Studies in applied behavior analysis have used percentage agreement as an index of interobserver reliability. Because percentage agreement is inflated by chance agreements, kappa has been recommended as a preferred alternative. In this article, we present a procedure to estimate maximum and minimum kappa from percentage agreement with limited information. The procedure will facilitate comparisons between studies and the reassessment of the reliabilities of previous studies.
|Original language||English (US)|
|Number of pages||4|
|State||Published - Sep 1 1984|
All Science Journal Classification (ASJC) codes
- Psychiatry and Mental health