Statalist


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

RE: Re: st: Principal Components Analysis with count data


From   "Verkuilen, Jay" <JVerkuilen@gc.cuny.edu>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   RE: Re: st: Principal Components Analysis with count data
Date   Fri, 14 Aug 2009 12:22:06 -0400

Lachenbruch, Peter wrote:

>>A short question on PCA for categorical variables:  wouldn't
correspondence analysis be useful here?  Or is my interpretation of CA
as the categorical analog of PCA way off base?<

Yes, and no, respectively. :)

Now for something like Poisson counts, CA isn't directly the tool for the job. At this point I suspect doing something like square root transforming the counts and then using ordinary PCA would probably better but there's just no way of telling short of knowing more. 

Jay

*
*   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