On Statistical Modeling of Covid-19 Spread Variations

The aim of the study is to predict how the spread model of the Covid-19 epidemic behaves in line with government interventions and to observe how a change in interventions affects the course of the epidemic. For this purpose, in our study we focus on a dynamic SIR model in which the recovery rate γ is fixed at 1/15, but the spread rate β depends on the interventions made rather than being constant. With the Kruskal Wallis test, we can say with %95 confidence that the differences in the estimated spreading rates were due to these interventions. Moreover, with the Dunn's test, it was obtained that there there were significant differences between full closure and partial closure, as well as between full closure and gradual normalization, with %99 confidence. This also shows that there is a significant difference in the number of cases that may occur with full closure compared to the number of cases after partial closure and gradual normalization. MSC Classification: 65H10 , 92D30 , 92D25 , 34A34 , 62F40 , 62G10