Factor Scores in a bifactor model PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Abu Minhajuddin posted on Tuesday, January 21, 2020 - 5:20 am
I have estimated a bifactor model using the following code:

analysis:
estimator=wlsmv;
parameterization=theta;
rotation=geomin;
Model:
gen by V1-V20;
F1 by V1-V5;
F2 by V6-V10;
F3 by V11-V15;
F4 by V16-V20;

gen with F1-F4@0;
F1 with F2-F4@0;
F2 with F3-F4@0;
F3 with F4@0;
gen@1; F1-F4@1;

savedata:
file is fs.dat;
save = fscores;
format is free;

output: stdyx svalues;


I have the following 3 questions:

1) In the saved output file, I get 10 new columns along with the data I used to build/estimate this model. With 1 general and 4 specific factors, shouldn't I get 5 new columns only? What are the additional 5 columns?

2) Since I specified the covariance between the general and specific factors to be 0, should I get factor scores that are uncorrelated or minimally correlated?

3) Are the factor loadings I get in the output from the original scale of the data or the rotated scale? How do I get the rotated factor loadings?

Thanks.
 Bengt O. Muthen posted on Wednesday, January 22, 2020 - 1:18 pm
Please send your output to Support along with your license number.
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: