Error intercorrelation PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
 Dennis Dietrich posted on Wednesday, August 27, 2014 - 5:04 am

I have a latent growth curve model with 8 time points. This 8 measurements I took within 4 weeks two times per week with identical items.

My question is if it is possible to inter-correlate the errors (what would be logical)? Or if I should not/can not do this in a LGCM?

(Also error intercorrelation would give me a much better model fit: RESMA .085 to .06 CFI .82 to .91)

Thank you for your answer.
 Linda K. Muthen posted on Wednesday, August 27, 2014 - 11:30 am
I believe residuals at adjacent time points are sometimes correlated.
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