Related Experiment Video
Updated: Jun 19, 2026

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Assessment of risks by predicting counterfactuals
1Department of Epidemiology and Biostatistics, Schulich School of Medicine and Dentistry, University of Western Ontario, London, Ont., Canada N6A5C1. gzou@robarts.ca
This study introduces new methods for risk assessment in epidemiology using counterfactual predictions. It provides tools for calculating risk difference and risk ratio, enhancing biomedical investigations.
Area of Science:
- Epidemiology and Biostatistics
- Statistical Modeling
Background:
- Risk assessment is crucial for epidemiological and biomedical research.
- Accurate estimation of risk measures like risk difference and risk ratio is essential.
Purpose of the Study:
- To assess risks using counterfactual outcomes.
- To propose novel confidence intervals for effect measures.
- To compare counterfactual-based risk ratios with those from the modified Poisson model.
Main Methods:
- Utilized probit, logistic, and extreme-value regression models for binary outcomes.
- Employed the method of variance estimates recovery for new confidence intervals.
- Conducted a simulation study to evaluate proposed methods.
- Developed a SAS macro for practical application.
Main Results:
- New confidence intervals were proposed and evaluated via simulation.
- Counterfactual-derived risk ratios were compared to modified Poisson model estimates.
- The study addressed concerns regarding the validity of the modified Poisson approach.
Conclusions:
- The proposed methods enhance risk assessment in epidemiological studies.
- Counterfactual-based risk ratio estimation offers a valid alternative.
- The provided SAS macro facilitates the application of these statistical techniques.
Related Concept Videos
Counterfactual Thinking
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Hindsight Biases
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Relative Risk
Design Example: Analyzing Capacity Contours for Flood Risk Assessment