A.V. Crawford

Evaluation of Parallel Analysis Methods for Determining the Number of Factors.

Population and sample simulation approaches were used to compare the performance of parallel analysis using principal component analysis (PA-PCA) and parallel analysis using principal axis factoring (PA-PAF) to identify the number of underlying factors. Additionally, the accuracies of the mean eigenvalue and the 95th percentile eigenvalue criteria were examined. The 95th percentile criterion was preferable for assessing the first eigenvalue using either extraction method. In assessing subsequent eigenvalues, PA-PCA tended to perform as well as or better than PA-PAF for models with one factor or multiple minimally correlated factors; the relative performance of the mean eigenvalue and the 95th percentile eigenvalue criteria depended on the number of variables per factor. PA-PAF using the mean eigenvalue criterion generally performed best if factors were more than minimally correlated or if one or more strong general factors as well as group factors were present.

Testing Gender Effects on the Mechanisms Explaining the Association between Post-Traumatic Stress Symptoms and Substance Use Frequency

The present study examines gender differences in the mechanisms that explain the association between PTSD symptoms and substance use frequency in a sample of 182 urban substance users. Specifically, the current study examined gender differences in the role of two potential explanatory variables, namely, difficulties controlling impulsive behavior when distressed (IMP), and a lack of emotional awareness and clarity (AW/CLAR). Multiple-group path modeling (across males and females) was used to examine gender differences in the path coefficients from PTSD symptoms to IMP and AW/CLAR, and from these latter variables to drug use frequency. Results indicated that PTSD symptoms were associated with IMP and AW/CLAR, and these path coefficients did not vary by gender. However, gender differences emerged when considering the path coefficients from AW/CLAR and IMP to substance use frequency. Specifically, for women, the association between PTSD and substance use was partially explained by IMP, whereas for men, the association between PTSD and substance use was partially explained by AW/CLAR. The current study is the first to examine gender differences in mechanisms accounting for the association between PTSD and substance use frequency, and these results also support the value and importance of examining gender differences in mechanisms underlying PTSD-SUD comorbidity.

A Bayesian Network Approach To Modeling Learning Progressions

A central challenge in using learning progressions (LPs) in practice is modeling the relationships that link student performance on assessment tasks to students’ levels on the LP. On the one hand, there is a progression of theoretically defined levels, each defined by a configuration of knowledge, skills, and/or abilities (KSAs). On the other hand, there are observed performances on assessment tasks, associated with levels but only imperfectly and subject to inconsistencies. What is needed is a methodology that can be used to map assessment performance onto the levels, to combine information across multiple tasks measuring similar and related KSAs, to support inferences about students, and to study how well actual data exhibit the relationships posited by the LP.