Regression Analysis for Identifying Factors Responsible for Total COVID-19 Cases

Abstract

Purpose: The research conducts a comprehensive analysis using multiple linear regression to investigate the factors influencing the spread of COVID-19 in India.
Methods: Data related to COVID-19 such as total cases, total deaths, movements of cases(transportation), and population of all Indian States and Union Territories, along with the number of hospitals in these were collected. Rigorous data preprocessing, normalization, and addressing multicollinearity were performed.
Results: The multiple regression model identifies "Aircraft Movements" and "Public Hospitals" as significant predictors of "Total Cases", highlighting the impact of air travel and the number of public hospitals on transmission. "Outgoing Trains from States" positively associated with "Total Cases," indicating the role of transportation networks in the virus’s spread. However, "Incoming Trains to States" and "Population" exhibited weak and insignificant relationships with "Total Cases."
Conclusions: The study emphasizes the importance of infrastructure, population density, and transportation in shaping the COVID-19 pandemic in India. Policymakers can use these findings to devise targeted measures, allocate resources, and bolster healthcare infrastructure in vulnerable regions. While the model shows moderate explanatory power, it acknowledges the influence of unmeasured factors, necessitating further research and advanced modeling techniques for enhanced accuracy and addressing limitations.