[R] Factor Analysis?
Zdenek.Skala at incoma.cz
Thu Feb 3 09:00:55 CET 2000
Maria Wolters wrote:
> I actually think it's an advantage of R that it discourages the innocent
> click'n'play approach fostered by GUI-based systems. In fact, using R has
> shown me (personally) how statistically illiterate I still am, and made me
> much more aware of many use and misuse issues.
Agree completely. I am a "simple user" of R, so unfortunately
unable to write new library and feel, of course, that it is harder to
write one than to require it... I would only argue in favor of factor
analysis in general, not to exclude it principally from the future R
development: (1) it is, in my opinion, not only for social sciences -
in "biostatistics" (and especially morphometrics) I feel high
potential for use of factor analysis; (2) at the same time, life
scientists are often using S(plus)/R - so the audience is prepared;
(3) my understanding of factor analysis is that it does not differ
from PCA primarily by rotation but by searching for structure within
a (partial) correlation matrix, not within a covariance matrix. As
such it *is*, in my opinion, intellectually attractive and not only
useful for practitioners.
] Zdenek Skala
] Zdenek.Skala at incoma.cz
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
More information about the R-help