Evaluating Exposure-Specific Risks: A Simulation Study
Author Information
Author(s): William M Reichmann, David Gagnon, C Robert Horsburgh, Elena Losina
Primary Institution: Brigham and Women's Hospital
Hypothesis
The study aims to evaluate the existing methodology for calculating exposure-specific risks and propose an improved estimator.
Conclusion
The revised product-based estimator provides much improved accuracy over the existing simple product-based method.
Supporting Evidence
- The revised product-based estimator exhibited little observed relative bias compared to the simple product-based estimator.
- Coverage probabilities for the 95% CI of the revised estimator were above 95% across most scenarios.
- The existing methodology performed well only when the exposure probability was low and the relative risk was small.
Takeaway
This study shows that a new way to calculate disease risk based on exposure is better than the old method, especially when the exposure is low.
Methodology
A simulation study was conducted to test the performance of two estimators and their associated confidence intervals.
Potential Biases
The existing methodology showed significant bias in certain scenarios, particularly with higher exposure probabilities.
Limitations
Simulation studies cannot be considered proof, and the validity of estimates may be questionable with small sample sizes.
Statistical Information
Confidence Interval
95%
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website