School dropout is a growing concern across Latin America because of its negative social and economic consequences. Identifying who is likely to drop out, and therefore could be targeted for interventions, is a well-studied prediction problem in countries with strong administrative data. In this paper, we use new data in Guatemala and Honduras to…

Purpose: In an era of unprecedented student measurement and emphasis on data-driven educational decision making, the full potential for using data to target resources to students has yet to be realized. This study explores the utility of machine-learning techniques with large-scale administrative data to identify student dropout risk. Research…

Data from a population-based repository in Manitoba showed that students who are male, young for grade, and in Grades 1, 2, 7, and 8 were the most likely to be retained. After controlling for key student factors including socioeconomic status, school changes, and key school characteristics including stability of the student body, retention was a…

"Straight A's: Public Education Policy and Progress" is a biweekly newsletter that focuses on education news and events both in Washington, DC and around the country. The following articles are included in this issue: (1) Show Me the Money: Alliance Analysis Finds That States Could Generate Millions More in Wages by Raising High School…

This report uses a unique set of data obtained from the Kids Integrated Data System (KIDS), which is housed at the University of Pennsylvania's Cartographic Modeling Laboratory. The KIDS system merges individual-level data on young people from the School District of Philadelphia and the city's social service agencies, including the Department of…