Identifiability, exchangeability and confounding revisited

Epidemiologic Perspectives and Innovations

Volumn 6, Issue 1, 2009, Pages

  Greenland, Sander ^a   Robins, James M ^b  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b HARVARD SCHOOL OF PUBLIC HEALTH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BIOSTATISTICS; EPIDEMIOLOGY; MATHEMATICAL MODEL; RANDOMIZATION; REVIEW; STATISTICAL PARAMETERS; STATISTICAL SIGNIFICANCE;

EID: 70349130001     PISSN: None     EISSN: 17425573     Source Type: Journal    
DOI: 10.1186/1742-5573-6-4     Document Type: Review

References (87)

1. Identifiability, exchangeability, and epidemiological confounding. S Greenland JM Robins, Int J Epidemiol 1986 15 413 419 10.1093/ije/15.3.413 3771081
2. Confounding and collapsibility in causal inference. S Greenland JM Robins J Pearl, Statistical Science 1999 14 29 46 10.1214/ss/1009211805
3. Estimating causal effects. G Maldonado S Greenland, Int J Epidemiol 2002 31 422 429 10.1093/ije/31.2.422 11980807
4. Confounding in health research. S Greenland H Morgenstern, Annu Rev Public Health 2001 22 189 212 10.1146/annurev.publhealth.22.1.189 11274518
5. The history of confounding. JP Vandenbroucke, History of Epidemiological Methods and Concepts Basel, Switzerland: Birkhaser Verlag, Morabia A, 2004 313 326
6. Confounding. S Greenland, Encyclopedia of Epidemiology Thousand Oaks, CA: Sage Publications, Boslaugh S, 2007
7. On the epidemiologic notion of confounding and confounder identification. M Nurminen, Scand J Work Environ Health 1997 23 64 68 9098915
8. JS Mill, A System of Logic, Ratiocinative and Inductive (1843 edition, reprinted in 1956) London: Longmans, Green, and Company 1956
9. Notes on the theory of association of attributes in statistics. GU Yule, Biometrika 1903 2 121 134 10.1093/biomet/2.2.121
10. Smoking and lung cancer: recent evidence and a discussion of some questions. J Cornfield W Haenszel EC Hammond AM Lilienfeld MB Shimkin EL Wynder, J Natl Cancer Inst 1959 22 173 203 13621204
11. Some statistical problems in research design. L Kish, Am Sociol Rev 1959 24 328 338 10.2307/2089381
12. H Blalock, Causal inference in nonexperimental research Chapel Hill, NC: University of North Carolina Press 1964
13. B MacMahon TF Pugh, Epidemiology: Principles and Methods Boston: Little, Brown and Company 1970
14. M Susser, Causal Thinking in the Health Sciences New York City: Oxford University Press 1973
15. DR Cox, Planning of Experiments New York City: John Wiley and Sons Inc 1958
16. Statistical methods in cancer research. Vol I: the analysis of case-control data Lyon, France: International Agency for Research on Cancer (IARC) 1980
17. Control of confounding in the assessment of medical technology. S Greenland R Neutra, Int J Epidemiol 1980 9 361 367 7203778
18. JJ Schlesselman, Case-Control Studies: Design, Conduct, Analysis Oxford: Oxford University Press 1982
19. On the application of probability theory to agricultural experiments. Essay on principles. Section 9 (1923). J Neyman, Stat Sci 1990 5 465 480
20. Epidemiologic methods in clinical trials. KJ Rothman, Cancer 1977 39 1771 1775 10.1002/1097-0142(197704)39:4+<1771::AID-CNCR2820390803>3.0.CO;2-2 322841
21. Confounding: essence and detection. OS Miettinen EF Cook, Am J Epidemiol 1981 114 593 603 7304589
22. RA Berk, Regression Analysis: A Constructive Critique Newbury Park, CA: Sage 2004
23. An overview of methods for causal inference from observational studies. S Greenland, Applied Bayesian modeling and causal inference from an incomplete-data perspective New York City: John Wiley & Sons, Gelman A, Meng XL, 2004
24. Measures of effect and association. S Greenland KJ Rothman TL Lash, Modern Epidemiology Philadelphia, PA: Lippincott Williams & Wilkins, Rothman KJ, Greenland S, Lash TL, 2008
25. J Pearl, Causality Cambridge: Cambridge University Press 2 2009
26. Causal analysis in the health sciences. S Greenland, Journal of the American Statistical Association 2000 95 286 289 10.2307/2669548
27. On the z-test in randomized blocks and Latin squares. BL Welch, Biometrika 1937 29 21 52
28. Randomization models for the matched and unmatched 2 × 2 tables. JB Copas, Biometrika 1973 60 467 476
29. Estimating causal effects of treatments in randomized and nonrandomized treatments. DB Rubin, J Educ Psychol 1974 66 688 701 10.1037/h0037350
