Related Experiment Video
Updated: Feb 15, 2026

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
Published on: August 25, 2014
The effect of risk factor misclassification on the partial population attributable risk.
Benedict H W Wong1, Sarah B Peskoe1, Donna Spiegelman2
1Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
Risk factor misclassification can significantly bias partial population attributable risk (pPAR) estimates, potentially leading to overestimations and incorrect conclusions in public health research. Understanding these biases is crucial for accurate intervention impact assessment.
Area of Science:
- Epidemiology
- Biostatistics
- Public Health
Background:
- Partial population attributable risk (pPAR) quantifies the population-level impact of preventive interventions for multifactorial diseases.
- Nondifferential risk factor misclassification can introduce bias into pPAR estimates.
- Crude and semiadjusted population attributable risk (PAR) formulas are still used despite potential biases.
Purpose of the Study:
- To evaluate the impact of nondifferential risk factor misclassification on the bias of pPAR estimands.
- To compare the bias in pPAR with that of crude and semiadjusted PAR estimators.
- To illustrate the extent of bias using a real-world example of colorectal cancer risk factors.
Main Methods:
- Mathematical modeling to assess bias in pPAR due to misclassification.
- Analysis of how sensitivities, specificities, relative risks, and prevalences affect pPAR bias.
- Application of pPAR and biased estimators to a colorectal cancer study dataset.
Main Results:
- Uncorrected pPAR bias depends nonlinearly and nonmonotonically on various factors, notably exposure sensitivity.
- Bias in pPAR can be substantial, sometimes directional away from the null, unlike crude PAR bias.
- In a colorectal cancer study, misclassification led to a 48% overestimation of pPAR for low folate intake.
Conclusions:
- Nondifferential risk factor misclassification can severely bias pPAR estimates, affecting public health conclusions.
- Crude and semiadjusted PAR estimators may also be biased, and their use requires careful consideration.
- Accurate risk factor assessment is critical to avoid overestimating intervention impact and ensure reliable public health strategies.
Related Concept Videos
Factors Affecting the Risk of Infection
The integrity and count of the white blood cells help the body resist pathogens and fight infection. When impaired, it reduces the body's resistance to pathogens. The acidic pH levels of the gastrointestinal, genitourinary tracts, and skin...
Drug Toxicity: Risk factors
Relative Risk
Attribution Theory
Fundamental Attribution Error
Design Example: Analyzing Capacity Contours for Flood Risk Assessment

