Abstract
Prediction of censored order statistics from a Type-II censored sample can be done with trivial bounds having perfect confidence. However, given independent samples from the same absolutely continuous distribution, improved bounds can be attained. In this regard, we develop here point prediction based on L-statistics for predicting order statistics (OS) from a future sample as well as for predicting censored OS from a Type-II censored sample. An example is taken to illustrate these ideas, and the limiting case wherein a single independent sample is arbitrarily large is also discussed.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 683-695 |
| Number of pages | 13 |
| Journal | Journal of Statistical Computation and Simulation |
| Volume | 84 |
| Issue number | 3 |
| DOIs | |
| State | Published - Mar 2014 |
| Externally published | Yes |
Keywords
- L-Statistic
- Type-II censoring
- coverage probability
- distribution-free method
- independent samples
- interval prediction
- large sample
- point prediction
ASJC Scopus subject areas
- Statistics and Probability
- Modeling and Simulation
- Statistics, Probability and Uncertainty
- Applied Mathematics