1
$\begingroup$

When I run coxph, R supplies me with the coefficients, exponentiated coefficient, and standard error. The standard error is for the regression coefficient, $\beta$. How can I get the standard error of the exponentiaed regression coefficient, $exp(\beta)$?

R code:

library("survival")
data("lung") #From the survival package
res.cox <- coxph(Surv(time, status) ~ sex, data = lung)
summary(res.cox)

Which gives me (sorry for the horrible formatting):

Call: coxph(formula = Surv(time, status) ~ sex, data = lung)

n= 228, number of events= 165

coef exp(coef) se(coef) z Pr(>|z|)
sex -0.5310 0.5880 0.1672 -3.176 0.00149 **

se(coef) is giving me the standard error of "sex". I would like the standard error of exp("sex").

I can find the variance using the delta method, but can R give me the results without doing the calculations myself?

$\endgroup$
2
$\begingroup$

You can do it manually by calculating $se(sex) \cdot \exp(sex)=0.1672 \cdot 0.5880=.0983136$ since the derivative of $\exp{}$ is $\exp{}$ itself, or like this using svycontrast() in the survey package:

library("survival")
library("survey")
data("lung") #From the survival package
res.cox <- coxph(Surv(time, status) ~ sex, data = lung)
summary(res.cox)
svycontrast(res.cox, quote(exp(sex)))

which yields

         nlcon     SE
contrast 0.588 0.0983
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.