In an increasingly data-driven society, making decisions with data is a requirement not only for research scientists but also for navigating life more generally (Kjelvik & Schultheis, 2019). An informed citizenry must be prepared to discover patterns, predict outcomes, make decisions with data, and evaluate data-based claims for legitimacy and…

U.S. middle school teachers have struggled to meet the instructional needs of students in the area of mathematics. Teachers' approaches to assessment and instructional strategies remain understudied; such knowledge could help educational leaders to devise strategies to boost student achievement. The purpose of this qualitative study was to examine…

Old habits die hard, particularly when they are part of the unexamined norms of schooling. In "Why Are We Still Doing That?," the best-selling authors of "Total Participation Techniques" lead a teacher-positive, empathetic inquiry into 16 common educational practices that can undermine student learning: (1) Round robin reading;…

Meaning-making in teaching-learning mathematical processes is a relevant issue analysed through different philosophical and educational frames. In particular, the use of digital tools in mathematics education affects the meaning-making processes. This paper discusses meaning-making from a phenomenological standpoint, in which interpretative…

We discuss the learning goals, content, and delivery of a University of Plymouth intensive module delivered over four weeks entitled MATH1608PP Understanding Big Data from Social Networks, aimed at introducing students to a broad range of techniques used in modern Data Science. This module made use of R, accessed through RStudio, and some popular…

Educational systems typically contain a large pool of items (questions, problems). Using data mining techniques we can group these items into knowledge components, detect duplicated items and outliers, and identify missing items. To these ends, it is useful to analyze item similarities, which can be used as input to clustering or visualization…

Latent variable models, such as the popular Knowledge Tracing method, are often used to enable adaptive tutoring systems to personalize education. However, finding optimal model parameters is usually a difficult non-convex optimization problem when considering latent variable models. Prior work has reported that latent variable models obtained…

The 10th International Conference on Educational Data Mining (EDM 2017) is held under the auspices of the International Educational Data Mining Society at the Optics Velley Kingdom Plaza Hotel, Wuhan, Hubei Province, in China. This years conference features two invited talks by: Dr. Jie Tang, Associate Professor with the Department of Computer…

Students wanting to succeed in higher education are required to adopt an adequate learning approach. By analyzing individual learning characteristics, teachers can give personal advice to help students identify their learning success factors. An expert system based on fuzzy logic can provide economically viable solutions to help students identify…

The 11th International Conference on Educational Data Mining (EDM 2018) is held under the auspices of the International Educational Data Mining Society at the Templeton Landing in Buffalo, New York. This year's EDM conference was highly competitive, with 145 long and short paper submissions. Of these, 23 were accepted as full papers and 37…

Implementation of effective interventions relies on the use of assessment data to adequately describe the learning problem and offer potential solutions. The use of curriculum-based assessment and measurement when combined with the learning hierarchy could offer a paradigm for decision making based on a skill-by-treatment interaction.…

Educational systems in the United States are generating vast amounts of data on student achievement. This may provide researchers and policy makers with long sought-after insight on the factors explaining student performance. This study uses recent data from Washington 10th graders to examine why some students learned more math than others.…

We propose the development of a "population" of high-quality assessment tasks that cover the performance goals set out in the "Common Core State Standards for Mathematics." The population will be published. Tests are drawn from this population as a structured random sample guided by a "balancing algorithm."

The American government set new standards mandating States to demonstrate adequate yearly progress for all students with the inception of the No Child Left Behind Act. To be eligible for the more recent Race to the Top funds, states must show, in part, a commitment to "building data systems that measure student growth and success, and inform…

The body of research on the design, implementation, and effects of performance-based compensation systems has influenced the design and evaluation of the 2010 Teacher Incentive Fund (TIF) grants. In the sections presented here, the authors describe the key components of 2010 TIF grants and the conceptual framework for the evaluation. The remainder…