Has any body looked at using parallel analysis with CATPCA

[Art Kendall]

Parallel analysis is extremely valuable when using factor.

Has anybody figured out how to do parallel analysis with CATPCA?

[Ryan]

Art,

You might find this blog interesting:

http://www.methodspace.com/profiles/blogs/factor-analysis-for-likert-ordinal-non-normal-data

Ryan

On Fri, Nov 2, 2012 at 3:27 PM, Art Kendall <[hidden email]> wrote:

> Parallel analysis is extremely valuable when using factor.
>
> Has anybody figured out how to do parallel analysis with CATPCA?
>
> --
> Art Kendall
> Social Research Consultants
>
>
> ________________________________
> View this message in context: Has any body looked at using parallel analysis
> with CATPCA
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Art Kendall]

It is a long time since I had a chance to look at this link.

At least since 1972, SPSS has had the ability to read in a correlation matrix for FACTOR.

Without testing whether one gets the same results, it is plausible that using something other than CORRELATIONS to create the matrix and then bringing that matrix into SPSS for the various kinds of factor analysis, rotations, etc. would be practical.

REGRESSION can also operate on a correlation matrix. 

It would be interesting to see if and how often one obtains substantively different results with (CATPCA, and FACTOR) (CATREG and REGRESSION), using (Pearson, polychoric, and tetrachoric) correlations.
On 11/2/2012 3:51 PM, R B wrote:

Art,

You might find this blog interesting:

http://www.methodspace.com/profiles/blogs/factor-analysis-for-likert-ordinal-non-normal-data

Ryan

On Fri, Nov 2, 2012 at 3:27 PM, Art Kendall [hidden email] wrote:

Parallel analysis is extremely valuable when using factor.

Has anybody figured out how to do parallel analysis with CATPCA?

--
Art Kendall
Social Research Consultants


________________________________
View this message in context: Has any body looked at using parallel analysis
with CATPCA
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD