|Saturday, February 25|
|CS22 In THIS Corner: X1! When Model Variables Compete||
Sat, Feb 25, 11:00 AM - 12:30 PM
River Terrace 3
Competing Risk Data and Semi-Competing Risk Data Analysis and Visualization in SAS and R (303331)*Ran Liao, Indiana University
Keywords: time to event data, competing risk, semi-competing risk, copula, frailty model, Fine-Gray model
Time to event data, especially time to failure data, are wildly existed in industrial data analysis, financial data analysis, and medical research. Recently, the present of competing risk and semi-competing has received exceptional attention due to the informative censoring caused by competing risks and semi-competing risks. In this presentation, we conducted a comprehensive model, methodologies and algorithms review of time to event data in present competing risks and semi-competing risk, such as copula model, frailty model and subdistribution hazard model(Fine and Gray model). Moreover, we focused on using standard procedures in SAS and existing packages R to perform analysis and visualization for competing risk data and semi-competing risk data. Examples of a health care dataset have been used as illustrations from difference aspects to demonstrate the results and interpretations obtained from each model and methodology. The advantage and disadvantage of each methodology have been compared. The recommendation for the choice of model, methodology, and tools to handle specific scenario has been addressed in the last.