Doing Statistical Mediation and Moderation

Written in a friendly, conversational style, this book offers a hands-on approach to statistical mediation and moderation for both beginning researchers and those familiar with modeling. Starting with a gentle review of regression-based analysis, Paul Jose covers basic mediation and moderation techniques before moving on to advanced topics in multilevel modeling, structural equation modeling, and hybrid combinations, such as moderated mediation. User-friendly features include numerous graphs and carefully worked-through examples; "Helpful Suggestions" about procedures and pitfalls; "Knowledge Boxes" delving into special topics, such as dummy coding; and end-of-chapter exercises and problems (with answers). The companion website provides downloadable sample data sets that are used in the book to demonstrate particular analytic strategies, and explains how researchers and students can execute analyses using Jose's online programs, MedGraph and ModGraph. Appendices present SPSS, AMOS, and Mplus syntax for conducting the key types of analyses.

Paul E. Jose, PhD, is Associate Professor of Psychology and Director of the Roy McKenzie Centre for the Study of Families at Victoria University of Wellington in New Zealand. He received his doctorate in Developmental Psychology from Yale University, completed a postdoc at the University of Illinois at Champaign-Urbana, and taught and conducted research at Loyola University Chicago for 15 years. Dr. Jose's research interests include gender differences in spoken discourse, moral development, cross-cultural comparisons of adolescent coping and family dynamics, children's preparation and motivation for academic achievement, adolescent anxiety and depression, and positive psychology. He has used mediation and moderation for over 20 years in his work.

1. A Basic Orientation *My Personal Journey *Confusions about Mediation and Moderation *Mediation and Moderation: The Synergism of Three Variables 2. Historical Background *The History of Mediation and Moderation *Two Strands of Thought within Statistics *The Historical Basis for the Methods of Mediation and Moderation *Baron and Kenny's Landmark Publication *Knowledge Box. A Note about Terminology: IV/DV versus Predictor/Outcome *Clarification of Mediation and Moderation Subsequent to Baron and Kenny's Article *Summary *Further Reading 3. Basic Mediation *Review of Basic Rules for Mediation *How to Do Basic Mediation *Knowledge Box. Controversy: Calculation of whether Significant Mediation Has Occurred *An Example of Mediation with Experimental Data *An Example of Null Mediation *Sobel's z versus Reduction of the Basic Relationship *Suppressor Variables in Mediation *Investigating Mediation When One Has a Nonsignificant Correlation *Understanding the Mathematical "Fine Print": Variances and Covariances *Discussion of Partial and Semipartial Correlations *Statistical Assumptions *Summary *Further Reading *In-Chapter Exercises *Additional Exercises 4. Special Topics in Mediation *Model Specification: Testing Models *Knowledge Box. Another Area of Potential Confusion: Implications for Naming Different Types of Mediation Results *Multiple Mediators *Bootstrapping (Resampling) *Longitudinal Mediation Models *Multilevel Mediation Models *Categorical Mediators and/or Outcomes (Logistic Regression) *Mediation with Quadratic Relationships *Summary *Further Reading *In-Chapter Exercises 5. Basic Moderation *Categorical Variable Moderation *Knowledge Box. A Short Tutorial on Dummy Coding *An Example of a Continuous Moderator *Knowledge Box. Graphing Moderation Patterns *Further Reading *In-Chapter Exercises *Additional Exercises 6. Special Topics in Moderation *Johnson-Neyman Regions of Significance *Multiple Moderator Regression Analyses *Moderation of Residualized Relationships *Quadratic Moderation *Basic Moderation in Path Analyses *Moderation in Multilevel Modeling (MLM) *Moderation with Latent Variables *Logistic Moderation? *Summary *Further Reading *In-Chapter Exercises *Additional Exercises 7. Mediated Moderation and Moderated Mediation *The Literature *Mediated Moderation: A Baron and Kenny-type Example *Moderated Mediation *Where to from Here? Bootstrapping for Moderated Mediation *More Complicated Variants: Moderated Mediated Moderation *Other Variants *Conclusions *Further Reading Suggested Answers to Exercises Appendix A. SPSS, AMOS, and MPlus Models Appendix B. Resources for Researchers Who Use Mediation and Moderation