A maximin model for test design based on item response theory is proposed. Only the relative shape of target test information function is specified. It serves as a constraint subject to which a linear programing algorithm maximizes the test information. The model is illustrated, and alternative models are discussed. (TJH)

The purposes of this paper are five-fold to discuss: (1) when item response theory (IRT) equating methods should provide better results than traditional methods; (2) which IRT model, the three-parameter logistic or the one-parameter logistic (Rasch), is the most reasonable to use; (3) what unique contributions IRT methods can offer the equating…

When the logistic function is substituted for the normal, Thurstone's Case V specialization of the law of comparative judgment for paired comparison responses gives an identical equation for the estimation of item scale values, as does the Rasch formulation for direct responses. Comparisons are made. (Author/CTM)

A method is described for simultaneous test construction using the Operations Research technique zero-one programming. The model for zero-one programming consists of two parts. The first contains the objective function that describes the aspect to be optimized. The second part contains the constraints under which the objective function should be…

Urry's procedure for approximating latent trait test models is shown to tend to underestimate item discriminatory power and overestimate item difficulty. A method for correcting these biases is provided, and implications of the procedures are discussed. (Author/JKS)

It is demonstrated, theoretically and empirically, that item sets can be selected that meet the unidimensionality assumption of most item response theory models, even though they require more than one ability for a correct response. A method for identifying such item sets for test development purposes is presented. (SLD)

This paper attempts to provide some initial information about the use of a variety of item response theory (IRT) models in the item selection process; its purpose is to compare the information curves derived from the selection of items characterized by several different IRT models and their associated parameter estimation programs. These…

Two procedures for Rasch, sample-free item calibration are reviewed and compared for accuracy. The theoretically ideal "conditional" procedure is impractical for more than fifteen items. The more practical but biased "unconditional" procedure is discussed in detail. (Author/JKS)

The construction of parallel tests from item response theory (IRT) based item banks is discussed. Tests are considered parallel whenever their information functions are identical. After the methods for constructing parallel tests are considered, the computational complexity of 0-1 linear programming and the heuristic procedure applied are…

A procedure for the sequential optimization of the calibration of an item bank is given. The procedure is based on an empirical Bayes approach to a reformulation of the Rasch model as a model for paired comparisons between the difficulties of test items in which ties are allowed to occur. First, it is indicated how a paired-comparisons design…

The aim of this paper is to explore the Rasch model as a criterion of test homogeneity. Two empirical studies are presented to demonstrate this usage. From these studies it is argued that statistical tests of item characteristic curve (ICC) slopes are not sufficient in testing for heterogeneity. Tests of equality of ICC's over groups of subject…

A new test construction method based on integer linear programming is described. This method selects optimal tests in small amounts of computer time. The new method, called the Cluster-Based Method, assumes that the items in the bank have been grouped according to their item information curves so that items within a group, or cluster, are…

The methods and approaches for estimating the operating characteristics of the discrete item responses without assuming any mathematical form have been developed and expanded. It has been made possible that, even if the test information function of a given test is not constant for the interval of ability of interest, it is used as the Old Test.…

When several ability scales in item response models are separately derived from different test forms administered to different samples of examinees, these scales must be equated to a common scale because their units and origins are arbitrarily determined and generally different from scale to scale. A general method for equating logistic ability…

Although two-stage testing is not the most efficient form of adaptive testing, it has some advantages. In this paper, linear programming models are given for the construction of two-stage tests. In these models, practical constraints with respect to, among other things, test composition, administration time, and inter-item dependencies play an…