Weibull inference using trimmed samples and prior information |
| |
Authors: | Arturo J Fernández |
| |
Institution: | (1) Facultad de Matemáticas, Departamento de Estadí stica e Investigación Operativa, Universidad de La Laguna, 38271 La Laguna, Spain |
| |
Abstract: | Trimmed samples are commonly used in several branches of statistical methodology, especially when the presence of contaminated
data is suspected. Assuming that certain proportions of the smallest and largest observations from a Weibull sample are unknown
or have been eliminated, a Bayesian approach to point and interval estimation of the scale parameter, as well as hypothesis
testing and prediction, is presented. In many cases, the use of substantial prior information can significantly increase the
quality of the inferences and reduce the amount of testing required. Some Bayes estimators and predictors are derived in closed-forms.
Highest posterior density estimators and credibility intervals can be computed using iterative methods. Bayes rules for testing
one- and two-sided hypotheses are also provided. An illustrative numerical example is included. |
| |
Keywords: | Bayesian estimation testing and prediction HPD estimator and interval Reliability function Order statistics |
本文献已被 SpringerLink 等数据库收录! |
|