Policymakers have implemented a wide range of non-pharmaceutical interventions to fight the spread of COVID-19. Variation in policies across jurisdictions and over time strongly suggests a difference-in-differences (DD) research design to estimate causal effects of counter-COVID measures. We discuss threats to the validity of these DD designs and make recommendations about how researchers can avoid bias, interpret results accurately, and provide sound guidance to policymakers seeking to protect public health and facilitate an eventual economic recovery.
Policymakers have implemented a wide range of non-pharmaceutical interventions to fight the spread of COVID-19. Variation in policies across jurisdictions and over time strongly suggests a difference-in-differences (DD) research design to estimate causal effects of counter-COVID measures. We discuss threats to the validity of these DD designs and make recommendations about how researchers can avoid bias, interpret results accurately, and provide sound guidance to policymakers seeking to protect public health and facilitate an eventual economic recovery.