grpreg
grpreg copied to clipboard
pbreheny
Regularization paths for regression models with grouped covariates
There is an inconsistency in documentation and vignettes for `grpreg` objective function: 1. [Instruction](https://cran.r-project.org/web/packages/grpreg/grpreg.pdf) on page 15 defines the objective function as $$Q = \frac{1}{n} * loss + penalty$$ 2....
Hi, Thanks for the amazing package! It's super fast and deals with a wide range of data. I was wondering if it's possible to add an offset option to the...
Hello, While doing a grouped lasso for time-to-event outcome in a stack of multiply imputed datasets with folds predefined to be the same for multiple imputations of individual patients, I...
One should be able to specify unpenalized groups through `group.multiplier`, as in: ```r data(Birthwt) X
Hello, I've just discovered the package and it looks great. However, the data I have at the moment uses time-varying covariates so I require compatibility with the [start, stop) representation...
- [ ] Improve `expand_spline()`: Allow user to pass vector argument specifying which columns should be expanded (default would be: all numeric columns) - [ ] Create an `expand_factor()` function...
Need to get in touch with Dan Kessler to see where this stands
Kind of similar to what **glinternet** does, but if part of **grpreg**, could use, say, group MCP as the penalty.