Mediation Analysis with Time-Varying Mediators and Exposures

Chapter
Part of the Springer Series in Statistics book series (SSS)

Abstract

An exposure often acts on an outcome of interest directly, or indirectly through the mediation of some intermediate variables. Identifying and quantifying these two types of effects contribute to further understanding of the underlying causal mechanism. Modern developments in formal nonparametric causal inference have produced many advances in causal mediation analysis in nonlongitudinal settings. (e.g., Robins and Greenland 1992; Pearl 2001; van der Laan and Petersen 2008; VanderWeele 2009; Hafeman and VanderWeele 2010; Imai et al. 2010b,a; Pearl 2011; Tchetgen Tchetgen and Shpitser 2011a,b; Zheng and van der Laan 2012b; Lendle and van der Laan 2011).

References

  1. C. Avin, I. Shpitser, J. Pearl, Identifiability of path-specific effects. Proceedings of International Joint Conference on Artificial Intelligence, 357–363 (2005)Google Scholar
  2. H. Bang, J.M. Robins, Doubly robust estimation in missing data and causal inference models. Biometrics 61, 962–972 (2005)MathSciNetCrossRefMATHGoogle Scholar
  3. P.J. Bickel, C.A.J. Klaassen, Y. Ritov, J. Wellner, Efficient and Adaptive Estimation for Semiparametric Models (Springer, Berlin, Heidelberg, New York, 1997b)MATHGoogle Scholar
  4. V. Didelez, A.P. Dawid, S. Geneletti, Direct and indirect effects of sequential treatments, in Proceedings of the 22nd Annual Conference on Uncertainty in Artificial Intelligence (2006), pp. 138–146Google Scholar
  5. D.M. Hafeman, T.J. VanderWeele, Alternative assumptions for the identification of direct and indirect effects. Epidemiology 22, 753–764 (2010)CrossRefGoogle Scholar
  6. M.A. Hernan, B. Brumback, J.M. Robins, Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men. Epidemiology 11(5), 561–570 (2000)CrossRefGoogle Scholar
  7. K. Imai, L. Keele, D. Tingley, A general approach to causal mediation analysis. Psychol methods 15(4), 309–334 (2010a)CrossRefGoogle Scholar
  8. K. Imai, L. Keele, T. Yamamoto, Identification, inference and sensitivity analysis for causal mediation effects. Stat. Sci. 25(1), 51–71 (2010b)MathSciNetCrossRefMATHGoogle Scholar
  9. S.D. Lendle, M.J. van der Laan, Identification and efficient estimation of the natural direct effect among the untreated. Technical Report, Division of Biostatistics, University of California, Berkeley (2011)MATHGoogle Scholar
  10. J. Pearl, Direct and indirect effects, in Proceedings of the 17th Conference Uncertainty in Artificial Intelligence (Morgan Kaufmann, San Francisco, 2001)Google Scholar
  11. J. Pearl, Causality: Models, Reasoning, and Inference, 2nd edn. (Cambridge, New York, 2009a)CrossRefMATHGoogle Scholar
  12. J. Pearl, The mediation formula: a guide to the assessment of causal pathways in nonlinear models, in Causality: Statistical Perspectives and Applications, ed. by C. Berzuini, P. Dawid, L. Bernardinelli (Springer, Berlin, 2011)Google Scholar
  13. M. Petersen, J. Schwab, S. Gruber, N. Blaser, M. Schomaker, M.J. van der Laan, Targeted maximum likelihood estimation for dynamic and static longitudinal marginal structural working models. J. Causal Inference 2(2), 147–185 (2014)CrossRefGoogle Scholar
  14. J.M. Robins, A new approach to causal inference in mortality studies with sustained exposure periods–application to control of the healthy worker survivor effect. Math. Modell. 7, 1393–1512 (1986)MathSciNetCrossRefMATHGoogle Scholar
  15. J.M. Robins, S. Greenland, Identifiability and exchangeability for direct and indirect effects. Epidemiol 3, 143–155 (1992)CrossRefGoogle Scholar
  16. J.M. Robins, Y. Ritov, Toward a curse of dimensionality appropriate (coda) asymptotic theory for semi-parametric models. Stat. Med. 16, 285–319 (1997)CrossRefGoogle Scholar
  17. O.M. Stitelman, V. De Gruttola, C.W. Wester, M.J. van der Laan, Rcts with time-to-event outcomes and effect modification parameters, in Targeted Learning: Causal Inference for Observational and Experimental Data, ed. by M. J. van der Laan, S. Rose (Springer, Berlin, 2011)Google Scholar
  18. E.J. Tchetgen Tchetgen, I. Shpitser, Semiparametric theory for causal mediation analysis: efficiency bounds, multiple robustness, and sensitivity analysis. Technical report 130, Biostatistics, Harvard University, June (2011a)Google Scholar
  19. E.J. Tchetgen Tchetgen, I. Shpitser, Semiparametric estimation of models for natural direct and indirect effects. Technical Report 129, Biostatistics, Harvard University, June (2011b)Google Scholar
  20. M.J. van der Laan, Targeted estimation of nuisance parameters to obtain valid statistical inference. Int. J. Biostat. 10(1), 29–57 (2014b)MathSciNetGoogle Scholar
  21. M.J. van der Laan, A generally efficient targeted minimum loss based estimator. Int. J. Biostat. 13(2), 1106–1118 (2017)Google Scholar
  22. M.J. van der Laan, S. Gruber, Targeted minimum loss based estimation of causal effects of multiple time point interventions. Int. J. Biostat. 8(1), Article 9 (2012)Google Scholar
  23. M.J. van der Laan, M.L. Petersen, Direct effect models. Int. J. Biostat. 4(1), Article 23 (2008)Google Scholar
  24. M.J. van der Laan, J.M. Robins, Unified Methods for Censored Longitudinal Data and Causality (Springer, Berlin Heidelberg New York, 2003)CrossRefMATHGoogle Scholar
  25. M.J. van der Laan, S. Rose, Targeted Learning: Causal Inference for Observational and Experimental Data (Springer, Berlin, Heidelberg, New York, 2011)CrossRefGoogle Scholar
  26. T.J. VanderWeele, Marginal structural models for the estimation of direct and indirect effects. Epidemiology 20, 18–26 (2009)CrossRefGoogle Scholar
  27. T.J. VanderWeele, E.J. Tchetgen Tchetgen, Mediation analysis with time-varying exposures and mediators. J. R. Stat. Soc. Ser. B 79(3), 917–938 (2017)MathSciNetCrossRefGoogle Scholar
  28. T.J. VanderWeele, S. Vansteelandt, J.M. Robins, Effect decomposition in the presence of an exposure-induced mediator-outcome confounder. Epidemiology 25(2), 300–306 (2014a)CrossRefGoogle Scholar
  29. W. Zheng, M.J. van der Laan, Causal mediation in a survival setting with time-dependent mediators. Technical Report, Division of Biostatistics, University of California, Berkeley (2012a)Google Scholar
  30. W. Zheng, M.J. van der Laan, Targeted maximum likelihood estimation of natural direct effects. Int. J. Biostat. 8(1), 1–40 (2012b)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.NetflixLos GastosUSA
  2. 2.Division of Biostatistics and Department of StatisticsUniversity of California, BerkeleyBerkeleyUSA

Personalised recommendations