Premium
Nonparametric Tests for Trend: Jonckheere's Test, a Modification and a Maximum Test
Author(s) -
Neuhäuser Markus,
Liu PingYu,
Hothorn Ludwig A.
Publication year - 1998
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/(sici)1521-4036(199812)40:8<899::aid-bimj899>3.0.co;2-9
Subject(s) - nonparametric statistics , goldfeld–quandt test , mathematics , statistics , type i and type ii errors , resampling , asymptotic distribution , inference , statistical hypothesis testing , estimator , computer science , test statistic , artificial intelligence , z test
Abstract Jonckheere's test is a frequently used nonparametric trend test for the evaluation of preclinical studies and clinical dose‐finding trials. In this paper, a modification of Jonckheere's test is proposed. If the exact permutation distribution is used for inference, the modified test can fill out the level of the type I error in a much more complete way and is substantially more powerful than the common Jonckheere test. If the asymptotic normality is used for inference, the modified test is slightly more powerful. In addition, a maximum test is investigated which is more robust concerning an a priori unknown dose‐response shape. The robustness is advantageous, especially in a closed testing procedure. The different tests are applied to two example data sets.