Four bootstrap methods are identified for constructing confidence intervals for the binomial-error model. The extent to which similar results are obtained and the theoretical foundation of each method and its relevance and ranges of modeling the true score uncertainty are discussed. (SLD)

The use of sampling weights in deriving population estimates for the National Assessment of Educational Progress (NAEP) and the effects of nonresponse and undercoverage on those estimates are described. The estimation of sampling variability from complex sample surveys is also reviewed, concentrating on the jackknife repeated replication…

A generalized variance criterion is proposed to measure efficiency in item-response-theory (IRT) models. Heuristic arguments are given to formulate the efficiency of a design in terms of an asymptotic generalized variance criterion. Efficiencies of designs for one-, two-, and three-parameter models are compared. (SLD)

A method is suggested to estimate the relationship between a latent trait and one or more manifest predictors without estimating subject parameters. The method, developed for the Rasch model, can be generalized to two-parameter and three-parameter logistic latent trait models. The model is illustrated with simulated and empirical data. (SLD)

The polytomous unidimensional Rasch model with equidistant scoring (rating scale model) is extended so that two parameters are linearly decomposed into certain basic parameters. A conditional maximum likelihood estimation procedure and a likelihood ratio test are presented in the context of the extended model (linear rating scale model). (SLD)

The stochastic interactive activation and competition (SIAC) model of perception is presented and tested using several data sets from previous research. The asymptotic predictions of the SIAC model are compared with those of the fuzzy logical model of perception (FLMP). Evidence favoring the FLMP is reviewed. (SLD)

To investigate the effect on item parameter estimation of pooling the raters' ratings and to examine the information content of 2 types of writing samples, the partial credit model was fit to 2,000 writing samples from secondary students that had been holistically scored. Implications for test construction are discussed. (SLD)

A procedure for evaluating a variety of rater reliability models is presented. A multivariate linear model is used to describe and assess a set of ratings. Parameters are represented in terms of a factor analytic model, and maximum likelihood methods test the model parameters. Illustrative examples are presented. (SLD)

Results obtained in a metanalysis using indirect alternative methods of computing standardized mean difference effect sizes (SMDESs) were compared with results obtained from direct calculations of SMDESs. In most cases, alternative methods yield very comparable results and are beneficial to use, especially when sample sizes are large. (SLD)

The sensitivity of marginal maximum likelihood estimation of item and ability (theta) parameters was examined when prior ability distributions were not matched to underlying ability distributions. Thirty sets of 45-item test data were generated. Conditions affecting the accuracy of estimation are discussed. (SLD)

A Monte Carlo study investigated the use of four cross-validation indices with confirmatory factor analysis models. Influences of sample size, loading size, and degree of model misspecification were studied. Larger sample sizes and better specified models result in better cross-validation results. (SLD)

Centering is a problem in multilevel analysis that needs to be addressed. Multilevel analysis gives researchers a choice between centering within context and grand mean centering, both statistically sound ways to improve estimation of the parameters in the model. Researchers of the most widely used software package for the analysis of…

Some item response theory (IRT) techniques work in applications even though the usual structural IRT assumptions, and local independence (LI) in particular, do not hold. When the departure from LI is too great, traditional procedures will break down. Although violations of strictly unidimensional, monotone, locally independent latent structure can…

This paper explores a logistic regression procedure for estimating item parameters in the Rasch model and testing the hypothesis of item parameter invariance across several groups/populations. Rather than using item responses directly, the procedure relies on "pseudo-paired comparisons" (PC) statistics defined over all possible pairs of…

Studies of differential item functioning (DIF) under item response theory require that item parameter estimates be placed on the same metric before comparisons can be made. Evidence that methods for linking metrics may be influenced by the presence of differentially functioning items has been inconsistent. The effects of three methods for linking…