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)

Criterion referenced test methodology is used in this study for determining the extent of overtraining and undertraining through the use of the minimally acceptable performance level (MAPL), as proposed by Nedelsky (1954). A MAPL was computed for each area on a 320-item, 12-area test. The raw area scores of the technicians were transformed to…

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…

This paper deals with problems of measuring change in motor behavior. Conventional measurement procedures and statistical analyses involving change are presented in the first section. This section discusses difference scores as the criterion measure and the use of all scores as the dependent variables. This latter category involves using either…

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)

An operational framework and a set of empirical procedures for building achievement tests sensitive to the instructional effects of school programs are presented. Procedures are illustrated using data from a comparative study of alternative item formats for a criterion-referenced test. Important differences in instructional sensitivity are shown.…

Describes study of undergraduates at Florida State University that examined whether the criteria for mastering unit quizzes in a mastery-oriented course should increase, decrease, or remain fixed across units. Hypotheses tested are discussed, results of unit quiz performance and final examination performance are analyzed, and student attitudes are…

The question of educational effects in higher education is reexamined by studying the effects of academic departments (rather than entire colleges) and employing as criterion measures achievement tests appropriate for the individual departments. (Editor/LBH)

This study investigated the use of word-visuals to aid university students' recall by examining relationships that exist among levels of learners' recall resulting from different presentation modes; between levels of field-dependent and field-independent learners' recall; and between levels of field-dependent and field-independent learners' recall…

Results indicate that students who have attended single-sex girls' schools and then proceed to an all women's college do not make as much progress toward maturity as other college students from co-educational schools. (Author/MB)

Describes study that compared the performance of high achieving and low achieving undergraduates on two computer assisted instruction modules, one in which learners were forced to review informational frames following errors and one where the review was optional. Dependent and collateral variables are discussed and criterion referenced tests used…

Describes a study of college students that examined the instructional effect of visual and verbal metaphors in facilitating student achievement of different educational objectives. The effect of students' verbal ability and the amount of time they spent interacting with their respective instructional modules were also measured. (Author/LRW)

A fixed-pace video-lesson which had adjunct questions (AQs) interspersed throughout was viewed by 134 freshman psychology students to determine if AQs have a facilitative effect on relevant and/or incidental learning from a videotape lesson, and, if they do, to discover the optimal combination of the factors of position and type of question, and…