Premium
Non‐parametric test of ordered alternatives in incomplete blocks
Author(s) -
Park Eunsik,
Lee Young Jack
Publication year - 2000
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/(sici)1097-0258(20000530)19:10<1329::aid-sim483>3.0.co;2-s
Subject(s) - wilcoxon signed rank test , statistics , parametric statistics , confidence interval , test statistic , statistic , monte carlo method , mathematics , sample size determination , block (permutation group theory) , computer science , nonparametric statistics , linear regression , sample (material) , statistical hypothesis testing , econometrics , mann–whitney u test , chemistry , chromatography , geometry
Often in medical studies, study subjects become a natural block of observations repeated over a time period. Some subjects miss observations, thus becoming incomplete blocks of observations. We are interested in testing an ordered alternative (or time trend), and propose a non‐parametric method to detect a trend in incomplete blocks. Our approach is to estimate the trend by the linear regression method within each block and apply the one‐sample Wilcoxon test to the estimated linear trends. The one‐sample Wilcoxon test will be sensitive to the trend if it exists. The proposed test statistic is asymptotically normal and consistent. We can also estimate the overall magnitude of the linear trend and its confidence interval by a proper non‐parametric method. By Monte Carlo studies, we compare the performance of the proposed test against extended Page and Jonckheere tests. Published in 2000 by John Wiley & Sons, Ltd.