Testing longitudinal invariance PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
 Erkan Er posted on Sunday, March 27, 2016 - 5:29 am
I have collected data at two time points from the same participants. I want to test if the model is invariant across time points. I cannot use chi-square difference test because of the violation of the independence assumption (as the data are from the same sample). What is the valid way of testing this the invariance in this scenario?
 Linda K. Muthen posted on Sunday, March 27, 2016 - 7:15 am
This is shown in the Topic 4 course handout on the website under multiple indicator growth.
 Erkan Er posted on Sunday, March 27, 2016 - 8:16 am
Thanks! Then, I can use chi-square test still although the samples were same at each time point, right? Or is there any recommended test in Mplus for this? Do you think chi-square test would work in my case?
 Linda K. Muthen posted on Sunday, March 27, 2016 - 8:44 am
See the handout. You can use chi-square as shown in the example.
 Erkan Er posted on Monday, March 28, 2016 - 5:03 pm

Do you know why I am receiving double coefficient values for the paths in my model even when the data across time points are constrained to be equal. I believe I am supposed to obtain a single value per path, am I right? Below are the links to input and output files. Do you see any problems with my code? Or is the result I am getting is okay?

Thanks for any help!


Output: https://drive.google.com/file/d/0B2eU5Y6sEfJ7UExBdWxIOWc5WWc/view?usp=sharing
 Linda K. Muthen posted on Monday, March 28, 2016 - 5:08 pm
Please send the output and your license number to support@statmodel.com.
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