Modern Regression Methods

by Ryan, Thomas P.

• ISBN13: 9780470081860
• ISBN10: 0470081864
• Edition: 2nd
• Format: Hardcover
• Copyright: 2008-11-10
• Publisher: Wiley-Interscience

Summary

This new edition of Regression Methods has been updated and enhanced to include all-new information on the latest advances and research in the evolving field of regression analysis. It provides a unique treatment of fundamental regression methods, such as diagnostics, transformations, robust regression, and ridge regression. Unifying key concepts and procedures, this new edition emphasizes applications to provide a more hands-on and comprehensive understanding of regression diagnostics.

Author Biography

Thomas P. Ryan, PhD, served on the Editorial Review Board of the Journal of Quality Technology from 1990–2006, including three years as the book review editor. He is the author of four books, all of which are published by Wiley, and he is also an elected Fellow of the American Statistical Association, the American Society for Quality, and the Royal Statistical Society. A former consultant to Cytel Software Corporation, Dr. Ryan currently teaches advanced courses at statistics.com on the design of experiments, statistical process control, and engineering statistics.

Table of Contents

Preface

Introduction

Simple Linear Regression Model

Uses of Regression Models

Graph the Data!

Estimation of 0 and

Inferences from Regression Equations

Regression Through the Origin

Additional Examples

Correlation

Miscellaneous Uses of Regression

Fixed Versus Random Regressors

Missing Data

Spurious Relationships

Software

Summary

Appendix

References

Exercises

Diagnostics and Remedial Measures

Assumptions

Residual Plots

Transformations

Influential Observations

Outliers

Measurement Error

Software

Summary

Appendix

References

Exercises

Regression with Matrix Algebra

Introduction to Matrix Algebra

Matrix Algebra Applied to Regression

Summary

Appendix

References

Exercises

Introduction to Multiple Linear Regression

An Example of Multiple Linear Regression

Centering And Scaling

Interpreting Multiple Regression Coefficients

Indicator Variables

Separation or Not?

Alternatives to Multiple Regression

Software

Summary

References

Exercises

Plots in Multiple Regression

Beyond Standardized Residual Plots

Some Examples

Which Plot?

Recommendations

Partial Regression Plots

Other Plots For Detecting Influential Observations

Recent Contributions to Plots in Multiple Regression

Lurking Variables

Explanation of Two Data Sets Relative to R

Software

Summary

References

Exercises

Transformations in Multiple Regression

Transforming Regressors

Transforming Y

Further Comments on the Normality Issue

Box-Cox Transformation

Box-Tidwell Revisited

Combined Box-Cox and Box-Tidwell Approach

Other Transformation Methods

Transformation Diagnostics

Software

Summary

References

Exercises

Selection of Regressors

Forward Selection

Backward Elimination

Stepwise Regression

All Possible Regressions

Newer Methods

Examples

Variable Selection for Nonlinear Terms

Must We Use a Subset?

Model Validation

Software

Summary

Appendix

References

Exercises

Polynomial and Trigonometric Terms

Polynomial Terms

Polynomial-Trigonometric Regression

Software

Summary

References

Exercises

Logistic Regression

Introduction

One Regressor

A Simulated Example

Detecting Complete Separation, Quasicomplete Separation and Near Separation

Measuring the Worth of the Model

Determining the Worth of the Individual Regressors

Confidence Intervals

Exact Prediction

Table of Contents provided by Publisher. All Rights Reserved.