Error intercorrelations PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
 JW posted on Monday, March 16, 2009 - 11:40 am
How does one specify how to inter-correlate the error variance between four single indicators in a LGM? Basically, I have four indicators, and I want to inter-correlate all their errors i.e., y1 with y2, y3, y4; y2 with y3, y4; y3 with y4 etc...
 Thuy Nguyen posted on Tuesday, March 17, 2009 - 1:31 pm
You use the WITH option, for example,

y1 WITH y2;
 JM posted on Friday, March 20, 2009 - 9:53 am
Thanks, So I'd write:

y1 WITH y2;
Y1 WITH y3;
Y1 WITH y4;
y2 WITH y3 etc...

I just wondered if there was a more compact way that I was missing.
 Bengt O. Muthen posted on Friday, March 20, 2009 - 12:01 pm
You can say:

y1-y5 with y1 with y5;

You get messages about duplicates that you can ignore.
 Bengt O. Muthen posted on Friday, March 20, 2009 - 12:02 pm
Sorry, that should be:

y1-y5 with y1-y5;
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