Re: [R] ordinal variables

From: Joris Meys <jorismeys_at_gmail.com>
Date: Thu, 03 Jun 2010 15:35:14 +0200

see ?factor and ?as.factor. On ordered factors you can technically do a spearman without problem, apart from the fact that a spearman test by definition cannot give exact p-values with ties present.

x <- sample(c("a","b","c","d","e"),100,replace=T) y <- sample(c("a","b","c","d","e"),100,replace=T)

x.ordered <- factor(x,levels=c("e","b","a","d","c"),ordered=T)
x.ordered
y.ordered <- factor(y,levels=c("e","b","a","d","c"),ordered=T)
y.ordered

cor.test(x.ordered,y.ordered,method="spearman")

require(pspearman)
spearman.test(x.ordered,y.ordered)

R commander has some menu options to deal with factors. R commander also provides a scripting window. Please do your students a favor, and show them how to use those commands.

Cheers
Joris

On Thu, Jun 3, 2010 at 2:25 PM, Iasonas Lamprianou <lamprianou_at_yahoo.com>wrote:

> Dear colleagues,
>
> I teach statistics using SPSS. I want to use R instead. I hit on one
> problem and I need some quick advice. When I want to work with ordinal
> variables, in SPSS I can compute the median or create a barchart or compute
> a spearman correlation with no problems. In R, if I "read" the ordinal
> variable as numeric, then I cannot do a barplot because I miss the category
> names. If I read the variables as characters, then I cannot run a spearman.
> How can I read a variable as numeric, still have the chance to assign value
> labels, and be able to get table of frequencies etc? I want to be able to do
> all these things in R commander. My students will probable be scared away if
> I try anything else other than R commander (just writing commands will not
> make them happy).
>
> I hope I am not asking for too much. Hopefully there is a way
>
>
>
>
> ______________________________________________
> 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 code.
>

-- 
Joris Meys
Statistical Consultant

Ghent University
Faculty of Bioscience Engineering
Department of Applied mathematics, biometrics and process control

Coupure Links 653
B-9000 Gent

tel : +32 9 264 59 87
Joris.Meys_at_Ugent.be
-------------------------------
Disclaimer : http://helpdesk.ugent.be/e-maildisclaimer.php

	[[alternative HTML version deleted]]

______________________________________________
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 code.
Received on Thu 03 Jun 2010 - 13:37:34 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Thu 03 Jun 2010 - 14:10:26 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive