1st Edition
Regression Analysis in R A Comprehensive View for the Social Sciences
Chapter 1. Introduction, Relationships and the Issue of Causality
Chapter 2. Describing Simple Relationships
2.1 Pearson Correlations
2.1.1Computation
2.1.2 R Examples
2.2 Extensions of the Pearson Correlation
2.2.1 Point Bi-Serial Correlation
2.2.2 Phi Coefficient
2.2.3 Spearman Rho
End of Chapter Comprehension Exercises
Chapter 3. Linear Regression Analysis
3.1 Simple Linear Regression
3.1.1 Equations
3.1.2 Model Fit Statistics
3.1.3 Significance Tests
3.2 Multiple Linear Regression
3.3 R Examples
End of Chapter Comprehension Exercises
Chapter 4. Regression Assumptions and Interpretational Considerations
4.1 Statistical Assumptions
4.2 Theoretical Assumptions
4.3 Interpretational Considerations
4.3.1Multicollinearity
4.3.2 Restriction of Range
4.3.3 Variability
End of Chapter Comprehension Exercises
Chapter 5. Dummy Variables and Interactions
5.1 Dummy coding
5.1.1 Dummy codes for 3 or more levels
5.1.2 Interpretation Examples
5.2 Interactions
5.2.1 Creating Interactions
5.2.2 Mean Centering for Interactions
5.2.3 Interpretation Examples
End of Chapter Comprehension Exercises
Chapter 6. Hierarchical Regression
6.1 Types of Hierarchical Regression
6.2 Model Comparison Statistics
6.3 R Examples
End of Chapter Comprehension Exercises
Chapter 7. Moderation and Mediation
7.1 Moderation
7.2 Mediation
7.2.1 Baron and Kenny
7.2.2 Tests of Indirect effects
End of Chapter Comprehension Exercises
Chapter 8. Dealing with Non Linearity
8.1 Transformations
8.2 Non Linear Terms
8.3 Overfitting – cross validation
End of Chapter Comprehension Exercises
Chapter 9. Regression Models for Nested Data
9.1 Fixed Effects Modeling
9.2 Hierarchical Linear Modeling
End of Chapter Comprehension Exercises
Appendix A
Basic R Use
Appendix B
Exercise Answers
Biography
Jocelyn E. Bolin is professor in the Department of Educational Psychology at Ball State University, where she teaches courses on introductory and intermediate statistics, multiple regression analysis, and multilevel modeling to graduate students in social science disciplines. She earned a PhD in educational psychology from Indiana University Bloomington. Her research interests include statistical methods for classification and clustering and use of multilevel modeling in the social sciences.
