Search

Confounding is an important source of bias, but it is often misunderstood. We consider how confounding occurs and how to address confounding using examples. Study results are confounded when the effect of the exposure on the outcome, mixes with the effects of other risk and protective factors for the outcome. This problem arises when these factors are present to different degrees among the exposed and unexposed study participants, but not all differences between the groups result in confounding. Thinking about an ideal study where all of the population of interest is exposed in one universe and is unexposed in a parallel universe helps to distinguish confounders from other differences. In an actual study, an observed unexposed population is chosen to stand in for the unobserved parallel universe. Differences between this substitute population and the parallel universe result in confounding. Confounding by identified factors can be addressed analytically and through study design, but only randomization has the potential to address confounding by unmeasured factors. Nevertheless, a given randomized study may still be confounded. Confounded study results can lead to incorrect conclusions about the effect of the exposure of interest on the outcome., (© 2018 Nordic Federation of Societies of Obstetrics and Gynecology.)

Confounding biases study results when the effect of the exposure on the outcome mixes with the effects of other risk and protective factors for the outcome that are present differentially by exposure status. However, not all differences between the exposed and unexposed group cause confounding. Thus, sources of confounding must be identified before they can be addressed. Confounding is absent in an ideal study where all of the population of interest is exposed in one universe and is unexposed in a parallel universe. In an actual study, an observed unexposed population represents the unobserved parallel universe. Thinking about differences between this substitute population and the unexposed parallel universe helps identify sources of confounding. These differences can then be represented in a diagram that shows how risk and protective factors for the outcome are related to the exposure. Sources of confounding identified in the diagram should be addressed analytically and through study design. However, treating all factors that differ by exposure status as confounders without considering the structure of their relation to the exposure can introduce bias. For example, conditions affected by the exposure are not confounders. There are also special types of confounding, such as time-varying confounding and unfixable confounding. It is important to evaluate carefully whether factors of interest contribute to confounding because bias can be introduced both by ignoring potential confounders and by adjusting for factors that are not confounders. The resulting bias can result in misleading conclusions about the effect of the exposure of interest on the outcome., (© 2018 Nordic Federation of Societies of Obstetrics and Gynecology.)

In a 1993 paper (Am J Epidemiol. 1993;137(1):1-8), Weinberg considered whether a variable that is associated with the outcome and is affected by exposure but is not an intermediate variable between exposure and outcome should be considered a confounder in etiologic studies. As an example, she examined the common practice of adjusting for history of spontaneous abortion when estimating the effect of an exposure on the risk of spontaneous abortion. She showed algebraically that such an adjustment could substantially bias the results even though history of spontaneous abortion would meet some definitions of a confounder. Directed acyclic graphs (DAGs) were introduced into epidemiology several years later as a tool with which to identify confounders. The authors now revisit Weinberg's paper using DAGs to represent scenarios that arise from her original assumptions. DAG theory is consistent with Weinberg's finding that adjusting for history of spontaneous abortion introduces bias in her original scenario. In the authors' examples, treating history of spontaneous abortion as a confounder introduces bias if it is a descendant of the exposure and is associated with the outcome conditional on exposure or is a child of a collider on a relevant undirected path. Thoughtful DAG analyses require clear research questions but are easily modified for examining different causal assumptions that may affect confounder assessment.

Purpose: Directed acyclic graphs (DAGs) are useful tools for assessing confounding. However, the basic approach to detecting confounding in DAGs does not distinguish among various forms of interaction between the exposure and covariates and between different target populations for which effects are estimated. We propose a simple modification of DAG rules to overcome this limitation., Methods: Using fundamental concepts and DAGs, we show that the basic approach can suggest confounding even when absent if the covariate has no effect in the reference population being used as the comparator for the target population, as occurs when the target population is the exposed and the covariate acts only when the exposure is present., Results: We present three examples that illustrate this scenario and propose a simple revision to the basic approach to detecting confounding in DAGs that makes confounding in the presence of causal interaction easier to evaluate visually. This revision extends to other scenarios involving other target populations and variables with multiple levels., Conclusions: A simple modification of the basic approach to identifying confounding in DAGs allows more frequent exclusion of confounding when it is absent., (Copyright © 2011 Elsevier Inc. All rights reserved.)

Prior pregnancy outcomes, such as spontaneous abortion and preterm birth, are often predictive of future pregnancy outcomes. Therefore, many researchers adjust for reproductive history. Although this adjustment may be appropriate for a predictive model, it is not necessarily appropriate when the goal is to obtain an unbiased estimate of the effect of exposure on disease. Reproductive history may seem to meet the conventional criteria for confounding because it is unlikely to be on the causal pathway between exposure and current outcome, is often associated with current outcome, and may be associated with exposure as well. However, whether reproductive history is a confounder or not depends on the underlying reason for its associations with exposure and current outcome. Thus, conventional methods for assessing confounding are often inadequate. Directed acyclic graphs (DAGs) can be used to evaluate complex scenarios for confounding when the research question is clearly defined with respect to the exposure, the outcome, and the effect estimate of interest. Special care is required when reproductive history affects future exposure. We use 5 DAGs to illustrate possible relations between reproductive history and current outcome. We assess each DAG for confounding, and identify the appropriate analytic technique. We provide a numeric example using data from the Collaborative Perinatal Project. There is no single answer as to whether reproductive history should be included in the model; the decision depends on the research question and the underlying DAG.