Estimating the reliability of continuous measures with Cronbach's alpha or the intraclass correlation coefficient: toward the integration of two traditions

Abstract

The epidemiological literature has been ambiguous concerning reliability estimates for continuous variables. Reproducibility and internal consistency have been presented as different aspects of reliability, the former being estimated with some form of intraclass correlation coefficient, the latter with Cronbach's alpha. Based on demonstrations available in the literature this paper recalls that both estimates are based on the same measurement model and on the same definition of reliability. It also highlights the conditions under which they are equivalent and provides practical suggestions concerning the estimation of reliability, based on design considerations.