Modeling COVID-19 Time Series Data

The novel coronavirus pandemic, known as COVID-19, could not have been more predictable; thus, the world encountered health crises and substantial economic crises. The deployment of various methodologies to estimate the statistical models for the COVID-19 infected cases has become a very important research area. The present book investigated the trends and cointegration relationships between COVID-19 infected cases and deaths in all 13 districts of Andhra Pradesh state during the year 2021; in all 37 districts of Tamil Nadu state, during the months of 3rd July 2020 to 31st March 2021; in all 30 districts of Karnataka state, from July 2020 to December 2021; in all 14 districts of Kerala state, India, during the year 2021. The pooled regression model was not suitable for studying the trends and relationship between new COVID-19 infections and deaths due to COVID-19 in Andhra Pradesh. The random effect model explains 80 % of the variations in the dependent variable, the number of deaths due to COVID-19 infections. The FM-OLS was found suitable to study the long-run equilibrium relationships between the number of COVID-19 infected cases and deaths due to COVID-19 infections in Tamil Nadu. The ARDL (p=1, q=0) was found suitable to investigate the short-run and long-run cointegration relations between the cumulative number of new COVID-19 infected cases and the cumulative number of deaths due to COVID-19 in Tamil Nadu state. To assess the dynamic relationships between COVID-19 infected cases and the number of deaths due to COVID-19 in all 30 districts of Karnataka state from July 2020 to December 2021, the Generalized Method of Moments method was found suitable. The panel VAR model was employed to study the causal relationships between COVID-19-infected cases and deaths in Kerala state. The exciting result is that even though the data is Panel type, none of the panel regression models was found suitable. In contrast, the constant coefficient model (Panel Pooled Regression Model) was found suitable to study the relationships between COVID-19 infections and deaths. The average death due to COVID-19 was about 1.6 %.