Subnational income, convergence, and the COVID-19 pandemic

  • This brief investigates the effects of the COVID-19 pandemic on gross national income in Pakistan and its districts.
  • To address the lack of available data, we developed a machine-learning algorithm that can predict economy activity in real time by leveraging administrative, night-light, and other real-time data.
  • Urban districts in Pakistan drove the slow-down in Pakistani income, and higher COVID-19 rates were significantly correlated with lower income growth.
  • Policymakers can measure real time economic activity by combining large datasets. Preemptive and prompt interventions are needed to limit spillovers across the whole country.