A measure of agreement between two observers, suggested by Cohen in 1960. Suppose that the observers are required, independently, to assign items to one of m classes. Let fjk be the number of individuals assigned to class j by the first observer and to class k by the second observer. Let , and . Define the quantities O and E by , so that O is the total number of individuals on which the observers are in complete agreement, and E is the expected total number of agreements that would have occurred if the observers had been statistically independent. The formula for Cohen's kappa is . A value of 0 indicates statistical independence, and a value of 1 indicates perfect agreement.
Subjects: Probability and Statistics.