Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "JVerkuilen (Gmail)" <jvverkuilen@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Re: Polychoric PCA error message |
Date | Mon, 25 Feb 2013 19:49:56 -0500 |
On Sun, Feb 24, 2013 at 8:46 PM, Nick Cox <njcoxstata@gmail.com> wrote: > My guess is that Jay meant Pearson correlations as calculated by -correlate-. Yes, that's right. Polychorics are nice in theory but they're unstable for many reasons already discussed. An ordinary Pearson correlation will often tell you quite a bit. So for instance, if one is massive and the rest are quite a bit smaller, you will almost certainly have issues. Also look at the two way tables. You can usually predict problems that way. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/