Reliability is defined as the degree to which study objects can be distinguished from each other, despite measurement errors
Good reliability is important in physical examination tests, because if people cannot agree on the interpretation of a special test, the test result will be of little use and thus the accuracy of this test will be lacking as well.
Reliability can further be divided into:
Intra-rater reliability, which is the degree to which one examiner can repeat the test with consistency and Inter-raterreliability, which captures the agreement in outcomes of a test between two different examiners.
If a special test has a dichotomous outcome (e.g. positive or negative), the degree of reliability can be measured with the Kappaĸ,both for intra- and inter-relater reliability. The next section will deal with the Kappa Statistic in detail.