A statistical method is proposed for assessing agreement between two clinical methods of measuring an unknown quantity. Its value is a function of the difference between measurements of the same sample by the two methods and their arithmetic and geometric means. The proposed method is motivated by the J-divergence rate and can be viewed as a measure of the distance between two distributions defined by measurements by the two methods. The paper concludes with a discussion regarding the simultaneous use of this and Bland-Altman methods.

measure of agreement, geometric mean, J-divergent, Bland-Altman, information.