Output factor scores with ID variable? PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Wouter Steenbeek posted on Tuesday, September 15, 2009 - 12:50 am
Is it possible to output an ID variable with the outputted factor scores? Then I can make absolutely sure that the Nth factor score also belongs to the Nth case in my original data.

This is especially important a hierarchical dataset. If I'm not mistaken, the saved factor scores are scrambled - case nr 1 in this new file is NOT the same as case nr1 in my original data file. I *think* Mplus reorders the dataset so that the largest level-2 units come first? But I'm not 100% sure, so I'm hesitant to use the factor scores now.
 Linda K. Muthen posted on Tuesday, September 15, 2009 - 6:15 am
Use the IDVARIABLE option of the VARIABLE command.
 Wouter Steenbeek posted on Tuesday, September 15, 2009 - 4:51 pm
Thank you!

FYI: The dataset I was trying out with, the example dataset ex9.6.dat, has no level-1/unique-case identifier, so therefore I didn't get it to work.

From what I see now, the IDVARIABLE option of the VARIABLE command isn't even necessary. After making afjusted the .dat file with a case nr identifier called "respnr", I think it doesn't matter if include that IDVARIABLE option or not; both methods also output the "clus" and the "respnr" variable in the factor scores output file.
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: