Try the following:

Holmbeck GN: Toward terminological, conceptual, and statistical clarity in the study of mediators and moderators: examples from the child-clinical and pediatric psychology literatures. Journal of Consulting & Clinical Psychology 1997; 65(4):599-610

Kraemer HC, Stice E, Kazdin A, Offord D, Kupfer D: How do risk factors work together? Mediators, moderators, and independent, overlapping, and proxy risk factors. Am J Psychiatry 2001; 158(6):848-56

At 05:39 PM 8/29/2002 -0400, Christina Cutshaw wrote: >Listmembers, > >Does anyone have any information, citations etc. on performing a >mediation analysis with a dichotomous versus a continuous dependent >variable. I have Baron and Kenny (1986) and other information on >mediation in linear regression, but cannot find any information about >whether the process is different in logistic regression. > >Any guidance would be appreciated. > >Thanks, > >Chris Cutshaw

********************************************************* John S. March, MD, MPH Professor of Psychiatry and Behavioral Sciences Department of Psychiatry and Behavioral Sciences Duke Child and Family Study Center 718 Rutherford Street Durham, NC 27705 919/416-2404 (P); 919/416-2420 (F) Email: jsmarch@acpub.duke.edu Website: http://www2.mc.duke.edu/pcaad

"I maintain there is much more wonder in science than in pseudoscience. And in addition, to whatever measure this term has any meaning, science has the additional virtue, and it is not an inconsiderable one, of being true." --Carl Sagan

*********************************************************