Details
| Original language | English |
|---|---|
| Pages (from-to) | 317-322 |
| Number of pages | 6 |
| Journal | Journal of Modern Applied Statistical Methods |
| Volume | 5 |
| Issue number | 2 |
| Publication status | Published - Nov 2006 |
Abstract
In some areas, e.g., statistical genetics, it is common to apply a maximum test, where the maximum of several competing test statistics is used as a new statistic, and the permutation distribution of the maximum is used for inference. Here, it is shown that maximum tests are special cases of adaptive permutation tests. The 30-year old idea of adaptive statistical tests is more flexible than previously thought when permutation tests are used, and the selector statistic is calculated for every permutation. Because the independence between the selector and the test statistics is no longer needed, the test statistics themselves can be used as selectors. Then, the maximum tests fit into the concept of adaptive tests. In addition to the gained flexibility, maximum tests can be more powerful than classical adaptive tests.
Keywords
- Adaptive test, Maximum efficiency robust test, Maximum test, Nonparametric statistics
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Decision Sciences(all)
- Statistics, Probability and Uncertainty
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Journal of Modern Applied Statistical Methods, Vol. 5, No. 2, 11.2006, p. 317-322.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Maximum tests are adaptive permutation tests
AU - Neuhäuser, Markus
AU - Hothorn, Ludwig A.
PY - 2006/11
Y1 - 2006/11
N2 - In some areas, e.g., statistical genetics, it is common to apply a maximum test, where the maximum of several competing test statistics is used as a new statistic, and the permutation distribution of the maximum is used for inference. Here, it is shown that maximum tests are special cases of adaptive permutation tests. The 30-year old idea of adaptive statistical tests is more flexible than previously thought when permutation tests are used, and the selector statistic is calculated for every permutation. Because the independence between the selector and the test statistics is no longer needed, the test statistics themselves can be used as selectors. Then, the maximum tests fit into the concept of adaptive tests. In addition to the gained flexibility, maximum tests can be more powerful than classical adaptive tests.
AB - In some areas, e.g., statistical genetics, it is common to apply a maximum test, where the maximum of several competing test statistics is used as a new statistic, and the permutation distribution of the maximum is used for inference. Here, it is shown that maximum tests are special cases of adaptive permutation tests. The 30-year old idea of adaptive statistical tests is more flexible than previously thought when permutation tests are used, and the selector statistic is calculated for every permutation. Because the independence between the selector and the test statistics is no longer needed, the test statistics themselves can be used as selectors. Then, the maximum tests fit into the concept of adaptive tests. In addition to the gained flexibility, maximum tests can be more powerful than classical adaptive tests.
KW - Adaptive test
KW - Maximum efficiency robust test
KW - Maximum test
KW - Nonparametric statistics
UR - http://www.scopus.com/inward/record.url?scp=48249083432&partnerID=8YFLogxK
U2 - 10.22237/jmasm/1162353780
DO - 10.22237/jmasm/1162353780
M3 - Article
AN - SCOPUS:48249083432
VL - 5
SP - 317
EP - 322
JO - Journal of Modern Applied Statistical Methods
JF - Journal of Modern Applied Statistical Methods
SN - 1538-9472
IS - 2
ER -