The problem of characterizing the manifest probabilities of a latent trait model is considered. The approach taken here differs from the standard approach in that a population of examinees is being considered as opposed to a single examinee. Particular attention is given to the Rasch model. (Author/JKS)

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)

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)

Recent advances in item analysis have provided greater capabilities for the analysis of tests, but have also significantly increased the gap between the theory and practice of item analysis. This paper traces the lines of development in item analysis under latent trait theory. (MV)

A procedure for obtaining Rasch model estimates of item difficulty and of ability is detailed. The procedure approximates the optimal but difficult to obtain "unconditional" estimates. (JKS)

A strategy for the pairwise assessment which may be used to evaluate the nature of both "prerequisite" and "transference" relations existing among a set of traits is presented. Both confirmatory and exploratory strategies are presented. An example of how the strategy would be used is presented in the exploratory context.…

Deciding whether sets of test data are consistent with any of a large class of item response models is considered. The assumption of local independence is weakened to a new condition, local nonnegative dependence (LND). Necessary and sufficient conditions are derived for a LND item response model. (Author/JKS)

A model of test item dependency is presented and used to illustrate the effect that violations of local independence have on the behavior of item characteristic curves. The dependency model is flexible enough to simulate the interaction of a number of factors including item difficulty and item discrimination, varying degrees of item dependence,…

A common problem in practical educational research is that of perfect scores which result when latent trait models are used. A simple procedure for managing the perfect and zero response problem encountered in converting test scores into measures is presented. It allows the test user to chose among two or three reasonable finite representations of…

This research simulated responses of 75 subjects to 30 items under the Birnbaum model and attempted a fit to the data using the Rasch model. When item discriminations varied from a variance of .05 to .25, there was only a slight increase in lack of fit as the variances increased. (Author/CTM)

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)

This article organizes models for categorical item response data into three distinct classes. "Difference models" are appropriate for ordered responses, "divide-by-total" models for either ordered or nominal responses, and "left-side added" models for multiple-choice responses with guessing. Details of the taxonomy…

A latent class model for rating data is presented which provides an alternative to the latent trait approach of analyzing test data. It is the analog of Andrich's binomial Rasch model for Lazarsfeld's latent class analysis (LCA). Response probabilities for rating categories follow a binomial distribution and depend on class-specific item…

Formulas for computing the exact signed and unsigned areas between two item characteristic curves (ICCs) are presented. It is further shown that when the "c" parameters are unequal, the area between two ICCs is infinite. The significance of the exact area measures for item bias research is discussed. (Author)

A method for detecting and interpreting disturbances of the local-independence assumption among items that share common stimulus material or other features is presented. Dichotomous and polytomous Rasch models are used to analyze structure of the learning outcome superitems. (SLD)