We are receiving a lot of questions about relevant analyses in the Analyse-it Method Validation edition to help in evaluating new diagnostic tests in the fight against COVID-19. Below are some quick links that will help, but contact us if you have questions - we are working as normal.
Also see our latest blog post: Sensitivity/Specificity and The Importance of Predictive Values for a COVID-19 test
When assessing the agreement between two methods, it is useful to the plot the
difference between methods against the mean of the methods (a difference plot).
difference plot is, effectively, a scatter plot rotated 45 degrees clockwise. However, a
difference plot is more informative than a scatter plot since the data points are not
tightly clustered around the diagonal. A difference plot also clearly shows any
relationship between the differences and the magnitude of measurement.
illustrate this concept, we will use an example from Bland & Altman’s 1986 paper.
This example compares two methods of measuring peak expiratory flow rate (PEFR). On each
of 17 subjects, two measurements were taken with a Wright meter, and two with a mini
Per Bland & Altman‘s paper, only the first measurement (replicate)
by each method is used to illustrate the difference plot and limits of
agreement. Both measurements (replicates) are used in the study of
The points on the difference plot roughly form a constant width horizontal band
across the measuring interval, and there is no obvious relationship between the
difference and the mean or the variability of the measurements and the mean.