Estimating Nationwide High-Dosage Tutoring Expenditures: A Predictive Model Approach

• In Event: Exploring the Adequacy and Equity of Federal Stimulus Funding and Beyond

Abstract

The COVID-19 pandemic caused unprecedented learning loss, with K-12 students losing up to half a grade level in certain subjects. To address this, the federal government allocated \$190 billion in relief. We know from previous research that tutoring was a common expenditure for districts. We don't know how much was spent. This study estimates district-level expenditures on high-dosage tutoring using custom scraped dataset from over 7,000 ESSER plans. Employing XGBoost, we predict tutoring expenses with an R² of 0.9335 and MAPE of 14.18\%. Applied to districts mentioning tutoring, the estimated total expenditure ranged from \$3.23 billion to \$3.98 billion, highlighting a significant investment in addressing learning loss. These findings offer insights for policymakers on effective resource allocation for educational recovery.

Authors

• Jason Godfrey, Harvard University

• Trisha Banerjee, University of Washington