標題: Validation of tolerance interval
作者: Lai, Yi-Hsuan
Yen, Ya-Fen
Chen, Lin-An
統計學研究所
Institute of Statistics
關鍵字: Confidence interval;Coverage interval;Tolerance interval
公開日期: 1-四月-2012
摘要: The tolerance interval receives very much attention in literature and is widely applied in industry. However, it is generally constructed through the criterion of minimum width by Eisenhart et al. (1947). Although effort for clarification of several prediction related intervals has been made recently by Huang et al. (2010). the appropriateness of the tolerance interval for its role in industry applications is insufficiently discussed. According to manufacturers' requests, a concept of admissibility of tolerance intervals is defined in this paper and we show that these types of tolerance intervals are not admissible due to short of confidence. We further prove that a 100(1-alpha)% confidence interval of a gamma-coverage interval is admissible and is appropriate for use. (C) 2011 Elsevier B.V. All rights reserved.
URI: http://dx.doi.org/10.1016/j.jspi.2011.10.012
http://hdl.handle.net/11536/15199
ISSN: 0378-3758
DOI: 10.1016/j.jspi.2011.10.012
期刊: JOURNAL OF STATISTICAL PLANNING AND INFERENCE
Volume: 142
Issue: 4
起始頁: 902
結束頁: 907
顯示於類別:期刊論文


文件中的檔案:

  1. 000299856500014.pdf