Three levels of a mathematics computation test were equated using the Rasch model. Sixth, seventh, and eighth graders were administered different levels of the test. Lack of consistency among equatings suggested that the Rasch model did not produce a satisfactory vertical equating of this computation test. (Author/RD)

The statistically correct conditional maximum likelihood (CML) estimation method has not been used because of numerical problems. A solution is presented which allows a rapid computation of the CML esitmates also for long tests. CML has decisive advantages in the construction of statistical tests of goodness of fit. (Author/CP)

TAILOR, a computer program which implements an approach to tailored testing, was examined by Monte Carlo methods. The evaluation showed the procedure to be highly reliable and capable of reducing the required number of tests items by about one half. (Author/JKS)

Criterion-keying of interest inventories involves selecting items which best distinguish a group of incumbents in a particular occupation from another group intended to represent the population of interest. This practice is questioned here and data are presented to support the author's contention. (Author/JKS)

Discusses a study to compare the performances of different item analysis procedures by using five scales covering intellectual and attitudinal domains. Results are presented. (Author/DB)

Describes a project used in a sophomore-level psychological testing and measurement course. Students worked through the different phases of developing a test focused on item writing, reliability, and validity. Responses from both students and instructors have been consistently positive. (MJP)

Content characteristics of 1,400 Graduate Record Examination (GRE) analytical reasoning items were coded for item difficulty and discrimination. The results provide content characteristics for consideration in extending specifications for analytical reasoning items and a better understanding of the construct validity of these items. (TJH)

Items showing sex differences on the revised Wechsler Adult Intelligence Scale (WAIS-R) were studied. In a sample of 206 young adults (110 males and 96 females), 15 items demonstrated significant sex differences, but there was no relationship of item-specific gender content to sex differences in item performance. (SLD)

A method is presented for estimating the item characteristic curve (ICC) using polynomial regression splines. Estimation of spline ICCs is described by maximizing the marginal likelihood formed by integrating ability over a beta prior distribution. Simulation results compare this approach with the joint estimation of ability and item parameters.…

Describes the development of a test of scientific creativity for use with secondary school students which was constructed on the basis of an analysis of meaning and aspects of scientific creativity. Reports that the scientific creativity of secondary school students increases with age and science ability is a necessary but not sufficient condition…

Opportunity to learn is considered an important contributing factor in learning outcomes. In some of the latest international comparative studies of mathematics achievement, such as SIMS and TIMSS, painstaking efforts have been made to find out what the participating students' opportunities to learn mathematics had been. However, there have been…

Item response theory (IRT) has become one of the most popular scoring frameworks for measurement data. IRT models are used frequently in computerized adaptive testing, cognitively diagnostic assessment, and test equating. This article reviews two of the most popular software packages for IRT model estimation, BILOG-MG (Zimowski, Muraki, Mislevy, &…

Preventing items in adaptive testing from being over- or underexposed is one of the main problems in computerized adaptive testing. Though the problem of overexposed items can be solved using a probabilistic item-exposure control method, such methods are unable to deal with the problem of underexposed items. Using a system of rotating item pools,…

To assess item dimensionality, the following two approaches are described and compared: hierarchical generalized linear model (HGLM) and multidimensional item response theory (MIRT) model. Two generating models are used to simulate dichotomous responses to a 17-item test: the unidimensional and compensatory two-dimensional (C2D) models. For C2D…

Despite evidence that the choice of dependent measures can significantly influence design sensitivity, many evaluators default to traditional measures that may be insensitive to intervention effects. This paper describes an innovative set of test development guidelines designed to select items and create aggregate scales that are better able to…