Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

RE: st: how to get the components variable after -pca- or -fa-?


From   Grace Jessie <[email protected]>
To   <[email protected]>
Subject   RE: st: how to get the components variable after -pca- or -fa-?
Date   Fri, 6 Apr 2012 11:13:37 +0000

Nick,thank you!
It is really the problem!
Grace

> Date: Tue, 3 Apr 2012 16:43:29 +0100
> Subject: Re: st: how to get the components variable after -pca- or -fa-?
> From: [email protected]
> To: [email protected]
> 
> You do not spell out the precise commands you used for -pca- or -fa-,
> although you went for factor analysis, it seems. But remember that by
> default the variables must be standardised first to mean 0 and
> variance 1. It doesn't seem that you did that.
> 
> Nick
> 
> 2012/4/3 Grace Jessie <[email protected]>:
> 
> > Could anyone tell me how to get the components variable after -pca- or -fa-?
> > I know -predict f1- works well for the first component. However, I want to know how to calculate it? In my mind, it should equal each variable multiplied by its score. Disppointedly, it does not. Could anyone explain to me?
> > for example,
> > predict p1
> > (regression scoring assumed)
> > Scoring coefficients (method = regression)
> > ------------------------
> > Variable | Factor1
> > -------------+----------
> > dv21 | 0.28335
> > dv22 | 0.28218
> > dv23 | 0.28129
> > dv24 | 0.27461
> > ------------------------
> > So P1=0.28335*dv21+0.28218*dv22+0.28129*dv23+0.27461*dv24? Why not?
> 
> *
> * 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/ 		 	   		  
*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index