Abstract
The statistical properties required for effective biomarkers for disease are examined. It is shown that an “effectiveness parameter” D can be calculated that summarises the performance of a given biomarker and can distinguish between effective and ineffective biomarkers. D can be readily calculated from published summaries of biomarker levels and provides a simpler alternative to the commonly used “Area under the Curve” statistic. The impact of within-individual and between-individual variation in biomarker levels is also evaluated. An approach to the choice of sample size for experiments to estimate D is described.