Functional data analysis: An application to COVID-19 data in the United States in 2020

Background: In this paper, we conduct an analysis of the COVID-19 data in United States 2020 via functional methods. Through research, investigate effectiveness practice public health measures, and assess correlation between infections deaths caused by COVID-19. Additionally, look into relationship spread geographical locations, propose a forecasting method to predict total number confirmed cases nationwide. Methods: The methods include principal methods, canonical expectation-maximization (EM) based clustering algorithm time series model used for forecasting. Results: It is evident that measures helps reduce growth rate epidemic outbreak over nation. We have observed high death cases. are geographically close hot spots likely be clustered together, population density appears critical factor affecting cluster structure. proposed gives more reliable accurate predictions than standard Conclusions: results obtained applying provide new insights States. With our recommendations, professionals can make better decisions epidemic, mitigate its negative effects national health.