Learn R Programming

What is this?

Accurate Generalized Linear Model (AGLM) is defined as a regularized GLM which applying a sort of feature transformations using a discretization of numerical features and specific coding methodologies of dummy variables. More details can be found in our paper.

2021/6/6: Now our paper won Charles A. Hachemeister Prize.

Installation

# The simplest way:
install.packages("aglm")

# Or the development version from GitHub:
# install.packages("devtools")
devtools::install_github("kkondo1981/aglm", ref="develop")

Usage

See the help as below after installing aglm.

library(aglm)
?"aglm-package"

Copy Link

Version

Install

install.packages('aglm')

Monthly Downloads

366

Version

0.4.1

License

GPL-2

Issues

3

Pull Requests

2

Stars

16

Forks

5

Maintainer

Kenji Kondo

Last Published

May 12th, 2025

Functions in aglm (0.4.1)

print.AccurateGLM

Display textual information of the model
getODummyMatForOneVec

Create a O-dummy matrix for one variable
getLVarMatForOneVec

Create L-variable matrix for one variable
deviance.AccurateGLM

Get deviance
getUDummyMatForOneVec

Create a U-dummy matrix for one variable
plot.AccurateGLM

Plot contribution of each variable and residuals
executeBinning

Binning the data to given bins.
residuals.AccurateGLM

Get residuals of various types
createEqualWidthBins

Create bins (equal width binning)
cva.aglm

Fit an AGLM model with cross-validation for both \(\alpha\) and \(\lambda\)
aglm-package

aglm: Accurate Generalized Linear Model
createEqualFreqBins

Create bins (equal frequency binning)
AccurateGLM-class

Class for results of aglm() and cv.aglm()
coef.AccurateGLM

Get coefficients
cv.aglm

Fit an AGLM model with cross-validation for \(\lambda\)
CVA_AccurateGLM-class

Class for results of cva.aglm()
AGLM_Input-class

S4 class for input
aglm

Fit an AGLM model with no cross-validation
predict.AccurateGLM

Make predictions for new data