Effect of Stay-At-Home Orders on the Growth Rate of COVID-19 cases

Presented by:
David Rice, Jonathan Garber, & Keegan Line (Western Washington University)

The COVID-19 pandemic has led to many governments taking drastic measures to keep people from infection. One of the main steps they have taken is implementing stay-at-home orders to deter the spread. The goal of our research was to see if there is a significant difference in the rate of infection between US counties before and after the order was put in place. Using the random forest algorithm as a main tool for classification of infection rates based on data from Bureau of Economic Affairs, John Hopkins University, and the Google Community Mobility Report, we show that the number of days since the start date of the stay-at-home order is significant in reducing infection rates. This result is further confirmed using the classification tree and lasso regression methods. Based on these results, we conclude that the stay-at-home orders did help reduce new cases of COVID-19 in the US.