COVID-19: Regression Approaches of Survival Data in the Presence of Competing Risks: An Application to COVID-19

COVID-19 Competing Risks

  • Sarada Ghosh
  • G. P. Samanta
  • Anuj Mubayi Arizona State University
Keywords: Competing risk, Cause speci c hazard regression, Sub-distribution hazard regression, Cumulative incidence function, Pseudo approach

Abstract

Coronavirus disease (COVID-19) is an infectious disease caused by a new virus. The disease causes respiratory illness (like the flu) with symptoms such as a cough, fever. It spreads primarily through contact with an infected person when they cough or sneeze. It also spreads when a person touches a surface or object that has the virus on it, then touches their eyes, nose, or mouth. For diseases with some level of associated mortality, the regression approaches for the competing risks setting are being increasingly applied and are used in this work also. The most commonly used approaches are the cause-specific and sub-distribution hazards regression which influence the incidence in the target population. These approaches have been implemented in this work. Additionally, the pseudo-observation approach that allows for the analysis of survival data via standard statistical methods, is also developed and used. The analytical illustrations of these statistical approaches predict the effect of infected people with COVID-19 based on their gender and age and also demonstrate the comparisons among underlying conditions. The simulation studies are applied for comparing relevant methods under different scenarios. These simulation studies and real data analysis are used for assessments and illustrations using R-software.

Published
2020-05-07
How to Cite
Ghosh, Sarada, G. P. Samanta, and Anuj Mubayi. 2020. “COVID-19: Regression Approaches of Survival Data in the Presence of Competing Risks: An Application to COVID-19”. Letters in Biomathematics, May. https://lettersinbiomath.journals.publicknowledgeproject.org/index.php/lib/article/view/307.
Section
COVID-19 Archives