Back to Search
Start Over
Geometry of the [formula omitted]-exponential distribution with dependent competing risks and accelerated life testing.
- Source :
-
Physica A . Feb2017, Vol. 468, p552-565. 14p. - Publication Year :
- 2017
-
Abstract
- In the information geometry suggested by Amari (1985) and Amari et al. (1987), a parametric statistical model can be regarded as a differentiable manifold with the parameter space as a coordinate system. Note that the q -exponential distribution plays an important role in Tsallis statistics (see Tsallis, 2009), this paper investigates the geometry of the q -exponential distribution with dependent competing risks and accelerated life testing (ALT). A copula function based on the q -exponential function, which can be considered as the generalized Gumbel copula, is discussed to illustrate the structure of the dependent random variable. Employing two iterative algorithms, simulation results are given to compare the performance of estimations and levels of association under different hybrid progressively censoring schemes (HPCSs). [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 03784371
- Volume :
- 468
- Database :
- Academic Search Index
- Journal :
- Physica A
- Publication Type :
- Academic Journal
- Accession number :
- 120559766
- Full Text :
- https://doi.org/10.1016/j.physa.2016.10.069