2
$\begingroup$

I am trying to replicate the "C3 Contrast" (Output 66.3.7) at the bottom of:

http://support.sas.com/documentation/cdl/en/statug/63962/HTML/default/viewer.htm#statug_phreg_sect048.htm

I am able to replicate everything in R except one thing and was hoping somone could provide guidance.

For example, for the first C3 contrast at the bottom of the page, R provides me the following:

log(HR) = 0.4567011
SE (log(HR)) = 0.2341913

When you exponentiate you get:

 exp(0.4567011) = 1.5789 

That's the exact value SAS gets. Further, if you do:

exp( 0.4567011 -/+ 1.96*0.2341913) = ( 0.9976888,2.498564) 

Again, that is the exact same value as SAS gets.

Thus, I'm pretty sure I know what the estimate and the standard error provided by are represent.

However, SAS gets an "standard error" value of "0.3698" for that row. Does anyone know where they get this number? Clearly, it's not the standard error that they use for the CI or the chi-square test. Nor is it the exp of the correct standard error 0.2341913. I've tried other combinations but don't quite see it.

Everything else matches up perfectly: the chi-square, the p-value, etc.

Any idea where they actually get that number? Thank you for your help!

$\endgroup$

Your Answer

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

Browse other questions tagged or ask your own question.