A Bayesian method for hazard rate estimation based on right-censored data
| Autor: | Guang-Yao Chen, 陳光堯 |
|---|---|
| Rok vydání: | 2007 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 95 Hess and Brown(1999) reviewed various kernel methods for hazard rate estimation based on right-censored data. Through simulations, they found that the boundary kernel estimator by Muller and Wang(1994) had improved performance. In this paper, we will propose a Bayesian estimator for hazard rate, using prior on Bernstein polynomials, and make inference using MCMC methods. Comparison using simulation shows that our Bayesian estimator performs better than the boundary kernel estimator of Muller and Wang(1994) in terms of mean-squared error. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|