Capstone Projects

Predicting Wisconsin School District Achievement Post-Pandemic

Program: Data Science Master's Degree
Location: Not Specified (remote)
Student: Sierra Erdmann

The COVID-19 pandemic disrupted K-12 education, and concerns about the pandemic affecting student achievement also spread. This case study uses data from the 2020 – 2021 school year to develop predictive linear regression models for Wisconsin school district report card achievement scores post-pandemic. Variables considered for predictors include the 2020 – 2021 Wisconsin district report card data and pandemic-related variables of student masking policies, ESSER (Elementary and Secondary School Emergency Relief) funds, and instructional learning modes for September 2020, January 2021, and May 2021. Interpreting the results of the best predictive model variables provides insight into factors that affect student achievement and whether the pandemic-related variables affected achievement post-pandemic. Understanding the factors contributing to achievement loss from the pandemic will help schools prepare for better outcomes in future educational emergencies.

Variables such as the percentage of economically disadvantaged students, the percentage of students with disabilities, and the percentage of English Language learners were common predictors that had negative associations with post-pandemic district achievement. Schools that did not require masks for students also had a negative association with achievement. Differences in post-pandemic achievement were indicated for different learning modes during specific months in the 2020 – 2021 school year. Due to the small dataset and limited categorical counts, further research into student masking policies and learning modes regarding post-pandemic achievement is recommended. Future studies should also investigate how schools used ESSER funds to address learning loss effectively.