Predicting student performance using educational data is a significant area of machine learning research. However, class imbalance in datasets and the challenge of developing interpretable models can hinder accuracy. This study compares different variations of the Synthetic Minority Oversampling Technique (SMOTE) combined with classification…

High dropout rate exists universally in massive open online courses (MOOCs) due to the separation of teachers and learners in space and time. Dropout prediction using the machine learning method is an extremely important prerequisite to identify potential at-risk learners to improve learning. It has attracted much attention and there have emerged…

This paper argues that engaging students in informal statistical reasoning from early school years is essential for the development of statistical understanding. We investigated if and how children aged six-seven years old identified variation in a table of data and made predictions through the design of a teaching experiment. The classroom…

To provide personalized support on educational platforms, it is crucial to model the evolution of students' knowledge states. Knowledge tracing is one of the most popular technologies for this purpose, and deep learning-based methods have achieved state-of-the-art performance. Compared to classical models, such as Bayesian knowledge tracing, which…

A distinction is made between scores as measures of a construct and predictions of a criterion or outcome variable. The interpretation attached to predictions of criteria, such as job performance or college grade point average (GPA), differs from that attached to scores that are measures of a construct, such as reading proficiency or knowledge…

The gold-standard for evaluating the effect of an educational intervention on student outcomes is running a randomized controlled trial (RCT). However, RCTs may often be small due to logistical considerations, and resulting treatment effect estimates may lack precision. Recent methods improve experimental precision by incorporating information…

Machine learning methods for predictive analytics have great potential for uncovering trends in educational data. However, simple linear models still appear to be most widely used, in part, because of their interpretability. This study aims to address the issues of interpretability of complex machine learning classifiers by conducting feature…

In institutional research, modern data mining approaches are seldom considered to address predictive analytics problems. The goal of this paper is to highlight the advantages of tree-based machine learning algorithms over classic (logistic) regression methods for data-informed decision making in higher education problems, and stress the success of…

Recent reforms emphasize a shift in how students should learn and demonstrate knowledge of science. These reforms call for students to learn content knowledge using science and engineering practices, creating integrated science knowledge. While there is existing literature about the development of integrated science knowledge assessments, few…

District and state education leaders frequently use screening assessments to identify students who are at risk of performing poorly on end-of-year achievement tests. This study examines the use of a universal screening assessment of reading skills for early identification of students at risk of low achievement on nationally normed tests of reading…

Although behavior analysis relies primarily on visual inspection for interpreting data, previous research shows that the method of display can influence the judgments. In the current study, 26 Board-Certified Behavior Analysts reviewed two data sets displayed on each of three methods--equal-interval graphs, tables, and Standard Celeration…

Predictions from the Rejection Sensitivity (RS) model concerning the social causes and consequences of RS were examined in a longitudinal study of 150 middle school students. Peer nominations of rejection, self-report measures of anxious and angry rejection expectations, and social anxiety, social withdrawal, and loneliness were assessed at two…

This study examines the use and cost of out-of-home placement for children who live away from their families in the state of Missouri. It was found that during the study period of fiscal year 1985 through fiscal year 1988: (1) an average of 12,321 children were in placement outside their homes annually; (2) the number of children placed in…

The purpose of this study was to examine the variable of estimated earnings in order to determine how forecasts might be utilized to develop a securities portfolio strategy. The hypothesis stated that there is an inverse relationship between projected change in earnings per share and security performance. Ninety-one New York Stock Exchange…

Time limits represent a substantial departure from previous welfare policy. Theory suggests that their effects should vary according to the age of the youngest child of the family. I test this prediction using data from the Current Population Survey and find that time limits indeed have larger effects on families with younger children. I further…