首页    期刊浏览 2024年10月07日 星期一
登录注册

文章基本信息

  • 标题:Detecting Non-Identifiability on the Poly-Weibull Model
  • 本地全文:下载
  • 作者:F. LOUZADA-NETO ; C. S. ANDRADE
  • 期刊名称:Brazilian Journal of Probability and Statistics
  • 印刷版ISSN:0103-0752
  • 出版年度:2001
  • 卷号:15
  • 期号:2
  • 页码:147-154
  • 出版社:Brazilian Statistical Association
  • 摘要:The poly-Weibull model is a general family which can accommodate not only con-stant, increasing or decreasing hazard curves with zero or non zero asymptotes,but also nonmonotones ones, including bathtub-shaped. In this paper we considerthe non-identifiability problem, which arises when the shape parameters of a poly-Weibull model are close. A graphical method based on the total-time-on-test plotand its simulated envelop is considered for detecting when a poly-Weibull modelis likely to be identifiable. We also provide a general framework for construct-ing hypothesis tests for non-identifiability by using parametric bootstrap-basedmetho ds. We set up a simulation study and show that the bootstrap tests havedesirable properties with respect to size and power
  • 关键词:Bi-Weibull model; hazard mo dels; hypothesis tests; non-identifia-;bility; TTT plot
国家哲学社会科学文献中心版权所有