Details
| Original language | English |
|---|---|
| Pages (from-to) | 635-641 |
| Number of pages | 7 |
| Journal | ENVIRONMETRICS |
| Volume | 15 |
| Issue number | 6 |
| Publication status | Published - 18 Aug 2004 |
Abstract
The statistical evaluation of in vitro genotoxicity data is commonly performed by dose-response analysis. Common trend tests cannot be recommended because non-monotonicity may occur due to the use of high dose levels. Several decision tree approaches using preliminary comparisons versus control and conditional eliminating of high doses were proposed. Their heuristic and conservative behavior can be overcome by multiple contrast test, which test on trend and on comparisons versus control simultaneously. Other versions of protected trend test were investigated - each sensitive to any shape of the dose-response. A simple bootstrap approach is proposed using SAS PROC MULTTEST for the analysis of real genotoxicity data.
Keywords
- Bootstrap, Dose-response analysis, Genotoxicity, Multiple contrast test, Trend test
ASJC Scopus subject areas
- Mathematics(all)
- Statistics and Probability
- Environmental Science(all)
- Ecological Modelling
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ENVIRONMETRICS, Vol. 15, No. 6, 18.08.2004, p. 635-641.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A robust statistical procedure for evaluating genotoxicity data
AU - Hothorn, Ludwig A.
PY - 2004/8/18
Y1 - 2004/8/18
N2 - The statistical evaluation of in vitro genotoxicity data is commonly performed by dose-response analysis. Common trend tests cannot be recommended because non-monotonicity may occur due to the use of high dose levels. Several decision tree approaches using preliminary comparisons versus control and conditional eliminating of high doses were proposed. Their heuristic and conservative behavior can be overcome by multiple contrast test, which test on trend and on comparisons versus control simultaneously. Other versions of protected trend test were investigated - each sensitive to any shape of the dose-response. A simple bootstrap approach is proposed using SAS PROC MULTTEST for the analysis of real genotoxicity data.
AB - The statistical evaluation of in vitro genotoxicity data is commonly performed by dose-response analysis. Common trend tests cannot be recommended because non-monotonicity may occur due to the use of high dose levels. Several decision tree approaches using preliminary comparisons versus control and conditional eliminating of high doses were proposed. Their heuristic and conservative behavior can be overcome by multiple contrast test, which test on trend and on comparisons versus control simultaneously. Other versions of protected trend test were investigated - each sensitive to any shape of the dose-response. A simple bootstrap approach is proposed using SAS PROC MULTTEST for the analysis of real genotoxicity data.
KW - Bootstrap
KW - Dose-response analysis
KW - Genotoxicity
KW - Multiple contrast test
KW - Trend test
UR - http://www.scopus.com/inward/record.url?scp=4544301509&partnerID=8YFLogxK
U2 - 10.1002/env.649
DO - 10.1002/env.649
M3 - Article
AN - SCOPUS:4544301509
VL - 15
SP - 635
EP - 641
JO - ENVIRONMETRICS
JF - ENVIRONMETRICS
SN - 1180-4009
IS - 6
ER -