Modeling Spatial Differences in Mortality Rate of Coronavirus (Covid-19) Using Geographically Weighted Regression Until the End of 2021: A Global Study

ABSTRACT

This research examines the Modeling spatial relationships of the mortality of COVID-19 that were tested in 213 countries worldwide. The database used in the research included variables per 1000 population, as follows the cumulative number of cases, hospital beds, and the unvaccinated population as health variables, the age population over 65 years, population number and population density as demographic variables for interpretation and prediction of mortality around the world. In total, it relied on 7 variables at the level of countries in the world based on the official COVID-19 data of the World Health Organization and World Bank indicators. Therefore, the aim of this research is to study whether the relationships between mortality rates and these variables differ spatially across different countries by means of applying modeling spatial relationships by Geographically Weighted Regression (GWR) and Ordinary Least Squares Rregression (OLS) available in statistical tools in a GIS environment. The results showed that there are spatially homogeneous relationships at the level of the countries to the variables of the cumulative number of cases, the number of the population over the age of 65 years, and the number of the unvaccinated population, which are statistically significant and collectively explained 97% of the variation in mortality of COVID-19. In conclusion, spatial information derived from this modeling provides valuable insights regarding the spatially varying relationship of COVID-19 mortality with these potential drivers to help establish preventive measures to reduce mortality around the world.