Presented and evaluated an adjusted Bonferroni method for controlling familywise rate when deleting parameters in specification addition searches. Simulation results show that the adjusted Bonferroni method controlled adequately for Type I errors in the initial addition stage of a two-stage search and with backward selection. (SLD)

This study explored alternative methods of estimating the number of latent dimensions represented by binary test data. The alternative methods vary in their complexity and include: (1) the minimum average partial correlation technique (MAP; W. Velicer, 1976) applied to phi correlations between binary responses; (2) the bootstrapped parallel…

Evaluated three types of multidimensional item response theory (MIRT) linking methods through two simulation studies. Results indicate that the best MIRT linking method was an unbiased, effective, and consistent estimator that produced accurate estimates of transformation parameters when errors in estimation of item parameters were manipulated…

Describes an idiosyncracy of the MULTILOG (D. Thissen, 1991) parameter estimation process discovered during a simulation study involving the graded response model. A misordering reflected in boundary function location parameter estimates resulted in a large negative contribution to the true score followed by a large positive contribution. These…

Relates Thurstonian models for paired comparisons data to Thurstonian models for ranking data and proposes an intermediate model for paired comparisons data that assigns nonzero probabilities to all transitive patterns and to some, but not all, intransitive patterns. Conducted a simulation study to investigate the performance of three alternative…

An Educational Testing Service (ETS) procedure was evaluated, which is based on item response theory and estimates true scores on tests not taken. The reading, vocabulary, and mathematics tests of high school seniors from the National Longitudinal Study (NLS) of 1972 and the High School and Beyond (HSB) seniors of 1980 and 1982 were found to share…

This study compared the performance of the LOGIST and BILOG computer programs on item response theory (IRT) based scaling and equating for the Test of English as a Foreign Language (TOEFL) using real and simulated data and two calibration structures. Applications of IRT for the TOEFL program are based on the three-parameter logistic (3PL) model.…

DETECT is a nonparametric, conditional covariance-based procedure to identify dimensional structure and the degree of multidimensionality of test data. The ability composite or conditional score used to estimate conditional covariance plays a significant role in the performance of DETECT. The number correct score of all items in the test (T) and…

Three common methods for equating parameter estimates from binary item response theory models are extended to the generalized grading unfolding model (GGUM). The GGUM is an item response model in which single-peaked, nonmonotonic expected value functions are implemented for polytomous responses. GGUM parameter estimates are equated using extended…

When categorical responses were simulated from a Multidimensional Many-FACETS Rasch Compensatory Model (MMFRCM), the effects of ability, task difficulty, and step difficulty estimates with the unidimensional Many-FACETS Rasch Model (MFRM; Linacre, 1999) were examined in terms of three error indexes, average absolute difference (AAD), bias, and…

The purpose of this study was to assess the dimensionality of attitudinal data arising from unfolding models for discrete data and to compute rough estimates of item and individual parameters for use as starting values in other estimation parameters. One- and two-dimensional simulated test data were analyzed in this study. Results of limited…

Developed a full maximum likelihood method for obtaining joint estimates of variances and correlations among continuous and polytomous variables with incomplete data that are missing at random with an ignorable missing mechanism. Simulation results and an empirical example illustrate the approach. (SLD)

Studied the effect of item parameter estimation for computation of linking coefficients for the test response function (TRF) linking/equating method. Simulation results showed that linking was more accurate when there was less error in the parameter estimates, and that 15 or 25 common items provided better results than 5 common items under both…

Presents a Bayesian method for obtaining an interval estimate of the population squared multiple correlation from an incomplete multivariate normal data set. Estimates were constructed using Gibbs sampling. Simulation studies indicate that the method can yield accurate interval estimates of the population squared multiple correlation. (SLD)

Presents and evaluates three estimators for "p," the proportion of success in predicting variable "Y," with nominal measurement, using predictor variables that also have nominal measurement. Showed through simulation that one estimator is always biased upward, and then proposed another possible estimator that involves using…