Statistical mediation has become one of the predominate models for the study of how an intervention leads to changes in behavior. This model was first proposed by Baron and Kynny in 1986 (Baron & Kenny, 1986) and the work by a number of authors (MacKinnon, 1994, 2008; MacKinnon & Dwyer, 1993; Sobel, 1990) has increased the practical utility of this powerul statistical approach. We provide SPSS and SAS programming which we have developed for the analysis of single mediator models with continuous variables (Dudley, Benuzillo, & Carrico, 2004) and binary variables (Jasti, Dudley, & Goldwater, 2008). We also encourage you to visit one or more of several helpful sites:
- David Kenny's site provides help on a number of issues including mediation
- Kristopher Preacher's site provides a very helpful calculator
- David Mackinnon's site provides a wealth of information on mediation
Helpful Papers and Books
- Baron, R. M., & Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51(6), 1173-1182.
- Dudley, W., Benuzillo, J., & Carrico, M. (2004). Methods. SPSS and SAS programming for the testing of mediation models. Nursing Research, 53(1), 59-62.
- Jasti, S., Dudley, W. N., & Goldwater, E. (2008). SAS macros for testing statistical mediation in data with binary mediators or outcomes. Nursing Research, 57(2), 118-122.
- MacKinnon, D. P. (1994). Analysis of mediating variables in prevention and intervention research. National Institute on Drug Abuse Research Monograph Series, 139, 127-153.
- MacKinnon, D. P. (2008). Introduction to statistical mediation. New York: Lawrence Erlbaum.
- MacKinnon, D. P., & Dwyer, J. H. (1993). Estimating mediated effects in prevention studies. Evaluation Review, 17(2), 144-158.
- Sobel, M. E. (1990). Effect analysis and causation in linear structural equation models. Psychometrika, 55(3), 495-515.