Three item selection methods for criterion-referenced tests are examined: the classical theory of item difficulty and item-test correlation; the latent trait theory of item characteristic curves; and a decision-theoretic approach for optimal item selection. Item contribution to the standardized expected utility of mastery testing is discussed. (CM)

One aim of criterion-referenced testing is to classify an examinee without reference to a norm group; therefore, any statements about the dependability of such classification ought to be group-independent also. A population-independent index is proposed in terms of the probability of incorrect classification near the cutoff true score. The…

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…

These studies in test adequacy focus on two problems: procedures for estimating reliability, and techniques for identifying ineffective distractors. Fourteen papers are presented on recent advances in measuring achievement (a response to Molenaar); "an extension of the Dirichlet-multinomial model that allows true score and guessing to be…

A model is presented using examinee judgements in detecting ambiguous/misinterpreted items on teacher-made criterion-referenced tests. A computational example and guidelines for constructing domain categories and interpreting the indices are presented. (Author/PN)

A latent trait method is presented to investigate the possibility that Angoff or Nedelsky judges specify inconsistent probabilities in standard setting techniques for objectives-based instructional programs. It is suggested that judges frequently specify a low probability of success for an easy item but a large probability for a hard item. The…

Latent trait models may offer considerable potential for the improvement of educational measurement practices, but until recently, they have received only limited attention from measurement specialists. This paper provides a brief introduction to latent trait models, and provides test practitioners with a non-technical introduction to the…

The potential of a cognitive model task analysis scheme (CMS) that specifies features of test problems shown by research to affect performance is explored. CMS describes the general skill area and the generic task or problem type. It elaborates features of the problem situation and required responses found by research to influence performance.…

This paper presents an introduction to the use of latent trait models for the estimation of domain scores. It was shown that these models provided an advantage over classical test theory and binomial error models in that unbiased estimates of true domain scores could be obtained even when items were not randomly selected from a universe of items.…

This paper argues that no single measurement strategy serves all purposes and that applying methods and techniques which allow a variety of data elements to be retrieved and juxtaposed may be an investment in the future. Item response theory, Rasch model, and latent trait theory are all approaches to a single conceptual topic. An abbreviated look…

This study investigates two fixed parameter models for calibrating test items for an item bank under local school district control. Mathematics, reading, and language tests administered to students (Grades 7-9) provided the criterion information. Model I used calibrations from the Northwest Evaluation Association Item Bank to calibrate new items…

Test item selection techniques based on traditional item analysis methods were compared to techniques based on item response theory. The consistency of mastery classifications in criterion referenced reading tests was examined. Pretest and posttest data were available for 945 first and second grade students and for 1796 fourth to sixth grade…

The effectiveness of a model for determining a minimal cut-off score for criterion-referenced tests was examined. The model, based upon techniques presented originally by Nedelsky and by Angoff, was first used in conjunction with a multiple choice test developed for use in certifying school counselors in Georgia. A "knowledge estimation panel" was…

In order to compose equivalent certification tests in the basic skills in reading, mathematics calculations and applications, and writing for high school graduation requirements, the San Jose Unified School District, California, used the Rasch computer program to arrive at the scaled difficulty level of test items. The procedure for achieving a…

A procedure which employs a method of item substitution based on item difficulty is recommended for developing parallel criterion referenced test forms. This procedure is currently being used in the Florida functional literacy testing program and the Georgia teacher certification testing program. Reasons for developing parallel test forms involve…