Linked school and human services data approach for predicting near-term academic risk¶

Element · All elements
Evidence · 3 claims (3 for) · 2 studies (2 associational), q2 · 0 of 2 report an effect size · 3 claims rest on one study

Description¶

This element is the data-linkage approach developed by the partnership: school records are combined with "data on child welfare events, justice system involvement, and other human services involvement and public benefits receipt" to flag students likely to face academic problems in the near term. The snapshot presents it as the foundation for an early warning system serving both educators and human services staff in the Pittsburgh-area partner agencies.

Design Implications¶

Context¶

Requirements¶

• School data must be linkable with child welfare, justice system, human services, and public benefits records

Constraints¶

Target Learners¶

• K-12 students in Pittsburgh Public Schools and the Propel Schools charter network

Target Learning Goals¶

• Identifying students at risk of near-term academic problems so resources can be targeted before risks become serious

Claims¶

• A partnership developed an approach for identifying at-risk students using school data linked with child welfare, justice, human services, and public benefits data. [+W]
• A predictive model built from school and child welfare data identifies students at risk of near-term academic problems [+W]
• A predictive model built on school and child welfare data was assessed for identifying at-risk students in two Allegheny County education agencies [+W]

Related Elements¶

• Predictive-model approach using school and child welfare agency data to flag near-term academic risk
• Predictive model of near-term academic risk combining school and child welfare data
• Linked five-year student-level administrative dataset from Pittsburgh Public Schools, Propel Schools, and Allegheny County DHS
• Machine learning early warning algorithm using in- and out-of-school data to estimate per-student, per-problem, per-quarter risk scores
• Arizona linked education–child welfare student database

Examples¶

• Use an early warning system based on linked school and human services data to target resources and lessen risks before they become more serious
• Combine in-school and out-of-school data sources to understand and support students flagged as at risk
• Broker a formal data-sharing agreement between child welfare and education agencies to identify and serve students in foster care
• Use linked cross-system data to target programs such as dropout prevention and postsecondary preparation for students in foster care
• Implement a coherent student database linking education, child welfare, mental health, and judicial systems rather than further studying data sharing

Key Sources¶

• Julie Bruch, Jonathan Gellar, Lindsay Cattell, John Hotchkiss, and Phil Killewald. (2020). Using Data from Schools and Child Welfare Agencies to Predict Near-Term Academic Risks, Snapshot. Regional Educational Laboratory Mid-Atlantic. https://ies.ed.gov/ncee/edlabs