[R] factor analysis

[Prof Brian D Ripley]

I have put a preliminary version of factanal in a package at
http://www.stat.ox.ac.uk/pub/R/fa_0.1-1.tar.gz
and would appreciate feedback.  In particular

1) What else you might want.  Please give precise references with
algorithmic details, as that has been a major problem for me.

2) Some convincing examples of factor analysis. Most (literally) of the
ones I have looked at are local maxima, not global maxima, and the latter
(or the best guess at) are much less convincing.

I should say that more than 50% of the published examples I have
re-analyzed I am convinced are wrong, in that they failed to optimize the
likelihood or rotation criterion.  So checking this against other packages
has been frustrating.  It cross-checks pretty well against S-PLUS.

[As history, this is based on some code I wrote in 1995 to cross-check
S-PLUS when I first came across the discrepancies.]

All being well, a descendant of this will go into package mva in R 1.2.1.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272860 (secr)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._