Abstract
Background
When assessing the association between a factor X and a subsequent outcome Y in observational studies, the question that arises is what are the variables to adjust for to reduce bias due to confounding for causal inference on the effect of X on Y. Disregarding such factors is often a source of overestimation because these variables may affect both X and Y. On the other hand, adjustment for such variables can also be a source of underestimation because such variables may be the causal consequence of X and part of the mechanism that leads from X to Y.
Methods
In this paper, we present a simple method to compute control variables in the presence of age at onset data on both X and a set of other variables. Using these age at onset data, control variables are computed that adjust only for conditions that occur prior to X. This strategy can be used in prospective as well as in survival analysis. Our method is motivated by an argument based on the counterfactual model of a causal effect.
Results
The procedure is exemplified by examining of the relation between panic attack and the subsequent incidence of MDD.
Conclusions
The results reveal that the adjustment for all other variables, irrespective of their temporal relation to X, can yield a false negative result (despite unconsidered confounders and other sources of bias).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
American Psychiatric Association (1994) Diagnostic and statistical manual of mental disorders, 4th edn. Washington DC
Cox DR, Wermuth N (1996) Multivariate dependencies. Models, analyses and interpretation. Chapman and Hall, London
Diggle PJ, Heagerty P, Liang K-Y, Zeger SL (2002) Analysis of longitudinal data, 2nd edition, chap. 12. Oxford University Press, Oxford
Golub A, Johnson BD, Labouvie E (2000) On correcting biases in self-reports of age at first substance use with repeated cross-section analysis. J Quant Criminol 16:45–68
Greenland S (2005) Multiple-bias modelling for analysis of observational data. J Roy Stat Soc, Series A 168:267–291
Greenland S, Pearl J, Robins JM (1999) Causal diagrams for epidemiological research. Epidemiology 10:37–48
Höfler M, Pfister H, Lieb R, Wittchen HU (2005). The use of statistical weights to account for non-response and drop-out. Soc Psychiatry Psychiatr Epidemiol 40:291–299
Johnson RA, Gerstein DR, Rasinski KA (1998) Adjusting survey estimates for response bias. Public Opin Q 62:354–377
Lieb R, Isensee B, Sydow von K, Wittchen HU (2000) The early developmental stages of the psychopathology study (EDSP): a methodological update. Eur Addict Res 6:170–182
Light RJ, Singer JD, Willett JB (1990) By design: planning research on higher education. Harvard University Press, Cambridge, MA
Little RJA, Rubin DB (2000) Causal effects in clinical and epidemiological studies via potential outcomes: concepts and analytical approaches. Annu Rev Public Health 21:121–145
Maclure M, Schneeweiß S (2001) Causation of bias: the episcope. Epidemiology 12:114–122
Parra GP, O'Neill SE, Sher KJ (2003) Reliability of self-reported age of substance involvement onset. Psychol Addict Behav 3:211–218
Pearl J (1995) Causal diagrams for empirical research. Biometrika 82:669–710
Pearl J (2000) Causality-models, reasoning and inference. Cambridge University Press, Cambridge
Robins JM, Blevins D, Ritter G, Wulfsohn M (1992) G-estimation of the effect of prophylaxis therapy for pneumocystis carinii pneumonia on the survival of AIDS patients. Epidemiology 13:319–336
Robins JM, Hernan MA, Brumback B (2000) Marginal structural models and causal inference in epidemiology. Epidemiology 11:550–560
Rosenbaum PR (2002) Observational studies, 2nd edn. Springer, Berlin Heidelberg New York
Rosenbaum PR, Rubin DB (1983) The central role of the propensity score in observational studies for causal inference. Biometrika 70:41–55
Royall RM (1986) Model robust confidence intervals using maximum likelihood estimators. Int Stat Rev 54:221–226
Rubin DB, Schenker N (1991) Multiple imputation in health care databases: an overview and some applications. Stat Med 10:585–598
StataCorp. (2003) Stata statistical software: release 8.0. Stata Corporation, College Station, TX
Trichtler D (1999) Reasoning about data with directed graphs. Stat Med 18:2067–2076
WHO (1997) Composite international diagnostic interview (CIDI, version 2.1). World Health Organisation, Geneva
Wittchen HU, Pfister H (eds) (1997) DIA-X-Interviews. Manual für Screening-Verfahren und Interview; Interviewheft Längsschnittsuntersuchung (DIA-X Lifetime); Ergänzungsheft (DIA-X Lifetime); Interviewheft Querschnittsuntersuchung (DIA-X 12 Monate); Ergänzungsheft (DIA-X 12 Monate); PC-Programm zur Durchführung der Interviews (Längs- und Querschnittsuntersuchung); Auswertungsprogramm, Frankfurt, Swets & Zeitlinger
Wittchen HU, Burke JD, Semler G, Pfister H, Cranach Von M, Zaudig M (1989) Recall and dating of psychiatric symptoms. Arch Gen Psychiatry 46:437–443
Wittchen HU, Perkonigg A, Lachner G, Nelson CB (1998) Early developmental stages of psychopathology study (EDSP): objectives and design. Eur Addict Res 4:18–27
Acknowledgements
This work is part of the Early Developmental Stages of Psychopathology study and is funded by the German Ministry of Research and Technology, project numbers 01 EB 9405/6 and 01 EB 9901/6. The principal investigators are Dr. Hans-Ulrich Wittchen and Dr. Roselind Lieb. Current or former staff members of the group are Dr. Kirsten von Sydow, Dr. Gabriele Lachner, Dr. Axel Perkonigg, Dr. Peter Schuster, Dr. Franz Gander, Dipl.-Stat. Michael Höfler, and Dipl.-Psych. Holger Sonntag, as well as Mag. Phil. Esther Beloch, Dr. Martina Fuetsch, Dipl.-Psych. Elzbieta Garczynski, Dipl.-Psych. Alexandra Holly, Dr. Barbara Isensee, Dr. Marianne Mastaler, Dr. Chris Nelson, Dipl.-Inf. Hildegard Pfister, Dr. Victoria Reed, Dipl.-Psych. Andrea Schreier, Dipl.-Psych. Dilek Türk, Dipl.-Psych. Antonia Vossen, Ursula Wunderlich, and Dr. Petra Zimmerman. Scientific advisors are Dr. Jules Angst (Zurich, Switzerland), Dr. Jürgen Margraf (Basel, Switzerland), Dr. Günther Esser (Potsdam, Germany), Dr. Kathleen Merikangas (NIMH, Bethesda, Md.) Dr. Ron Kessler (Harvard, Boston), and Dr. Jim van Os (Maastricht).
Author information
Authors and Affiliations
Corresponding author
Additional information
An erratum to this article can be found at http://dx.doi.org/10.1007/s00127-005-1006-y.
Rights and permissions
About this article
Cite this article
Höfler, M., Brueck, T., Lieb, R. et al. Calculating control variables with age at onset data to adjust for conditions prior to exposure. Soc Psychiat Epidemiol 40, 731–736 (2005). https://doi.org/10.1007/s00127-005-0944-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00127-005-0944-8