Education Data Done Right II
New volume of Education Data Done Right showcases applied data science strategies and lessons learned in education agencies across the country. New chapters cover data governance, data documentation, early warning systems, personal and professional identities, and more and are written by 6 data analysts with expertise in public education agencies across the country.
Education Data Done Right
New book covering the missing elements critical to success in building data capacity in education agencies. Authored by 3 data analysts with expertise in public education agencies.
Delivery of State-provided Predictive Analytics to Schools: Wisconsin’s DEWS and the Proposed EWIMS Dashboard
Situates the Wisconsin Dropout Early Warning System in the context of national models of predictive analytic systems in education, including a focus on the Early Warning Implementation Monitoring System (EWIMS).
Effect of English Proficiency Classification on Student Outcomes: Evidence from Wisconsin
Article examines English Language Learner reclassification policies using a regression discontinuity framework to show that being reclassified as fully English proficient has positive effects for students' educational outcomes.
Education Early Warning Systems
The award-winning Wisconsin Dropout Early Warning System was co-developed with educators to ensure that the sophisticated enterprise scale machine-learning provides schools with a timely list of students who should be considered for additional support and attention.
Building an Accurate Statewide Dropout Early Warning System in Wisconsin
Describes the Wisconsin Dropout Early Warning System (DEWS), a predictive model of student dropout risk for students in grades 6-9. Explains how DEWS' publicly available software modules can be applied to new data and outcomes.
School Boards and the Democratic Promise
Examines the degree of democratic control communities exercise over school boards through elections, combining election results for Wisconsin school districts with administrative records on local conditions.
This data simulation package creates realistic synthetic data that allows users to collaborate across agencies without privacy concerns or the need for a data sharing agreement, while writing code that can then be translated back to the original data.
Civilytics provides R training ranging from single workshop introductions to R to advanced R training on spatial data analysis, web application development with Shiny, predictive analytics and more. The 'model and coach' approach is central to many of Civilytics' trainings.