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…

Knowledge tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive (AR) modeling on the sequence of former exercises…

In the context of education big data, it uses data mining and learning analysis technology to accurately predict and effectively intervene in learning. It is helpful to realize individualized teaching and individualized teaching. This research analyzes student life behavior data and learning behavior data. A model of student behavior…

Inappropriate treatment of missing data may introduce bias into the value-added estimation. We consider a commonly used value-added model (VAM), which includes the past student test score as a covariate. We formulate a joint model of student achievement and missing data, in which the probability of observing a test score depends on observing the…

States can and should continue to measure student growth in 2021. Growth data will be crucial to understanding how school closures due to COVID-19 have affected student progress and what supports they will need to get back on track. Education leaders will also need growth data to ensure that any recovery efforts are equitable as well as effective…

Using a sample of schools testing annually in grades 9-11 with a vertically linked series of assessments, a latent growth curve model is used to model test scores with student intercepts and slopes nested within school. Missed assessments can occur because of student mobility, student dropout, absenteeism, and other reasons. Missing data…

This dissertation's two primary purposes were to construct an alternative socioeconomic status model and estimate how it predicts student success in higher education. This research filled a gap in knowledge about the widely acknowledged disparities in higher education based on socioeconomic status. Prior research has often relied on parental…

The purpose of this qualitative phenomenological study was to explore how the post-adoption experiences of elementary school leaders influence their use of student achievement data in making educational decisions, after the implementation of a student information system (SIS). The participants consisted of K-5 elementary principals and assistant…

California's K-12 system relies on the Smarter Balanced Assessment Consortium (SBAC) English and mathematics tests to measure student academic progress and assess school and district performance. This report uses publicly available data to explore trends in student performance during the first three years this test has been in place. Key findings…

In this book, best-selling author Susan M. Brookhart helps teachers and administrators understand the critical elements and nuances of assessment data and how that information can best be used to inform improvement efforts in the school or district. Readers will learn: (1) What different kinds of data can--and cannot--tell us about student…

Does data use make a difference in student achievement? Despite the field's optimism on this matter, relatively few studies have attempted to quantify the effects of data use. These studies have often used the presence of a data use intervention (e.g., a data system or data coaching) as a proxy for use, as opposed to tracking teachers' direct…

Data has played an important role in England's recent school improvement journey. The evolution of the approach has not been perfect but the National Pupil Database has become a vital tool for health checking the education system, driving accountability, directing education policymaking, and tracking the educational attainment of key vulnerable…

This study investigates: (1) how principals' data-driven practices may vary by principals' and school backgrounds and how that changes over time; (2) how principals' data-driven practices influence teacher buy-in; and (3) how principals' data-driven practices and teachers' buy-in influence student outcomes. This study uses data from the Study of…

In this paper I propose Bayesian estimation of a nonlinear panel data model with a fractional dependent variable (bounded between 0 and 1). Specifically, I estimate a panel data fractional probit model which takes into account the bounded nature of the fractional response variable. I outline estimation under the assumption of strict exogeneity as…

College graduation rates in the United States are low in both real and relative terms. This has left all stakeholders looking for novel solutions while perhaps ignoring extant but underused programs. This article examines the effect of "summer bridge" programs, which have students enroll in coursework prior to beginning their first full…