Complementary log log

#1
Hi

I have a model with a binomial error distribution. Instead of the logit link I use the complementary log log. What is the interpretation of the B-coefficients?

Thanks
 

Masteras

TS Contributor
#2
you can say that the change refers to the cloglog of the dependent variable. If you want to say about the y itself then you can transform back. But if you stay as you are it is ok.