Mediation misgivings: Ambiguous clinical and public health interpretations of natural direct and indirect effects

International Journal of Epidemiology

Volumn 43, Issue 5, 2014, Pages 1656-1661

  Naimi, Ashley I ^a   Kaufman, Jay S ^a   MacLehose, Richard F ^b  

^a MCGILL UNIVERSITY   (Canada)

^b UNIVERSITY OF MINNESOTA   (United States)

Author keywords

Causal inference; Controlled direct effect; Effect decomposition; Epidemiological methods; Intervention; Mediation; Natural direct effect; Natural indirect effect

Indexed keywords

DECOMPOSITION; EPIDEMIOLOGY; HEALTH RISK; NUMERICAL MODEL; PUBLIC HEALTH;

ARTICLE; MATHEMATICAL ANALYSIS; POLICY; PUBLIC HEALTH; REGRESSION ANALYSIS; STATISTICAL MODEL; EPIDEMIOLOGY; HUMAN; INTERPERSONAL COMMUNICATION; PROCEDURES; STATISTICS; TREATMENT OUTCOME;

CAUSALITY; HUMANS; MODELS, STATISTICAL; NEGOTIATING; PUBLIC HEALTH; STATISTICS AS TOPIC; TREATMENT OUTCOME;

EID: 84913543449     PISSN: 03005771     EISSN: 14643685     Source Type: Journal    
DOI: 10.1093/ije/dyu107     Document Type: Article

References (58)

