Article commented on a study by Harris, who presented formulas for the variance of errors of estimation (of a true score from an observed score) and the variance of errors of prediction (of an observed score from an observed score on a parallel test). (Author/RK)

Suggests that there are major issues involved in using criterion-referenced reading tests that are unclear or unresolved, including their place in the system of teaching reading, their validity, their reliability, and how cut-off scores are set and evaluated. (TJ)

A number of different definitions and indices of reliability for mastery tests have recently been proposed in an attempt to cope with possible lack of score variability that attenuates traditional coefficients. One promising index that has been suggested is the proportion of students in a group that are consistently assigned to the same mastery…

A computer simulation study was conducted to investigate Subkoviak's index of reliability for criterion-referenced tests, called the coefficient of agreement. Results indicate that the index can be adequately estimated. (JKS)

Four different methods for estimating the proportions of testees properly classified as having mastered or not mastered test content are examined, using data from the Scholastic Aptitude Test. All four methods prove reasonably accurate and all show some bias under certain conditions. (JKS)

Descriptions are presented of two related probabilistic models that can be used for making classification decisions with respect to mastery of specific concepts or skills. Determination of cutoff scores, minimal number of items necessary, and the assessment of the quality of tests provided by the model are discussed. (Author/JKS)

Criterion-referencing is a way to enhance the interpretation of test scores by referencing them to well-defined behavior domains. Behavior domains may be ordered or unordered; several varieties of criterion-referenced tests within each of these types are discussed. (Author/RL)

Explains Subkoviak's method for estimating alternate-form reliability from one administration of a criterion-referenced test and describes computer program that handles tests for large number of examinees and allows application of Subkoviak's technique. Concludes that program is superior to other methods since user can directly check…

Criterion-referenced assessment arguably results in greater reliability, validity and transparency than norm-referenced assessment. This article examines this assertion with reference to an example from a second year undergraduate law unit at the Queensland University of Technology, LWB236 Real Property A. When designing criterion-referenced…

In tertiary institutions in Australia, and no doubt elsewhere, there is increasing pressure for accountability. No longer are academics assumed "a priori" to be responsible and capable of self management in teaching and assessing the subjects they run. Procedures are being dictated more from the "top down". Although academics…

Various item selection techniques are compared on criterion-referenced reliability and validity. Techniques compared include three nominal criterion-referenced methods, a traditional point biserial selection, teacher selection, and random selection. (Author)

Classical test construction and analysis procedures are applicable and appropriate for use with criterion referenced tests when samples of both mastery and nonmastery examinees are employed. (Author/BB)

The basis for selection of the calibration sample determines the kind of scale which will be developed. A random sample from a population of individuals leads to a norm-referenced scale, and a sample representative of abilities of a range of characteristics leads to a criterion-referenced scale. (Author/BB)

Seventeen statistics for measuring the reliability of criterion-referenced tests were critically reviewed. The review was organized into two sections: (1) a discussion of preliminary considerations to provide a foundation for choosing the appropriate category of "reliability" (threshold loss function, squared-error loss-function, or…