Skip to main content

New answers tagged

-1 votes

R: glm function with family = "binomial" and "weight" specification

Too large weights in glm() disturb the search for the maximum likelihood. But in general, proportional altering the weights does ...
DrJerryTAO's user avatar
  • 2,353
3 votes
Accepted

Weights in beta regression

What you are looking is typically referred to as precision weights. This means that the variance is proportional to the weights and is invariant to rescaling the weights. This is what is implemented ...
Achim Zeileis's user avatar

Top 50 recent answers are included