A method for determining the sampling ratio in epidemiologic studies

Abstract

This paper presents a new method for determining the optimal sampling ratio and sample size in different types of study designs involving binary exposure and disease variables. The sampling ratio is optimized by maximizing cost efficiency, which is the ratio of the precision in effect estimation to the total sampling cost. One may easily compute the optimal sampling ratio with a hand calculator, and it is independent of the sample sizes of the compared groups. Optimal sample sizes obtain from use of the optimal sampling ratio in the appropriate asymptotic power function for comparing two proportions or rates with unequal sample sizes. We illustrate the method with a case-control design, compare it with other methods for optimizing the sampling strategy, and discuss it in a practical context.