Unverfälschte Variablenprüfpläne für exponentialverteilte Merkmale mit zweiseitigen Toleranzgrenzen |
| |
Authors: | W. Krumbholz C. D. Ludwig |
| |
Affiliation: | 1. Institut für Statistik und quantitative ?konomik, HSBw Hamburg, Postfach 70 08 22, D-2000, Hamburg 70
|
| |
Abstract: | As a well known fact the standard X2-procedures (e.g. confidence intervals for σ2, tests of the hypothesis H:″σ=σo″ in the case of normal population with variance σ2) are biased. We refer to some useful tables which enable in the case of normal population to procure unbiased confidence intervals or confidence intervals with minimal length for σ2, control charts for σ with minimal distance between the limit lines, and unbiased tests of H:″σ=σo″. Another important application yields—as main result of the present paper—unbiased sampling plans in the case of an exponential distributed attribute with upper and lower specification limit (two-way-protection). It turns out to be possible, also in the case of exponential distribution, to reduce the sample size by using incomplete prior information about the proportion p of defectives. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|