As part of the effort to develop an improved oral reading fluency (ORF) assessment system, Kara et al. estimated the ORF scores based on a latent variable psychometric model of accuracy and speed for ORF data via a fully Bayesian approach. This study further investigates likelihood-based estimators for the model-derived ORF scores, including…

Equating methods make use of an appropriate transformation function to map the scores of one test form into the scale of another so that scores are comparable and can be used interchangeably. The equating literature shows that the ways of judging the success of an equating (i.e., the score transformation) might differ depending on the adopted…

Three local observed-score kernel equating methods that integrate methods from the local equating and kernel equating frameworks are proposed. The new methods were compared with their earlier counterparts with respect to such measures as bias--as defined by Lord's criterion of equity--and percent relative error. The local kernel item response…

An alternative formula is presented for the reliability of a difference score that contains the correlation between true scores instead of the correlation between observed scores. This approach provides more useful information and yields values that are not as anomalous as those usually obtained. (SLD)

This note shows that the formula suggested by N. D. Bryant and S. Gokhale (1972) for correcting indirectly restricted correlations when no information is available on the third (directly restricted) variable is accurate only in one special instance. A more general correction formula is illustrated. (SLD)

A relatively simple method is developed to obtain confidence intervals for a student's proportion of domain mastery in criterion-referenced or mastery measurement situations. The method uses the binomial distribution as a model for the student's scores under hypothetically repeated assessments, and it makes use of widely available "F"…

K. May and W. A. Nicewander recently concluded (1994) that percentile ranks are inferior or raw scores as indicators of latent ability. It is argued that their conclusions are incorrect, and an error in their derivation is identified. The incorrect equation results in an incorrect conclusion, as work by F. M. Lord (1980) also indicates.…

Dato de Gruijter is correct in the recent conclusion that one equation derived by the present authors should be changed to reflect that it is an approximation, but it is still argued that percentile ranks for difficult tests can have substantially lower reliability and information relative to their number correct scores holds. (SLD)

The distinction between deterministic and statistical reasoning in the application of models to educational measurement is explicated. Issues addressed include the relationship between data and estimation equations, distinction between parameters and parameter estimates, and power of tests of fit of responses across the ability continuum. (TJH)

D. R. Divgi (1986) demonstrated that the bias of unconditional maximum likelihood (UCON) item-parameter estimates is not removed by the factor (n-1)/n. D. Andrich (1989) argued that the demonstration was faulty. In this note, a complete proof of Divgi's conclusion is presented. (Author/TJH)

Using the generalized partial-credit item response theory (IRT) model, polytomous items from the 1991 field test of the National Assessment of Educational Progress reading test were calibrated with multiple-choice and open-ended items. Polytomous items provide more information than dichotomous items. (SLD)

Generalizability theory is used to show that the assumption that reliability for groups is greater than that for persons (and that error variance for groups is less than that for persons) is not necessarily true. Examples are provided from course evaluation and performance test literature. (SLD)

Using several data sets, the relative performance of the beta binomial model and two more general strong true score models in estimating several indices of classification consistency is examined. It appears that the beta binomial model can provide inadequate fits to raw score distributions compared to more general models. (TJH)

Loglinear latent class models are used to detect differential item functioning (DIF). Likelihood ratio tests for assessing the presence of various types of DIF are described, and these methods are illustrated through the analysis of a "real world" data set. (TJH)

A statistical method, W. F. Stout's statistical test of essential unidimensionality (1990), for exploring the lack of unidimensionality in test data was studied using Monte Carlo simulations. The statistical procedure is a hypothesis test of whether the essential dimensionality is one or exceeds one, regardless of the traditional dimensionality.…