Partial measurement invariance PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 JM posted on Monday, May 11, 2009 - 11:43 am
Hi, I'm conducting an eval of partial measurement invariance using a multiple indicator growth model. I ran the full model in the equal factor loadings and the data did not fit. Upon a suggestion, I freely estimated one of the factor loadings - I want to be sure I have the syntax correct:

W1 BY posit1
ysr1
totsubd1 (1);
W2 BY posit2
ysr2
totsubd2 (1);
W3 BY posit3
ysr3
totsubd3 (1);
W4 BY posit4
ysr4
totsubd4 (1);

So, this would set posit1-4 as the marker, freely estimate ysr1-4 and the constrain totsub1-4 to equality enabling the examination of equal factor loadings. Then, when I conduct the equal indicator intercepts model, I only include the following:
[posit1 posit3 posit3 posit4] (2);
[totsubd1 totsubd2 totsubd3 totsubd4] (3);
[w1@0 w2 w3 w4];
and not include the [ysr1-4]...right?
 Linda K. Muthen posted on Tuesday, May 12, 2009 - 8:59 am
You can include it but without the equality label.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: