Parameter Estimation in GLMs

Formulate the log-likelihood function for a GLM based on its specified distribution.

Derive the score equations by differentiating the log-likelihood with respect to the model parameters.

Describe the steps of the Fisher scoring algorithm and its connection to Iteratively Reweighted Least Squares (IRWLS).

Execute one iteration of the IRWLS algorithm to update GLM parameters, given initial values, a working response, and weights.

Compute the deviance of a fitted GLM and interpret it as a measure of model fit.