Mediation, Moderation, and Conditional Process Modeling Summer School
Aims
In this course you will learn how to conduct and interpret the results of mediation, moderation, and conditional process analyses. Mediation describes the case where an independent variable X influences another variable M (mediator), which in turn influences the dependent variable Y. For example, giving time to others (X) has been shown to enhance one’s own feelings of competence (M), which in turn leads to the feeling that one has more time available (Y), (Mogilner, Chance, and Norton 2012). Moderation describes the case where the effect of the independent variable X on the dependent variable Y changes across different levels of another variable M (moderator). For instance, perceived conflict between goals (X) makes consumers feel that they have less time available (Y) and this effect is further moderated by breathing speed (M). When consumers are nudged to breathe slowly the negative effect of perceived goal conflict on feelings of time is reduced (Etkin, Evangelidis, and Aaker 2015). Conditional process modeling describes models that include both mediation and moderation.
This is an applied course: knowledge of algebra is not required, yet a basic understanding of OLS regression is necessary. This course is targeted to any person doing social science research that wants to learn how to test for mediation and moderation in his or her data.
Information
Mediation topics include: 1) simple mediation with any type of independent and dependent variables (i.e., continuous, dichotomous, multicategorical), 2) mediation with multiple parallel mediators, 3) mediation with multiple serial mediators. Moderation topics include: 1) moderation models with up to 2 moderators (3-way interactions) using any type of independent and dependent variables, 2) analysis of unconditional versus conditional effects, 3) Model estimation and interpretation, 4) Visualization. I will also discuss how to analyze conditional process models (i.e., models that include both mediation and moderation). Depending on the pace of the course I will also try to cover some specialized topics such as mediation analysis in within-participants designs and mediation analysis using a binary mediator. The course will be focused on teaching you how to conduct the appropriate analysis and interpret your results. We will be using PROCESS (Hayes, 2013) for the purposes of this course. Attendants should have a recent version of SPSS (or SAS) and PROCESS installed on their computer.
Assessment
1) Participants will need to work on daily assignments. Datasets for these assignments will be provided by the lecturer and will be discussed during class.
2) Participants are encouraged to bring up and discuss during class a specific problem that they faced in their own research (e.g., how to test a specific theoretical model, how to test for moderation when M is …, etc.). On the last day of this course we will work together on solving problems that you faced in your own research, and discuss what are the best approaches to test for mediation, moderation, or conditional processes in your data.
Additional info
PhD candidates, Research Master students and faculty members of ERIM can register for this course via SIN Online Registration.
External (non-ERIM) participants are welcome to this course. To register, please fill in the registration form and e-mail it to miizuka@rsm.nl by 3 weeks prior to the start of the course. Please note that the number of places for this course is limited.
This course is free of charge for ERIM members (faculty members, PhD candidates and Research Master students). For external participants, the course fee is 250 euro per ECTS credit.
