6 Multiple Mediators Consider two mediators, M 1 and M 2, Now two indirect effects a 1 b 1 and a 2 b 2. Can test: –Is the sum different from zero? –Is each different from zero? –Is one larger than the other? 6
7 Dual Mediation: Special Example of Two Mediators X has two levels Each level is intervention Both equally effective Each works through a different mechanism (i.e., mediator). 7
13 Covariates Often there are variables in the analysis that need to be controlled: –Demographics –Baseline measures If a covariate interacts with X, it becomes a moderator. 13
14 Why Add Covariates? Causal Inference: Covariate might be an omitted variable or a confounder. Power –If covariate is not correlated with the predictor but with the outcome, it leads to an increase in power. 14
15 Causal Assumptions Generally assumed that covariates only cause M and Y and are not caused by them. Covariates may cause or be caused by X, but that covariation is generally left unanalyzed. 15
Your consent to our cookies if you continue to use this website.