COVID-19: Tail Risk and Predictive Regressions

Abstract

Reliable analysis and forecasting of the spread of COVID-19 pandemic and its impacts on global finance and World's economies requires application of econometrically justified and robust methods. At the same time, statistical and econometric analysis of financial and economic markets and of the spread of COVID-19 is complicated by the inherent potential non-stationarity, dependence, heterogeneity and heavy-tailedness in the data. This project focuses on econometrically justified robust analysis of the effects of the COVID-19 pandemic on the World's financial markets in different countries across the World. Among other results, the study focuses on robust inference in predictive regressions for different countries across the World. We also present a detailed study of persistence, heavy-tailedness and tail risk properties of the time series of the COVID-19 death rates that motivate the necessity in applications of robust inference methods in the analysis. Econometrically justified analysis is based on application of heteroskedasticity and autocorrelation consistent (HAC) inference methods, related approaches using consistent standard errors, recently developed robust 𝑡-statistic inference procedures and robust tail index estimation approaches.

Power Law in COVID-19 Cases in China

“…On the other hand, a power law distribution is able to capture the heavy upper tail of the data more closely, outperforming a number of alternative distributions. For sound analysis of the effects of COVID-19 pandemic, using statistically justified and robust methods that account for possible heavy tailedness and tail risk properties is integral (Distaso et al, 2020).…”