Agreement between 2 measurement methods


New Member

I am trying to find the agreement between 2 methods that estimate the size of a knee (CT and MRI).
n brief, each knee can get a size from 1-7 where 1 represents the smallest size available and 7 represents the biggest size available. In my study, I have 100 different knees that were scanned by both MRI and CT. Once I complete the analysis for all knees in both techniques (CT and MRI) I need to conclude whether those two methods agree (or correlate?) .
The problem I am facing is that this is not a continuous parameter and therefore I can't use the Bland-Altman plot and this is not really a categorical variable and therefore I cont use the Kappa weighted approach.

I am not sure which approach I should take and would appreciate any help here.



Active Member
CT and MRI are ordinal variables. They cannot be put on a scale but for each two values we know which one is bigger. Therefore, the most appropriate metrics for quantifying the codependence of CT and MRI are rank-based measures, like Spearman's rho or Kendall's tau.