On Conditional Expectations of Location Statistics
作者:
RobertV. Hogg,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1960)
卷期:
Volume 55,
issue 292
页码: 714-717
ISSN:0162-1459
年代: 1960
DOI:10.1080/01621459.1960.10483370
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
LetT1andT2be two odd location statistics, such as the sample mean and the sample median. LetS1andS2be two even location-free statistics, such as the sample variance and the sample range. When sampling from a symmetric distribution, it is proved that the conditional expectation of either odd location statistic, given the even location-free statistics, is equal to θ, the midpoint of the distribution. This implies that if the random weightsW1andW2are functions of even location-free statistics so thatW1+W2= 1, thenW1T1+W2T2is an unbiased estimator of θ.
点击下载:
PDF (319KB)
返 回