Learn R Programming

⚠️There's a newer version (2.8.0) of this package.Take me there.

projpred (version 2.0.2)

Projection Predictive Feature Selection

Description

Performs projection predictive feature selection for generalized linear models and generalized linear and additive multilevel models (see, Piironen, Paasiniemi and Vehtari, 2020, , Catalina, Brkner and Vehtari, 2020, ). The package is compatible with the 'rstanarm' and 'brms' packages, but other reference models can also be used. See the package vignette for more information and examples.

Copy Link

Version

Install

install.packages('projpred')

Monthly Downloads

1,863

Version

2.0.2

License

GPL-3

Homepage

https://mc-stan.org/projpred/

Maintainer

Alejandro Catalina

Last Published

October 28th, 2020

Functions in projpred (2.0.2)

break_up_matrix_term

Sometimes there can be terms in a formula that refer to a matrix instead of a single predictor. Because we can handle search_terms of predictors, this function breaks the matrix term into individual predictors to handle separately, as that is probably the intention of the user.

Projection to submodels

Add extra fields to the family object.

Summary statistics related to variable selection

Variable selection for generalized linear models

Extra family objects.

Plot summary statistics related to variable selection

Mesquite data set.

Projection predictive feature selection

Get reference model structure

Objects exported from other packages

Cross-validated variable selection (varsel)

Recovers solution path from a variable selection object.

Suggest model size

predict.refmodel

Predict method for reference model objects

Binomial toy example.

Execute a Function Call

Gaussian toy example.

Print methods for vsel/vsel objects

Utilities to handle formulas for the external user

Create cross-validation indices

Extract draws of the linear predictor and draw from the predictive distribution of the projected submodel