Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness

详细信息    查看全文

• 作者：Sander Greenland ; Mohammad Ali Mansournia
• 关键词：Causal graphs ; Confounding ; Directed acyclic graphs ; Ignorability ; Inverse probability weighting ; Unfaithfulness
• 刊名：European Journal of Epidemiology
• 出版年：2015
• 出版时间：October 2015
• 年：2015
• 卷：30
• 期：10
• 页码：1101-1110
• 全文大小：513 KB
• 参考文献：1.Glymour MM, Greenland S. Causal diagrams. In: Rothman KJ, Greenland S, Lash T, editors. Modern epidemiology. 3rd ed. Philadelphia: Lippincott Williams & Wilkins; 2008. p. 183–209.
  2.Pearl J. Causality. 2nd ed. New York: Cambridge University Press; 2009.CrossRef
  3.Hernán MA, Robins JM. Causal inference. London: Chapman & Hall/CRC; 2015.
  4.Greenland S, Robins JM. Identifiability, exchangeability, and epidemiological confounding. Int J Epidemiol. 1986;15:413–9.CrossRef PubMed
  5.Greenland S, Robins JM, Pearl J. Confounding and collapsibility in causal inference. Stat Sci. 1999;14:29–46.CrossRef
  6.Greenland S, Robins JM. Identifiability, exchangeability and confounding revisited. Epidemiol Perspect Innov. 2009;6:4.PubMedCentral CrossRef PubMed
  7.Rothman KJ. Epidemiologic methods in clinical trials. Cancer. 1977;39:1771–5.CrossRef PubMed
  8.Greenland S, Neutra RR. Control of confounding in the assessment of medical technology. Int J Epidemiol. 1980;9:361–7.CrossRef PubMed
  9.Matthews JNS. An introduction to randomised controlled clinical trials. 2nd ed. Boca Raton: Chapman & Hall/CRC; 2006.CrossRef
  10.Robins JM. Confidence intervals for causal parameters. Stat Med. 1988;7:773–85.CrossRef PubMed
  11.Rosenbaum PR. Model-based direct adjustment. J Am Stat Assoc. 1987;82:387–94.CrossRef
  12.Senn SJ. Testing for baseline balance in clinical trials. Stat Med. 1994;13:1715–26.CrossRef PubMed
  13.Robins JM, Scheines R, Spirtes P, Wasserman L. Uniform consistency in causal inference. Biometrika. 2003;90:491–515.CrossRef
  14.Spirtes P, Glymour C, Scheines R. Causation, prediction, and search. 2nd ed. Cambridge: MIT Press; 2001.
  15.Mansournia MA, Hernán MA, Greenland S. Matched designs and causal diagrams. Int J Epidemiol. 2013;42:860–9.PubMedCentral CrossRef PubMed
  16. Mansournia MA, Greenland S. The relation of collapsibility and confounding to faithfulness and stability. Epidemiology. 2015;26: in press.
  17.Cox DR, Hinkley DV. Theoretical statistics. New York: Chapman and Hall; 1974.CrossRef
  18.Greenland S. Randomization, statistics, and causal inference. Epidemiology. 1990;1:421–9.CrossRef PubMed
  19.Greenland S. On the logical justification of conditional tests for two-by-two contingency tables. Am Stat. 1991;45:248–51.
  20.Rosenbaum PR. Observational studies. 2nd ed. New York: Springer; 2002.CrossRef
  21.Richardson TS, Robins JM. Single world intervention graphs: a primer. Second UAI Workshop on Causal Structure Learning, Bellevue, Washington, 2013.
  22.Robins JM, Richardson TS. Alternative graphical causal models and the identification of direct effects. In: Shrout P, Keyes K, Ornstein K, editors. Causality and psychopathology: finding the determinants of disorders and their cures. Oxford: Oxford University Press; 2011. p. 1–52.
  23.Greenland S, Pearl J, Robins JM. Causal diagrams for epidemiologic research. Epidemiology. 1999;10:37–48.CrossRef PubMed
  24.Greenland S, Pearl J. Causal diagrams. In: Boslaugh S, editor. Encyclopedia of epidemiology. Thousand Oaks: Sage Publications; 2008. p. 149–56.
  25.Pearl J. Causal diagrams for empirical research. Biometrika. 1995;82:669–710.CrossRef
  26.Rubin DB. Practical implications of modes of statistical inference for causal effects and the critical role of the assignment mechanism. Biometrics. 1991;47:1213–34.CrossRef PubMed
  27.Rosenbaum P, Rubin DB. The central role of the propensity score in observational studies for causal effects. Biometrika. 1983;70:41–55.CrossRef
  28.Ho DE, Imai K, King G, Stuart EA. Matching as nonparametric preprocessing for reducing model dependence in parametric causal inference. Polit Anal. 2007;15:199–236.CrossRef
  29.Stuart EA. Matching methods for causal inference: a review and a look forward. Stat Sci. 2010;25:1–21.PubMedCentral CrossRef PubMed
  30.Waernbaum I. Model misspecification and robustness in causal inference: comparing matching with doubly robust estimation. Stat Med. 2012;31:1572–81.CrossRef PubMed
  31.Imai K, Ratkovic M. Covariate balancing propensity score. J R Stat Soc Ser B. 2014;76:243–63.CrossRef
  32.Kurth T, Walker AM, Glynn RJ, Chan KA, Gaziano JM, Berger K, Robins JM. Results of multivariable logistic regression, propensity matching, propensity adjustment, and propensity-based weighting under conditions of nonuniform effect. Am J Epidemiol. 2006;163:262–70.CrossRef PubMed
  33.Fisher RA. The design of experiments. Edinburgh: Oliver and Boyd; 1935.
  34.Robins JM, Morgenstern H. The foundations of confounding in epidemiology. Comp Math Appl. 1987;14:869–916.CrossRef
  35.Senn S. Seven myths of randomisation in clinical trials. Stat Med. 2013;32:1439–50.CrossRef PubMed
  36.Rosenberger WF, Lachin JM. Randomization in clinical trials: theory and practice. New York: Wiley; 2002.CrossRef
  37.Friedman LM, Furberg CD, DeMets DL. Fundamentals of clinical trials. 4th ed. New York: Springer; 2010.CrossRef
  38.Chow SC, Liu JP. Design and analysis of clinical trials. 2nd ed. Hoboken: Wiley; 2004.
  39.Lauritzen SL, Dawid AP, Larsen BN, Leimar HG. Independence properties of directed Markov fields. Networks. 1990;20:491–505.CrossRef
  40.Robins JM, Hernán MA, Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology. 2000;11:550–60.CrossRef PubMed
  41.Sato T, Matsuyama Y. Marginal structural models as a tool for standardization. Epidemiology. 2003;14:680–6.CrossRef PubMed
  42.Kang JD, Schafer JL. Demystifying double robustness: a comparison of alternative strategies for estimating a population mean from incomplete data (with discussion). Stat Sci. 2007;22:523–80.CrossRef
  43.Cochran WG. Sampling techniques. 3rd ed. New York: Wiley; 1977.
  44.Sjölander A, Greenland S. Ignoring the matching variables in cohort studies—When is it valid and why? Stat Med. 2013;32:4696–708.CrossRef PubMed
  45.Greenland S, Pearl J. Adjustments and their consequences—collapsibility analysis using graphical models. Int Stat Rev. 2011;79:401–26.CrossRef
  46.Gail MH. Adjusting for covariates that have the same distribution in exposed and unexposed cohorts. In: Moolgavkar SH, Prentice RL, editors. Modern statistical methods in chronic disease epidemiology. New York: Wiley; 1986. p. 3–18.
  47.Robinson LD, Jewell NP. Some surprising results about covariate adjustment in logistic regression. Int Stat Rev. 1991;59:227–40.CrossRef
  48.Neuhaus J, Jewell NP. A geometric approach to assess bias due to omitted covariates in generalized linear models. Biometrika. 1993;80:807–15.CrossRef
  49.Robinson LD, Dorroh JR, Lien D, Tiku ML. The effects of covariate adjustment in generalized linear models. Commun Stat Theory Methods. 1998;27:1653–75.CrossRef
  
• 作者单位：Sander Greenland (1) (2)
  Mohammad Ali Mansournia (3)
  
  1. Department of Epidemiology, UCLA School of Public Health, University of California, Los Angeles, CA, USA
  2. Department of Statistics, UCLA College of Letters and Science, University of California, Los Angeles, CA, USA
  3. Department of Epidemiology and Biostatistics, School of Public Health, Tehran University of Medical Sciences, PO Box: 14155-6446, Tehran, Iran
  
• 刊物类别：Medicine
• 刊物主题：Medicine & Public Health
  Epidemiology
  Public Health
  Infectious Diseases
  Cardiology
  Oncology
  
• 出版者：Springer Netherlands
• ISSN：1573-7284

文摘

We describe how ordinary interpretations of causal models and causal graphs fail to capture important distinctions among ignorable allocation mechanisms for subject selection or allocation. We illustrate these limitations in the case of random confounding and designs that prevent such confounding. In many experimental designs individual treatment allocations are dependent, and explicit population models are needed to show this dependency. In particular, certain designs impose unfaithful covariate-treatment distributions to prevent random confounding, yet ordinary causal graphs cannot discriminate between these unconfounded designs and confounded studies. Causal models for populations are better suited for displaying these phenomena than are individual-level models, because they allow representation of allocation dependencies as well as outcome dependencies across individuals. Nonetheless, even with this extension, ordinary graphical models still fail to capture distinctions between hypothetical superpopulations (sampling distributions) and observed populations (actual distributions), although potential-outcome models can be adapted to show these distinctions and their consequences.