[R] glm (probit/logit) optimizer

Ben Bolker bbolker at gmail.com
Fri Oct 5 14:48:50 CEST 2012

Dimitris.Kapetanakis <dimitrios.kapetanakis <at> gmail.com> writes:

> I am using glm function in order to estimate a logit model i.e. glm(Y ~
> data[,2] + data[,3], family = binomial(link = "logit")).
> I also created a function that estimates logit model and I would like it to
> compare it with the glm function. 
> So, does anyone know what optimizer or optimization method glm uses in order
> to derive the result?

  Iteratively reweighted least squares.

  If you need the gory details, look at the code of glm.fit() by typing


More information about the R-help mailing list