Print

---

Hi,

I have the following hurdle model written in SAS:

proc nlmixed data=Helen.Helen qpoints=50;

parms b0=0 b1=0 b2=0 b3=0 b4=0 b5=0 b6=0 b7=0 b8=0

a0=0 a1=0 a2=0 a3=0 a4=0 a5=0 a6=0 a7=0 a8=0;

eta1 = b0 + b1*Year +b2*Longitude+ b3*Latitude + b4*Depth + b5*Front + b6*Slope + b7*chl + b8*Sst;

expeta1 = exp(eta1);

eta2 = a0 + a1*Year + a2*Longitude + a3*Latitude + a4*Depth + a5*Front + a6*Slope + a7*chl + a8*Sst;

expeta2 = exp(eta2);

if total=0 then ll= -log(1+expeta1);

else

ll=eta1-log(1+expeta1)+total*eta2-log(exp(expeta2)-1)-lgamma(total+1);

model total ~ general(ll);

run;



I want to add a predict statement to predict the expectation (mean abundance) for this hurdle model using the above parameterisation. But I'm not quite sure what it is for this parameterisation.

Any help would be fantastic!

Helen