Mousum Dutta

> @mousum-github Maybe you know the answer to https://github.com/JuliaStats/GLM.jl/pull/499/files#r976581242? > > @palday Do you plan to add test for other method families? I am not sure about the relationship. I...

I would like to add a few more test cases this week.

> @mousum-github please don't start making changes on my PR without asking me first. Sure, @palday. It is my bad. Please let me know if I can do anything. I...

The following compares three types of residuals (response, deviance and Pearson) for different distributions and link functions in Julia and R. Overall the comparisons look good. ```julia julia> using GLM,...

@nalimilan - I also considered suggesting some tests within existing test cases. Since there are conflicts in the `runtests.jl` right now, just checked new functionalities only with `R`, especially with...

For residuals functionalities, Existing Test cases: - Poisson GLM - (Binomial, Bernoulli) with LogitLink - Gamma - InverseGaussian - Geometric is a special case of NegativeBinomial - linear model with...

The changes in the residuals function with `lm` are like the following, ```julia resid = response(model) - fitted(model) if length(model.rr.wts) > 0 && (type === :deviance || type === :pearson)...

Thanks @nalimilan. I have raised the PR #540. @palday - hope it will help.

Thanks, Viral. I will check it this week.

The PR is now cleaned up and merged with the latest master branch.