Nested model comparisons with imputed... PreviousNext
Mplus Discussion > Missing Data Modeling >
 George Howe posted on Tuesday, July 26, 2011 - 10:27 am
I've created 50 imputed data sets using MPLUS, and have been running some structural equation models. I'd like to do nested model comparisons to test some equality constraints, but am not sure this is acceptable. In addition I've been using MLR, and no correction factor is provided, so it looks like Satorra-Bentler is not possible? (I haven't seen anything on this in the imputation literature, but am still trying to run down Craig Ender's book; references would be nice if you know of any).
 Tihomir Asparouhov posted on Tuesday, July 26, 2011 - 11:32 am
Currently the only likelihood ratio test available with imputations is the ML estimator (for testing unrestricted against a structural model).

You can easily however use the Wald test for your testing purposes with imputation. Look at page 618 "Model Test" command.
 George Howe posted on Tuesday, July 26, 2011 - 12:57 pm
Thanks, Tihomir, I'd wondered about that. Worked fine!

 shaun goh posted on Saturday, March 09, 2013 - 9:30 pm
I'm wondering how to compare two nested models from 2 multiple imputed data sets in a multi-group, LGC setting.

I am interested in group differences of trajectories - differences in the means of the latent factors of the growth curves between 2 groups. I was going to constrain the means to equality and employ chi-sq testing, but am unsure how to conduct likelihood testing with multiple imputed data. Is there a way to do so in Mplus
(i.e. by "Model Test" or by hand-calculation of chi-sq differences?)
 Linda K. Muthen posted on Sunday, March 10, 2013 - 7:31 am
You can use MODEL TEST. Difference testing using chi-square or the loglikelihood has not yet been developed for multiple imputation.
 shaun goh posted on Sunday, March 10, 2013 - 4:21 pm
Thanks Linda, I will utilise MODEL TEST.

I was wondering, if difference testing using chi-square/loglikelihood/fit statistics have not yet been developed for multiple imputation, how does MODEL TEST run a valid test for equivalence between two nested models in the multiple imputation context?
 Linda K. Muthen posted on Monday, March 11, 2013 - 10:56 am
MODEL TEST uses a Wald test. It is not based on the loglikelihood.
 Joseph posted on Thursday, August 15, 2013 - 8:59 am
Hi Linda,

can I used the MODEL TEST option with the WLSMV estimator?

 Linda K. Muthen posted on Thursday, August 15, 2013 - 10:15 am
 Christoph Weber posted on Friday, July 18, 2014 - 12:59 am
Dear Mplus-Team!
to clear things up (may be a silly question):
How does the Model test option calcultes the Wald test of parameter constraints?
 Linda K. Muthen posted on Friday, July 18, 2014 - 1:15 pm
See the following link:
 Fabian Kirsch posted on Wednesday, April 05, 2017 - 5:43 am
Dear MPlus-Team,

I am currently working with multiply imputed data sets and want to compare models. I used the model test command (Wald tests) as were recommended in this thread, and this worked fine.
However, I wonder whether there is a publication (or something like that) that I can refer to (cite) to argue that traditional chi-square difference tests are not yet implemented when using multiple imputation?

Thank you in advance
Fabian Kirsch
 Bengt O. Muthen posted on Wednesday, April 05, 2017 - 4:02 pm
Refer to our short course on this topic (see Missing Data).
 Mohini Lokhande posted on Friday, June 09, 2017 - 2:31 am
Dear MPlus-Team,

I also used M.I. data sets for a multiple group analyses (Twolevel regression) and used the model test command (Wald test) to compare a nested/constraint model with a comparison model where no constraints are set. In the latter model I do not get any Wald chi square statistic that would allow me to do difference testing using chi-square.

Is there any other possibility to do such a comparison between nested and comparison models with the wald statistic or any other statistic?

Thank you for your response.

Kind regards
Mohini Lokhande
 Bengt O. Muthen posted on Friday, June 09, 2017 - 4:38 pm
The Wald test of Model Test is done in a single run, not comparing two runs. So use it for the less restricted model and test the restrictions you are interested in.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message