1. Judd CM, Kenny DA. Process analysis: Estimating mediation in treatment evaluations. Eval Rev 1981;5:602-19.
2. Baron RM, Kenny DA. The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. J Pers Soc Psychol 1986;51:1173-82.
3. Robins JM, Greenland S. Identifiability and exchangeability for direct and indirect effects. Epidemiology 1992;3:143-55.
4. Pearl J. Direct and indirect effects. In: Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence. San Francisco, CA: Morgan Kaufmann, 2001.
5. Robins JM. Semantics of causal DAG models and the identification of direct and indirect effects. In: Green PJ, Hjort NL, Richardson S (eds). Highly Structured Stochastic Systems. Oxford, UK: Oxford University Press, 2003.
6. VanderWeele TJ. Marginal structural models for direct and indirect effects. Epidemiology 2009;20:18-26. See also erratum in Epidemiology 2009;20:629.
7. Ten Have TR, Joffe MM, Lynch KG, Brown GK, Maisto SA, Beck AT. Causal mediation analyses with rank preserving models. Biometrics 2007;63:926-34.
8. Hafeman DM, Schwartz S. Opening the black box: a motivation for the assessment ofmediation. Int J Epidemiol 2009;38:838-45.
9. Hafeman DM. 'Proportion explained': a causal interpretation for standard measures of indirect effect? Am J Epidemiol 2009;170:1443-48.
10. Hafeman DM. A sufficient cause based approach to the assessment of mediation. Eur J Epidemiol 2008;23:711-21.
11. Ten Have TR. Invited commentary: pushing the mediation envelope. Am J Epidemiol 2010;172:1352-54.
12. Lange T, Vansteelandt S, Bekaert M. A simple unified approach for estimating natural direct and indirect effects. Am J Epidemiol 2012;176:190-95.
13. Daniels MJ, Roy JA, Kim C, Hogan JW, Perri MG. Bayesian inference for the causal effect of mediation. Biometrics 2012;68:1028-36.
14. Albert JM, Nelson S. Generalized causal mediation analysis. Biometrics 2011;67:1028-38.
15. Kaufman JS, Maclehose RF, Kaufman S. A further critique of the analytic strategy of adjusting for covariates to identify biologic mediation. Epidemiol Perspect Innov 2004;1:4.
16. VanderWeele TJ. A three-way decomposition of a total effect into direct, indirect, and interactive effects. Epidemiology 2013; 24:224-32.
17. Albert JM. Distribution-free mediation analysis for nonlinear models with confounding. Epidemiology 2012;23:879-88.
18. Lange T, Hansen JV. Direct and indirect effects in a survival context. Epidemiology 2011;22:575-81.
19. Albert JM. Mediation analysis via potential outcomes models. Stat Med 2008;27:1282-304.
20. Ten Have TR, Joffe MM. A review of causal estimation of effects in mediation analyses. Stat Methods Med Res 2012;21:77-107.
21. Ananth CV, VanderWeele TJ. Placental abruption and perinatal mortality with preterm delivery as a mediator: disentangling direct and indirect effects. Am J Epidemiol 2011;174:99-108.
22. Nandi A, Glymour MM, Kawachi I, VanderWeele TJ. Using marginal structural models to estimate the direct effect of adverse childhood social conditions on onset of heart disease, diabetes, and stroke. Epidemiology 2012;23:223-32.
23. Bennett AC, Rankin KM, Rosenberg D. Does a medical home mediate racial disparities in unmet healthcare needs among children with special healthcare needs? Matern Child Health J 2012;16(Suppl 2):330-38.
24. VanderWeele TJ, Lauderdale DS, Lantos JD. Medically induced preterm birth and the associations between prenatal care and infant mortality. Ann Epidemiol 2013;23:435-40.
25. Subbaraman MS, Lendle S, van der Laan M, Kaskutas LA, Ahern J. Cravings as a mediator and moderator of drinking outcomes in the COMBINE study. Addiction 2013; 108:1737-44.
26. Smith PM, Smith BT, Mustard CA, Lu H, Glazier RH. Estimating the direct and indirect pathways between education and diabetes incidence among Canadian men and women: a mediation analysis. Ann Epidemiol 2013;23:143-49.
27. Galea S. An argument for a consequentialist epidemiology. Am J Epidemiol 2013;178:1185-91.
28. Glass TA, Goodman SN, Hernán MA, Samet JM. Causal inference in public health. Annu Rev Public Health 2013;34: 61-75.
29. Ahern J, Hubbard A, Galea S. Estimating the effects of potential public health interventions on population disease burden: a stepby- step illustration of causal inference methods. Am J Epidemiol 2009;169:1140-47.
30. Rockhill B. Theorizing about causes at the individual level while estimating effects at the population level: implications for prevention. Epidemiology 2005;16:124-29.
31. Kaufman JS, Cooper RS. Seeking causal explanations in social epidemiology. Am J Epidemiol 1999;150:113-20.
32. Holland PW. Statistics and causal inference. J Am Stat Assoc 1986;81:945-60.
33. Robins JM. A new approach to causal inference in mortality studies with a sustained exposure period-application to control of the healthy worker survivor effect. Mathematical Modelling 1986;7:1393-512.
34. Robins JM, Greenland S. Causal inference without counterfactuals: Comment. J Am Stat Assoc 2000;95:431-35.
35. Hernán MA. Invited commentary: Hypothetical interventions to define causal effects-afterthought or prerequisite? Am J Epidemiol 2005;162:618-20.
36. Kaufman JS. Commentary: Gilding the black box. Int J Epidemiol 2009;38:845-47.
37. Vansteelandt S. Estimation of controlled direct effects on a dichotomous outcome using logistic structural direct effect models. Biometrika 2010;97:921-34.
38. Pearl J. Causality: Models, Reasoning and Inference. 2nd edn. Cambridge, UK: Cambridge University Press, 2009.
39. Schwartz S, Hafeman D, Campbell U, Gatto N. Authors' response to: Commentary: Gilding the black box. Int J Epidemiol 2010;39:1399-401.
40. VanderWeele TJ, Vansteelandt S, Robins JM. Effect decomposition in the presence of an exposure-induced mediator-outcome confounder. Epidemiology 2014;25:300-06.
41. Tchetgen Tchetgen EJ, VanderWeele TJ. Identification of natural direct effects when a confounder of the mediator is directly affected by exposure. Epidemiology 2014;25:282-91.
42. Richiardi L, Bellocco R, Zugna D. Mediation analysis in epidemiology: methods, interpretation and bias. Int J Epidemiol 2013;42:1511-19.
43. Robins J, Richardson T. Alternative graphical causal models and the identification of direct effects. In: Keyes KM, Ornstein K, Shrout PE (eds). Causality and Psychopathology: Finding the Determinants of Disorders and Their Cures. Oxford, UK: Oxford University Press, 2011.
44. Pearl J. Interpretation and identification in causal mediation analysis. Psychol Methods 2014. In press.
45. Avin C, Shpitser I, Pearl J. Identifiability of path specific effects. In: Proceedings of the International Joint Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2005.
46. Richardson TS, Robins JM. Single world intervention graphs (SWIGs): A unification of the counterfactual and graphical approaches to causality. Tech. Rep. Number 128. Center for Statistics and the Social Sciences, University of Washington. http://www.csss.washington.edu/Papers/wp128.pdf 26 August 2013, date last accessed).
47. Vansteelandt S. Estimation of direct and indirect effects. In: Carlo Berzuini LB, Philip Dawid, Bernardinelli L et al. (eds). Causality: Statistical Perspectives and Applications. Chichester, UK: Wiley, 2012.
48. Rosenbaum P. Observational Studies. New York, NY: Springer, 1995.
49. Morgan SL, Winship C. Counterfactuals and Causal Inference: Methods and Principles for Social Research. New York, NY: Cambridge University Press, 2007.
50. Hernán MA, Robins J. Causal Inference. New York, NY: Chapman/Hall/CRC. In press. http://www.hsph.harvard.edu/ miguel-hernan/causal-inference-book (12 March 2014, date last accessed).
51. Petersen ML, Sinisi SE, van der Laan MJ. Estimation of direct causal effects. Epidemiology 2006;17:276-84.
52. Robins JM. Testing and estimation of direct effects by reparameterizing directed acyclic graphs with structural nested models. In: Glymour C, Cooper G (eds). Computation, Causation, and Discovery. Menlo Park, CA / Cambridge, MA: AAAI Press/The MIT Press., 1999.
53. Kaufman JS. Invited commentary: Decomposing with a lot of supposing. Am J Epidemiol 2010;172:1349-51.
54. Imai K, Keele L, Yamamoto T. Identification, inference and sensitivity analysis for causalmediation effects. Stat Sci 2012;25:51-71.
55. Shpitser I. Counterfactual graphical models for longitudinal mediation analysis with unobserved confounding. Cogn Sci 2013;37:1011-35.
56. Joffe MM, Byrne C, Colditz GA. Postmenopausal hormone use, screening, and breast cancer: characterization and control of a bias. Epidemiology 2001;12:429-38.
57. Bollen KA, Pearl J. Eight myths about causality and structural equation models. In: Handbook of Causal Analysis for Social Research. New York, NY: Springer, 2013.
58. VanderWeele TJ, Hernán MA. Causal effects and natural laws: Towards a conceptualization of causal counterfactuals for nonmanipulable exposures, with applications to the effects of race and sex. In: Berzuini C, Dawid AP, Bernardinelli L (eds). Causality: Statistical Perspectives and Applications. Chichester, UK: Wiley, 2012.