Efficient Unbiased Quantile Estimators for Moderate-Size Complete Samples from Extreme-Value and Weibull Distributions; Confidence Bounds and Tolerance and Prediction Intervals
作者:
NancyR. Mann,
KennethW. Fertig,
期刊:
Technometrics
(Taylor Available online 1977)
卷期:
Volume 19,
issue 1
页码: 87-93
ISSN:0040-1706
年代: 1977
DOI:10.1080/00401706.1977.10489504
出版商: Taylor & Francis Group
关键词: Quantile estimators;Unbiased quantile estimators;Weibull tolerance bounds
数据来源: Taylor
摘要:
Tables of factors are given for complete samples of sizen(n= 20(1)40) for correcting small-sample bias in Hassanein's [4] asymptotically unbiased quantile estimators of extreme-value location and scale parameters. Hassanein'sk-order-statistic estimators of the two parameters are based on the same set of spacings for eachk(k= 2. … 10) and are asymptotically best of this type of linear estimator (with asymptotic efficiencies of .977 and .937, respectively, fork= 10). The tabulated values not only allow one to obtain estimates based on the specified set of ordered observations that are best linear unbiased or best linear invariant (for the specified set of weights), but they also enable one to use procedures described in Mann. Schafer, and Singpurwalla [13] to compute approximate confidence bounds and tolerance and prediction intervals. Also tabulated are efficiencies of unbiased versions of the estimators relative to Cramér-Rao bounds for regular unbiased estimators and to best linear unbiased estimators (where available). The efficiencies of the ten-order-statistic unbiased estimators relative to the best linear unbiased estimators (compared for samples of sizes 20 through 25) are very close to I.
点击下载:
PDF (711KB)
返 回