My study is comparing definitions for a certain condition.
500 patients have had either a positive or negative diagnosis of a condition, for 10 different definitions.
I want to determine which definition relates to survival best.
I have therefore done a cox proportional hazards for each of the definitions and therefore produced 10 hazard ratios (one per definition).
The hazard ratios are all broadly similar with overlap of the confidence intervals.
however I want a method of actually comparing these confidence intervals, and definitively saying whether they are all similar or if there is one that is superior.
I've searched around but I am unable to find a method of comparing hazard ratios.
Is there a reasonable way to do this?
Many thanks for your help.
Advertise on Talk Stats