Hi, I'm adjusting a binomial gam and I use the inverse variance of each proportion as weights in the gam function (it's a model for the sex ratio of hake).
My doubt is what are these weights doing ? I get a negative UBRE and if I use GCV the scale parameter is close to 0 ... Regards EJ ______________________________________________ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html