Arasan, Jayanthi and Lunn, Mary (2008) Alternative interval estimation for parameters of bivariate exponential model with time varying covariate. Computational Statistics, 23 (4). pp. 605-622. ISSN 0943-4062
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/s00180-007-0101-9
This paper investigates several alternative methods of constructing confidence interval estimates based on the bootstrap and jackknife techniques for the parameters of a parallel two-component system model with dependent failure and a time varying covariate, when data is censored. This model is an extension of the bivariate exponential model. Bootstrap confidence interval techniques, the bootstrap-t, bootstrap-percentile andBCamethods are compared with the confidence interval based on the jackknife via coverage probability study using simulated data. The results clearly indicate that the jackknife technique works far better than any of the bootstrap techniques when dealing with censored data.
|Keyword:||Bootstrap, Jackknife, Censoring, Covariates|
|Faculty or Institute:||Faculty of Science|
|Deposited By:||Najwani Amir Sariffudin|
|Deposited On:||01 Jun 2010 09:08|
|Last Modified:||19 Aug 2010 05:16|
Repository Staff Only: Edit item detail
Document Download Statistics
This item has been downloaded for since 01 Jun 2010 09:08.