I am running a nonparametric regression using the following code:

Code:
npregress kernel log_totExp age, vce(bootstrap, reps(20) seed(12345))
margins, at(age = (55(5)85)) vce(bootstrap, reps(20) seed(12345))
I get a nice margins plot and an average derivative of -.023. But what I would like to have is what is the average derivative from age 55-65 and then from 66+. Is there a way to do that?

Thanks!
Tim