Is anyone familiar with the code to Tibshirani's AVAS function? For example,
what do the different subroutines like rlsmo.r and smother() do?
I was hoping to modify the code slightly to fit my problem:
h(y)=x+g1(x)+g2(z)+error
Clearly, I could combine x+g1(x)=g3(x) and estimate it using AVAS.
Unfortunately, I need
g1(.) to be monotonic, not just g3(.). Since, I already know the coefficient
on x (unity), I want to just subtract this off and include it in the
back-fitting.
Joe Kaboski
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
|