SOFTWARE
Mediation analysis: A new test when all or some variables are categorical
Abstract: Statistical tests for mediation in consumer research typically use a regression coefficients (RegCoeff)-based framework. We present a new test based on likelihood ratio principles to complement the RegCoeff approach. We compare the new test’s performance to conventional methods that use PROCESS and extensions thereof to categorical measures. Our test addresses situations in which the assumptions of current methods tend not to hold; relationships among constructs (or measures thereof) may be non-linear or one or more variables may be categorical. In such environments, results significantly favor our new test in power and in its ability to accurately assess effect size. To assist researchers, we detail how and when the new test can best complement existing methods and offer software (SPSS and SAS macros) that runs the new test for any combination of continuous and categorical variables.
SPSS (version 1.2, March 02 2018):
Update summary:
Suppress interim results in the output window
Save interim datasets in a temporary folder. Such datasets can be deleted after testing is completed.
Include a testing code template for easy use.
SAS (version 1.1, February 16 2018):
Testing Code Template