30. Bayesian inference for causal effects: the role of randomization. DB Rubin, Ann Stat 1978 6 34 58 10.1214/aos/1176344064
31. The randomization analysis of a generalized randomized block design. M Wilk, Biometrika 1955 42 70 79
32. PR Rosenbaum, Observational Studies New York City: Springer 2 2002
33. Randomization, statistics, and causal inference. S Greenland, Epidemiology 1990 1 421 429 10.1097/00001648-199011000-00003 2090279
34. On the logical justification of conditional tests for two-by-two-contingency tables. S Greenland, The American Statistician 1991 45 248 251 10.2307/2684304
35. Interpretation and choice of effect measures in epidemiologic analyses. S Greenland, Am J Epidemiol 1987 125 761 768 3551588
36. Epidemiologic measures and policy formulation: lessons from potential outcomes. S Greenland, Emerg Themes Epidemiol 2005 2 5 10.1186/1742-7622-2-5 15921514
37. Invited commentary: hypothetical interventions to define causal effects - afterthought or prerequisite? MA Hernan, Am J Epidemiol 2005 162 618 620 10.1093/aje/kwi255 16120710
38. Statistics and causal inference (with discussion). PW Holland, J Am Stat Assoc 1986 81 945 970 10.2307/2289064
39. A graphical approach to the identification and estimation of causal parameters in mortality studies with sustained exposure periods. J Robins, J Chronic Dis 1987 40 Suppl 2 139S 161S 10.1016/S0021-9681(87)80018-8 3667861
40. The role of model selection in causal inference from nonexperimental data. JM Robins S Greenland, Am J Epidemiol 1986 123 392 402 3946386
41. Causal diagrams for epidemiologic research. S Greenland J Pearl JM Robins, Epidemiology 1999 10 37 48 10.1097/00001648-199901000-00008 9888278
42. Causal knowledge as a prerequisite for confounding evaluation: an application to birth defects epidemiology. MA Hernan S Hernandez-Diaz MM Werler AA Mitchell, Am J Epidemiol 2002 155 176 184 10.1093/aje/155.2.176 11790682
43. A structural approach to selection bias. MA Hernan S Hernandez-Diaz JM Robins, Epidemiology 2004 15 615 625 10.1097/01.ede.0000135174.63482.43 15308962
44. Confounding and misclassification. S Greenland JM Robins, Am J Epidemiol 1985 122 495 506 4025298
45. Process analysis: Estimating mediation in treatment evaluations. CM Judd DA Kenny, Evaluation Review 1981 5 602 619 10.1177/0193841X8100500502
46. Identifiability and exchangeability for direct and indirect effects. JM Robins S Greenland, Epidemiology 1992 3 143 155 10.1097/00001648-199203000-00013 1576220
47. Graphs, causality, and structural equation models. J Pearl, Sociological Methods Research 1998 27 226 284 10.1177/0049124198027002004
48. Fallibility in estimating direct effects. SR Cole MA Hernan, Int J Epidemiol 2002 31 163 165 10.1093/ije/31.1.163 11914314
49. Causal Diagrams. S Greenland J Pearl, Encyclopedia of Epidemiology Thousand Oaks, CA: Sage Publications, Boslaugh S, 2007 149 156
50. Causal diagrams. MM Glymour S Greenland, Modern Epidemiology Philadelphia, PA: Lippincott Williams & Wilkins, Rothman KJ, Greenland S, Lash TL, 2008
51. Causal diagrams for empirical research. J Pearl, Biometrika 1995 82 669 710 10.1093/biomet/82.4.669
52. Quantifying biases in causal models: classical confounding vs collider-stratification bias. S Greenland, Epidemiology 2003 14 300 306 10.1097/00001648-200305000-00009 12859030
53. Invited commentary: variable selection versus shrinkage in the control of multiple confounders. S Greenland, Am J Epidemiol 2008 167 523 529 10.1093/aje/kwm355 18227100
54. Comment: Graphical models, causality, and intervention. J Pearl, Stat Sci 1993 8 266 269 10.1214/ss/1177010894
55. The foundations of confounding in epidemiology. JM Robins H Morgenstern, Comp Math Appl 1987 14 869 916 10.1016/0898-1221(87)90236-7
56. B Ostle, Statistics in Research Ames, Iowa: Iowa State University Press 2 1963
57. The University Group Diabetes Program. A further statistical analysis of the mortality findings. J Cornfield, JAMA 1971 217 1676 1687 10.1001/jama.217.12.1676 4937386
58. Recent methodological contributions to clinical trials. J Cornfield, Am J Epidemiol 1976 104 408 421 788503
59. Testing for baseline balance in clinical trials. S Senn, Stat Med 1994 13 1715 1726 10.1002/sim.4780131703 7997705
