jump to main area
:::
A- A A+

Postdoc Seminars

A Joint Frailty Model for Longitudinal and Multiple Survival Data

  • 2016-04-27 (Wed.), 11:00 AM
  • Recreation Hall, 2F, Institute of Statistical Science
  • The reception will be held at 10:40 at the lounge on the second floor of the Institute of Statistical Science Building
  • Dr. Ling-Ya Yang
  • 金融機構

Abstract

In epidemioloical and medical studies, joint frailty approach has been commonly used to analyze two correlated processes, which include longitudinal process and multiple survival process. We construct a joint frailty approach for the accelerated failure time model to handle the two correlated processes simultaneously. The proposed joint frailty approach combines a joint likelihood function for the accelerate failure time model with a frailty model to take the correlated survival event times into account. The simultaneous estimation of parameters is based on the maximization of the joint likelihood function of the proposed methodology through EM-algorithm and a Gaussian quadrature technique. In this study, the performance of the proposed method is verified by simulation studies. A case study of acquired immunodeficiency syndrome data in Taiwan is implemented to manifest the proposed methodology.

Update:
scroll to top