Two fundamental problems in mental test theory are to estimate true score and to estimate the amount of error when testing an examinee. In this report, three probability models which characterize a single test item in terms of a population of examinees are described. How these models may be modified to characterize a single examinee in terms of an…

The appropriateness of the use of the standardized residual (SR) to assess congruence between sample test item responses and the one parameter latent trait (Rasch) item characteristic curve is investigated. Latent trait theory is reviewed, as well as theory of the SR, the apparent error in calculating the expected distribution of the SR, and…

Several methods of assessing test item bias are described, and the concept of fair use of tests is examined. A test item is biased if individuals of equal ability have different probabilities of attaining the item correct. The following seven general procedures used to examine test items for bias are summarized and discussed: (1) analysis of…

Assuming vectors of item responses depend on ability through a fully specified item response model, this paper presents maximum likelihood equations for estimating the population parameters without estimating an ability parameter for each subject. Asymptotic standard errors, tests of fit, computing approximations, and details of four special cases…

The purpose of this study was to compare the relative robustness of the one-, two-, and modified two-parameter latent trait logistic models for the Iowa Tests of Educational Development. Results suggest that the modified two-parameter model may provide the best representation of the data. (Author/BW)

This volume and its companion, "Part 2," bring together transactions of the Rasch measurement special interest group of the American Educational Research Association. This volume opens with a discussion of the early years in Rasch measurement and then presents the "transactions" in chronological order, from a 1987 discussion…

This volume and its companion, "Part 1," bring together transactions of the Rasch measurement special interest group of the American Educational Research Association. It presents "transactions" in chronological order, from a 1992 discussion through the winter 1995 volume. Four issues of the "Transactions" are…

The Rasch model was used to equate reading comprehension tests of widely different difficulty for three groups of fifth grade students of widely different ability. Under these extreme circumstances, the Rasch model equating was unsatisfactory. (Author/CTM)

A method is proposed for the detection of item bias with respect to observed or unobserved subgroups, using a loglinear item response theory model assuming a Rasch model for ability and difficulty. A simulation study was performed with 200 sets of data to check the robustness of the method. (SLD)

The PARallELogram Analysis (PARELLA) model is a probabilistic parallelogram model that can be used for the measurement of latent attitudes or latent preferences. A method is presented for testing for differential item functioning (DIF) for the PARELLA model using the approach of D. Thissen and others (1988). (SLD)

The National Assessment of Educational Progress (NAEP) makes possible comparison of groups of students and provides information about what these groups know and can do. The scale anchoring techniques described in this chapter address the latter purpose. The direct method and the smoothing method of scale anchoring are discussed. (SLD)

An extension is proposed for the network algorithm introduced by C.R. Mehta and N.R. Patel to construct exact tail probabilities for testing the general hypothesis that item responses are distributed according to the Rasch model. A simulation study indicates the efficiency of the algorithm. (SLD)

A test theory using only ordinal assumptions is presented, based on the idea that the test items are a sample from a universe of items. The sum across items of the ordinal relations for a pair of persons on the universe items is analogous to a true score. (SLD)

Derivations of several item selection algorithms for use in fitting test items to target information functions (IFs) are described. These algorithms, which use an average growth approximation of target IFs, were tested by generating six test forms and were found to provide reliable fit. (SLD)

A new test construction model based on the Rasch model is proposed. This model, the cluster-based method, considers groups of interchangeable items rather than individual items and uses integer programing. Results for six test construction problems indicate that the method produces accurate results in small amounts of time. (SLD)