StepReg - A Comprehensive and Intuitive R Package for Stepwise Regression
Analysis
Stepwise regression is a statistical technique used for
model selection. This package streamlines stepwise regression
analysis by supporting multiple regression types(linear, Cox,
logistic, Poisson, Gamma, and negative binomial), incorporating
popular selection strategies(forward, backward, bidirectional,
and subset), and offering essential metrics. It enables users
to apply multiple selection strategies and metrics in a single
function call, visualize variable selection processes, and
export results in various formats. StepReg offers a
data-splitting option to address potential issues with invalid
statistical inference and a randomized forward selection option
to avoid overfitting. We validated StepReg's accuracy using
public datasets within the SAS software environment. For an
interactive web interface, users can install the companion
'StepRegShiny' package. The methodology is described in Li et
al. (2026) <doi:10.32614/RJ-2026-005>.
