What question did this study set out to answer?

This work discusses ridge regression's role in biased estimation and its advantages in model building.

February 1, 1975The American Statistician875 citations

Ridge Regression in Practice

Key Points

This work discusses ridge regression's role in biased estimation and its advantages in model building.
Simulation experiment conducted to assess ridge regression performance
Review of three real-world applications of ridge regression
Analysis of variable selection and model validation procedures
Ridge regression provides better predictive capability than least squares under high correlation of predictor variables
Demonstrated reliability in variable selection without overfitting
Comments on computational processes for ridge and generalized inverse regression enhance understanding of model implementation

Abstract

Summary The use of biased estimation in data analysis and model building is discussed. A review of the theory of ridge regression and its relation to generalized inverse regression is presented along with the results of a simulation experiment and three examples of the use of ridge regression in practice. Comments on variable selection procedures, model validation, and ridge and generalized inverse regression computation procedures are included. The examples studied here show that when the predictor variables are highly correlated, ridge regression produces coefficients which predict and extrapolate better than least squares and is a safe procedure for selecting variables.

Ask AI

Helpful

Bookmark

View Full Paper