CFA of Symptom inventory PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Jeremy E Halstead posted on Friday, April 20, 2007 - 7:20 am
I have developed a 19 item symptom inventory using an iterative process that has good exploratory FA characteristics. More specifically in the development samples there were 6 stable factors of 3 or 4 items.It makes sense from a clinical point of view to combine these factors to produce larger groupings corresponding with clinical descriptors.
Let us say the factors are a b c d e f
a b c & d predict depression
e & f predict anxiety
although it may be that
e f & d predict anxiety more accurately
I would be interested in views on the best way to proceed with Mplus with the goals of further validating (if that is the right word) the previously found 6 factor structure but also producing some justifiable anxiety and depression scales.

For this analysis the amount of data available is around 500 complete cases and that number could be doubled, while maintaining a justifiable experimental design

I am interested in your views

thanks
 Linda K. Muthen posted on Friday, April 20, 2007 - 9:01 am
I think the next step would be to do CFA and see how a model with a more simple structure that EFA fits the data. Once you get well-fitting measures, you can use the to predict anxiety and depression.
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: