سال انتشار: ۱۳۷۹

محل انتشار: پنجمین کنفرانس آمار ایران

تعداد صفحات: ۱۴

نویسنده(ها):

H. Ishwaran – The Cleveland Clinic Foundation. Postal Address; Depatrment of Biostatistics and Epidemiology, 9500 Euclid Avenue Cleveland, OH 44195, U.S.A.
Lanclot – The Cleveland Clinic Foundation. Postal Address; Depatrment of Biostatistics and Epidemiology, 9500 Euclid Avenue Cleveland, OH 44195, U.S.A.
F. James – Department of mathernatical Sciences, The Johns Hopkins University, 34th & Cahrles Streets, Baltimore, MD 21218, U.S.A
M. Zarepour – Department of Mathematics and Statistics, University of Ottawa, Ottawa, Ontario, KIN 6N5, Canada.

چکیده:

It is a well known fact that the Efron’s usual bootstrap fails for the mean of heavy tail distributions. We demonstrate that this same type of failure also occurs in many types of weighted bootstraps, including the Bayesian bootstrap. Only through a careful selection for the weights we can produce a consistent weighted bootstrap procedure that will work for the mean and other useful statistics.