creating a factor using cfa

Lindy — Tue, 01 May 2018 17:45:20 GMT

Hi folks,

I created several latent factors using proc factor.

The items under each factor loads well, and I created the value of the composite using factor scores.

However, when I am about to use the factors as my independent variables in a model and I need to report descriptive statistics, I found generally the standard deviation of the facotrs are bigger than their means. Usually people would see a redflag when S.D. is bigger than the mean...But I think this rule may not apply to factors created based on factor scores? How can I explain it?

Mean Std Dev Minimum Maximum
0.158052 0.9290338 -3.4236783 1.781888

Mean Std Dev Minimum Maximum
-0.0573974 0.9146756 -0.6069258 5.511616

Mean Std Dev Minimum Maximum
-0.1035039 0.8218769 -0.3771253 9.7391213

Re: creating a factor using cfa

PaigeMiller — Tue, 01 May 2018 17:51:32 GMT

Means of factors should be close to zero. This is not a problem with the factors.

topic Re: creating a factor using cfa in Statistical Procedures

creating a factor using cfa

Re: creating a factor using cfa