ANOVA (Van Ginkel & Kroonenberg, 2014), F-tests for regression (Van Ginkel, 2019), and most recently on R² and standardized regression coefficients in regression (Van Ginkel, 2020). Additionally, I have provided an SPSS macro that performs some of the combination rules that are not implemented in SPSS (available from my personal page: https://www.universiteitleiden.nl/en/staffmembers/joost-van-ginkel#tab-1).

Now what I have noticed so far is that somehow SPSS does not pick up the things I have done in my publications. None of the things that I have developed or written about have been implemented in SPSS so far. On the one hand that's in my advantage, because many people who don't know what to do when SPSS doesn’t provide combined results start searching for answers, run into my papers, use my SPSS macros, and consequently the number of citations of these papers rise sky high. On the other hand, it is ultimately not my goal to get many citations, but to bring my solutions to the people. It would therefore really help if SPSS would pick up my ideas. I was wondering if any of the listers know how to get in touch with the right SPSS people to get my ideas implemented. Or are some of the developers of SPSS by any chance on this list and listening? I would really like to discuss my ideas with you. The relevant references are:

 

Van Ginkel, J.R. (2020). Standardized regression coefficients and newly proposed estimators for R² in multiply imputed data. Psychometrika. doi: 10.1007/s11336-020-09696-4

 

Van Ginkel, J.R. (2019). Significance tests and estimates for R² for multiple regression in multiply imputed datasets: A cautionary note on earlier findings, and alternative solutions. Multivariate Behavioral Research, 54, 514-529. doi: 10.1080/00273171.2018.1540967

 

Van Ginkel, J.R.  & Kroonenberg, P.M. (2014a). Using Generalized Procrustes analysis for multiple imputation in Principal component analysis. Journal of Classification, 31, 242-261. doi: 10.1007/s00357-014-9154-y

 

Van Ginkel, J.R.  & Kroonenberg, P.M. (2014b). Analysis of variance of multiply imputed data. Multivariate Behavioral Research, 49, 78–91.

doi: 10.1080/00273171.2013.855890

 

Van Ginkel, J.R. & Kiers, H.A.L. (2011). Constructing bootstrap confidence intervals for principal component loadings in the presence of missing data: a multiple-imputation approach. British Journal of Mathematical and Statistical Psychology, 64, 498-515. doi: 10.1111/j.2044-8317.2010.02006.x

 

I hope to hear from you. Many thanks!

 

Best regards,

 

Joost van Ginkel

 

 

 

 

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD