A Test for Constant Hazard Against a Change-Point Alternative

被引:3
|
作者
Suresh, R. P. [1 ]
机构
[1] GM Global R&D, India Sci Lab, Bangalore 560066, Karnataka, India
关键词
Likelihood ratio test; Log gamma; Mean residual life; Weibull;
D O I
10.1080/03610926.2010.546549
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this article, we consider the change-point hazard rate model which arises quite commonly in mechanical or biological systems, which experience a high hazard rate early in their lifetime due to infant mortality and then a constant or steady hazard rate after the threshold time. We first derive the corresponding mean residual life function (MRLF) and observe that the MRLF is initially increasing and then constant. Here, we derive a test statistic for exponentiality against Increasing Initially then Constant Mean Residual Life (ICMRL). We also derive the asymptotic distribution of the test statistic and compare the power of the test with other existing tests such as likelihood ratio, Weibull, and Log gamma tests considered in the literature. The test performs quite well as compared to other alternatives studied.
引用
收藏
页码:1583 / 1589
页数:7
相关论文
共 50 条