Learn R Programming

selectiveInference (version 1.2.5)

Tools for Post-Selection Inference

Description

New tools for post-selection inference, for use with forward stepwise regression, least angle regression, the lasso, and the many means problem. The lasso function implements Gaussian, logistic and Cox survival models.

Copy Link

Version

Install

install.packages('selectiveInference')

Monthly Downloads

533

Version

1.2.5

License

GPL-2

Maintainer

Last Published

September 7th, 2019

Functions in selectiveInference (1.2.5)

debiasingMatrix

Find an approximate inverse of a non-negative definite matrix.
estimateSigma

Estimate the noise standard deviation in regression
forwardStop

ForwardStop rule for sequential p-values
plot.fs

Plot function for forward stepwise regression
plot.lar

Plot function for least angle regression
predict.fs

Prediction and coefficient functions for forward stepwise regression
predict.groupfs

selectiveInference

Tools for selective inference
selectiveInference-internal

Internal PMA functions
scaleGroups

Center and scale design matrix by groups
fsInf

Selective inference for forward stepwise regression
randomizedLassoInf

Inference for the randomized lasso, with a fixed lambda
groupfs

Select a model with forward stepwise.
fs

Forward stepwise regression
larInf

Selective inference for least angle regression
lar

Least angle regression
groupfsInf

Compute selective p-values for a model fitted by groupfs.
manyMeans

Selective inference for many normal means
predict.lar

Prediction and coefficient functions for least angle regression
randomizedLasso

Inference for the randomized lasso, with a fixed lambda
ROSI

Relevant One-step Selective Inference for the LASSO
factorDesign

Expand a data frame with factors to form a design matrix with the full binary encoding of each factor.
TG.interval

Truncated Gaussian confidence interval.
TG.limits

Truncation limits and standard deviation.
fixedLassoInf

Inference for the lasso, with a fixed lambda
TG.pvalue

Truncated Gaussian p-value.