Related Experiment Videos
Competing risks bias arising from an omitted risk factor
1Division of Cancer Prevention and Control, National Cancer Institute, Bethesda, MD 20892-4200.
American Journal of Epidemiology
|April 1, 1989
Summary
A secondary disease can skew study results by removing susceptible individuals. This selection bias can create false inverse or attenuated associations between exposures and primary diseases, especially with unknown risk factors.
Area of Science:
- Epidemiology
- Biostatistics
- Medical Research Methodology
Background:
- Selection bias is a critical concern in epidemiological studies.
- Understanding biases is essential for accurate interpretation of disease associations.
- Previous research has identified various sources of bias in observational studies.
Purpose of the Study:
- To describe a specific type of selection bias.
- To illustrate how a secondary disease can induce this bias.
- To demonstrate the impact on the observed association between exposures and a primary disease.
Main Methods:
- Conceptual description of selection bias.
- Presentation of two illustrative examples.
- Identification of necessary conditions for the bias to manifest (e.g., unknown risk factors).
Main Results:
- A secondary disease can selectively remove individuals susceptible to a primary disease.
- This can lead to an apparent inverse association where none exists.
- Alternatively, it can attenuate a true direct association between an exposure and the primary disease.
Conclusions:
- Selection bias due to secondary disease removal can distort epidemiological findings.
- The presence of unmeasured confounding risk factors exacerbates this bias.
- Researchers must consider such biases when evaluating exposure-disease relationships.