JuliaStats / GLM.jl

Generalized linear models in Julia

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Change `wts` keyword argument name to `weights`

pdeffebach opened this issue · comments

As mentioned in #341 , wts is a bit esoteric and unclear. Better to use weights as the name of the keyword argument for weights.

Let me know your thoughts on changing the name of keyword argument or if I should change the name of the field in GlmResp, LmResp etc. as well.

Probably better also rename the field, though that's secondary.

Actually, weights should go in the formula call.

I'm about to spend a lot of time re-writing R-code because the observations that have NA are different than the weights that have NA and I want all of them. One way to handle this is to have StatsModels take care of it when creating the model matrix.

It's been discussed a few times before (JuliaStats/StatsModels.jl#21). One alternative possibility would be to pass a symbol or string to the weights argument, and have a way to pass this to StatsModels when constructing the model matrix. We should settle this in StatsModels.

One alternative possibility would be to pass a symbol or string to the weights argument

That's what FixedEffectModels.jl does