Journal of Statistical and Econometric Methods

An Econometric Panel Data Model of the COVID-19 Pandemic

  • Pdf Icon [ Download ]
  • Times downloaded: 7902
  • Abstract


    New flexible-form and semi-parametric autoregressive non-linear count models for panel data are developed to analyse the spread and containment of the COVID-19 pandemic. The models are based on a discrete time form of the SIR model. These methods lead naturally to estimators of the infection process and daily reproduction numbers by jurisdiction. Two semi-parametric versions of the reproduction numbers are developed corresponding to currently popular parametric estimators. The estimators are applied to a large international data set to estimate these parameters for 221 jurisdictions at both national and subnational levels.



    JEL classification numbers: C14, C23, I18.

    Keywords: COVID-19, Reproduction Numbers, Panel Data, Count Models, Semi-parametric Approach.