However, the application of appropriate statistical measures is necessary to ensure reliability. Epidemiological studies often collect personal information on disease or risk factor status. With nominal data, the easiest way would be to assess reliability by simply calculating the observed match. The problem with this approach is that „this measure is biased in favour of dimensions with a small number of categories“ (Scott ). To avoid this problem, two other reliability measures were proposed, Scotts ft  and Cohens Kappa  that correct the agreement respected for the randomly awaited agreement. Because the original kappa coefficient (as well as Scott`s pi) is limited to the particular case of two advisors, several researchers have modified and expanded it to process different data formats . Although there are Kappa limitations that have already been discussed in the literature (z.B. [7-9]), kappa and its variations are still widespread. A frequently used cappa coefficient was proposed by Fleiss  and allows for the inclusion of two or more crants and two or more categories. Although the coefficient is a generalization of Scott`s Pi, not Cohen`s La Kappa (see z.B.  or ), it is most often called Fleiss` Kappa.
As we do not want to immortalize this misunderstanding, we will call it below as Fleiss` K, as proposed by Siegel and Castellan . Guess A, Taylor SJ, Spencer A, Diaz-Ordaz K, Eldrige S, Underwood M. The agreement between proxy and EQ-5D completed itself for care home residents was better for index scores than individual domains. J Clin Epidemiol. 2014;67(9):1035-43. Kappa is similar to a correlation coefficient, as it can`t exceed 1.0 or -1.0. Because it is used as a measure of compliance, only positive values are expected in most situations; Negative values would indicate a systematic disagreement. Kappa can only reach very high values if the two matches are good and the target condition rate is close to 50% (because it incorporates the base rate in the calculation of joint probabilities).