Anchor points in scales PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 April Martin posted on Tuesday, August 11, 2009 - 2:57 pm
My advisor (who doesn't have a thorough knowledge of SEM) has just reviewed my dissertation and has some concerns with my analyses.

He questions whether I should be using more than one scale to represent my manifest variables since their anchor points are different. For example, my latent variable is work outcomes. The indicators predicting this are job sat, org. commit, engagement, and intent to turnover. Two scales have subscales and the anchor points are different for each of them. Does this pose a problem? He thinks I have too many variables representing my latent variable.
 Linda K. Muthen posted on Tuesday, August 11, 2009 - 5:11 pm
You could try doing an EFA at the subscale level to see how many factors are represented by your data.
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: