|
Abstract:
|
The Bland-Altman plot with the limit of agreement has been widely used as a visual tool for assessing test-retest reliability or reproducibility between two measurements. We have observed, however, that in the settings that the scaled index such as concordance correlation coefficient (CCC) or intraclass correlation coefficient (ICC) is employed, the limit of agreement approach may not be consistent with the scaled index. Particularly, if an acceptable difference is not known and two measurements are highly concordant, but the common variance of the data is large, the broad width of the limit of agreement may incorrectly indicate a lack of agreement. This paper proposes a novel, scaled index-based guidance for graphical evaluation of reproducibility or reliability. We create a 100(1-?) % reference band from two measurements, which is based on the concordance correlation coefficient. Simulation studies have been carried out to demonstrate the benefits of our method over the limit of agreement. Our simulation study results and real data application show that the proposed method can provide practitioners with a novel graphical evaluation method that is consistent with the CCC values.
|
