Hi everyone,
I'm currently working on my thesis which involves mediation using nominal independents and dependents, as well as scale mediators. I understand that binary mediation is possible, using logit or probit models. However, is it possible to test for mediation when your dependent involves multiple categorical options? Here is my model:
X (binary) > M (multiple scales) > Y (nominal: 14 outcomes)
I will convert Y into a binary variable to test for robustness, but keeping the categories separate will allow for more analysis and conclusions.
Thanks for the help!
I'm currently working on my thesis which involves mediation using nominal independents and dependents, as well as scale mediators. I understand that binary mediation is possible, using logit or probit models. However, is it possible to test for mediation when your dependent involves multiple categorical options? Here is my model:
X (binary) > M (multiple scales) > Y (nominal: 14 outcomes)
I will convert Y into a binary variable to test for robustness, but keeping the categories separate will allow for more analysis and conclusions.
Thanks for the help!