Estimating the Reliability of Criterion-Referenced Tests before Administration.
Clint Chase · ScholarWorks@BGSU (Bowling Green State University) · 1996
The classical procedures for calculating the two indexes of decision consistency (P and Kappa) for criterion-referenced tests require two testings on each child. Huynh and Peng & Subkoviak have presented one-testing procedures for these indexes. This article shows how these indices can be estimated without any test administration using Ebel's estimates of the mean, standard deviation and KR21.