ON THE POWER FUNCTION OF A SIGN TEST FORMED BY USING SUBSAMPLES

reportActive / Technical Report | Accession Number: AD0604059 | Open PDF

Abstract:

The sign test can be used to obtain significance tests for the population median under extremely general conditions. The purpose of this paper is to investigate the power efficiency of the significance tests for the median formed in this way for the particular case in which each observation is drawn from the same normal population. For the cases considered, it is found that the power efficiency is almost always decreased by using two or more subsets rather than all the observations as a single set sometimes this decrease in power efficiency is very large. Also, for a given significance level, it is found that the power efficiency can vary noticeably with the manner in which the test is formed.

Author(s):
Walsh, John E.
Author Organization(s):
RAND CORP SANTA MONICA CA
Supplementary Note:
Prepared in cooperation with Douglas Aircraft Co., Inc.
Pagination:
0014

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release
Distribution Statement:
Approved For Public Release; Distribution Is Unlimited.

RECORD

Collection: TR
Identifying Numbers
Report Number(s):
P-7
Monitor Series:
XD
 Subject Terms
Joint Capability Areas:
JCA_1.4.1_Force Health Protection; JCA_1.4_Force Support
Communities of Interest:
Energy and Power Technologies
Descriptor(s):
*FUNCTIONS(MATHEMATICS), *STATISTICAL ANALYSIS, POPULATION(MATHEMATICS), POWER, SAMPLING, SET THEORY, STATISTICAL TESTS
Field(s)/Group(s):
Numerical Mathematics
Report Date:
1948 Jan 07