|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Competing models estimated by WLMSV |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
Chris Stride posted on Wednesday, November 01, 2006 - 9:46 am
|
|
|
When comparing competing nested models estimated using WLSMV, is there any way of testing the significance of the difference between the resulting chi-sq stats? I note that the technical appendices offer a way for MLR and MLM chi-square stats but nothing for WLSMV? If not, is there any way around this problem: I have a SEM with three dichotomous outcome variables. |
|
|
Use the DIFFTEST option. See the user's guide. |
|
Back to top |
|
|