COX models and continuous variables

#1
Hello everyone.
I have a simple and basic question about cox model. When I introduce a continuous variable in the model, the hazard ratio assessed for this variable relates the increase (decrease) of the risk after an increase of one unit of the continuous variable. How to extrapolate for more than one unit (for example 10 units) increase . Is that only the HR multiplied by 10 or is there a specific formula for this extrapolation ?
For example, a scientific question would be what is the hazard ratio of cordiovacular disease for an increase of 10 mmhg of blood pressure.
Thanks for your help!!
 

maartenbuis

TS Contributor
#2
The easiest solution is to just prepare your data such that it has the unit of your choice. So in your case just divide your continuous variable by 10 before estimating your Cox model. Alternatively, the hazard ratio for a 10 unit increase is the original hazard ratio to the power 10.
 

hlsmith

Less is more. Stay pure. Stay poor.
#4
If I remember correctly, I believe you exponentiate model terms to get the relative values, so maartenbuis suggestion is good approach. If using a software package, you could also request these estimates for different unit values.