Re: need help with factor analysis of matrix of polychoric correlations
- From: John Uebersax <jsuebersax@xxxxxxxxx>
- Date: Sat, 7 Mar 2009 01:26:22 -0800 (PST)
Hi Mark,
If you would like to drop me an email maybe I could make a suggestion.
A place to begin, though, might be to try factor analysis a matrix of
Pearson or Spearman correlation coefficients; if those results don't
suggest a strongly unidimensional solution, that supplies evidence
that something is amiss with the polychoric correlation coefficients.
John Uebersax PhD
On Mar 2, 4:59 pm, "mark@hsph" <msch...@xxxxxx> wrote:
have ordinal rating scale data on a moderate mumber of items and I
would like to extract a few common factors from the data. I've used
the SAS macro %polychor to create a matrix of polychoric
correlations.
However, when I try to perform the factor analysis, I get strange
results. The first eigenvalue accounts for 99% of the variation in
the
correlation matrix and all the variables load on that factor almost
exclusively. Examining the polychoric correlation matrix produced by
%polychor suggests this is just
not so, but I don't have any idea what I'm doing wrong. I can send
the
correlation matrix to anyone who may have an idea how to make the
thing work.
Thanks,
Mark Schultz
.
- References:
- Prev by Date: Sharepoint Expert (Developer Lead) With CMMi 3 Product Development Company
- Next by Date: what about x^x
- Previous by thread: Re: need help with factor analysis of matrix of polychoric correlations
- Next by thread: Re: need help with factor analysis of matrix of polychoric correlations
- Index(es):
Relevant Pages
|
