Package: multipathaic 0.1.1

multipathaic: Multi-Path Stepwise Selection with AIC

Implements a multi-path forward selection algorithm using the Akaike Information Criterion (AIC) for both linear (Gaussian) and logistic (binomial) regression models. Unlike traditional stepwise methods that follow a single path, this approach explores multiple competitive model paths simultaneously by retaining near-optimal models at each step. The package includes stability estimation via bootstrap resampling and identifies plausible models based on AIC tolerance and variable stability thresholds.

Authors:Michael Obuobi [aut, cre]

multipathaic_0.1.1.tar.gz
multipathaic_0.1.1.zip(r-4.7-any)multipathaic_0.1.1.zip(r-4.6-any)multipathaic_0.1.1.zip(r-4.5-any)
multipathaic_0.1.1.tgz(r-4.6-any)multipathaic_0.1.1.tgz(r-4.5-any)
multipathaic_0.1.1.tar.gz(r-4.7-any)multipathaic_0.1.1.tar.gz(r-4.6-any)
multipathaic_0.1.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
multipathaic/json (API)

# Install 'multipathaic' in R:
install.packages('multipathaic', repos = c('https://mobuobi.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/mobuobi/multipathaic/issues

On CRAN:

Conda:

4.48 score 6 exports 0 dependencies

Last updated from:812c589129. Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develOK125
source / vignettesOK239
linux-releaseOK136
macos-releaseOK168
macos-oldrelOK179
windows-develOK96
windows-releaseOK99
windows-oldrelOK91
wasm-releaseOK106

Exports:build_pathsconfusion_metricslaunch_appmultipath_aicplausible_modelsstability

Dependencies:

Multi-Path AIC Selection: Diabetes Progression Analysis
About the multipathaic Package | Core Functions | Supported Models | Introduction | Load the Package and Data | Feature Engineering | Train/Test Split | Multi-Path AIC Procedure | Algorithm 1: Multi-Path Forward Selection | Algorithm 2: Stability Estimation | Algorithm 3: Plausible Model Selection | Model Evaluation on Test Set | Summary and Parameter Justification | Recommended Parameter Choices | Justification | References
Rendered fromdiabetes-analysis.Rmdusingknitr::rmarkdown

Last update: 2026-10-07
Started: 2025-12-17

Multi-Path AIC Selection: Methodology
Introduction | Problem Setup | Notation | Objective | Algorithm 1: Multi-Path Forward Selection | Motivation | The Multi-Path Approach | Algorithm Details | Input Parameters | Pseudocode | Key Design Choices | Example: Visualization | Algorithm 2: Stability Estimation | Bootstrap Stability | Design Considerations | Example Output | Algorithm 3: Plausible Model Selection | Filtering Criteria | Interpretation of Results | Plausible Models Table | Variable Summary Table | Example | Complete Pipeline: multipath_aic() | Output Structure | Parameter Tuning Guidelines | Quick Reference | Detailed Guidance | Exploration vs. Computation Tradeoff | Problem-Specific Adjustments | Statistical Justification | Why AIC? | Why Delta = 2? | Why Bootstrap Stability? | Why tau = 0.6? | Advantages Over Traditional Methods | vs. Single-Path Forward Selection | vs. All-Subsets Regression | vs. Lasso/Ridge Regression | Practical Recommendations | Workflow | Reporting Results | Limitations and Considerations | Computational Complexity | Model Family | Assumptions | References | Appendix: Mathematical Details | AIC Derivation | Stability Score Estimation | Average Stability for a Model
Rendered frommethod_vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-07
Started: 2025-12-17