Robustness of Selection Procedures

✍ Scribed by H. Domröse; D. Rasch

• Publisher: John Wiley and Sons
• Year: 1987
• Tongue: English
• Weight: 513 KB
• Volume: 29
• Category: Article
• ISSN: 0323-3847
• DOI: 10.1002/bimj.4710290504

✦ Synopsis

I n the article Bechhofers Indifference-zone formulation for selecting the t populatiom with the 1 highest means is considered in a Bet of non-normal distributions.

Selection rules based on the sample mean, the 10 o/o and the 20 (\lo trimmed means, two estim&tors proposed by TIKU (1981) for valuating the emallest and highest accepted sample values higher, the sample median and a linear combination of quantile estimatorti, two adaptive procedures and a ranksum proceduro are investigated in a large scale simulation experiment in respect of their robustness against deviations from an assumed distribution. Robustness is understood 88 a small percentage of the difference P A -p between the actual probability of incorrect selection /?A and the nominal B-value. We obtained R relatively good robustness for the classical sample mean selection rule and useful derivations for the employment of other selection rules in a n area of practical importance.