Advanced Analysis of Multiple Linear Regression: A Comparative Study of Classical Methods and Modern Regularization Techniques

Read full text Summarise with VIRAT
Authors: Heyam A. A. Hayawi
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study explores the enhancement of multiple linear regression models by integrating traditional estimation approaches with modern regularization techniques. Although Ordinary Least Squares (OLS) is widely used for parameter estimation, its effectiveness declines in the presence of multicollinearity, outliers, and influential observations. To overcome these challenges, Ridge and LASSO regression methods are employed as more robust alternatives. Ridge regression improves model stability by shrinking coefficient estimates, while LASSO enhances model simplicity by performing automatic variable selection. In addition, various diagnostic tools are utilized to identify irregular observations and assess model adequacy. An empirical analysis based on simulated data is conducted to compare the performance of the different models. The findings indicate that regularization-based methods outperform OLS in terms of prediction accuracy and reliability, particularly in complex data environments. The study highlights the importance of combining diagnostic analysis with regularization techniques to develop more stable, interpretable, and efficient regression models.

Fields of Study & Subjects

Advanced Statistical Methods and Models Statistical Methods and Inference Statistical Methods and Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
30 March 2026
Language
EN