We consider estimating the effect of a treatment on a given outcome measured on subjects tested both before and after treatment assignment in observational studies. A vast literature compares the competing approaches of modelling the post-test score conditionally on the pre-test score versus modelling the difference, namely, the gain score. Our…

Sometimes a treatment, such as receiving a high school diploma, is assigned to students if their scores on two inputs (e.g., math and English test scores) are above established cutoffs. This forms a multidimensional regression discontinuity design (RDD) to analyze the effect of the educational treatment where there are two running variables…

This study explores three understudied facets--quadratic effects, change over time, and gender as a moderator--of the otherwise well-documented relationships between statistics anxiety and academic performance. Using pre- and post- course survey data among a sample of 111 undergraduate students in Social Statistics courses at a U.S. Midwestern…

Educators commonly use school climate survey scores to inform and evaluate interventions for equitably improving learning and reducing educational disparities. Unfortunately, validity evidence to support these (and other) score uses often falls short. In response, Whitehouse et al. proposed a collaborative, two-part validity testing framework for…

Multilevel Rasch models are increasingly used to estimate the relationships between test scores and student and school factors. Response data were generated to follow one-, two-, and three-parameter logistic (1PL, 2PL, 3PL) models, but the Rasch model was used to estimate the latent regression parameters. When the response functions followed 2PL…

Background: The unprecedented access to information in the 21st century entails a deep understanding of information and communication technology (ICT)-related factors in education and their impacts on learning and teaching. The role of attitudes towards ICT is a proven factor in student achievement. However, there is no consensus about the…

The purpose of this study was to explore potential effects of a 12-week therapeutic mentoring program targeting social, emotional, and behavioral concerns in 52 children and adolescents between 11 and 17 years of age. Self-reported scores on a norm-referenced behavioral questionnaire were tracked across the span of a mentoring program, and then…

Lord's Paradox occurs when a continuous covariate is statistically controlled for and the relationship between a continuous outcome and group status indicator changes in both magnitude and direction. This phenomenon poses a challenge to the notion of evidence-based policy, where data are supposed to be self-evident. We examined 50 effect size…

Although much attention has been given to rater effects in rater-mediated assessment contexts, little research has examined the overall stability of leniency and severity effects over time. This study examined longitudinal scoring data collected during three consecutive administrations of a large-scale, multi-state summative assessment program.…

Linking score scales across different tests is considered speculative and fraught, even at the aggregate level (Feuer et al., 1999; Thissen, 2007). We introduce and illustrate validation methods for aggregate linkages, using the challenge of linking U.S. school district average test scores across states as a motivating example. We show that…

To plan cluster-randomized trials with sufficient statistical power to detect intervention effects on student achievement, researchers need multilevel design parameters, including measures of between-classroom and between-school differences and the amounts of variance explained by covariates at the student, classroom, and school level. Previous…

Policymakers have grown increasingly interested in how experimental results may generalize to a larger population. However, recently developed propensity score-based methods are limited by small sample sizes, where the experimental study is generalized to a population that is at least 20 times larger. This is particularly problematic for methods…

The Every Student Succeeds Act requires states to identify schools with low-performing student subgroups for Targeted Support and Improvement or Additional Targeted Support and Improvement. Random differences between students' true abilities and their test scores, also called measurement error, reduce the statistical reliability of the performance…

The "Stabilizing Subgroup Proficiency Results to Improve the Identification of Low-Performing Schools" study used Bayesian stabilization to improve the reliability (long-term stability) of subgroup proficiency measures that the Pennsylvania Department of Education (PDE) uses to identify schools for Targeted Support and Improvement (TSI)…

This study examined the effect of similar vs. dissimilar proficiency distributions on uniform DIF detection on a statewide eighth grade mathematics assessment. Results from the similar- and dissimilar-ability reference groups with an SWD focal group were compared for four models: logistic regression, hierarchical generalized linear model (HGLM),…