[R] Descriptive stats for factors in SEM

Sebastian Spaeth sspaeth at ethz.ch
Wed Mar 4 14:14:41 CET 2009


John Fox wrote:
> Dear Sebastian,
> 
> What you're looking for are factor-score coefficients, which would allow you
> to estimate the values of the factors from the observed variables. Then,
> given the original dataset from which the input-covariance matrix to sem()
> was computed, you could find the factor scores. The sem packages doesn't
> provide factor-score coefficients, but this is a reasonable request, and
> I'll add it to my to-do list. I can't promise when I'll get this done.
> 
> I'm not sure why you want the means, standard deviations, and correlations
> of the latent variables. In most models, the means will be 0. You could
> figure out the covariance matrix of the latent variables; sem()doesn't
> provide that either. 

I was looking at Piccolo, R. F. & COLQUITT, J. A. TRANSFORMATIONAL
LEADERSHIP AND JOB BEHAVIORS: THE MEDIATING ROLE OF CORE JOB
CHARACTERISTICS Academy of Management Journal, 2006, 49, 327-34

and other articles using SEM and they provide those factor-score
coefficents. (pdf for article here:
http://www.ximb.ac.in/~jgeorge/transforjobbehavior.pdf , table on p.8)

I have never published an SEM model before, so I assume it is standard
to provide those.
Anyway, thank you for your hint, and thanks for putting it on your TODO
list. I am amazed by the speed you were replying, much appreciated. I
have just ordered another of your books :-).

Sebastian Spaeth




More information about the R-help mailing list