eduzhai > Physical Sciences > Physics Sciences >

On the Index of Repeatability: Estimation and Sample Size Requirements

  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Background: Repeatability is a statement on the magnitude of measurement error.When biomarkers are used for disease diagnoses, they should be measuredaccurately. Objectives: We derive an index of repeatability based on theratio of two variance components. Estimation of the index is derived from theone-way Analysis of Variance table based on the one-way random effects model.We estimate the large sample variance of the estimator and assess its adequacyusing bootstrap methods. An important requirement for valid estimation ofrepeatability is the availability of multiple observations on each subject takenby the same rater and under the same conditions. Methods: We use thedelta method to derive the large sample variance of the estimate ofrepeatability index. The question related to the number of required repeats persubjects is answered by two methods. In first methods we estimate the number ofrepeats that minimizes the variance of the estimated repeatability index, andthe second determine the number of repeats needed under cost-constraints. Resultsand Novel Contribution: The situation when the measurements do not followGaussian distribution will be dealt with. It is shown that the required samplesize is quite sensitive to the relative cost. We illustrate the methodologieson the Serum Alanine-aminotransferase (ALT) available from hospital registrydata for samples of males and females. Repeatability is higher among females incomparison to males.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...