Trent Henderson

icon indicating a website link https://hendersontrent.github.io

icon company Nous Group icon location Canberra, Australia icon location Accredited statistician and lead data scientist. Coding in R, Julia, Stan & Python. Interested in time series, statistical modelling & genetic programming

Results 15 issues of Trent Henderson

Need better options for discrete-valued PPCs

enhancement
plot-aesthetics

Change plots to recipes for better user flexibility

enhancement

Proper penalisation, multiple covariate fits, and general cleanup

Closes #34 Closes #32 Closes #33

documentation
enhancement
statistics
optimization

Should `GCV` change to accommodate GLM framework?

1 comment

Currently, the code is as per the below, but should we really be using RSS for say a Poisson problem? function GCV(param::AbstractVector, Basis::BSplineBasis{Vector{Float64}}, x::AbstractVector, y::AbstractVector) n = length(Basis.breakpoints) Xp, yp...

bug
statistics

Get incorrect result for `Height` on `trees` test dataset, but `Girth` seems okay

Could be due to the fact it is an integer variable.

bug
statistics

Add `summary` type function that returns important estimates as a table after fitting a GAM

enhancement
statistics

Add model fit indices and other calculations for model comparisons

enhancement
statistics

Add parallel computation to `calculate_features()`

enhancement

Update link to new docs

documentation

C code should be upstream pulled from original catch22 repo

This could be written as a shell bash script.

upstreaming