Mediation, Moderation, and Conditional Process Analysis On Demand

The topics addressed in these courses include the following:

In HSK 847, Introduction to Mediation, Moderation, and Conditional Process Analysis:

1. Estimation and interpretation of the simple mediation model; total, direct, and indirect effects; path analysis tracing rules, illustration of computations using SPSS/SAS/R syntax.
2. Statistical inference about total, direct, and indirect effects in a mediation model; an overview of the mechanics of bootstrapping and the reasons why bootstrap confidence intervals are preferred to more classical inferential techniques.
3. Introduction to the PROCESS tool for SPSS, SAS, and R; common questions about bootstrapping and PROCESS.
4. The uses and limitations of data analysis in causal inference; the design-analysis-theory tripod of inference; confounding in a mediation model; how to account for confounds through the inclusion of covariates in a PROCESS command. 
5. An example of the application of mediation analysis using PROCESS when the causal antecedent X is dichotomous; partially standardized effect relative to the completely standardized effect; reasons to avoid completely standardized measures of effects when X is dichotomous.
6. An overview of the influential but now outdated "causal steps" procedure for assessing mediation (also known as the "Baron and Kenny" approach); a critique of the concepts of complete and partial mediation
7. The parallel multiple mediator model; reasons for estimating such a model with more than one mediator; path analysis rules in a parallel mediation model; implementation in PROCESS; the comparison of indirect effects through different mediators.
8. The fundamentals of moderation; the distinction between conditional and unconditional effects; how to set up a regression model to allow one variable's effect to depend on another variable in the model; the symmetry property of interactions; interpretation of regression coefficients. 
9. Linear moderation analysis with a dichotomous focal predictor and continuous moderator; how to visualize a model, interpreting regression coefficients; simplification of the analysis using PROCESS.
10. Probing moderation using the pick-a-point approach/spotlight analysis and the Johnson-Neyman technique/floodlight analysis; the distinction between testing for moderation and probing moderation; probing options available in PROCESS.
11. Debunking of two widely-believed myths about moderation analysis: the need to "mean center" or standardized focal predictor and moderator, and that to test a moderation hypothesis, a model should be built in stages using hierarchical variable entry. 
12. The generalization of principles of moderation analysis discussed in the course to this point to models with a continuous focal predictor and a dichotomous moderator.
13. Additional generalization of the principles of moderation analysis to quantitative focal predictors and quantitative moderators; good and bad approaches to producing standardized regression coefficients in a moderation analysis.
14. The integration of mediation and moderation analysis as "conditional process analysis”; the conditional indirect effect and a test of moderated mediation; the index of moderated mediation; example analysis of a second stage conditional process model using PROCESS; the similarities and differences between the use of PROCESS and a structural equation modeling program.
15. Illustrating, using PROCESS, the analysis of a first stage conditional process model that includes moderation of the direct and indirect effect of X.

In HSK 848, Mediation, Moderation, and Conditional Process Analysis: A Second Course

1. Review of the fundamentals from HSK 847 and the use of PROCESS
2. A conditional process model that combines moderation with parallel multiple mediation
3. The serial mediation model, including path analysis tracing rules for partitioning an effect into direct and indirect components when a mediator is allow to affect other mediator; illustration of serial mediation analysis using PROCESS; custom assignment of covariates to equations using PROCESS; model pruning.
4. A conditional process model that blends serial mediation with moderation; more on model pruning to simplify an unnecessarily complex model.
5. Mediation analysis when the independent variable X is multicategorical; representing a multicategorical variable in a regression model; estimation of relative total, direct, and indirect effects of a multicategorical X; how to determine whether X's effect on Y is mediated; example analysis using PROCESS
6. Moderation analysis when the focal predictor or moderator is multicategorical; conditioning a multicategorical X's effect on a moderator; probing and visualizing the model using features available in PROCESS.
7. Conditional process analysis when X is multicategorical; an illustration using PROCESS and how to test for moderation of mediation and quantify the relationship between moderator and the size of relative indirect and direct effects that are conditional on a moderator.
8. Moderation analysis with more than one moderator; the additive multiple moderator model that allows X's effect on Y to vary linearly but independently by moderators W and Z; moderated moderation or “three-way” interaction that allows the moderation of X's effect by moderator W to depend on moderator Z; techniques for visualizing and probing, facilitated by PROCESS.
9. Creating a custom model in PROCESS from scratch; editing and customizing a preprogrammed, numbered model.
10. Conditional process models with one of the two paths defining an indirect effect moderated simultaneously by two variables; visualization and interpretation; partial moderated mediation and how to test a partial moderated mediation hypothesis using PROCESS.
11. Conditional process models with two moderators of the indirect effect effect, one operating on the first stage and one on the second stage; moderated moderated mediation and conditional moderated mediation; visualizing conditional indirect effects; testing for moderation of moderated mediation and conditional moderated mediation using PROCESS.

In HSK 849, Mediation, Moderation, and Conditional Process Analysis: The Complete Course

1. All the topics described above covered in HSK 847 and HSK 848
2. Mediation analysis in the two-group pretest-posttest design. Illustration of various approaches using PROCESS
3. Moderation analysis in the 2 x 2 design (when both focal predictor and moderator are dichotomous) from a regression perspective using PROCESS; main and simple effects parameterizations of the 2 x 2 design; Regression versus factorial ANOVA.

