In the mid to late 1970s, considerable research was conducted on the properties of Rasch fit mean squares, resulting in transformations to convert the mean squares into approximate t-statistics. In the late 1980s and the early 1990s, the trend seems to have reversed, with numerous researchers using the untransformed fit mean squares as a means of…

RESGEN is a computer program designed to generate simulated latent trait distributions and then dichotomous or polytomous item responses based on item response models. The latent trait distributions can be univariate or multivariate normal, log-normal, uniform, or gamma. The item response models utilized in this program may have characteristics…

The effects on Rasch measurement of both response underfit (noise) and overfit (mutedness or superuniformity) are described and illustrated. Misfit is identified by mean-square fit statistics. Person separation and reliability are shown to be deceptive indicators of measurement effectiveness when some items exhibit marked overfit. Theoretical…

F. Samejima (1973) proposed a continuous response model in which item response is on a continuous scale rather than some discrete levels. This model has potential because in many psychological and educational assessments, the responses are on a conceptual continuum rather than on some fixed levels. As a first step toward studying the applicability…

How common patterns of rater errors may be detected in a large-scale performance assessment setting is discussed. Common rater effects are identified, and a scaling method that can be used to detect them in operational data sets is presented. Simulated data sets are generated to exhibit each of these rater effects. The three continua that depict…

This paper investigates methods that avoid using multiple groups to represent the missing data patterns in covariance structure modeling, attempting instead to do a single-group analysis where the only action the analyst has to take is to indicate that data is missing. A new covariance structure approach developed by B. Muthen and G. Arminger is…

The work of R. MacCallum et al. (1992) was extended by examining chance modifications through a Monte Carlo simulation. The stability of post hoc model modifications was examined under varying sample size, model complexity, and severity of misspecification using 2- and 4-factor oblique confirmatory factor analysis (CFA) models with four and eight…

This report describes a classroom project that groups sophomore biology students into "companies" bidding for a "contract" to build a self-sufficient, enclosed city by producing a manual and model of their version of a biosphere. Students must develop technological support systems, social and economic parameters, and systems…

Recent research has demonstrated that knowledge about specific instances may be of more relevance to reasoning than has previously been assumed. Students can rely on principles they have learned, or they can recall something similar previously experienced, and base the new prediction on it in an instance-based approach. Instance-based (or…

Tukey's Honestly Significant Difference (HSD) procedure (J. Tukey, 1953) is probably the most recommended and used procedure for controlling Type I error rate when making multiple pairwise comparisons as follow-ups to a significant omnibus F test. This study compared observed Type I errors with nominal alphas of 0.01, 0.05, and 0.10 compared for…

This paper describes a computer model that simulates the way children develop the reasoning skills of transitive inference and the construction of ordered sets. The computer model begins from general operations, such as setting and removing goals, storing and retrieving information, comparing elements to find matches, reading premises, and giving…

This repeated measures factorial design study compared the results of two procedures for identifying multivariate outliers under varying conditions, the Mahalanobis distance and the Andrews-Pregibon statistic. Results were analyzed for the total number of outliers identified and number of false outliers identified. Simulated data were limited to…

Sequential probability ratio testing (PRT), which usually is applied in situations requiring a decision between two simple hypotheses or a single decision point, is extended to include situations involving k decision points and [(k + 1)-choose-2] sets of simultaneous, simple hypotheses, where k>1. The multiple-decision point or…

Multiple-hypothesis testing in the context of a correlation matrix is used to compare the statistical power of the original Bonferroni with six modified Bonferroni procedures that control the overall Type I error rate. Three definitions of statistical power are considered: (1) the ability to detect at least one true relationship; (2) the ability…

Using computer simulated data, the Type I error rate and statistical power were empirically estimated for several pairwise multiple comparison strategies for situations where population variances differ. Focus was on comparing modified Bonferroni procedures with Dunnett's solutions, and determining whether or not J. P. Shaffer's suggestion of…