Abstract
We propose goodness-of-fit tests for Birnbaum-Saunders distributions with type-II right censored data. Classical goodness-of-fit tests based on the empirical distribution, such as Anderson-Darling, Cramér-von Misses, and Kolmogorov-Smirnov, are adapted to censored data, and evaluated by means of a simulation study. The obtained results are applied to real-world censored reliability data.
Original language | English |
---|---|
Article number | 6784482 |
Pages (from-to) | 543-554 |
Number of pages | 12 |
Journal | IEEE Transactions on Reliability |
Volume | 63 |
Issue number | 2 |
DOIs | |
State | Published - Jun 2014 |
Externally published | Yes |
Keywords
- Anderson-Darling
- Cramér-von Mises
- Kolmogorov-Smirnov tests
- Monte Carlo simulation
- empirical distribution function
- hypothesis testing
- order statistics
- type-II censoring