Position effects may occur in both paper--pencil tests and computerized assessments when examinees respond to the same test items located in different positions on the test. To examine position effects in large-scale assessments, previous studies often used multilevel item response models within the generalized linear mixed modeling framework.…

This article promotes the use of modern test theory in testing situations where sum scores for binary responses are now used. It directly compares the efficiencies and biases of classical and modern test analyses and finds an improvement in the root mean squared error of ability estimates of about 5% for two designed multiple-choice tests and…

The aim of this study is to determine variance difference between maximum likelihood and expected A posteriori estimation methods viewed from number of test items of aptitude test. The variance presents an accuracy generated by both maximum likelihood and Bayes estimation methods. The test consists of three subtests, each with 40 multiple-choice…

The current study used simulated data to investigate the properties of a newly proposed method (Yao's rater model) for modeling rater severity and its distribution under different conditions. Our study examined the effects of rater severity, distributions of rater severity, the difference between item response theory (IRT) models with rater effect…

Nested logit item response models for multiple-choice data are presented. Relative to previous models, the new models are suggested to provide a better approximation to multiple-choice items where the application of a solution strategy precedes consideration of response options. In practice, the models also accommodate collapsibility across all…

An extension of the Bock-Samejima model for multiple choice items is introduced. The model provides for varying probabilities of the response alternative when the examinee guesses. A marginal maximum likelihood method is devised for estimating the item parameters, and likelihood ratio tests for comparing more and less constrained forms of the…

A method for determining invariant item parameters is presented, along with a scheme for obtaining test scores which are interpretable in terms of a common metric. The method assumes a unidimensional latent trait and uses a three parameter normal ogive model. The assumptions of the model are explored, and the methods for calculating the proposed…

This is a continuation of a previous study in which a new method of estimating the operating characteristics of discrete item responses based upon an Old Test, which has a non-constant test information function, was tested upon each of two subtests of the original Old Test, Subtests 1 and 2. The results turned out to be quite successful. In the…

The purpose of this study was to examine the potential effect of false assumptions regarding the motivation of examinees on item calibration and test construction. A simulation study was conducted using data generated by means of several models of examinee item response behaviors (the three-parameter logistic model alone and in combination with…

In order to evaluate our methods and approaches of estimating the operating characteristics of discrete item responses, it is necessary to try other comparable methods on similar sets of data. LOGIST 5 was taken up for this reason, and was tried upon the hypothetical test items, which follow the normal ogive model and were used frequently in…

Formula score theory (FST) associates each multiple choice test with a linear operator and expresses all of the real functions of item response theory as linear combinations of the operator's eigenfunctions. Hard measurement problems can then often be reformulated as easier, standard mathematical problems. For example, the problem of estimating…

This study compares the fit of the 3-parameter model to the Ability Removing Random Guessing (ARRG) model on data from a wide range of tests of cognitive ability in three representative samples. When the guessing parameters under the 3-parameter model are estimated individually for each item, the 3-parameter model yields the better fit to…

Detecting differential item functioning (DIF) on test items constructed to favor 1 group over another was investigated on parameter estimates from 2 item response theory-based computer programs--BILOG and LOGIST--using data for 1,000 White and 1,000 Black college students. Use of prior distributions and marginal-maximum a posteriori estimation is…