Teacher classroom teaching behavior indicators serve as a crucial foundation for guiding instructional evaluation. Existing indicator system suffers from limitations such as strong subjectivity and weak contextual generalization capabilities. Generalized category discovery (GCD) enables automatic data clustering to identify known categories and…

Statewide longitudinal data systems (SLDSs) often rely on personal identifiers to securely link individual-level data across early childhood, K-12, higher education, and the workforce. However, different sectors use different types of personal identifiers which can make accurately connecting records difficult. Driver's license data offers a single…

Response styles pose great threats to psychological measurements. This research compares IRTree models and anchoring vignettes in addressing response styles and estimating the target traits. It also explores the potential of combining them at the item level and total-score level (ratios of extreme and middle responses to vignettes). Four models…

Adapting interventions based on learner progress is paramount to the effectiveness of interventions in special education and applied behavior analysis. Although there is some research on effective methods for training practitioners to make general instructional decisions (e.g., modify an intervention) based on graphed performance data, research on…

Institutional researchers are acutely aware of the systemic inequities pervasive throughout higher education in the United States because the data that we collect, analyze, visualize, and disseminate quantifies and reveals them. As calls for addressing issues of equity have intensified across campuses, the question of how institutional research…

Background: Randomized controlled trials (RCTs) give unbiased estimates of average effects. However, positive effects for the majority of students may mask harmful effects for smaller subgroups, and RCTs often have too small a sample to estimate these subgroup effects. In many RCTs, covariate and outcome data are drawn from a larger database. For…

Learning analytics (LA) provides insight into student performance and progress, allowing for targeted interventions and support to improve the student learning experience. Uses of LA are diverse, including measuring student engagement, retention, progression, student well-being and curriculum development. This article provides perspectives on the…

Academic dropout remains a significant challenge for education systems, necessitating rigorous analysis and targeted interventions. This study employs machine learning techniques, specifically random forest (RF) and feature tokenizer transformer (FTT), to predict academic attrition. Utilizing a comprehensive dataset of over 40 000 students from an…

Data-based decision-making, which involves evaluating students' progress and making instructional decisions, is an integral competency for preservice teachers. Several studies have found that visual aids, such as decision-making models, may be an effective way to train preservice teachers to make instructional decisions. The purpose of this study…

In recent years, there has been growing interest in the use of data-driven learning (DDL) in L2 writing instruction. This paper examined whether and to what extent DDL activities could enhance the writing complexity, accuracy, and fluency (CAF) of 30 Thai EFL learners. The presentation of DDL in this study was hands-on concordancing with the…

Through time-series graphs, teachers often evaluate progress monitoring data to make both low- and high-stakes decisions for students. The construction of these graphs--specifically, the presence of an aimline and the data points per x- to y-axis ratio (DPPXYR)--may impact decisions teachers make. The purpose of this study was to evaluate the…

Randomized A/B tests within online learning platforms represent an exciting direction in learning sciences. With minimal assumptions, they allow causal effect estimation without confounding bias and exact statistical inference even in small samples. However, often experimental samples and/or treatment effects are small, A/B tests are underpowered,…

Promoting a high level of student engagement has been a goal for many teachers. Opportunities to respond (OTR) offer a low-cost instructional practice that allows teachers to improve student engagement in the classroom. In this study, we explored the potential effects of a data-driven coaching model on one elementary school teacher's…

Accurate and efficient universal screening is a foundational component of multi-tiered systems of support for reading. By the time students reach middle school, educators often have extant data available to inform screening decisions. Therefore, the decision to collect additional data to inform screening should be considered carefully. The…

Presenting novel numbers about climate change to people after they estimate those numbers can shift their attitudes and scientific conceptions. Prior research suggests that such science learning can be supported by encouraging learners to make use of given benchmark information, however there are several other numerical estimation skills that may…