We report on a randomized controlled trial of an intervention that leverages the availability of laptops for all public-school students in the state of Maine. The intervention, called "ASSISTments," provides feedback to students as they solve mathematics homework problems and automatically prepares reports for teachers about student…

Recent studies [10, 23] using US nationwide databases showed high school boys spent significantly less time doing homework than girls, based on their responses to questionnaires and surveys. To investigate gender differences in homework in middle school, in this paper, we analyzed computer log data and standardized test scores of more than 1,000…

In a randomized field trial with 2,850 seventh-grade mathematics students, we evaluated whether an educational technology intervention increased mathematics learning. Assigning homework is common yet sometimes controversial. Building on prior research on formative assessment and adaptive teaching, we predicted that combining an online homework…

In a rigorous evaluation of ASSISTments as an online homework support conducted in the state of Maine, SRI International reported that "the intervention significantly increased student scores on an end-of-the-year standardized mathematics assessment as compared with a control group that continued with existing homework practices."…

In a randomized field trial with 2,850 seventh-grade mathematics students, we evaluated whether an educational technology intervention increased mathematics learning. Assigning homework is common yet sometimes controversial. Building on prior research on formative assessment and adaptive teaching, we predicted that combining an online homework…

Recent studies [10, 23] using US nationwide databases showed high school boys spent significantly less time doing homework than girls, based on their responses to questionnaires and surveys. To investigate gender differences in homework in middle school, in this paper, we analyzed computer log data and standardized test scores of more than 1,000…

This report presents the findings from interviews with principals about their schools' participation in the ASSISTments efficacy study on seventh-grade mathematics. The purpose of the interviews was to explore the following areas: To what extent schools had policies or expectations regarding homework practice and completion; To what extent schools…

The field of learning analytics is rapidly developing techniques for using data captured during online learning. In this article, we develop an additional application: the use of analytics for improving implementation fidelity in a randomized controlled efficacy trial. In an efficacy trial, the goal is to determine whether an innovation has a…

Much research has been done on the development of an intelligent tutoring system (ITS), and small empirical studies have demonstrated the effectiveness of ITS at promoting student learning. However, large-scale implementation of ITS in school settings has not been researched thoroughly. In this paper, we describe an ongoing randomized controlled…

Homework has been a mysterious world to educators due to the fact that it is hard to collect data with regard to homework behaviors. Little is known about when a student works on homework, how long it takes him to complete the homework, how much time he spends on a problem and whether and where he has struggled, etc. Such information not only have…

Personalized learning considers that the causal effects of a studied learning intervention may differ for the individual student. Making the inference about causal effects of studies interventions is a central problem. In this paper we propose the Residual Counterfactual Networks (RCN) for answering counterfactual inference questions, such as…

Data is flexible in that it is molded by not only the features and variables available to a researcher for analysis and interpretation, but also by how those features and variables are recorded and processed prior to evaluation. "Big Data" from online learning platforms and intelligent tutoring systems is no different. The work presented…

Data is flexible in that it is molded by not only the features and variables available to a researcher for analysis and interpretation, but also by how those features and variables are recorded and processed prior to evaluation. "Big Data" from online learning platforms and intelligent tutoring systems is no different. The work presented…

In this work, we describe a new statistical method to improve the detection of treatment effects in interventions. We call our method TAME (Trained Across Multiple Experiments). TAME takes advantage of multiple experiments with similar designs to create a single model. We use this model to predict the outcome of the dependent variable in unseen…

Student affect has been found to correlate with short- and long-term learning outcomes, including college attendance as well as interest and involvement in Science, Technology, Engineering, and Mathematics (STEM) careers. However, there still remain significant questions about the processes by which affect shifts and develops during the learning…