video

sound

Persian Version

View:

154

Download:

90

Cites:

Information Journal Paper

Title

BAYESIAN ANALYSIS OF COMPETING RISK DATA USING POSSITIVE STABLE COPULA FUNCTION

Pages

 Start Page 9 | End Page 20

Abstract

 Introduction: In recent years, the use of copula function for modeling multivariate survival data has been drastically increased. One of multivarite survival data is COMPETING RISK DATA.Aim: The purpose of this study is to introduce bayesian analysis of COMPETING RISK DATA using possitive stable copula function. At the end we used the proposed model on the Diethylstilbestrol clinical trial data. In this clinical trial 506 prostate cancer patients were treated using different dosage of Diethylstilbestrol drug.Materials and Methods: After constructing likelihood function using copula, by choosing appropriate prior distribution for parameters, we obtain the posterior distribution of parameters using the Metropolis-Hastings algorithms and Slice sampling.Result: Fitting bayesian models to the data indicated that the effect of type of treatment on the time of the death from prostate cancer depended on age and weight of the patiens. The results is in line with the clasic methods.Conclustion: The obtained estimation of Tau Kendall correlation coefficien shows less variation in Bayesian model compared with classical model.

Cites

  • No record.
  • References

  • No record.
  • Related Journal Papers

    Related Seminar Papers

  • No record.
  • Related Plans

  • No record.