Point biserial correlation => Is there any specific command or could I just use cor.test?

An embedded and charset-unspecified text was scrubbed...
Name: not available
URL: <https://stat.ethz.ch/pipermail/r-help/attachments/20120120/55b5b762/attachment.pl>
Hello,

I found in the forum two threads about point biserial correlation. One of
them (1) mentioned "a point-biserial correlation is just a Pearson
correlation where one of the variables is dichotomous.  Thus,  the command
is just the normal cor function". The other (2) mentioned "Professor Fox's
package polycor" as a way to calculate  point biserial correlation?
polycor calculate polyserial correlations. I am confident if John Fox 
had meant point polyserial he would have written thus. You can always 
check what it is doing by downloading the source - R is open source.

HELP: I am a little confused about what to do. I just need to obtain the
correlation index and p-value. Could I just use cor.test? Or is necessary to
use other command or even "Professor Fox's package polycor"?

Thanks in advance,

Cadu

1. http://r.789695.n4.nabble.com/Point-biserial-correlation-td862060.html

2.
http://r.789695.n4.nabble.com/Correlation-dichotomous-factor-continous-numer
ical-and-ordered-factor-td865214.html#a865215

        [[alternative HTML version deleted]]
Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html
Dear Michael and Cadu,

Sorry -- I missed the original question.

The polycor package has functions for polyserial and polychoric correlations; biserial and tetrachoric correlations are special cases for dichotomous variables. The point biserial correlation is just the Pearson correlation between a numeric variable and a dummy variable.

Best,
John

------------------------------------------------
John Fox
Sen. William McMaster Prof. of Social Statistics
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox/
On Sat, 21 Jan 2012 13:31:48 +0000
At 13:15 20/01/2012, Cadu wrote:
Hello,

I found in the forum two threads about point biserial correlation. One of
them (1) mentioned "a point-biserial correlation is just a Pearson
correlation where one of the variables is dichotomous.  Thus,  the command
is just the normal cor function". The other (2) mentioned "Professor Fox's
package polycor" as a way to calculate  point biserial correlation?
polycor calculate polyserial correlations. I am confident if John Fox had meant point polyserial he would have written thus. You can always check what it is doing by downloading the source - R is open source.

HELP: I am a little confused about what to do. I just need to obtain the
correlation index and p-value. Could I just use cor.test? Or is necessary to
use other command or even "Professor Fox's package polycor"?

Thanks in advance,

Cadu

1. http://r.789695.n4.nabble.com/Point-biserial-correlation-td862060.html

2.
http://r.789695.n4.nabble.com/Correlation-dichotomous-factor-continous-numer
ical-and-ordered-factor-td865214.html#a865215

        [[alternative HTML version deleted]]
Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html

______________________________________________
R-help at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible