Combining directed acyclic graphs and the change-in-estimate procedure as a novel approach to adjustment-variable selection in epidemiology

BMC Medical Research Methodology

Antoine Flahault⁴  Christian Verger³  Thierry Lobbedez²  Basile Chaix¹  David Evans³ 

[1] UPMC-Sorbonne Université, Paris, France;Nephrology Department, CHU Clemenceau, Caën, France;Registre de Dialyse Péritonéale de Langue Française, Pontoise, France;EHESP School of Public Health, Rennes-Sorbonne Paris Cité, Paris, France

关键词: Peritoneal dialysis;    Change-in-estimate;    Adjustment-variable selection;    Directed acyclic graph;   

Others  :  1126600
DOI  :  10.1186/1471-2288-12-156

 received in 2012-03-12, accepted in 2012-10-01,  发布年份 2012

【 摘 要 】

Background

Directed acyclic graphs (DAGs) are an effective means of presenting expert-knowledge assumptions when selecting adjustment variables in epidemiology, whereas the change-in-estimate procedure is a common statistics-based approach. As DAGs imply specific empirical relationships which can be explored by the change-in-estimate procedure, it should be possible to combine the two approaches. This paper proposes such an approach which aims to produce well-adjusted estimates for a given research question, based on plausible DAGs consistent with the data at hand, combining prior knowledge and standard regression methods.

Methods

Based on the relationships laid out in a DAG, researchers can predict how a collapsible estimator (e.g. risk ratio or risk difference) for an effect of interest should change when adjusted on different variable sets. Implied and observed patterns can then be compared to detect inconsistencies and so guide adjustment-variable selection.

Results

The proposed approach involves i. drawing up a set of plausible background-knowledge DAGs; ii. starting with one of these DAGs as a working DAG, identifying a minimal variable set, S, sufficient to control for bias on the effect of interest; iii. estimating a collapsible estimator adjusted on S, then adjusted on S plus each variable not in S in turn (“add-one pattern”) and then adjusted on the variables in S minus each of these variables in turn (“minus-one pattern”); iv. checking the observed add-one and minus-one patterns against the pattern implied by the working DAG and the other prior DAGs; v. reviewing the DAGs, if needed; and vi. presenting the initial and all final DAGs with estimates.

Conclusion

This approach to adjustment-variable selection combines background-knowledge and statistics-based approaches using methods already common in epidemiology and communicates assumptions and uncertainties in a standardized graphical format. It is probably best suited to areas where there is considerable background knowledge about plausible variable relationships. Researchers may use this approach as an additional tool for selecting adjustment variables when analyzing epidemiological data.

【 授权许可】

   
2012 Evans et al.; licensee BioMed Central Ltd.

【 图 表 】

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

Figure 12.

Figure 13.

Figure 14.

【 参考文献 】

• [1]Greenland S, Pearl J, Robins JM: Causal diagrams for epidemiologic research. Epidemiology 1999, 10:37-48.
• [2]Glymour M, Greenland S: Causal diagrams. In Modern epidemiology. 3rd edition. Philadelphia, PA: Lippincott Williams &Wilkins; 2008:183-209.
• [3]Pearl J: Causality: models, reasoning, and inference. 2nd edition. Cambridge: Cambridge University Press; 2009.
• [4]Greenland S: Modeling and variable selection in epidemiologic analysis. Am J Public Health 1989, 79:340-349.
• [5]Vansteelandt S, Bekaert M, Claeskens G: On model selection and model misspecification in causal inference. Stat Methods Med Res 2012, 21:7-30.
• [6]Weng HY, Hsueh YH, Messam LLM, Hertz-Picciotto I: Methods of covariate selection: directed acyclic graphs and the change-in-estimate procedure. Am J Epidemiol 2009, 169:1182-1190.
• [7]Spirtes P, Glymour C, Scheines R: Causation, prediction, and search, second edition. 2nd edition. Cambridge: The MIT Press; 2001.
• [8]Glymour C, Cooper G (Eds): Rejoinder to glymour and spirtes In Computation, causation, and discovery. Cambridge MA: AAAI Press/The MIT Press; 1999:333-342.
• [9]Leiss JK: Management practices and risk of occupational blood exposure in U.S. Paramedics: Non-intact skin exposure. Ann Epidemiol 2009, 19:884-890.
• [10]Nyitray AG, Smith D, Villa L, Lazcano Ponce E, Abrahamsen M, Papenfuss M, Giuliano AR: Prevalence of and risk factors for anal human papillomavirus infection in Men Who have Sex with women: a cross national study. J Infect Dis 2010, 201:1498-1508.
• [11]Rod NH, Vahtera J, Westerlund H, Kivimaki M, Zins M, Goldberg M, Lange T: Sleep disturbances and cause-specific mortality: results from the GAZEL cohort study. Am J Epidemiol 2010, 173:300-309.
• [12]Edmonds A, Yotebieng M, Lusiama J, Matumona Y, Kitetele F, Napravnik S, Cole SR, Van Rie A, Behets F: The effect of highly active antiretroviral therapy on the survival of HIV-infected children in a resource-deprived setting: a cohort study. PLoS Med 2011, 8:e1001044.
• [13]Leval A, Sundström K, Ploner A, Arnheim Dahlström L, Widmark C, Sparén P: Assessing perceived risk and STI prevention behavior: a national population-based study with special reference to HPV. PLoS One 2011, 6:e20624.
• [14]Gaskins AJ, Mumford SL, Rovner AJ, Zhang C, Chen L, Wactawski-Wende J, Perkins NJ, Schisterman EF, for the BioCycle Study Group: Whole grains Are associated with serum concentrations of high sensitivity C-reactive protein among premenopausal women. J Nutr 2010, 140:1669-1676.
• [15]Gaskins AJ, Mumford SL, Zhang CL, Wactawski-Wende J, Hovey KM, Whitcomb BW, Howards PP, Perkins NJ, Yeung E, Schisterman EF: Effect of daily fiber intake on reproductive function: the BioCycle study. Am J Clin Nutr 2009, 90:1061-1069.
• [16]Pearl J, Paz A: Confounding equivalence in observational studies (or, when are two measurements equally valuable for effect estimation?). In Proceedings of the twenty-sixth conference on uncertainty in artificial intelligence. Corvallis: AUAI; 2010:433-441.
• [17]Greenland S, Pearl J: Adjustments and their consequences - Collapsibility analysis using graphical models. Int Stat Rev 2011, 79:401-426.
• [18]Shrier I, Platt RW: Reducing bias through directed acyclic graphs. BMC Med Res Methodol 2008, 8:70. BioMed Central Full Text
• [19]Fleischer NL, Diez Roux AV: Using directed acyclic graphs to guide analyses of neighbourhood health effects: an introduction. J Epidemiol Community Health 2008, 62:842-846.
• [20]Richiardi L, Barone-Adesi F, Merletti F, Pearce N: Using directed acyclic graphs to consider adjustment for socioeconomic status in occupational cancer studies. J Epidemiol Community Health 2008, 62:e14.
• [21]Vanderweele TJ, Shpitser I: A New criterion for confounder selection. Biometrics 2011, 67:1406-1413.
• [22]Tsai C-L, Camargo CA Jr: Methodological considerations, such as directed acyclic graphs, for studying “acute on chronic” disease epidemiology: chronic obstructive pulmonary disease example. J Clin Epidemiol 2009, 62:982-990.
• [23]Dawid AP: Beware of the DAG! Journal of Machine Learning Research Workshop and Conference Proceedings 2010, 6:59-86.
• [24]Dawid AP: Influence diagrams for causal modelling and inference. Int Stat Rev 2002, 70:161-189.
• [25]Petersen ML, Sinisi SE, van der Laan MJ: Estimation of direct causal effects. Epidemiology 2006, 17:276-284.
• [26]Robins JM, Greenland S: Identifiability and exchangeability for direct and indirect effects. Epidemiology 1992, 3:143-155.
• [27]Shpitser I, Vanderweele TJ: A complete graphical criterion for the adjustment formula in mediation analysis. Int J Biostat 2011, 7:16.
• [28]Shpitser I, VanderWeele TJ, Robins JM: On the validity of covariate adjustment for estimating causal effects. Proceedings of the Twenty-Sixth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-10). Corvallis: AUAI; 2010:527-536.
• [29]Greenland S, Robins JM, Pearl J: Confounding and collapsibility in causal inference. Stat Sci 1999, 14:29-46.
• [30]Breitling L: A suite of R functions for directed acyclic graphs. Epidemiology 2010, 21:586-587.
• [31]Knueppel S, Stang A: DAG program: identifying minimal sufficient adjustment sets. Epidemiology 2010, 21:159.
• [32]Rothman K, Greenland S, Lash T: Modern epidemiology. 3rd edition. Philadelphia: Lipincott Williams &Wilkins; 2008.
• [33]Kaufman JS: Marginalia: comparing adjusted effect measures. Epidemiology 2010, 21:490-493.
• [34]Greenland S: Absence of confounding does not correspond to collapsibility of the rate ratio or rate difference. Epidemiology 1996, 7:498-501.
• [35]Miettinen OS, Cook EF: Confounding - essence and detection. Am J Epidemiol 1981, 114:593-603.
• [36]Austin PC, Laupacis A: A tutorial on methods to estimating clinically and policy-meaningful measures of treatment effects in prospective observational studies: a review. Int J Biostat 2011, 7(1):6.
• [37]Austin PC: Absolute risk reductions, relative risks, relative risk reductions, and numbers needed to treat can be obtained from a logistic regression model. J Clin Epidemiol 2010, 63:2-6.
• [38]Gehrmann U, Kuss O, Wellmann J, Bender R: Logistic regression was preferred to estimate risk differences and numbers needed to be exposed adjusted for covariates. J Clin Epidemiol 2010, 63:1223-1231.
• [39]McNutt L-A, Wu C, Xue X, Hafner JP: Estimating the relative risk in cohort studies and clinical trials of common outcomes. Am J Epidemiol 2003, 157:940-943.
• [40]Maldonado G, Greenland S: Simulation study of confounder-selection strategies. Am J Epidemiol 1993, 138:923-936.
• [41]Hernán MA, Cole SR: Invited Commentary: causal diagrams and measurement bias. Am J Epidemiol 2009, 170:959-962.
• [42]Brenner H: Bias due to non-differential misclassification of polytomous confounders. J Clin Epidemiol 1993, 46:57-63.
• [43]Ogburn EL, VanderWeele TJ: On the nondifferential misclassification of a binary confounder. Epidemiology 2012, 23:433-439.
• [44]Greenland S: Intuitions, simulations, theorems: the role and limits of methodology. Epidemiology 2012, 23:440-442.
• [45]Vanderweele TJ, Ogburnb EL: Theorems, proofs, examples, and rules in the practice of epidemiology. Epidemiology 2012, 23:443-445.
• [46]Pearl J: On a class of bias-amplifying covariates that endanger effect estimates. Proceedings of the twenty-sixth conference on uncertainty in artificial intelligence, 417--424. AUAI, Corvallis, OR, 2010 2010, 417-424. Technical report (R-356)
• [47]Wooldridge J: Should instrumental variables be used as matching variables? Tech. Rep. Michigan state university 2006.
• [48]Myers JA, Rassen JA, Gagne JJ, Huybrechts KF, Schneeweiss S, Rothman KJ, Joffe MM, Glynn RJ: Effects of adjusting for instrumental variables on bias and precision of effect estimates. Am J Epidemiol 2011, 174:1213-1222.
• [49]Pearl J: Invited commentary: understanding bias amplification. Am J Epidemiol 2011, 174:1223-1227.
• [50]Rassen JA, Brookhart MA, Glynn RJ, Mittleman MA, Schneeweiss S: Instrumental variables I: instrumental variables exploit natural variation in nonexperimental data to estimate causal relationships. J Clin Epidemiol 2009, 62:1226-1232.
• [51]Lobbedez T, Touam M, Evans D, Ryckelynck J-P, Knebelman B, Verger C: Peritoneal dialysis in polycystic kidney disease patients. Report from the French peritoneal dialysis registry (RDPLF). Nephrol Dial Transplant 2011, 26:2332-2339.
• [52]Cheung YB: A modified least-squares regression approach to the estimation of risk difference. Am J Epidemiol 2007, 166:1337-1344.
• [53]Groenwold RHH, Hak E, Hoes AW: Quantitative assessment of unobserved confounding is mandatory in nonrandomized intervention studies. J Clin Epidemiol 2009, 62:22-28.
• [54]Robins JM: Data, design, and background knowledge in etiologic inference. Epidemiology 2001, 12:313-320.
• [55]Kalisch M, Fellinghauer BAG, Grill E, Maathuis MH, Mansmann U, Bühlmann P, Stucki G: Understanding human functioning using graphical models. BMC Med Res Methodol 2010, 10:14. BioMed Central Full Text
• [56]Robinson LD, Jewell NP: Some surprising results about covariate adjustment in logistic-regression models. Int Stat Rev 1991, 59:227-240.
• [57]Pearl J, Bareinboim E: Transportability across studies: a formal approach. Technical report R-372 2011.
• [58]VanderWeele TJ, Robins JM: Signed directed acyclic graphs for causal inference. Journal of the Royal Statistical Society Series B-Statistical Methodology 2009, 72:111-127.
• [59]VanderWeele TJ, Robins JM: Directed acyclic graphs, sufficient causes, and the properties of conditioning on a common effect. Am J Epidemiol 2007, 166:1096-1104.