[R] SAS and R code hazard ratios

Thomas Lumley tlumley at u.washington.edu
Wed Jan 10 21:50:30 CET 2007

On Wed, 10 Jan 2007, Colleen.Ross at kp.org wrote:
> I am new to R and have been comparing CPH survival analysis hazard ratios
> between R and SAS PhReg.  The binary covariates' HRs are the same, however
> the continuous variables, for example age, have quite different HRs
> although in the same direction.  SAS PhReg produces HRs which are the
> change in risk for every one increment change in the independent variable.
> How do I interpret the HRs produced by R?    Thanks much, C

What function did you use to fit the model in R?  If you used coxph(), in 
the survival package then you should get the same answers as SAS. If you 
used cph() in the design package then the output says what the increment 
is that correponds to the quoted hazard ratio, and the default is the 
interquartile range.


More information about the R-help mailing list