Inter-rater reliability

Hi,

I am trying to find out inter-rater reliability between 3 readers. The data is nominal. There were two categories used to grade the samples: FID denoted with 1 and AFID denoted with 0. I am not sure how to go about writing a code to determine inter rater reliabilty between these readers for this data.

Answer 1

[Star Strider]

If I understand what your data are and what you want to do, The correct test for your data is Fleiss’s kappa statistic. As I remember, the statistic is normally distributed, so a normal distribution will define the confidence intervals for it. The Wikipedia article on Fleiss’ kappa will provide necessary background.