Edgeworth Corrected Generalized Confldence Intervals

作者: Anindya Roy , Arup Bose

DOI:

关键词:

摘要: Generalized confldence intervals provide for complicated parametric functions in many common practical problems. They do not have exact frequentist coverage general, but often close to the nominal value and correct asymptotic cover- age. However, applications generalized satisfactory flnite sample performance. We derive expansions quantities associated with one- sided intervals, which helps explain above limited then show how use these obtain improved by suitable calibration. implement ideas a few examples demonstrate performance of corrected intervals. AMS 2000 subject classiflcations: Primary 62F25; secondary 62F05, 62F40, 62J10. Keywords phrases: Average bioequivalence, Behrens-Fisher prob- lem, bootstrap, Cornish-Fisher expansion, probability, Edgeworth pivot..

参考文章(31)
Richard K. Burdick, Connie M. Borror, Douglas C. Montgomery, Design and Analysis of Gauge R&R Studies Society for Industrial and Applied Mathematics. ,(2005) , 10.1137/1.9780898718379
Shu-Hui Lin, Jack C. Lee, Exact tests in simple growth curve models and one-way ANOVA with equicorrelation error structure Journal of Multivariate Analysis. ,vol. 84, pp. 351- 368 ,(2003) , 10.1016/S0047-259X(02)00060-X
Samaradasa Weerahandi, Exact Statistical Methods for Data Analysis ,(2003)
Kam-Wah Tsui, Samaradasa Weerahandi, Generalized p-Values in Significance Testing of Hypotheses in the Presence of Nuisance Parameters Journal of the American Statistical Association. ,vol. 84, pp. 602- 607 ,(1989) , 10.1080/01621459.1989.10478810
K Krishnamoorthy, Thomas Mathew, Inferences on the means of lognormal distributions using generalized p-values and generalized confidence intervals Journal of Statistical Planning and Inference. ,vol. 115, pp. 103- 121 ,(2003) , 10.1016/S0378-3758(02)00153-2
Samaradasa Weerahandi, Vance W. Berger, Exact inference for growth curves with intraclass correlation structure. Biometrics. ,vol. 55, pp. 921- 924 ,(1999) , 10.1111/J.0006-341X.1999.00921.X