Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: re: factor analysis


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: re: factor analysis
Date   Mon, 29 Jun 2009 16:14:44 +0100

Depending on which version of Stata you have 

0. It may predate any factor analysis or PCA command. (You are working
with a real antique.) 

1. It may support -factor- with PCA functionality included. -score- is
available to calculate scores afterwards. 

2. It may support -factor- and -pca- separately with -score- available
afterwards. 

3. It may support -factor- and -pca- separately with -predict- available
afterwards. 

At this moment I lack the inclination to rummage around to work out
exactly when these changes were made. But Evans Jadotte's advice here is
incorrect, as if -score- won't work after -factor- it won't work with
-pca-. That is, in any version of Stata with -factor- and -pca- the
appropriate command for calculating scores used to be -score-, but is
now -predict-. 

Nick 
n.j.cox@durham.ac.uk 

Evans Jadotte

Try with pca (principal component analysis) that does support score.

francis wasswa wrote:

> I am trying to create an asset index using DHS data. 
>
> I used the following command:
>
> fac v119 - v129 v153, pcf
> score wealthindex
>
> I do get an error message that score is not allowed after factor. 
>
> Any idea as to how i should create this asset index.


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index