Hi, I am trying to fit a polytomous logistic regression with inverted sampling probabity as weight. I've tried multinom(nnet) function. While the results look not right. For example, the results were not the same for the following two model. Should I normalize the weights first? Or there were some other functions to use?
multinom(y~x,weights=rep(2,length(y)) vs. multinom(y~x) Thanks, Yinghui ______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
