Previous work on the effects of dimensionality on parameter estimation was extended from dichotomous models to the polytomous graded response (GR) model. A multidimensional GR model was developed to generate data in one-, two-, and three-dimensions, with two- and three-dimensional conditions varying in their interdimensional associations. Test…

The results obtained from two basic types of pre-equatings of tests were compared: the item response theory (IRT) pre-equating and section pre-equating (SPE). The simulated data were generated from a modified three-parameter logistic model with a constant guessing parameter. Responses of two replication samples of 3000 examinees on two 72-item…

Arguments have recently been put forth that standard textbook procedures for determining the sample size necessary to achieve a certain level of power in a completely randomized design are incorrect when the dependent variable is fallible because they ignore measurement error. In fact, however, there are several correct procedures, one of which is…

Because latent trait models require that large numbers of items be calibrated or that testing of the same large group be repeated, item parameter estimates are often obtained by administering separate tests to different groups and "linking" the results to construct an adequate item pool. Four issues were studied, based upon the analysis…

Factor structure of the Reactions to Tests (RTT) scale measuring test anxiety was studied by testing a series of confirmatory factor models including a second-order structure with 636 college students. Results support a shorter 20-item RTT but also raise questions about the cross-validation of covariance models. (SLD)

The authors present a Markov Chain Monte Carlo (MCMC) parameter estimation procedure for the generalized graded unfolding model (GGUM) and compare it to the marginal maximum likelihood (MML) approach implemented in the GGUM2000 computer program, using simulated and real personality data. In the simulation study, test length, number of response…

The use of indices and statistics based on nonlinear factor analysis (NLFA) has become increasingly popular as a means of assessing the dimensionality of an item response matrix. Although the indices and statistics currently available to the practitioner have been shown to be useful and accurate in many testing situations, few studies have…

Effects of test length, sample size, and assumed ability distribution were investigated in a multiple replication Monte Carlo study under the 1-parameter (1P) and 2-parameter (2P) logistic graded model with five score levels. Accuracy and variability of item parameter and ability estimates were examined. Monte Carlo methods were used to evaluate…

Rasch between and total weighted and unweighted fit statistics were compared using varying test lengths and sample sizes. Two test lengths (20 and 50 items) and three sample sizes (150, 500, and 1,000 were crossed. Each of the six combinations were replicated 100 times. In addition, power comparisons were made. Results indicated that there were no…

In most reliability studies, the precision of a reliability estimate varies inversely with the number of examinees (sample size). Thus, to achieve a given level of accuracy, some minimum sample size is required. An approximation for this minimum size may be made if some reasonable assumptions regarding the mean and standard deviation of the test…

As item response theory (IRT) becomes popular in educational and psychological testing, there is a need of reporting IRT-based effect size measures. In this study, we show how the standardized mean difference can be generalized into such a measure. A disattenuation procedure based on the IRT test reliability is proposed to correct the attenuation…

Equating tests from different calibrations under item response theory (IRT) requires calculation of the slope and intercept of the appropriate linear transformation. Two methods have been proposed recently for equating graded response items under IRT, a test characteristic curve method and a minimum chi-square method. These two methods are…

DIMTEST is a statistical test procedure for assessing essential unidimensionality of binary test item responses. The test statistic T used for testing the null hypothesis of essential unidimensionality is a nonparametric statistic. That is, there is no particular parametric distribution assumed for the underlying ability distribution or for the…

When criterion-referenced tests are used to assign examinees to states reflecting their performance level on a test, the better known methods for determining test length, which consider relationships among domain scores and errors of measurement, have their limitations. The purpose of this paper is to present a computer system named TESTLEN, which…

Hierarchical Bayes procedures were compared for estimating item and ability parameters in item response theory. Simulated data sets from the two-parameter logistic model were analyzed using three different hierarchical Bayes procedures: (1) the joint Bayesian with known hyperparameters (JB1); (2) the joint Bayesian with information hyperpriors…