11111111

Essentially, MacKinnon (Introduction to Statistical Mediation Analysis,Routledge 2008)treats mediation as existing on a continuum rather than being either present or absent (which is the way Baron and Kenny's old article does).

Andrew F. Hayes at Ohio State University provide a tutorial illustrating an approach to estimation of and inference about direct,
indirect, and total effects in statistical mediation analysis with a multicategorical independent variable (http://www.quantpsy.org/pubs/hayes_preacher_(in.press).pdf)
Nathaniel R. Herr introduce the Mediation with Dichotomous Outcomes at http://www.nrhpsych.com/mediation/logmed.html

谢谢~~~~~~

到底问题解决了么？