Factor scores with repeated measures PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Anil Saboo posted on Saturday, November 16, 2013 - 11:19 am
I have three waves of responses from multiple customers. I want to compute the factor scores from these responses to be used for subsequent analyses.

What is the best approach in this case? I understand that I should account for the dependence across the repeated measures from the same individual, but am not sure how to carry out in MPlus. Kindly advice.

Look forward to your assistance.
 Bengt O. Muthen posted on Saturday, November 16, 2013 - 6:06 pm
Since you mention factor scores, I assume that you have responses to a multi-item measurement instrument at each time point. So just set up a longitudinal factor analysis model where the number of variables is the number of items times 3 (the number of time points). If long'l FA is unfamiliar to you, see our Topic 1 teaching on the website.
 Anil Saboo posted on Sunday, November 17, 2013 - 5:06 pm
Thanks Dr. Muthen for your response. I looked up the Topic 1 teaching note (page 165)on the website, but only found the figure, which seems to accurately capture what I am looking for.

I have multi-items (a1-a10) at each of the tree time points for several individuals (id identifies the individuals).

Could you provide some guidance on the code...thanks!!
 Linda K. Muthen posted on Monday, November 18, 2013 - 7:49 am
See multiple indicator growth in either the Topic 3 or 4 course handouts. The beginning of this shows the inputs for testing for measurement invariance across time.
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: