Introduction to Linear Regression Analysis is a textbook intended for an upper-level undergraduate or introductory graduate course in regression analysis. It assumes students have taken an introductory statistics courses and are familiar with concepts such as hypothesis testing, confidence intervals, and the normal, t, F and chi-squared distributions. It also requires some knowledge of matrix algebra and access to a computer and statistical software such as SAS or MINITAB.
Introduction to Linear Regression Analysis is organized in two parts. The first ten chapters are the nucleus of the book and cover topics which would typically be included in any regression course, beginning with an introduction to the basic concepts of linear regression and model building. Topics spill over from one chapter to another, and it is assumed that all ten chapters will be covered in a basic regression course. In contrast, each of last five chapters are self-contained and focus on a specific topic, such as robust regression, which may be included or omitted depending on the specific focus of the class. The final chapter includes brief introductions to some more recent topics in regression, including bootstrapping, classification and regression trees, and neural networks.
Introduction to Linear Regression Analysis was developed from course notes for a regression analysis course for students in engineering, chemistry, physical science, statistics, mathematics and management. Most of the examples pertain to those fields, making it less attractive as a text in the social sciences. It is also more mathematical than the typical statistics texts used in social science departments. The strongest merits of Introduction to Linear Regression Analysis are the clarity of exposition, including many illustrations and solved examples, and the integration of computer use into the instruction. Instructions for executing the different types of analyses in SAS and MINITAB are included, as are annotated output from those programs. An appendix also provides a basic introduction to SAS. Introduction to Linear Regression Analysis is also an excellent reference and could also serve as a self-teaching text for anyone with a basic level of statistical knowledge.
The webpage for Introduction to Linear Regression Analysis includes electronic versions of the data sets used in the book. An instructor's manual also includes electronic copies of the data sets as well as solutions to all exercises and suggested examination problems, and the student solutions guide includes solutions to selected exercises.
The authors of Introduction to Linear Regression Analysis have varied backgrounds. Douglas C. Montgomery is a Professor of Industrial & Management Systems Engineering at Arizona State University; his research interests focus on engineering applications of statistics and operational research methods. Elizabeth A. Peck is a Logistics Modeling Specialist at the Coca-Cola Company in Atlanta, GA. G. Geoffrey Vining is Professor and Head of the Statistics Department at Virginia Polytechnic Institute; his research.
Sarah Boslaugh, PhD, MPH, is a Performance Analyst for BJH HealthCare in Saint Louis, Missouri. She published An Intermediate Guide to SPSS Programming with Sage in 2005 and is currently editing The Encyclopedia of Epidemiology for Sage (forthcoming, 2007) and writing Secondary Data Sources for Public Health (forthcoming, 2007) for Cambridge University Press.
2. Simple Linear Regression.
3. Multiple Linear Regression.
4. Model Adequacy Checking.
5. Transformations and Weighting to Correct Model Inadequacies.
6. Diagnostics for Leverage and Influence.
7. Polynomial Regression Models.
8. Indicator Variables.
9. Variable Selection and Model Building.
10. Validation of Regression Models.
12. Robust Regression.
13. Introduction to Nonlinear Regression.
14. Generalized Linear Models.
15. Other Topics in the Use of Regression Analysis.
Appendix A: Statistical Tables.
Appendix B: Data Sets For Exercises.
Appendix C: Supplemental Technical Material.