Use compatibility intervals in regulatory toxicology

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Ludwig A. Hothorn
  • Ralph Pirow

Research Organisations

External Research Organisations

  • Federal Institute for Risk Assessment (BfR)
View graph of relations

Details

Original languageEnglish
Article number104720
JournalRegulatory Toxicology and Pharmacology
Volume116
Early online date6 Jul 2020
Publication statusPublished - Oct 2020

Abstract

Recently it was recommended to avoid significance tests, in particular dichotomization into significant/non-significant on the basis of a p-value and a fixed 5% significance level (i.e. false positive rate). As an alternative, the interpretation of a suitable effect size and its compatibility interval is recommended, i.e. confidence intervals whose compatibility with the data, the assumptions, and the models is shown. This concept is used for the evaluation of assays in regulatory toxicology with special emphasis on the proof of hazard and proof of safety. Three case studies for multiple endpoints, multiple models and the consideration of historical controls illustrate the applicability of this concept. The corresponding software code for the open-source R project for statistical computing (www.r-project.org) is provided.

Keywords

    Compatibility intervals, Statistics

ASJC Scopus subject areas

  • Pharmacology, Toxicology and Pharmaceutics(all)
  • Toxicology

Cite this

Use compatibility intervals in regulatory toxicology. / Hothorn, Ludwig A.; Pirow, Ralph.
In: Regulatory Toxicology and Pharmacology, Vol. 116, 104720, 10.2020.

Research output: Contribution to journalArticleResearchpeer review

Hothorn LA, Pirow R. Use compatibility intervals in regulatory toxicology. Regulatory Toxicology and Pharmacology. 2020 Oct;116:104720. Epub 2020 Jul 6. doi: 10.1016/j.yrtph.2020.104720
Hothorn, Ludwig A. ; Pirow, Ralph. / Use compatibility intervals in regulatory toxicology. In: Regulatory Toxicology and Pharmacology. 2020 ; Vol. 116.
Download
@article{0f8ea6c82f1f401297069effca8294fa,
title = "Use compatibility intervals in regulatory toxicology",
abstract = "Recently it was recommended to avoid significance tests, in particular dichotomization into significant/non-significant on the basis of a p-value and a fixed 5% significance level (i.e. false positive rate). As an alternative, the interpretation of a suitable effect size and its compatibility interval is recommended, i.e. confidence intervals whose compatibility with the data, the assumptions, and the models is shown. This concept is used for the evaluation of assays in regulatory toxicology with special emphasis on the proof of hazard and proof of safety. Three case studies for multiple endpoints, multiple models and the consideration of historical controls illustrate the applicability of this concept. The corresponding software code for the open-source R project for statistical computing (www.r-project.org) is provided.",
keywords = "Compatibility intervals, Statistics",
author = "Hothorn, {Ludwig A.} and Ralph Pirow",
year = "2020",
month = oct,
doi = "10.1016/j.yrtph.2020.104720",
language = "English",
volume = "116",
journal = "Regulatory Toxicology and Pharmacology",
issn = "0273-2300",
publisher = "Academic Press Inc.",

}

Download

TY - JOUR

T1 - Use compatibility intervals in regulatory toxicology

AU - Hothorn, Ludwig A.

AU - Pirow, Ralph

PY - 2020/10

Y1 - 2020/10

N2 - Recently it was recommended to avoid significance tests, in particular dichotomization into significant/non-significant on the basis of a p-value and a fixed 5% significance level (i.e. false positive rate). As an alternative, the interpretation of a suitable effect size and its compatibility interval is recommended, i.e. confidence intervals whose compatibility with the data, the assumptions, and the models is shown. This concept is used for the evaluation of assays in regulatory toxicology with special emphasis on the proof of hazard and proof of safety. Three case studies for multiple endpoints, multiple models and the consideration of historical controls illustrate the applicability of this concept. The corresponding software code for the open-source R project for statistical computing (www.r-project.org) is provided.

AB - Recently it was recommended to avoid significance tests, in particular dichotomization into significant/non-significant on the basis of a p-value and a fixed 5% significance level (i.e. false positive rate). As an alternative, the interpretation of a suitable effect size and its compatibility interval is recommended, i.e. confidence intervals whose compatibility with the data, the assumptions, and the models is shown. This concept is used for the evaluation of assays in regulatory toxicology with special emphasis on the proof of hazard and proof of safety. Three case studies for multiple endpoints, multiple models and the consideration of historical controls illustrate the applicability of this concept. The corresponding software code for the open-source R project for statistical computing (www.r-project.org) is provided.

KW - Compatibility intervals

KW - Statistics

UR - http://www.scopus.com/inward/record.url?scp=85087816628&partnerID=8YFLogxK

U2 - 10.1016/j.yrtph.2020.104720

DO - 10.1016/j.yrtph.2020.104720

M3 - Article

C2 - 32645430

AN - SCOPUS:85087816628

VL - 116

JO - Regulatory Toxicology and Pharmacology

JF - Regulatory Toxicology and Pharmacology

SN - 0273-2300

M1 - 104720

ER -