In this paper four classes of procedures for measuring the instructional sensitivity of reading comprehension test items are reviewed. True experimental designs are not recommended because some of the most important reading comprehension variables do not lend themselves to experimental manipulation. "Ex post facto" factorial designs are…

Differences between traditional linear regression and a Bayesian approach to classification are discussed. Classification consists of assigning subjects to one of several available treatments on the basis of their test scores when the success of each treatment is measured by a different criterion. Formulating this problem as an empirical Bayes…

The three-parameter logistic model discussed was used by CTB/McGraw-Hill in the development of the Comprehensive Tests of Basic Skills, Form U (CTBS/U) and the Test of Cognitive Skills (TCS), published in the fall of 1981. The development, standardization, and scoring of the tests are described, particularly as these procedures were influenced by…

A simulation study to determine appropriate linking methods for adaptive testing items was designed. Three basic data sets for responses were created. These were randomly sampled, systematically sampled, and selected data sets. The evaluative criteria used were fidelity of parameter estimation, asymptotic ability estimates, root-mean-square error…

Despite advances in common factor analysis, a review of 89 studies published in four selected journals between 1963 and 1976 indicated that behavioral scientists preferred principal components analysis, followed by varimax or orthogonal rotation. Resultant row sums of squares of factor matrices from principal component analyses of real data sets…

This document contains summaries of six courses presented at the Second Annual Presessions of the American Educational Research Association: (1) Bayesian statistical analysis, (2) curriculum research and evaluation, (3) design and analysis of comparative experiments in education, (4) educational research management procedures, (5) multivariate…

This paper considers the application of Bayesian techniques for simultaneous estimation to the specification of regression weights for selection tests used in various technical training courses in the Marine Corps. It concludes that a hypothesis of complete generalization of the predictor-criterion relationship would only be retained for selected…

The theoretical rationales and procedures of five adaptive computer-based instruction models were reviewed: the mathematical model, the regression model, the Bayesian probabilistic model, the testing and branching model, and artificially intelligent instructional systems. Each model is assessed for contrast of methods and forms, identifiable…

Empirical Bayes methods are shown to provide a practical alternative to standard least squares methods in fitting high dimensional models to sparse data. An example concerning prediction bias in educational testing is presented as an illustration. (Author)

This research follows up a study conducted in 1998 by the National Foundation for Educational Research (NFER) to investigate teachers' and students' views on the factors affecting students' choices of whether or not to apply to Oxford and Cambridge universities. It identifies what has changed since 1998 and areas in which the universities could…

Using oral survey methods, this study examined potential language maintenance or loss of Mayan languages among the Guatemalan-Maya communities of Southeast Florida. Among dislocated immigrants and their children, the language of the dominant socio-economic forces often displaces other languages (Fishman, 1967). A Guatemalan community in Los…

Explains a new way of viewing Bayes' formula. Discusses the revision factor and its interpretation. (YP)

Included are probability models for various strategies that contestants on the television game show, "Let's-Make-a-Deal," might use when given the option to stick with their original choice of three unopened doors or switch to the unopened door after one of the other two doors has been opened. (JJK)

Illustrates some applications of elementary probability and statistics to epidemiology, the branch of medical science that attempts to discover associations between events, patterns, and the cause of disease in human populations. Uses real-life examples involving cancer's link to smoking and the AIDS virus. (MDH)

Explores the potential utility of Bayesian statistical methods in determining the predictability of multiple polls. Compares Bayesian techniques to the classical statistical method employed by pollsters. Considers these questions in the context of the 1992 presidential elections. (HB)