Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 215-227 |
| Seitenumfang | 13 |
| Fachzeitschrift | Journal of applied statistics |
| Jahrgang | 31 |
| Ausgabenummer | 2 |
| Publikationsstatus | Veröffentlicht - 1 Feb. 2004 |
Abstract
For the non-parametric two-sample location problem, adaptive tests based on a selector statistic are compared with a maximum and a sum test, respectively. When the class of all continuous distributions is not restricted, the sum test is not a robust test, i.e. it does not have a relatively high power across the different possible distributions. However, according to our simulation results, the adaptive tests as well as the maximum test are robust. For a small sample size, the maximum test is preferable, whereas for a large sample size the comparison between the adaptive tests and the maximum test does not show a clear winner. Consequently, one may argue in favour of the maximum test since it is a useful test for all sample sizes. Furthermore, it does not need a selector and the specification of which test is to be performed for which values of the selector. When the family of possible distributions is restricted, the maximin efficiency robust test may be a further robust alternative. However, for the family of t distributions this test is not as powerful as the corresponding maximum test.
ASJC Scopus Sachgebiete
- Mathematik (insg.)
- Statistik und Wahrscheinlichkeit
- Entscheidungswissenschaften (insg.)
- Statistik, Wahrscheinlichkeit und Ungewissheit
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Journal of applied statistics, Jahrgang 31, Nr. 2, 01.02.2004, S. 215-227.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Maximum test versus adaptive tests for the two-sample location problem
AU - Neuhäuser, Markus
AU - Büning, Herbert
AU - Hothorn, Ludwig A.
N1 - Funding Information: The authors would like to thank an anonymous reviewer for helpful comments and suggestions. Markus Neuhäuser gratefully acknowledges support of his research by a University of Otago Research Grant.
PY - 2004/2/1
Y1 - 2004/2/1
N2 - For the non-parametric two-sample location problem, adaptive tests based on a selector statistic are compared with a maximum and a sum test, respectively. When the class of all continuous distributions is not restricted, the sum test is not a robust test, i.e. it does not have a relatively high power across the different possible distributions. However, according to our simulation results, the adaptive tests as well as the maximum test are robust. For a small sample size, the maximum test is preferable, whereas for a large sample size the comparison between the adaptive tests and the maximum test does not show a clear winner. Consequently, one may argue in favour of the maximum test since it is a useful test for all sample sizes. Furthermore, it does not need a selector and the specification of which test is to be performed for which values of the selector. When the family of possible distributions is restricted, the maximin efficiency robust test may be a further robust alternative. However, for the family of t distributions this test is not as powerful as the corresponding maximum test.
AB - For the non-parametric two-sample location problem, adaptive tests based on a selector statistic are compared with a maximum and a sum test, respectively. When the class of all continuous distributions is not restricted, the sum test is not a robust test, i.e. it does not have a relatively high power across the different possible distributions. However, according to our simulation results, the adaptive tests as well as the maximum test are robust. For a small sample size, the maximum test is preferable, whereas for a large sample size the comparison between the adaptive tests and the maximum test does not show a clear winner. Consequently, one may argue in favour of the maximum test since it is a useful test for all sample sizes. Furthermore, it does not need a selector and the specification of which test is to be performed for which values of the selector. When the family of possible distributions is restricted, the maximin efficiency robust test may be a further robust alternative. However, for the family of t distributions this test is not as powerful as the corresponding maximum test.
KW - Location-shift model
KW - Maximin efficiency robust test
KW - Measures of skewness and tailweight
KW - Non-parametric tests
KW - Selector statistic
KW - Two-sample location problem
UR - http://www.scopus.com/inward/record.url?scp=0442312340&partnerID=8YFLogxK
U2 - 10.1080/0266476032000148876
DO - 10.1080/0266476032000148876
M3 - Article
AN - SCOPUS:0442312340
VL - 31
SP - 215
EP - 227
JO - Journal of applied statistics
JF - Journal of applied statistics
SN - 0266-4763
IS - 2
ER -