# [R] Correlation dichotomous factor, continous (numerical) and ordered factor

Birgitle birgit.lemcke at systbot.uzh.ch
Wed Aug 6 16:16:22 CEST 2008

Hello R-User!

I appologise in advance if this should also go into statistics but I am
presently puzzled.
I have a data.frame (about 300 rows and about 80 variables) and my variables
are dichotomous factors, continuous (numerical) and ordered factors.

I would like to calculate the linear correlation between every pair of my
variables, because I would like to perform a logistic regression (glm())
without the correlation between variables.

I thought I could use for the continous (numerical) and ordered factor a
spearman correlation that is using the ranks.

But I thought also that I have to use a contingency table for the
dichotomous factors.

I read also that it is possible to use a point-biserial correlation to
calculate the correlation between dichotomous and continuous variables.

Now I am confused what I should use to calculate the correlation using all
my variables and how I could do that in R.
Is it possible with cor(), rcorr(), cormat() or other R-functions using one
of the available correlation-coefficients.

I would be very happy if somebody could enlighten my darkness.

B.

-----
The art of living is more like wrestling than dancing.
(Marcus Aurelius)
--
View this message in context: http://www.nabble.com/Correlation-dichotomous-factor%2C-continous-%28numerical%29-and-ordered-factor-tp18852158p18852158.html
Sent from the R help mailing list archive at Nabble.com.