Premium
Point estimates and confidence intervals for two‐sample rank tests
Author(s) -
Morton Anthony P.,
Dobson Annette J.
Publication year - 1988
Publication title -
medical journal of australia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.904
H-Index - 131
eISSN - 1326-5377
pISSN - 0025-729X
DOI - 10.5694/j.1326-5377.1988.tb93817.x
Subject(s) - confidence interval , statistics , rank (graph theory) , point estimation , mathematics , point (geometry) , test (biology) , percentage point , sample (material) , econometrics , combinatorics , biology , paleontology , chemistry , geometry , chromatography
The editorial policy of most medical journals now requires authors to provide point estimates and confidence intervals in addition to P values. To compare data from two groups, the rank‐sum test (for independent groups) and the signed‐ranks test (for related groups) provide P values but do not give estimates for the size of the difference between the groups. Point estimates and confidence intervals, which were developed by Hodges and Lehmann, that correspond to these rank tests are described and illustrated.