JSM Preliminary Online Program
This is the preliminary program for the 2006 Joint Statistical Meetings in Seattle, Washington.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2006 Program page

Activity Number: 76
Type: Contributed
Date/Time: Sunday, August 6, 2006 : 8:00 PM to 9:50 PM
Sponsor: Social Statistics Section
Abstract - #307553
Title: Mediation Analysis with Multilevel Data
Author(s): Jungwha Lee*+ and Eisuke Segawa and Sue Curry
Companies: Institute for Health Research and Policy and Institute for Health Research and Policy and University of Illinois at Chicago
Address: 1747 W. Roosevelt Road, Chicago, IL, 60608 ,
Keywords: mediation analysis ; multilevel data
Abstract:

A basic mediation model has three variables, the response variable (Y), the covariate (X), and the mediator (M). How X effects Y is of our interest, by assuming that X causes M which in turn causes Y. In multilevel data, Y, X, and M can be measured in different levels of hierarchy. Krull and MacKinnon (2001) introduced multilevel modeling of mediated effects by first solving two multilevel regressions, and then combining the two results to get the direct and indirect effects. However, if the residuals of the two regressions are correlated, their approach may not be ideal. We present mediating mechanisms to incorporate the multilevel regressions. Helping Young Smokers Quit (HYSQ) study data as well as the simulated data are used to apply mediation analyses.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2006 program

JSM 2006 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised April, 2006