Comparison of Regression Approaches for Analyzing Survival Data in the Presence of Competing Risks
An Application to COVID-19
Emerging infectious diseases have impacted human race regularly with the past few decades alone has been rife with outbreaks such as H7N9 Avian-influenza (2013), Ebola (2014), MERS-CoV (2012), SARS-CoV1 (2003), and Zika (2015). COVID-19 coronavirus variants are emerging across the globe causing ongoing pandemic. Older age, male sex, number of comorbidities, and access to timely health care are identified as some of the risk factors associated with COVID-19 mortality. The regression approaches for capturing the competing risks are applied to COVID-19 in this work. The most commonly used approaches are the cause-specific and sub-distribution hazards regression which are applied on the COVID-19 incidence-data from USA. Additionally, the pseudo-observation approach, which allows for analysis of survival data, is applied on the same data. The simulations are carried out to compare approaches under different scenarios and also illustrate the relative effect of COVID-19 infected people based on their gender and age.