Constraints on criterion-referenced tests to make mastery/nonmastery classifications of motor skills can lead to excessively long tests. A sequential probability ratio test classified many subjects' golf shots quickly but required many trials for four subjects. The test's classification accuracy makes it a potentially useful device for physical…

Concern about passing those examinees who should pass, and retaining those who need remedial work, is one problem related to criterion-referenced testing. This paper deals with one aspect of that problem. When determining how many items to include on a criterion-referenced test, practitioners must resolve various non-statistical issues before a…

Procedures for establishing standards and determining the number of items needed in criterion referenced measures were reviewed. Discussion of setting a passing score was organized around: performance of others, item content, educational consequences, psychological and financial costs, and error due to guessing and item sampling. (Author)

This paper presents an algorithm for determining the number of items to measure each objective in a criterion-referenced test when testing time is fixed and when the objectives vary in their levels of importance, reliability, and validity. Results of four special applications of the algorithm are presented. (BS)

The effectiveness of various tailored testing strategies for use in objective based instructional programs was investigated. The three factors of a tailored testing strategy under study with various hypothetical distributions of abilities across two learning hierarchies were test length, mastery cutting score, and starting point. (Author/JKS)

When determining criterion-referenced test length, problems of guessing are shown to be more serious than expected. A new method of scoring is presented that corrects for guessing without assuming that guessing is random. Empirical investigations of the procedure are examined. Test length can be substantially reduced. (Author/CM)

A problem of considerable importance in certain educational settings is determining how many items to include on a mastery test. Applying ranking and selection procedures, a solution is given which includes as a special case all existing single-stage, non-Bayesian solutions based on a strong true-score model. (Author/JKS)

A computer simulation was undertaken to determine the effects of using Huynh's single-administration estimates of the decision consistency indices for agreement and coefficient kappa, under conditions that violated the beta-binomial assumption. Included in the investigation were two unimodal score distributions that fit the model and two bimodal…

A new method was developed to assist in the selection of a test length by utilizing computer simulation procedures and item response theory. A demonstration of the method presents results which address the influences of item pool heterogeneity matched to the objectives of interest and the method of item selection. (Author/PN)

The adequacy of a test developed for statewide assessment of basic mathematics skills was investigated. The test, comprised of multiple-choice items reflecting a series of behavioral objectives, was compared with a more extensive criterion measure generated from the same objectives by the application of a strict item sampling model. In many…

This special issue covers recent technical developments in the field of criterion-referenced testing. An introduction, six papers, and two commentaries dealing with test development, test score uses, and evaluation of scores review relevant literature, offer new models and/or results, and suggest directions for additional research. (SLD)

Six experimental approaches to the problems of setting cutoff scores and choosing proper test length are briefly mentioned. Most of these methods share the premise that a test is a random sample of items, from a domain associated with a carefully specified objective. Each item is independent and is scored zero or one, with no provision for…

Two approaches to criterion-referenced test construction are compared. Classical test theory is based on the practice of random sampling from a well-defined domain of test items; latent trait theory suggests that the difficulty of the items should be matched to the achievement level of the student. In addition to these two methods of test…

Addressing the shortcomings of classical item statistics for selecting criterion-referenced test items, this paper describes an optimal item selection procedure utilizing item response theory (IRT) and offers examples in which random selection and optimal item selection methods are compared. Theoretical advantages of optimal selection based upon…

A computer simulation of Bayes' Theorem was conducted in order to determine the probability that an examinee was a master conditional upon his test score. The inputs were: number of mastery states assumed, test length, prior expectation of masters in the examinee population, and conditional probability of a master getting a randomly selected test…