12. The Mediation Formula: A Guide to the Assessment of Causal Pathways in Nonlinear Models

  1. Carlo Berzuini,
  2. Philip Dawid and
  3. Luisa Bernardinelli
  1. Judea Pearl

Published Online: 25 JUN 2012

DOI: 10.1002/9781119945710.ch12

Causality: Statistical Perspectives and Applications

Causality: Statistical Perspectives and Applications

How to Cite

Pearl, J. (2012) The Mediation Formula: A Guide to the Assessment of Causal Pathways in Nonlinear Models, in Causality: Statistical Perspectives and Applications (eds C. Berzuini, P. Dawid and L. Bernardinelli), John Wiley & Sons, Ltd, Chichester, UK. doi: 10.1002/9781119945710.ch12

Editor Information

  1. Statistical Laboratory, Centre for Mathematical Sciences, University of Cambridge, Cambridge, UK

Author Information

  1. Computer Science Department, University of California, Los Angeles, California, USA

Publication History

  1. Published Online: 25 JUN 2012
  2. Published Print: 13 JUL 2012

Book Series:

  1. Wiley Series in Probability and Statistics

Book Series Editors:

  1. Walter A. Shewhart and
  2. Samuel S. Wilks

ISBN Information

Print ISBN: 9780470665565

Online ISBN: 9781119945710

SEARCH

Keywords:

  • mediation formula, causal pathways in nonlinear models;
  • direct effects, in legal disputes over hiring race/sex, and the discrimination;
  • structural equation models, for analyzing path-specific effects;
  • controlled direct effect, in linear systems, to path coefficient of link;
  • identification of direct effects, not ‘ignorability’ or ‘sequential ignorability’;
  • hiring context, path-specific effects in policy making;
  • mediation effects in nonparametric, nonlinear models;
  • mediation effects in linear, logistic, and probit models;
  • analytical ‘sensitivity analysis’ in statistics for parameter estimation;
  • mediation formulas, causal pathway assessment in the sciences

Summary

This chapter contains sections titled:

  • Mediation: Direct and indirect effects

  • The mediation formula: A simple solution to a thorny problem

  • Relation to other methods

  • Conclusions

  • Acknowledgments

  • References