Mixture model with informative censoring

• Grant number: 12/19745-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2012
• End date: November 30, 2013
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics
• Principal Investigator: Juliana Cobre
• Grantee: Andre Luis Soares
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The Survival Analysis usually ignores the possible dependence between the censoring time and the failure time and also ignores the possibility that the individual is no longer susceptible to the event of interest (e.g., be cured), which may undermine the conclusions of the study. In this paper, we propose the study of informative censoring to model the dependence between failure times and censoring times, into a model with a long duration that takes into consideration the possibility of cure. Specifically, we will study the mixture model combined with informative censoring and with the uniform-exponential distribution. The statistical knowledge acquisition and consolidation of mathematical knowledge are the expected results.(AU)