Related Experiment Videos
Sample size requirements for prospective studies, with examples for coronary heart disease
1Department of Clinical Epidemiology & General Practice, Royal Free Hospital Medical School, London, England.
Journal of Clinical Epidemiology
|January 1, 1989
Summary
Determining the necessary number of disease cases for prospective studies is crucial. For coronary heart disease risk factors, aim for at least 400 cases for reliable estimation, especially with continuous risk factors under normal distribution.
Area of Science:
- Epidemiology
- Biostatistics
Background:
- Prospective studies are vital for identifying disease risk factors.
- Accurate sample size calculation is essential for reliable results in epidemiological research.
Purpose of the Study:
- To evaluate methods for determining the required number of disease cases in prospective studies.
- To assess the reliability of estimation formulae for continuous and categorical risk factors using coronary heart disease data.
Main Methods:
- Simulation exercises using data from a British prospective study of coronary heart disease.
- Evaluation of univariate and multivariate formulae for estimating required disease cases.
- Assessment of methods for continuous and categorical risk factors.
Main Results:
- A univariate formula for standardized relative odds reliably estimates cases for continuous risk factors with near-normal distributions.
- Formula extensions for multivariate adjustments were less satisfactory.
- An adapted univariate method for categorical risk factors provides reliable estimates, contingent on prior knowledge of relative odds.
Conclusions:
- Prospective studies on coronary heart disease risk factors generally require at least 400 cases for accurate estimation.
- The reliability of estimation formulae depends on the nature of the risk factor and the statistical model used.