Improved LARS algorithm for adaptive LASSO in the linear regression model

TL;DR

This paper introduces a modified LARS algorithm that integrates adaptive LASSO with various biased estimators to improve variable selection in linear regression, supported by simulation and real data analysis.

Contribution

It presents a novel modification of the LARS algorithm combining adaptive LASSO with biased estimators for enhanced variable selection.

Findings

Improved variable selection accuracy in simulations

Enhanced performance demonstrated on real-world data

Effective combination of adaptive LASSO with biased estimators

Abstract

The adaptive LASSO has been used for consistent variable selection in place of LASSO in the linear regression model. In this article, we propose a modified LARS algorithm to combine adaptive LASSO with some biased estimators, namely the Almost Unbiased Ridge Estimator (AURE), Liu Estimator (LE), Almost Unbiased Liu Estimator (AULE), Principal Component Regression Estimator (PCRE), r-k class estimator, and r-d class estimator. Furthermore, we examine the performance of the proposed algorithm using a Monte Carlo simulation study and real-world examples.