As noted above, correlation is not synonymous with concordance. Correlation refers to the existence of a relationship between two different variables, while concordance refers to the concordance between two measures of a variable. Two groups of highly correlated observations may have a mismatch; However, if the two groups of values are identical, they will certainly be highly correlated. For example, in the example of hemoglobin, the correlation coefficient between the values of the two methods is high, although the concordance is poor [Figure 2]; (r = 0.98). The other way to look at it is that, although the individual points are not close enough to the dotted line (the smallest square line;[ 2] which indicates a good correlation), these are quite far from the black line crossed which represents the line of the perfect correspondence (Figure 2: the black line crossed). If a good match is made, points are expected to fall on or near this line (the black line) crossed. Nevertheless, significant guidelines have appeared in the literature. Perhaps the first Landis and Koch, the values < 0 were not compliant and 0-0.20 as low, 0.21-0.40 as fair, 0.41-0.60 as moderate, 0.61-0.80 as substantial, and 0.81-1 almost perfect. However, these guidelines are not universally recognized; Landis and Koch did not provide evidence to support this, but supported them on personal opinions. It was found that these guidelines could be more harmful than useful.
 Fleiss`s:218 equally arbitrary guidelines characterize kappas from over 0.75 as excellent, 0.40 to 0.75 as just right, and below 0.40 as bad. Methods for evaluating concordance between observers according to the nature of the variables measured and the number of observers Cohen`s Kappa statistics (or simply Kappa) must measure the concordance between two evaluators. “This book is a welcome addition to the literature at Bayes` inference, as it presents methods for the design and analysis of compliance studies. The approach presented by the author is new and the beginner finds in an appendix a useful introduction to Bayes` inference. . The text is legible and is a valuable source of reference. For those who are not familiar with WinBUGS, the author introduces the basics of programming and running BUGS. ” – International Statistical Review, 2010 In a 3 x 3 table, there are two options that would not provide a match at all (the # gives a count): it is important to note that in each of the three situations in Table 1, the pass percentages for the two controllers are the same, and if both examiners are compared to a test 2 × 2 for the associated data (McNemar test), no difference would be found between their performance; on the other hand, the concordance between observers in the three situations is very different.
. . .