The analysis of variance model for estimating reliability in norm referenced tests is extended to criterion referenced tests. The essential modification is that the criterion or cut-off score is substituted for the population mean. An example and discussion are presented. (JKS)

The validity of five methods of estimating the reliability of criterion-referenced tests was evaluated across nine conditions of variability among item means. The results were analyzed by analysis of variance, the Newman-Keuls test, and a nonparametric procedure. There was a tendency for all of the methods to be conservative. (Author/JKS)

The problem that this research addressed was one of decision making. Given three sets of criterion-referenced tests which were designed to be parallel in content, would a traditional reliability coefficient produce different decisions about the reliability of those tests than would kappa? The procedure used collected statewide results on 136 test…

Livingston's work is a careful analysis of what occurs when one pools two populations with different means, but similar variances and reliability coefficients. However, his work fails to advance reliability theory for the special case of criterion-referenced testing. See ED 042 802 for Livingston's paper. (MS)

A three-part correlational study examined the explanatory power of the Lexile theory of reading comprehension, which was based on the semantic and syntactic components of prose. Correlations were performed between the item difficulties of nine nationally normed reading comprehension tests and computer generated difficulties which were reported in…

Using the basic principles of generalizability theory, a psychometric model for domain-referenced interpretations is proposed, discussed, and illustrated. This approach, assuming an analysis of variance or linear model, is applicable to numerous data collection designs, including the traditional persons-crossed-with-items design, which is treated…

The concepts of universe of admissible observation and universe of generalization from the generalizability theory were applied to calculate the intraclass correlation coefficient of a licensure test. The internal consistency coefficient of a dichotomously scored test is identical to the intraclass correlation coefficient of a two-facet design.…

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…

It is argued in this paper that generalizability theory provides a uniquely useful framework for defining and quantifying the dependability of data for decision making. It does so by requiring careful specification of the conditions of measurement and the anticipated sources of variation in the results of the measurement procedure. A distinction…

This paper examines the development and evaluation of criterion-referenced measures, and elaborates on the distinction between them and norm-referenced measures. The concept of sensitivity is introduced as an appropriate method for evaluating such measures, and a sensitivity index is proposed. The traditional model for the response of a subject to…

Investigations into item bias provide an empirical basis for the identification and elimination of test items which appear to measure different traits across populations or cultural groups. The Psychometric rationales for six approaches to the identification of biased test items are reviewed: (1) Transformed item difficulties: within-group…

This chapter should not only acquaint the reader with the present state of the art on Criterion-Referenced (CR) measurement but also suggest possible directions for further inquiry. The goal of the first part of this chapter is to deal with the definitional dilemma of CR measurement by proceeding from the more traditional view of CR measurement to…