Calculating p-value and confidence intervals for RERI in Cox's proportional hazards model

[SokolowLyon]

Hello!

I'm calculating the relative excess risk due to interaction (RERI) using Cox's proportional hazards model by using the formula according to Li et al.: RERI(HR) = HR(1,1) - HR(1,0) - HR(0,1) + 1. This generates a number indicating whether or not there is an additive interaction. My question is how can I retrieve a P-value and a 95 % confidence interval for this excess risk using the SAS software?

Thank you very much for your help!

SokolowLyon

[Reeza]

You need to use an ESTIMATE statement to get your custom estimates. 

https://documentation.sas.com/?docsetId=statug&docsetTarget=statug_phreg_syntax11.htm&docsetVersion=...

If you're not familiar with ESTIMATE or CONTRAST statements, I suggest reading this paper first:

https://support.sas.com/resources/papers/proceedings11/351-2011.pdf

---

@SokolowLyon wrote:

Hello!

I'm calculating the relative excess risk due to interaction (RERI) using Cox's proportional hazards model by using the formula according to Li et al.: RERI(HR) = HR(1,1) - HR(1,0) - HR(0,1) + 1. This generates a number indicating whether or not there is an additive interaction. My question is how can I retrieve a P-value and a 95 % confidence interval for this excess risk using the SAS software?

Thank you very much for your help!

SokolowLyon

---