A Method for Detection of Residual Confounding in Time-series and Other Observational Studies

Background: A difficult issue in observational studies is assessment of whether important confounders are omitted or misspecified. In this study, we present a method for assessing whether residual confounding is present. Our method depends on availability of an indicator with 2 key characteristics: first, it is conditionally independent (given measured exposures and covariates) of the outcome in the absence of confounding, misspecification, and measurement errors; second, it is associated with the exposure and, like the exposure, with any unmeasured confounders. Methods: We demonstrate the method using a time-series study of the effects of ozone on emergency department visits for asthma in Atlanta. We argue that future air pollution may have the characteristics appropriate for an indicator, in part because future ozone cannot have caused yesterday's health events. Using directed acyclic graphs and specific causal relationships, we show that one can identify residual confounding using an indicator with the stated characteristics. We use simulations to assess the discriminatory ability of future ozone as an indicator of residual confounding in the association of ozone with asthma-related emergency department visits. Parameter choices are informed by observed data for ozone, meteorologic factors, and asthma. Results: In simulations, we found that ozone concentrations 1 day after the emergency department visits had excellent discriminatory ability to detect residual confounding by some factors that were intentionally omitted from the model, but weaker ability for others. Although not the primary goal, the indicator can also signal other forms of modeling errors, including substantial measurement error, and does not distinguish between them. Conclusions: The simulations illustrate that the indicator based on future air pollution levels can have excellent discriminatory ability for residual confounding, although performance varied by situation. Application of the method should be evaluated by considering causal relationships for the intended application, and should be accompanied by other approaches, including evaluation of a priori knowledge.

[1]  C. Granger Testing for causality: a personal viewpoint , 1980 .

[2]  J. Robins Data, Design, and Background Knowledge in Etiologic Inference , 2001, Epidemiology.

[3]  J. Robins General methodological considerations , 2003 .

[4]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[5]  W. J. Granger,et al.  The Nobel Memorial Prize for Clive , 2004 .

[6]  C. Granger Testing for causality: a personal viewpoint , 1980 .

[7]  F. Diebold The Nobel Memorial Prize for , 2004 .

[8]  H. Frumkin,et al.  Ambient Air Pollution and Respiratory Emergency Department Visits , 2005, Epidemiology.

[9]  M. Hernán,et al.  Causal knowledge as a prerequisite for confounding evaluation: an application to birth defects epidemiology. , 2002, American journal of epidemiology.

[10]  F. Dominici,et al.  Fine particulate air pollution and hospital admission for cardiovascular and respiratory diseases. , 2006, JAMA.

[11]  B G Armstrong,et al.  Effect of measurement error on epidemiological studies of environmental and occupational exposures. , 1998, Occupational and environmental medicine.

[12]  David F. Hendry,et al.  The Nobel Memorial Prize for Clive W. J. Granger , 2004 .

[13]  J. Pearl,et al.  Causal diagrams for epidemiologic research. , 1999, Epidemiology.

[14]  T. Louis,et al.  Model choice in time series studies of air pollution and mortality , 2006 .

[15]  M. Lipsitch,et al.  Negative Controls: A Tool for Detecting Confounding and Bias in Observational Studies , 2010, Epidemiology.

[16]  J. Robins A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect , 1986 .

[17]  S L Zeger,et al.  Exposure measurement error in time-series studies of air pollution: concepts and consequences. , 2000, Environmental health perspectives.

[18]  J M Robins,et al.  Identifiability, exchangeability, and epidemiological confounding. , 1986, International journal of epidemiology.

[19]  S. Cole,et al.  Invited Commentary: Causal diagrams and measurement bias. , 2009, American journal of epidemiology.

[20]  L. Leemis Applied Linear Regression Models , 1991 .

[21]  J. Robins,et al.  Estimation of the Causal Effect of a Time-Varying Exposure on the Marginal Mean of a Repeated Binary Outcome , 1999 .