Date of Conferral
Doctor of Education (Ed.D.)
Educators in the United States (U.S.) are increasingly turning to intelligent tutoring systems (ITS) to provide differentiated math instruction to high school students. However, many struggling high school learners do not perform well on these platforms, which reinforces the need for more awareness about effective supports that influence the achievement of learners in these milieus. The purpose of this study was to determine what factors of the Assessment and Learning in Knowledge Spaces (ALEKS), an ITS, are predictive of struggling learners' performance in a blended-learning Algebra 1 course at an inner city technical high school located in the northeastern U.S. The theoretical framework consisted of knowledge base theory, the zone of proximal development, and cognitive learning theory. Three variables (student retention, engagement time, and the ratio of topics mastered to topics practiced) were used to predict the degree of association on the criterion variable (mathematics competencies), as measured by final course progress grades in algebra, and the Preliminary Scholastic Assessment Test (PSATm) math scores. A correlational predictive design was applied to assess the data of a purposive sample of 265 struggling students at the study site; multiple regression analysis was also used to investigate the predictability of these variables. Findings suggest that engagement time and the ratio of mastered to practiced topics were significant predictors of final course progress grades. Nevertheless, these factors were not significant contributors in predicting PSATm score. Retention was identified as the only statistically significant predictor of PSATm score. The results offer educators with additional insights that can facilitate improvements in mathematical content knowledge and promote higher graduation rates for struggling learners in high school mathematics.