Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: RE: the "score" command in factor analysis

From   "louis boakye-yiadom" <[email protected]>
To   [email protected]
Subject   RE: st: RE: the "score" command in factor analysis
Date   Thu, 17 Mar 2005 11:29:44 +0000

Many thanks, Nick and Richard. I was simply giving the command "score", without specifying any variable names. One more question ... can you please point me to where I can get information about how "score" generates the estimates of the factors? This is because it appears the factor estimates are not simply linear combinations of the observed variables with the scoring coefficients. Thank you.


I am not clear what your point is here.

If you are saying that the sentence you
are quoting from the help is abbreviated
as a summary of what -score- does, then
you are correct. But the fact that
the scores are calculated using the
coefficients is not contentious. It could
hardly be otherwise.

The help cannot provide complete documentation
for what a command does. That goes beyond the main
role of a help file, especially for official Stata
command backed up by the manuals and by
literature references.

-score- also follows -pca-, but a similar
point applies.

[email protected]

louis boakye-yiadom

> According to stata's help document for -score-, "score
> creates a set of new
> variables that are estimates of the factors produced by
> factor or rotate
> (i.e., unrotated or rotated factors)". It seems to me though
> that what the
> -score- command actually does, is to generate coefficients
> (rather than the
> actual scores) which can then be used to generate esimates of
> the factors
> (the factor scores?). Can anyone help be know whether I'm right in my
> understanding of what -score- does?

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index