[R] cox models

John Fox jfox at mcmaster.ca
Sun Nov 6 14:37:03 CET 2005


Dear Bertrand,

There are only 4 degrees of freedom for a 5-level factor. By default, R
creates contrasts for an unordered factor in a model formula using the
function contr.treatment(), which, also by default, treats the first level
of the factor (class, in your case) as the baseline or reference level. To
see the contrasts, enter the command contrasts(igr1$class). 

A bit more information on contrasts is in Section 11.1.1 of the introductory
manual that comes with R.

I hope this helps,
 John

--------------------------------
John Fox
Department of Sociology
McMaster University
Hamilton, Ontario
Canada L8S 4M4
905-525-9140x23604
http://socserv.mcmaster.ca/jfox 
-------------------------------- 

> -----Original Message-----
> From: r-help-bounces at stat.math.ethz.ch 
> [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of bertrand
> Sent: Sunday, November 06, 2005 4:21 AM
> To: r-help-request at stat.math.ethz.ch
> Cc: r-help at stat.math.ethz.ch
> Subject: [R] cox models
> 
> Hello,
> i'm a french student of medical oncology and i'm working on 
> breast cancer. I have a variable with the histologic type of 
> tumor wich is between 1 and 5. I use as.factor function to 
> make some variable with level between 1 and 5. When i put it 
> in the cox model i have only the level between 2 and 5. The 
> level 1 doesn't appear. I think i have to change the number 
> of level but i don't really know. Please can you help me?
> 
> 
> Class
> Levels: 1 2 3 4 5
> coxph(formula = Surv(delai.etat, etat) ~ class, data = igr1)
> 
> 
>           coef exp(coef) se(coef)     z       p
> class2 -0.093     0.911    0.245 -0.38 7.0e-01
> class3 -0.749     0.473    0.286 -2.62 8.9e-03
> class4 -0.600     0.549    0.343 -1.75 8.0e-02
> class5 -0.874     0.417    0.197 -4.44 8.9e-06
> 
> Likelihood ratio test=24.9  on 4 df, p=5.28e-05  n=740 (1 
> observations deleted due to missing)
> 
> 
> 
> Thanks for your help
> 
> 
> Bertrand
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html




More information about the R-help mailing list