Strategies for assessing item bias are discussed. Correct response probabilities in latent trait models are compared conditional on latent ability. Probabilities are compared conditional on the observed test score in Scheuneman's method. A method to assess item bias and distinguish between uniform and nonuniform bias is described. (Author/DWH)

Section pre-equating (SPE) equates a new test to an old test prior to the actual use of a new test by making extensive use of experimental sections of a testing instrument. SPE theory is extended to allow for practice effects on both the old and new tests. (Author/BS)

Maximum likelihood procedures are presented for a general model to unify the various models and techniques that have been proposed for item analysis. Unconditional maximum likelihood estimation, proposed by Wright and Haberman, and conditional maximum likelihood estimation, proposed by Rasch and Andersen, are shown as important special cases. (JAZ)

The applicability of a new multiple-group factor analysis of dichotomous variables is shown and contrasted with the item response theory approach to item bias analysis. Situations are considered where the same set of test items has been administered to more than one group of examinees. (Author/BS).

A five by five covariance matrix representing longitudinal measurements at five occasions is used to illustrate that markedly different types of learning curves may generate indistinguishable covariance structures. An excellent fit of a simplex structure can be misleading. Common uses of covariance structure models for growth studies are…

Drawing on recently developed methodology for structural equation modeling with categorical data, this article proposes a new approach for investigating the behavior of dichotomously scored test items in relation to other relevant (observed) variables. A linear structural model relates the latent ability variable to a set of observed scores.…

A statistical test is described which determines homogeneity of effect size of an experiment series. An overall fit statistic is partitioned into between-class fit statistic and within-class fit statistic. These statistics permit assessment of differences between effect sizes for different classes and homogeneity of effect size within classes.…

An equating design in which two groups of examinees from slightly different populations are administered a different test form with a subset of common items is widely used. This paper presents standard errors and a simulation that verifies the equation for large samples for an equipercentile equating procedure for this design. (Author/BS)

Barcikowski has provided tables for use in situations where means are to be used as the unit of analysis. This article argues that the conditions specified for use of these tables are not practical. It explicates a methodology for carrying out analyses based on group means. (Author/JAZ)

To facilitate meta-analysis of diverse study findings, a mixed linear model with fixed random effects is presented and illustrated with data from teacher expectancy experiments. The standardized effect size is viewed as random and the variation among effect sizes is modeled as a function of study characteristics. (Author/BS).

In this paper a Bayesian procedure is developed for the simultaneous estimation of the reading ability and difficulty parameters which are assumed to be factors in reading errors by the multiplicative Poisson Model. According to several criteria, the Bayesian estimates are better than comparable maximum likelihood estimates. (Author/JAZ)

Multidimensional item response data were created. The strength of a general factor, the number of common factors, the distribution of items loadingon common factors, and the number of items in simulated tests were manipulated. LOGIST effectively recovered both item and trait parameters in nearly all of the experimental conditions. (Author/JAZ)

The Lisrel-model with structured means was used to study similarities and differences in the development of mathematical ability between two student groups as measured by two tests on three successive occasions. Procedures for testing models to assess the contribution on an individual parameter to the goodness of fit are described. (Author/BS)