Automatic machine learning (AutoML) methods automate the time-consuming, feature-engineering process so that researchers produce accurate student models more quickly and easily. In this paper, we compare two AutoML feature engineering methods in the context of the National Assessment of Educational Progress (NAEP) data mining competition. The…

An alternative to null hypothesis significance testing is presented and discussed. This approach, referred to as observation-oriented modeling, is centered on model building in an effort to explicate the structures and processes believed to generate a set of observations. In terms of analysis, this novel approach complements traditional methods…

Model evaluation -- the process of making inferences about the performance of predictive models -- is a critical component of predictive modelling research in learning analytics. We survey the state of the practice with respect to model evaluation in learning analytics, which overwhelmingly uses only naïve methods for model evaluation or…

Traditional knowledge-component models describe students' content knowledge (e.g., their ability to carry out problem-solving procedures or their ability to reason about a concept). In many STEM domains, instruction uses multiple visual representations such as graphs, figures, and diagrams. The use of visual representations implies a…

The pronunciation of regular past tense verbs seems to be difficult for most L2 learners, especially in L2 learners whose first language phonological system is different from the English one. It is predicted that Thai EFL students could encounter difficulties perceiving English coda clusters like the '-ed' ending sounds. For this reason, this…

Online education is rapidly becoming a significant method of course delivery in higher education. Consequently, instructors analyze student performance in an attempt to better scaffold student learning. Learning analytics can provide insight into online students' course behaviors. Archival data from 167 graduate level education students enrolled…

While multilingualism itself is a widely analyzed topic, a study about multilingualism at German schools abroad is so far unique. This quantitative study investigates the differences in the size of German expressive and receptive vocabulary between monolingual and multilingual students, aged between 5 and 11 years. A cohort of 65 multilingual…

The study is a comparative analysis of physics candidates' scores in West African and National Examinations Councils. It also investigates influence of gender. Results of 480 candidates were randomly selected form three randomly selected Senior Science Colleges using the WASSCE and NECOSSCE computer printout sent to the schools, transformed using…

Higher education research highlights the difficulties students face when transitioning from a junior college to a traditional university. This study explored a gap between junior vs. traditional university students' academic self-efficacy beliefs. This study also controlled for the effects of the student role-identity and academic performance on…

Prior learning assessment (PLA) is the process of evaluating learning, regardless of when or where the learning occurred, and, if the learning is at the college level, awarding college credit to the possessor of that learning. This article provides an overview of the PLA program at a large public U.S. institution and presents the findings of the…

This dissertation investigated citizen science, a tool that connects the public to the scientific community through research-based projects and education campaigns. Benefits include volunteers adding data to long-term data sets and improved scientific literacy among the public. Oftentimes, there is trepidation among scientists, managers, and…

Undergraduate research experiences confer benefits on students bound for science, technology, engineering, and mathematics (STEM) careers, but the low number of research professionals available to serve as mentors often limits access to research. Within the context of our summer research program (BRAIN), we tested the hypothesis that a team-based…

Team-based learning (TBL) has been shown to improve many aspects of student learning, but no previous research has systematically examined the effects of group exams on English as an Additional Language (EAL) students in university classrooms. This study is a small-scale action research examining the role of students' English language status in…

There are so many different intervention programs for educators to use to increase the reading achievement of below grade level students, that it can often be difficult to choose the appropriate one for the students. Most programs are scripted and are used with small groups of students. Reading Recovery is not a scripted program and is taught in a…

Based on national sampling survey data from 2006, 2008, and 2011, the author uses the Mare educational transition model to systematically examine changing trends in inequalities in urban-rural educational opportunities at all educational stages from 1940 to 2010. Through a comparative analysis of five birth year groups, inequalities in urban-rural…