Joint Modeling Item Response Theory (IRT) and Survival Analysis Model for Clinical Trials Data

• Grant number: 11/14065-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2011
• End date: September 30, 2012
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Applied Probability and Statistics
• Principal Investigator: Vera Lucia Damasceno Tomazella
• Grantee: Amanda Morales Eudes
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Item Response Theory (IRT) provides sets of models that represent certain characteristics unobservable (latent traits) of individuals (or companies, schools, etc.). This modeling is based on the probability of response of the individual items (or attributes of the latent trait) conditional on latent traits and characteristics of measuring instruments, such as level of difficulty of an item. In clinical and epidemiological research, the questionnaire data are often used to measure the status of a patient's health or functioning (cognitive or physical). The observations of multiple answers that are recorded through a standardized test is used to measure a continuous latent variable. The variation of the latent variable can not be fully explained by the usual measurement model when it comes to a highly heterogeneous study population. In practice, the study population may consist of several sub-populations or internally homogeneous latent classes, which complicates the measurement of the latent variable. The objective of this work is to study the relationship of each latent variable continues with survival where the population under study is heterogeneous