Limits of agreement (Bland-Altman method)

Reply to Dr Myers' Commentary on the Use of Automated Blood Pressure Machines in Office Blood Pressure Measurements

“…2,3 Correlation coefficients and average bias data do not paint a complete picture when one is comparing two different methods. 5,6 The primary outcome of our study was the Bland-Altman analysis, and we reported wide limits of agreement (À31, +33 mm Hg) between AOBP and ABPM, 3,5 which were quite similar to that reported by Dr Myers in the CAMBO trial 2 (À31.9, +33.6 mm Hg) despite the difference in the AOBP resting period. The scatter plots in our study ( Figure 1) 3 and in the CAMBO study 2 ( Figure 2) are indeed strikingly similar; however, with different conclusions being drawn.…”

Reliability and agreement studies: a guide for clinical investigators

“…In order to calculate it, they plotted the mean difference between raters’ scores of the two observers against the difference between the scores of the observers. For instance, a recent paper by Sedwick,70 showed a Bland-Altman plot which investigated the agreement between primary care and daytime ambulatory monitoring in blood pressure. Online supplementary figure S3 shows the mean systematic difference between both readings (d, green line), and two other lines (red, dotted), which represent the ‘limits of agreement’ as estimated by d±1.96x SD of the differences.…”

A method comparison of a food frequency questionnaire to measure folate, choline, betaine, vitamin C and carotenoids with 24-h dietary recalls in women of reproductive age

“…When the difference between the two measurements was not normally distributed, data were log transformed and plotted. 38 …”