×

Pitman closeness comparison of best linear unbiased and invariant predictors for exponential distribution in one- and two-sample situations. (English) Zbl 1244.62145

Summary: Best linear unbiased, best linear invariant, and maximum likelihood predictors are commonly used in reliability studies for predicting either censored failure times or life times from a future life-test. In this article, by assuming a Type-II right-censored sample from an exponential distribution, we compare best linear unbiased (BLUP) and best linear invariant (BLIP) predictors of the censored order statistics in the one-sample case and order statistics from a future sample in the two-sample case, in terms of the E.J.G. Pitman [Proc. Camb. Philos. Soc. 33, 212–222 (1937; Zbl 0016.36404)] closeness criterion. Some specific conclusions are drawn and supporting numerical results are presented.

MSC:

62N05 Reliability and life testing
62N02 Estimation in survival analysis and censored data
62N01 Censored data models
62G30 Order statistics; empirical distribution functions
65C60 Computational problems in statistics (MSC2010)

Citations:

Zbl 0016.36404
Full Text: DOI

References:

[1] Arnold B. C., A First Course in Order Statistics. (2008) · Zbl 1172.62017 · doi:10.1137/1.9780898719062
[2] Balakrishnan N., Order Statistics and Inference: Estimation Methods (1991) · Zbl 0732.62044
[3] Balakrishnan N., Commun. Statist. Simul. Computat. 38 pp 802– (2009) · Zbl 1290.62025 · doi:10.1080/03610910802650313
[4] Balakrishnan N., Statist. Probab. Lett. 79 pp 1759– (2009) · Zbl 1169.62324 · doi:10.1016/j.spl.2009.04.016
[5] Keating J. P., Pitman’s Measure of Closeness (1993) · Zbl 0779.62019 · doi:10.1137/1.9781611971576
[6] Nagaraja H. N., Sankhy , Series B 48 pp 10– (1986)
[7] Pitman E. J. G., Proce. Cambridge Philosoph. Soc. 33 pp 212– (1937) · JFM 63.0515.03 · doi:10.1017/S0305004100019563
[8] Rao C. R., Statistics and Related Topics (1981)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.