Regression With Dummy Variables

Second Edition

Melissa A. Hardy - Pennsylvania State University, USA

Volume: 93

Series:
Quantitative Applications in the Social Sciences

Courses:
Regression & Correlation | Statistics - General Interest

September 2026 | 160 pages | SAGE Publications, Inc

Regression analysis is one of the most flexible and widely used techniques of quantitative analysis and dummy variables have been central to the growing flexibility and complexity of statistical models. This thoroughly updated Second Edition combines presentation of the principles behind the use of dummy variables, application of these lessons using an extract from the American Community Survey, and visualization of the results. Melissa Hardy helps readers understand the basic distributional properties of dummy variables and how they can be used to interpret their data.

Available Formats

ISBN: 9781544334585 Paperback Suggested Retail Price: $51.00 Bookstore Price: $40.80

See what’s new to this edition by selecting the Features tab on this page. Should you need additional information or have questions regarding the HEOA information provided for this title, including what is new to this edition, please email sageheoa@sagepub.com. Please include your name, contact information, and the name of the title for which you would like more information. For information on the HEOA, please go to http://ed.gov/policy/highered/leg/hea08/index.html.

For assistance with your order: Please email us at textsales@sagepub.com or find your Sage repfind your Sage rep.

Sage
2455 Teller Road
Thousand Oaks, CA 91320
www.sagepub.com

Series Editor Introduction

Preface

Acknowledgements

About the Authors

Chapter 1: Introduction

Regression Models

The Data

What Are Dummy Variables?

Review of Multiple Regression and Functional Forms

Using OLS to Analyze Personal Income

Chapter 2: Creating and Using Binary-Coded Dummy Variables

Defining Dummy Variables

Describing Distributions

Correlation with Dummy Variables

Chapter 3: Using Dummy Variables as Regressors

Regression With One Dummy Variable

Regression With Two Dummy Variables

Regression With Multiple Dummy Variables for a Single Classification

Assessing Income Differences Between Included Categories

Including Three Classifications Using Seven Dummy Variables

Visualizing Results

Shifting Reference Groups and Zero-Points

Chapter 4: Assessing Whether Relationships Differ by Group

Revisiting Some Assumptions

Interaction with Two Dichotomous Relationships

Interacting Binary and Multicategory Classifications

Adding a Quantitative Independent Variable

Illustrating these Relationships

Interaction Between Multicategory and Quantitative Variables

Illustrating Interaction Effects

Interaction of Dichotomous with Quadratic Variables

Recapping Key Points

Separate Subgroup Regressions

Chapter 5: Specification, Significance, and Assumptions

Recoding Discrete Independent Variables

Specifying Education Using Categories

Specifying Education Using a Quadratic Function

Specifying Education Using Piecewise Linear Regression

Interpreting Dummy Variables in Semilogarithmic Equations

Interpreting Dummy Variables with Square Root Transformations

Interpreting Dummy Variables in Logit Models

Dealing with Group Heteroscedasticity

Making Multiple Comparisons with Non-independent Tests

Chapter 6: Alternative Coding Schemes for Dummy Variables

Effects-Coded Dummy Variables

Contrast-Coded Dummy Variables

Conclusion

Notes

References

This book takes a clear, methodical, and data-driven approach to teaching regression with dummy variables, making it a valuable resource for both students and instructors. One of its standout features is its consistent use of real-world data, which grounds abstract statistical concepts in meaningful, socially relevant examples.

Sarah M. Wolff

University of Nevada, Las Vegas

The textbook offers a clear and structured approach to understanding complex statistical concepts, making it a valuable resource for both students and instructors.

Diana Blakeney-Billings

Alabama A&M University

The book provides a gentle introduction to linear regression by starting from the basics of regression using the equation of a straight line and then builds up on it to multiple regression models. Overall, this book reads like the author is sitting by the reader and guiding them on how to implement as well as accurately interpret coefficients for categorical variables in regression models.

Duke Appiah

Texas Tech University

Key features

The purpose of the text is to help readers:

Code and specify binary-coded dummy variables to test contrasts between specific groups or sets of groups.
Visualize results for simple and more complex models.
Use dummy variables to predict outcomes that require a quadratic, logarithmic, piecewise, or alternative functional form to best represent associations.
Use and interpret interaction terms to test group differences in outcome and process.
Consider alternative coding schemes that reframe group contrasts to test additional hypotheses.

You are here

Regression With Dummy Variables

Sage College Publishing

Related Products