[R] User defined GLM?

[francogrex]

Emmanuel Charpentier wrote:
> 
> I do not understand the problem as stated. if x[i] and n[i] are known,
> and unless sum(n)=0, your dataset reduces to a set of nrow(dataset)
> independent linear equations with nrow(dataset) unknowns (the beta[i]),
> whose solution is trivially beta[i]=log(x[i]/n[i])-log(sum(x)/sum(n),
> except when n[i]=0 in which case your equation has no solution.
> Could you try to re-express your problem ?
> 

This is taken from this article: "Methods for confidence interval estimation
of a ratio parameter with application to location quotients". The authors
argue that it's not the solution to find beta that they're after but the
side effect of having the profile-likelihood confidence intervals in the
estimation process. Those guys say they used the SAS "Genmod" procedure. I
thought I could use glm in R and find the profile-likelihood CIs using
"confint" on the glm results.

-- 
View this message in context: http://www.nabble.com/User-defined-GLM--tp24150859p24154447.html
Sent from the R help mailing list archive at Nabble.com.