Bayesian joint analysis of longitudinal data and interval-censored failure time data.

Area of Science:

• Statistics
• Biostatistics
• Longitudinal Data Analysis

Background:

• Joint modeling of longitudinal and survival data is crucial in statistical research.
• Existing methods often focus on right-censored data, limiting applicability.
• Interval-censored survival data, common in clinical studies, requires specialized models.

Purpose of the Study:

• To propose a new frailty model for the joint analysis of longitudinal responses and interval-censored survival times.
• To provide a flexible statistical framework accommodating complex data structures from periodic or irregular follow-ups.
• To enable interpretation of regression coefficients as marginal effects on both response types.

Main Methods:

• A nonlinear mixed-effects submodel for the longitudinal response.
• A semiparametric probit submodel for interval-censored survival time, incorporating shared normal frailty.
• Utilizing splines for flexible approximation of unknown baseline functions.
• Developing an efficient Gibbs sampler for posterior computation.

Main Results:

• The proposed joint model demonstrates good estimation performance in simulation studies.
• The methodology was successfully applied to real-life patient data from the Aerobics Center Longitudinal Study.
• The model allows for robust joint analysis of mixed-effects longitudinal data and interval-censored survival data.

Conclusions:

• The developed joint frailty model offers a powerful tool for analyzing complex longitudinal and survival data.
• The use of splines and Gibbs sampling ensures computational efficiency and modeling flexibility.
• This approach enhances the understanding of relationships between longitudinal processes and time-to-event outcomes in various research fields.