All courses are delivered in online format asynchronously through pre-recorded video through the user interface at http://ccram.digitalchalk.com. Learners can begin the course when registration is completed, and access to the content is provided for 45 days (HSK 847, HSK 848) or 100 days (HSK 849) after registration. There is no limit to the number of times a video can be viewed, and controls for pausing, forwarding, and rewinding are provided on the user interface. Each course also contains a number of downloadable activities and self-assessments, with corresponding videos describing the answers to each activity and assessment task.

All data files, statistical code, activities, and PDFs of content of the videos can be downloaded and saved to the learner's storage medium for viewing even after the end of the access period. Videos cannot be downloaded or viewed offline. 

In all courses, learners can interact with the instructor through email. In HSK 849, an online discussion forum and occasional open group office hours through Zoom are provided for learners and the instructor to interact in real time during the learner's access period.

All courses are taught in English. There are no foreign language subtitles or closed captioning available on the videos, and all course materials are provided in English.

Computer applications will focus on the use of ordinary least squares regression and the PROCESS macro for SPSS, SAS and R, developed by the instructor, that makes the analyses described in this class much easier than they otherwise would be. This is a hands-on course, so maximum benefit results when learners can follow along with analyses using a laptop or desktop computer with a recent version of SPSS Statistics (version 27 or later), SAS (release 9.3 or later, with PROC IML installed) or R (version 3.6 or later; base module only. No packages are used in this course). Learners can choose which statistical package they prefer to use. STATA users can benefit from the course content, but PROCESS makes these analyses much easier and is not available for STATA. You can keep what you download, but videos are not downloadable.

The course content can be viewed from any technology capable of accessing web pages and viewing video files, including most tablets, phones, desktop, and laptop computers. An internet connection is required.

These courses will be helpful for researchers in any field – including psychology, sociology, education, business, human development, social work, public health, communication and others that rely on social science methodology – who want to learn how to apply the methods of moderation and mediation analysis using widely-used software such as SPSS, SAS and R.

Learners are recommended to have familiarity with the practice of multiple regression analysis and elementary statistical inference. No knowledge of matrix algebra is required or assumed, nor is matrix algebra used in the delivery of course content. Learners should also have some experience with the use of SPSS, SAS or R, including opening and executing data files and programs.

Upon completion, you will be able to:

• statistically partition one variable’s effect on another into its primary pathways of influence, direct and indirect
• understand modern approaches to inference about indirect effects in mediation models
• test competing theories of mechanisms statistically through the comparison of indirect effects in models with multiple mediators
• understand how to build flexibility into a regression model that allows a variable’s effect to be a function of another variable in a model
• visualize and probe interactions in regression models (e.g. using the simple slopes/spotlight analysis and Johnson-Neyman/floodlight analysis approaches)
• integrate models involving moderation and mediation into a conditional process model
• estimate the contingencies of mechanisms through the computation and inference about conditional indirect effects
• determine whether a mechanism is dependent on a moderator variable
• apply the methods discussed in this course using the PROCESS procedure for SPSS, SAS and R
• talk and write in an informed way about the mechanisms and contingencies of causal effects

A certificate of completion from the Canadian Centre for Research Analysis and Methods is provided at the end of the course.

In these courses, we focus primarily on research designs that are experimental, cross-sectional, or 2-wave longitudinal in nature, with continuous outcomes. We do not cover complex models involving dichotomous outcomes, latent variables, nested data (i.e., multilevel models) or the use of structural equation modeling. We also do not address the "counterfactual" or "potential outcomes" approaches to mediation analysis or discuss directed acyclic graphs (DAGs).

To see excepts of some of the videos that are in this collection of online courses, point your browser to https://www.youtube.com/watch?v=Lz_xHk-jmS0 or click the button below.

First, create an account on CCRAM's online course management portal, DigitalChalk. Only your name and email address are required, but you may complete other fields in the form if you want. Click the button below to create your account. Note: If you already have an account with ccram.digitalchalk.com, you may skip this step.

Next, pay the required tuition. Click the link below for the course in which you wish to register. Once you have put the course in your basket and attempt to check out, you will be directed to a site to pay your tuition. During this process, you will be required to set up an account with the University of Calgary Continuing Education. Your access to the course content begins after this step, so wait to the pay tuition until just before you plan on starting the course.

Register and pay for HSK 847 ($595 CAD + 5% GST)

Register and pay for HSK 848 ($595 CAD + 5% GST)

Register and pay for HSK 849 ($995 CAD + 5% GST)

Once you have paid the tuition, please return to ccram.digitalchalk.com and log in to your account using the name and password you used to set up your DigitalChalk account. Eventually, you will find the course in your dashboard, at which point you are officially enrolled in the course. It may take up to 48 hours for the course to appear in your dashboard, but usually it won't take more than a few hours. You can begin the course once it does. The time to complete the course begins counting as soon as the course appears in your dashboard, not when you actually start the course.