 |
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: PCA and panel data
Thanks Nick, I fixed the problem.
----- Original Message -----
From: Nick Cox <[email protected]>
Date: Saturday, January 10, 2009 3:43 am
Subject: st: RE: PCA and panel data
To: [email protected]
> Please send plain text emails only to the list. (This posting arrived
> swatched in e-gunk.)
>
> These days, almost everyone wants to stress that PCA and factor
> analysisare related but disjoint, although the perspective is
> different. For PCA
> enthusiasts, factor analysis is a bizarre variant on PCA. For factor
> analysis enthusiasts, PCA is an uninteresting limiting or
> special case
> of factor analysis.
>
> Setting aside this confusion, the direct answer to your question can
> only be a guess. But my guess is that despite what you say, you
> do not
> have complete observations on the variables concerned. So,
> look again
> at your data.
>
> Among other tools, -nmissing- from the SJ files gives a concise report
> on missing values.
>
> Nick
> [email protected]
>
> [email protected]
>
> I am trying to conduct a factor analysis on panel data. However,
> the pca
> only seems to run for a 1/4 of the total number of observations
> in my
> dataset. I have done ipolate to account for missing data and all
> obervations are standardised. What I am doing wrong?
>
> *
> * 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/
>