Note on the Consistency of Some Distribution-Free Tests for Dispersion
作者:
Constance van Eeden,
期刊:
Journal of the American Statistical Association
(Taylor Available online 1964)
卷期:
Volume 59,
issue 305
页码: 105-119
ISSN:0162-1459
年代: 1964
DOI:10.1080/01621459.1964.10480704
出版商: Taylor & Francis Group
数据来源: Taylor
摘要:
In this paper the consistency of the two-sample tests of Sukhatme [6], Ansari and Bradley [1], Siegel and Tukey [5], and Mood [3] is investigated. Each of these tests is a distribution-free analogue of theF-test for testing the equality of the variances of two normal distributions. If the two samples are taken from continuous distributions with the same median (say 0) and distribution functionsF(x) andF(x/a) respectively, the hypothesis tested states thata= 1 and the two-sided tests are consistent fora≠ 1. If, however, the samples are from continuous distributions with the same median 0 and arbitrary distribution functionsFandG, little is known about their asymptotic properties. In this paper the conditions for consistency for this case are given; further it is investigated if the corresponding estimates of differences in dispersion satisfy the usual properties of measures of dispersion, namely 1) thatXand −Xhave the same dispersion and 2) that, ifXhas a larger (or equal or smaller) dispersion thanY, − Xhas a larger (or equal or smaller) dispersion thanY.
点击下载:
PDF (586KB)
返 回