Analysis of survival data in the presence of competing risks

• Published in: AIP conference proceedings Vol. 2850; no. 1
• Main Authors: Ramakrishnan, M., Mohan, N., Jagathesan, T.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Melville American Institute of Physics 17.05.2024
• Subjects: Remarriage; Statistical models; Survival; Survival analysis
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0208265

The modelling of “time-to event” data is known as survival analysis. Many Survival Methods were introduced for this type of data. These Models are inappropriate for competing risk data. Competing risks may hinder observation of the outcome of interest. The methods Cause Specific Hazard (CSH) associated with Cumulative Incidence Function (CIF) and Sub Distribution Hazard (SDH) model are specifically designed for analysing competing risks. By treating competing events as censoring, the significant factors on cause specific hazard may be discovered using a traditional Cox proportional hazard model. CIF is used to identify impact of covariates in the SDH. In this model, subjects experiencing competing events continue to be in risk set and treated that particular subject remains uncensored. This study explains the above described models and a real time data is considered to test the model and the results of which are discussed in terms of estimated coefficient, hazard ratio and their standard errors.