FixedEffectModels.jl
FixedEffectModels.jl copied to clipboard
Fast Estimation of Linear Models with IV and High Dimensional Categorical Variables
- [x] Add more tests that residuals and fixedeffects are correct in the case of IV, weights, subsets in [RegressionResult](https://github.com/matthieugomez/FixedEffectModels.jl/blob/master/test/RegressionResult.jl). - [ ] Check that standard errors and F-stat are...
When I using `method = :gpu`, it gets an error. I run in Mac OS, version 1.8.1 ``` julia> using RDatasets julia> using CUDA, FixedEffectModels julia> df = dataset("plm", "Cigar")...
The following seems like a 'classic' trap: ``` using FixedEffectModels, RDatasets df = dataset("plm", "Cigar") # assume some entries are Inf df.Sales[1] = 0.0 df.logsales = log.(df.Sales) reg(df, @formula(logsales ~...
I would like to have confidence intervals for `predict`. In GLM.jl, `predict` takes a keyword argument `interval=:confidence` that permits this. Is it possible to get confidence intervals in FixedEffectModels predictions?
`StatsAPI` provides `fit` for fitting a statistical model which is used by StatsBase.jl, GLM.jl, and Econometrics.jl. It would be convenient if FixedEffects.jl used this as well so I could just...
This is sort of self-assigned: ``` julia> using FixedEffectModels, DataFrames julia> df = DataFrame(y=rand(10), id = rand(1:2, 10), t = rand(1:2, 10)); julia> predict(reg(df, @formula(y ~ fe(id) + fe(t)), save...
The results display does not include the name of the dependent variable. For a series of regressions, or looking at results after time has gone by, it can be confusing...
Hi The new Macs have quite a few GPUs which can be used to make computation orders of magnitude faster. However the current support of FixedEffects.jl only works with NVIDIA...
Before handing things over to `ivreg2`, `ivregdfe` partials out the FE _and_ identifies and drops singletons. I'm making `reghdfejl` optionally do the same thing now--call partial_out() and then use ivreg2...
Hi all, I was wondering if you know if it is possible to add the `method=:AMD` option using [AMDGPU.jl](https://github.com/JuliaGPU/AMDGPU.jl). I am definately a novice in julia programming, but I would...