60. Estimating exposure effects by modelling the expectation of exposure conditional on confounders. JM Robins SD Mark WK Newey, Biometrics 1992 48 479 495 10.2307/2532304 1637973
61. RA Fisher, The Design of Experiments Edinburgh, Scotland: Oliver and Boyd 1935
62. Confidence intervals for causal parameters. JM Robins, Stat Med 1988 7 773 785 10.1002/sim.4780070707 3406605
63. B de Finetti, The Theory of Probability New York: John Wiley & Sons 1974 I
64. Problems due to small samples and sparse data in conditional logistic regression analysis. S Greenland JA Schwartzbaum WD Finkle, Am J Epidemiol 2000 151 531 539 10707923
65. False models and post-data model construction. EE Leamer, J Am Stat Assoc 1974 69 122 131 10.2307/2285510
66. When should epidemiologic regressions use random coefficients? S Greenland, Biometrics 2000 56 915 921 10.1111/j.0006-341X.2000.00915.x 10985237
67. The performance of random coefficient regression in accounting for residual confounding. P Gustafson S Greenland, Biometrics 2006 62 760 768 10.1111/j.1541-0420.2005.00510.x 16984318
68. Principles of multilevel modelling. S Greenland, Int J Epidemiol 2000 29 158 167 10.1093/ije/29.1.158 10750618
69. Multilevel modeling and model averaging. S Greenland, Scand J Work Environ Health 1999 25 Suppl 4 43 48 10628440
70. Multiple-bias modelling for analysis of observational data. S Greenland, J R Stat Soc Series A 2005 168 267 306 10.1111/j.1467-985X.2004.00349.x (Pubitemid 40427711)
71. Bayesian perspectives for epidemiologic research. III. Bias analysis via missing-data methods. S Greenland, Int J Epidemiol 2009
72. Bayesian sensitivity analysis for unmeasured confounding in observational studies. LC McCandless P Gustafson A Levy, Stat Med 2007 26 2331 2347 10.1002/sim.2711 16998821
73. Relaxation penalties and priors for plausible modeling of nonidentified bias sources. S Greenland, Statistical Science 2010
74. G-estimation of the effect of prophylaxis therapy for Pneumocystis carinii pneumonia on the survival of AIDS patients. JM Robins D Blevins G Ritter M Wulfsohn, Epidemiology 1992 3 319 336 10.1097/00001648-199207000-00007 1637895
75. Marginal structural models and causal inference in epidemiology. JM Robins MA Hernan B Brumback, Epidemiology 2000 11 550 560 10.1097/00001648- 200009000-00011 10955408
76. Correcting for non-compliance in randomized trials using rank preserving structural failure time models. JM Robins AA Tsiatis, Commun Stat 1991 20 2609 2631 10.1080/03610929108830654
77. Adjusting for differential rates of prophylaxis therapy for PCP in high versus low dose AZT treatment arms in an AIDS randomized trial. JM Robins S Greenland, J Am Stat Assoc 1994 89 737 749 10.2307/2290899
78. Estimation of direct causal effects. ML Petersen SE Sinisi MJ van der Laan, Epidemiology 2006 17 276 284 10.1097/01.ede.0000208475.99429.2d 16617276
79. Marginal structural models for the estimation of direct and indirect effects. TJ VanderWeele, Epidemiology 2009 20 18 26 10.1097/EDE.0b013e31818f69ce 19234398
80. Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. JM Robins A Rotnitzky DO Scharfstein, Statistical models in epidemiology New York City: Springer-Verlag, Halloran ME, Berry DA, 1999 1 92
81. Sensitivity analyses for unmeasured confounding assuming a marginal structural model for repeated measures. BA Brumback MA Hernan SJ Haneuse JM Robins, Stat Med 2004 23 749 767 10.1002/sim.1657 14981673
82. Causal directed acyclic graphs and the direction of unmeasured confounding bias. TJ VanderWeele MA Hernan JM Robins, Epidemiology 2008 19 720 728 10.1097/EDE.0b013e3181810e29 18633331
83. Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models. JM Robins Y Ritov, Stat Med 1997 16 285 319 10.1002/(SICI)1097-0258(19970215)16:3<285::AID-SIM535>3.0.CO;2-# 9004398
84. Conditioning, likelihood, and coherence: A review of some foundational concepts. JM Robins L Wasserman, J Am Stat Assoc 2000 95 1340 1346 10.2307/2669784
85. M van der Laan JM Robins, Unified methods for censored longitudinal data and causality New York City: Springer 2003
86. Doubly robust estimation in missing data and causal inference models. H Bang JM Robins, Biometrics 2005 61 962 973 10.1111/j.1541-0420.2005.00377.x 16401269
87. Comment: Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. G Ridgeway D McCaffrey, Stat Sci 2007 22 540 543 10.1214/07-STS227C