Colleges have increasingly turned to predictive analytics to target at-risk students for additional support. Most of the predictive analytic applications in higher education are proprietary, with private companies offering little transparency about their underlying models. We address this lack of transparency by systematically comparing two…

These are the appendices for "Transitioning to College and Work. Part 2: A Study of Potential Enrollment Indicators," which examined potential indicators of college enrollment school and district staff might use to identify and support students at risk of not attending college. The study used administrative data from the Houston…

Dual credit courses are legislated course enrollment options available to ninth- to twelfth-grade students in the State of Texas. The dual credit program provides the opportunity for all high school students, regardless of grade level, to earn college credits while working toward a high school diploma (Houston ISD, 2018). There is no limit to the…

During the 2013/14 school year two Florida school districts sought to develop an early warning system to identify students at risk of low performance on college readiness measures in grade 11 or 12 (such as the SAT or ACT) in order to support them with remedial coursework prior to high school graduation. The study presented in this report provides…

The purpose of this study was to examine the cognitive predictors of calculations and number line estimation with whole numbers and fractions. At-risk 4th-grade students (N = 139) were assessed on 6 domain-general abilities (i.e., working memory, processing speed, concept formation, language, attentive behavior, and nonverbal reasoning) and…

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…

The document are the appendixes for the full report, "Using Data from Schools and Child Welfare Agencies to Predict Near-Term Academic Risks." The study team collected and linked five academic years of student-level administrative data from Pittsburgh Public Schools (PPS), Propel Schools, and the Allegheny County Department of Human…

This report looks at children's education careers by drawing on data from a sample of more than 3,000 young people who have been tracked through school since the age of three. In particular, this research identified a group of disadvantaged children, establishing what predicted their academic success at the age of 11 and following them up to age…

The North Carolina Pre-Kindergarten Program (NC Pre-K) is a state-funded initiative for at-risk 4-year-olds, designed to provide a high quality, classroom-based educational program during the year prior to kindergarten entry. Children are eligible for NC Pre-K based on age, family income (at or below 75% of state median income), and other risk…

Only about 59 percent of full-time, first-time students at four-year institutions complete such a degree within six years at the same school. Completion rates are even lower for those starting part-time, or at less than four-year schools (and planning to transfer). Which social indicators--such as student engagement, enrollment status, and family…

There are many factors which might cause a student to drop out of a course of study; some of these are preventable. This paper describes the piloting of a survey tool designed to identify students at risk of not completing. Attendance was found to be the strongest predictor of module completion; low or declining scores on the survey were also…

This Technical Brief presents an historical analysis of key indicators of dropout for Delaware students in grades 9-12. Cut points for key risk indicators of high school dropout for the State of Delaware are provided. Using data provided by the Delaware Department of Education (DDOE), relationships between student dropout and several student…

The purpose of this study was to identify differences in performance if any, between learners with a high school diploma, and those with a GED credential, at two postsecondary institutions, Holland College on Prince Edward Island (PEI) and Nova Scotia Community College in Nova Scotia (NS). Of interest is how these adults perform in a postsecondary…

Ninth-grade predictors of dropout risk among Austin Independent School District's English language learner students included the following: having an attendance rate below 90%, being 16 years or older, earning less than 5 course credits, attending a Title I campus and scoring beginning or intermediate on the state's English proficiency assessment…

The main aim of this study was to gain a better understanding of why students abandon their studies, or perform less well than expected given their high school grades, and to develop predictive models that can help identify those students most at-risk at the time they enter college. This will allow teachers and those responsible for student…