A Quasi-Experimental Evaluation of An On-Line Formative Assessment and Tutoring System

Abstract

ASSISTments is a web-based math tutor designed to address the need for timely student assessment while simultaneously providing instruction, thereby avoiding lost instruction time that typically occurs during assessment. This article presents a quasi-experiment that evaluates whether ASSISTments use has an effect on improving middle school students' year-end test scores. The data was collected from 1240 seventh graders in three treatment schools and one comparison school. Post-test (7th grade year-end test) results indicate, after adjusting for the pre-test (6th grade year-end test), that students in the treatment schools significantly outperformed students in the comparison school and the difference was especially present for special education students. A usage analysis reveals that greater student use of ASSISTments is associated with greater learning consistent with the hypothesis that it is useful as a tutoring system. We also found evidence consistent with the hypothesis that teachers adapt their whole class instruction based on overall

Automated, adaptive guidance for K-12 education

“…The few studies that found promising outcomes concerned how the teacher and computer worked together (Koedinger, McLaughlin, & Heffernan, 2010;McElhaney et al, 2012;White et al, 2010). For example, Koedinger et al (2010) found that automated, adaptive guidance may have helped teachers lead large classes with diverse students. The ASSISTments program provided students with detailed individualized guidance in solving mathematics problems and provided teachers with diagnostic reports of their students' performance.…”

“…When guidance is automated teachers can direct their efforts to students the guidance system identifies as not making progress (Poulsen, Hastings, & Allbritton, 2007;Rich, 2012). Teachers can also review automated scores to gauge overall class progress or to design activities that address specific conceptual difficulties (Koedinger et al, 2010;McElhaney et al, 2012). Instructors can use student responses immediately to adjust their instruction and annually to revise instruction for the next group of students.…”

ELM-ART – An Interactive and Intelligent Web-Based Electronic Textbook

“…Together with other early adaptive and intelligent Web-based educational systems (Brusilovsky & Peylo, 2003), ELM-ART encouraged a whole generation of more recent systems including such popular systems as SQL-Tutor (Mitrovic, 2003) and Assistments (Koedinger et al, 2010). While switching from a conventional system to a Web-based application appears to be a technical rather than conceptual innovation, the ability to access an education system anytime, from anywhere, and without installation struggle is very important.…”

Toward a New Approach to the Evaluation of a Digital Curriculum Using Learning Analytics

“…This kind of research is more common in higher education to help retain students and improve outcomes (Dietz-Uhler & Hurn, 2013;Olmos & Corrin, 2012;Smith, Lange, & Huston, 2012). In grades K-12, researchers use student data to predict future achievement, as is the case with the ASSISTments initiative at Worcester Polytechnic Institute, which has produced a corpus of LA research ranging from measuring ASSISTment's effect on math achievement (Koedinger, McLaughlin, & Heffernan, 2010) to comparing the effect of traditional and computer-supported homework on student outcomes (Mendicino, Razzaq, & Heffernan, 2009). Similarly, using data from users interacting with videos in the Khan Academy, Muñoz-Merino, Ruip erez, and Delgado (2013) proposed a set of variables to measure diverse learning constructs.…”