Greater empirical attention directed toward gender-sensitive assessment strategies that concentrate on family-specific factors is thought to be both timely and necessary, especially with regard to outcome variables associated with mental health and substance abuse in at-risk adolescent populations. A sample of 2,646 court-involved adolescents was…

The purpose of this validity study was to improve measurement of coaching efficacy, an important variable in models of coaching effectiveness. A revised version of the coaching efficacy scale (CES) was developed for head coaches of high school teams (CES II-HST). Data were collected from head coaches of 14 relevant high school sports (N = 799).…

The cultural capital in families, more specifically, the educational level of parents, has during the last decades been shown to be the most important dimension of socioeconomic influence on school performance in many countries. Less is known about the factors that actually mediate this influence. The aim, therefore, is to investigate the relative…

This study examines the contribution of the "Responsive Classroom" (RC) Approach, a set of teaching practices that integrate social and academic learning, to children's perceptions of their classroom, and children's academic and social performance over time. Three questions emerge: (a) What is the concurrent and cumulative relation between…

This study investigated the benefits of creating item "testlets" or "parcels" in the context of structural equation modeling confirmatory factor analysis (CFA). Testlets are defined as groups of items related to a single content area that is developed as a unit. The strategy is illustrated using data from the administration of…

This paper illustrates the differences in inference that can be seen when traditional and multilevel structural equation modeling techniques are applied to hierarchical data. Research on faculty is an area in which multilevel data exist, and where previous research generally has not modeled the nested structure. Using data from the National Study…

Demonstrated, through simulation, that stationary autoregressive moving average (ARMA) models may be fitted readily when T>N, using normal theory raw maximum likelihood structural equation modeling. Also provides some illustrations based on real data. (SLD)

Proposed a method for extending the Bollen-Stine bootstrap model (K. Bollen and R. Stine, 1992) fit to structural equation models with missing data. Developed a Statistical Analysis System macro program to implement this procedure, and assessed its usefulness in a simulation. The new method yielded model rejection rates close to the nominal 5%…

Presents KANT, a FORTRAN 77 software program that tests assumptions of multivariate normality in a data set. Based on the test developed by M. V. Mardia (1985), the KANT program is useful for those engaged in structural equation modeling with latent variables. (SLD)

A general linear model framework is used to suggest that structure coefficients ought to be interpreted in structural equation modeling confirmatory factor analysis (CFA) studies in which factors are correlated. Two heuristic data sets make the discussion concrete, and two additional studies illustrate the benefits of CFA structure coefficients.…

Structural equation modelling is becoming increasingly popular in education. This article examines and compares a number of alternative assumptions governing nondirected paths in structural equation models without latent variables vis-a-vis a data set on lung ventilation. Some problems with the conventional procedures in path analysis are pointed…

Provides an introduction to the structural equation modeling concepts developed by J. Pearl, discussing the concept he calls "d-separation." Explains how d-separation connects to control variables, partial correlations, causal structuring, and even a potential mistake in regression. (SLD)

Illustrates how commonly available structural equation modeling programs can be used to conduct some basic matrix manipulations and generate multivariate normal data with given means and positive definite covariance matrix. Demonstrates the outlined procedure. (SLD)

Established a new criterion for the identification of recursive linear models in which some errors are correlated. Shows that identification is assured as long as error correlation does not exist between a cause and its direct effect; no restrictions are imposed on errors associated with indirect causes. (SLD)

Some problems of multiple-group factor rotation based on the parallel proportional profiles and confactor rotation of R. B. Cattell are described, and several alternative modeling solutions are proposed. Benefits and limitations of the structural-modeling approach to oblique confactor resolution are examined, and opportunities for research are…