Predicting student performance using educational data is a significant area of machine learning research. However, class imbalance in datasets and the challenge of developing interpretable models can hinder accuracy. This study compares different variations of the Synthetic Minority Oversampling Technique (SMOTE) combined with classification…

This work reports on the implementation of a self-contained data-literacy exercise designed for use in undergraduate classes to help students practice data literacy skills such as interpreting and evaluating evidence and assessing arguments based on data. The exercises use already developed data-visualizations to test and develop students' ability…

How do people reason with data to make sense of the world? What implications might everyday practices hold for data literacy education? We leverage the unique context of the COVID-19 pandemic to shed light on these questions. COVID-19 has engendered a complex, multimodal ecology of information resources, with which people engage in high-stakes…

In education settings, treatments are often non-randomly assigned to clusters, such as schools or classrooms, while outcomes are measured for students. This research design is called the clustered observational study (COS). We examine the consequences of common support violations in the COS context. Common support violations occur when the…

Choices made on data visualizations guide how users make meaning of the information presented. This research investigates design decisions made on 115 state-level dashboards reporting school safety data. Using pre-determined codes drawn from a framework of visualization rhetoric, dashboard characteristics were described and analyzed. Analysis…

In institutional research, modern data mining approaches are seldom considered to address predictive analytics problems. The goal of this paper is to highlight the advantages of tree-based machine learning algorithms over classic (logistic) regression methods for data-informed decision making in higher education problems, and stress the success of…

Internationally, there has been a policy push for using student data for instruction. Yet, research has noted few examples of actually understanding how this data-use practice takes place. This study presents a case of an instructional data team making sense of student data. The study shares data to show how teachers' process for using data to…

The quality of a data display can have an impact on the interpretation of those data. A survey of the literature indicates that data displays can vary in quality of accuracy, clarity, and efficacy. In this study we develop and apply an evaluative rubric to graphs in a sample of six education journals: three research and three practitioner. Results…

Data driven pedagogy has been introduced into Australian schools over the last decade to improve student learning outcomes, but are teacher educators preparing preservice teachers to be data literate? We used a survey to investigate ready-to-graduate preservice teachers' beliefs regarding their knowledge and skills in data literacy. Before…

In this study, we used a paper-pencil questionnaire to investigate whether teachers, administrators, and parents differed in their preferences and accuracy when interpreting visual data displays for decision making. For the data analysis, we used nonparametric tests due to violations of distributional assumptions for using parametric tests. We…

This study examines how geoscience experts and novices make meaning from an iconic type of data visualization: shaded relief images of bathymetry and topography. Participants examined, described, and interpreted a global image, two high-resolution seafloor images, and 2 high-resolution continental images, while having their gaze direction…

This phenomologic study was carried out in order to determine how 63 pre-service chemistry teachers graduated from Chemistry Branch of Science Faculty in the pedagogical training program during 2013-2015 academic years defined the concepts of density and melting and boiling points and how they interpreted the data in micro levels. A diagnostic…

There is much agreement among chemical education researchers that expertise in chemistry depends in part on the ability to coordinate understanding of phenomena on three levels: macroscopic (observable), sub-microscopic (atoms, molecules, and ions) and symbolic (chemical equations, graphs, etc.). We hypothesize this "level-coordination…

Although practical laboratory activities are often considered the linchpin of science education, asking students to produce many large practical reports can be problematic. Practical reports require diverse skills, and therefore do not focus the students' attention on any one skill where specific skills need to be enhanced. They are also…

Data literacy is recognized as a critically important skill in today's society, but thinking with and about data is often ignored in K-12 curricula. The Thinking With Data (TWD) project advocates that data literacy is a skill that should be addressed in an interdisciplinary manner. This article provides an overview of the TWD curriculum for middle…