×

A two-stage procedure with accelerated test for selecting the best exponential population. (English) Zbl 0993.62015

Summary: We discuss a two-stage procedure for selecting the largest location parameter among \(k\;(\geq 2)\) two-parameter exponential populations (or products) from an accelerated test. The accelerated test will be conducted at a higher stress level than that of normal in the second stage. Under certain assumptions between parameter and stress level, the two-stage selection procedure, which guarantees that the probability of correct selection is at least \(p^*\) is proposed. At the end of the paper, we present some useful tables that serve as a guide for the needed sample size in the second stage.

MSC:

62F07 Statistical ranking and selection procedures
62L10 Sequential statistical analysis
62N05 Reliability and life testing
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1214/aoms/1177728845 · Zbl 0055.13003 · doi:10.1214/aoms/1177728845
[2] DOI: 10.1080/03610927708827565 · Zbl 0398.62022 · doi:10.1080/03610927708827565
[3] Lam K., Cornman. In. Statist. Simulation and Computation. 17 pp 55– (1988)
[4] DOI: 10.1080/07474949008836202 · Zbl 0716.62031 · doi:10.1080/07474949008836202
[5] DOI: 10.1080/03610927908827791 · Zbl 0444.62035 · doi:10.1080/03610927908827791
[6] Mukhopadhyay N., Sankhya. Ser 45 pp 3– (1983)
[7] DOI: 10.1016/0378-3758(84)90042-9 · Zbl 0545.62022 · doi:10.1016/0378-3758(84)90042-9
[8] DOI: 10.1080/07474948408836052 · doi:10.1080/07474948408836052
[9] Nelson W., Accelerated Testing-Statistics Models, Test Plans, and Data Analysys (1990)
[10] Viertl R., Statistical Method in Accelerated Life Testing (1988) · Zbl 0665.62098
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.