Hello,

I ran nbreg for the same outcome variable with two different primary independent variables and same covariates.


Code:
 nbreg conditions var1 covar1 covar2 covar3 covar4, exposure(pop) irr
Code:
 nbreg conditions  var2  covar1 covar2 covar3 covar4, exposure(pop) irr
Both of VAR1 and VAR2 were statistically significant. But IRR was larger for var1 than for var2.
If var1 has larger IRR, can I say that var1 is a better pridictor for the outcome variable?
Is there any way that I can compare these two different primary independent variables?

IRR Std. Err. z P>|z| [95% Conf. Interval]
var1 1.16 . 0171759 9.70 0.000 1.121926 1.189264

IRR Std. Err. z P>|z| [95% Conf. Interval]
var2 1.10 .0145721 6.83 0.000 1.066957 1.124085

Thank you.