Studied whether circular equating could provide an adequate measure of various types of equating error when applied to different equating methods under different equating designs. Analyses and simluations show that circular equating is generally invalid as a criterion to evaluate the adequacy of equating. (SLD)

Shows that the conventional noncentrality parameter estimator of covariance structure models, currently implemented in popular structural modeling programs, possesses asymptotically potentially large bias, variance, and mean squared error (MSE). Presents a formal expression for its large-sample bias and quantifies large-sample bias and MSE. (SLD)

Presents an alternative statistical test, BOOT(subscript)med for the two-group situation when a small experimental group is being compared with a large control group. BOOTmed is a between-groups median test derived through bootstrapping techniques. Empirical validation indicates that BOOTmed maintains relatively robust error rates under a variety…

Proposes the use of statistical power subsequent to the results of hypothesis testing in business research. Describes how posttest use of power might be integrated into business statistics courses. (SK)

Studied sources of measurement error variance in the Teacher Efficacy Scale (TES) (Gibson and Dembo, 1984). Used reliability generalization to characterize the typical score reliability for the TES and potential sources of measurement error variance across 43 studies. Also examined related instruments for measurement integrity. (SLD)

Markov models provide a general framework for analyzing and interpreting time dependencies in psychological applications. Recent work extended Markov models to the case of latent states because frequently psychological states are not directly observable and subject to measurement error. This article presents a further generalization of latent…

A covariance structure modeling method to test equality in proportions explained variance in studied unobserved dimensions by means of latent predictors is outlined. The procedure is applicable with multiple-indicator, structural equation models where of interest is to compare the predictive power of sets of latent independent variables for given…

The recent development of multilevel IRT models (Fox & Glas, 2001, 2003) has been shown to be very useful for analyzing relationships between observed variables on different levels containing measurement error. Model parameter estimates and their standard deviations are concurrently estimated taking account of measurement error in observed…

This study examines the effects of kindergarten retention on children's social-emotional development in the early, middle, and late elementary years. Previous studies have generated mixed results partly due to some major methodological challenges, including selection bias, measurement error, and divergent perceptions of multiple respondents in…

In light of a recent revelation that Gersten (1985) included erroneous information on one of two programs for English Language Learners (ELLs), the authors re-calculate results of their earlier meta-analysis of program effectiveness studies for ELLs in which Gersten's studies had behaved as outliers (Rolstad, Mahoney & Glass, 2005). The correction…

Extensive education research on the contribution of teachers to student achievement produces two generally accepted results. First, teacher quality varies substantially as measured by the value added to student achievement or future academic attainment or earnings. Second, variables often used to determine entry into the profession and…

An analysis was conducted to identify sources of true and error variance in measuring swimming drag force to draw valid conclusions about performance factor effects. Passive drag studies were grouped according to methodological differences: tow line in pool, tow line in flume, and carriage in tow tank. Active drag studies were grouped according to…

This Monte Carlo study examined the impact of misspecifying the [big sum] matrix in longitudinal data analysis under both the multilevel model and mixed model frameworks. Under the multilevel model approach, under-specification and general-misspecification of the [big sum] matrix usually resulted in overestimation of the variances of the random…

This study aimed at estimating the correlation between true scores (true consistency) of vocational interest over a short time span in a sample of 1089 adults. Participants were administered 54 items assessing vocational, family, and leisure interests twice over a 1-month period. Responses were analyzed with a multitrait (MT) model, which supposes…

Unlike a substantial part of reliability literature in the past, this article is concerned with weighted combinations of a given set of congeneric measures with uncorrelated errors. The relationship between maximal coefficient alpha and maximal reliability for such composites is initially dealt with, and it is shown that the former is a lower…