Details
| Original language | English |
|---|---|
| Pages (from-to) | 789-797 |
| Number of pages | 9 |
| Journal | BIOMETRICS |
| Volume | 78 |
| Issue number | 2 |
| Early online date | 9 Feb 2021 |
| Publication status | Published - 5 Jul 2022 |
Abstract
In dose–response analysis, it is a challenge to choose appropriate linear or curvilinear shapes when considering multiple, differently scaled endpoints. It has been proposed to fit several marginal regression models that try sets of different transformations of the dose levels as explanatory variables for each endpoint. However, the multiple testing problem underlying this approach, involving correlated parameter estimates for the dose effect between and within endpoints, could only be adjusted heuristically. An asymptotic correction for multiple testing can be derived from the score functions of the marginal regression models. Based on a multivariate t-distribution, the correction provides a one-step adjustment of p-values that accounts for the correlation between estimates from different marginal models. The advantages of the proposed methodology are demonstrated through three example datasets, involving generalized linear models with differently scaled endpoints, differing covariates, and a mixed effect model and through simulation results. The methodology is implemented in an R package.
Keywords
- adjustment of p-values, dose–response, multiple endpoints, multivariate normal, toxicology
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: BIOMETRICS, Vol. 78, No. 2, 05.07.2022, p. 789-797.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - The Tukey trend test
T2 - Multiplicity adjustment using multiple marginal models
AU - Schaarschmidt, Frank
AU - Ritz, Christian
AU - Hothorn, Ludwig A.
N1 - Funding Information: Open access funding enabled and organized by Projekt DEAL.
PY - 2022/7/5
Y1 - 2022/7/5
N2 - In dose–response analysis, it is a challenge to choose appropriate linear or curvilinear shapes when considering multiple, differently scaled endpoints. It has been proposed to fit several marginal regression models that try sets of different transformations of the dose levels as explanatory variables for each endpoint. However, the multiple testing problem underlying this approach, involving correlated parameter estimates for the dose effect between and within endpoints, could only be adjusted heuristically. An asymptotic correction for multiple testing can be derived from the score functions of the marginal regression models. Based on a multivariate t-distribution, the correction provides a one-step adjustment of p-values that accounts for the correlation between estimates from different marginal models. The advantages of the proposed methodology are demonstrated through three example datasets, involving generalized linear models with differently scaled endpoints, differing covariates, and a mixed effect model and through simulation results. The methodology is implemented in an R package.
AB - In dose–response analysis, it is a challenge to choose appropriate linear or curvilinear shapes when considering multiple, differently scaled endpoints. It has been proposed to fit several marginal regression models that try sets of different transformations of the dose levels as explanatory variables for each endpoint. However, the multiple testing problem underlying this approach, involving correlated parameter estimates for the dose effect between and within endpoints, could only be adjusted heuristically. An asymptotic correction for multiple testing can be derived from the score functions of the marginal regression models. Based on a multivariate t-distribution, the correction provides a one-step adjustment of p-values that accounts for the correlation between estimates from different marginal models. The advantages of the proposed methodology are demonstrated through three example datasets, involving generalized linear models with differently scaled endpoints, differing covariates, and a mixed effect model and through simulation results. The methodology is implemented in an R package.
KW - adjustment of p-values
KW - dose–response
KW - multiple endpoints
KW - multivariate normal
KW - toxicology
UR - http://www.scopus.com/inward/record.url?scp=85102637910&partnerID=8YFLogxK
U2 - 10.1111/biom.13442
DO - 10.1111/biom.13442
M3 - Article
AN - SCOPUS:85102637910
VL - 78
SP - 789
EP - 797
JO - BIOMETRICS
JF - BIOMETRICS
SN - 0006-341X
IS - 2
ER -