Biostatistical Design and Analyses of Long-Term Animal Studies Simulating Human Postmenopausal Osteoporosis

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

  • Ludwig A. Hothorn
  • Frieder Bauss

Organisationseinheiten

Externe Organisationen

  • Ruprecht-Karls-Universität Heidelberg
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)47-56
Seitenumfang10
FachzeitschriftTherapeutic Innovation & Regulatory Science
Jahrgang38
Ausgabenummer1
PublikationsstatusVeröffentlicht - 20 Dez. 2004

Abstract

Using three well-designed experimental studies as illustration, we demonstrate that the biostatistical design and analysis of long-term animal studies simulating human osteoporosis should be analogous to the design and analysis of randomized clinical trials. This principal is in accordance with the recommendations from the International Conference on Harmonisation guidelines concerning statistical principles in clinical trials (1). An important element of biostatistical study design is sample size. The three studies that are described herein used an a-priori sample size estimation for the one-way layout that included controls and several treatment and dose groups. In these k-sample designs, with at least one control group, both the multiple comparison procedure and trend tests within procedures for identification of the minimal-effective dose are recommended. Although p-values in pharmacology are quite common, confidence intervals should be used according to their interpretation for both statistical significance and clinical relevance. The use of one-sided confidence intervals for both the difference and the ratio to control for proving either superiority or at least noninferiority is demonstrated by real data examples. Relevant and relatively straightforward software is available for biostatistical analysis and can also be used to aid design. In summary, referring to published, well-designed experimental studies can help to assist with ensuring the quality of future investigations.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

Biostatistical Design and Analyses of Long-Term Animal Studies Simulating Human Postmenopausal Osteoporosis. / Hothorn, Ludwig A.; Bauss, Frieder.
in: Therapeutic Innovation & Regulatory Science, Jahrgang 38, Nr. 1, 20.12.2004, S. 47-56.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Download
@article{16ff3092b12a480d9cb54dfe892a9e42,
title = "Biostatistical Design and Analyses of Long-Term Animal Studies Simulating Human Postmenopausal Osteoporosis",
abstract = "Using three well-designed experimental studies as illustration, we demonstrate that the biostatistical design and analysis of long-term animal studies simulating human osteoporosis should be analogous to the design and analysis of randomized clinical trials. This principal is in accordance with the recommendations from the International Conference on Harmonisation guidelines concerning statistical principles in clinical trials (1). An important element of biostatistical study design is sample size. The three studies that are described herein used an a-priori sample size estimation for the one-way layout that included controls and several treatment and dose groups. In these k-sample designs, with at least one control group, both the multiple comparison procedure and trend tests within procedures for identification of the minimal-effective dose are recommended. Although p-values in pharmacology are quite common, confidence intervals should be used according to their interpretation for both statistical significance and clinical relevance. The use of one-sided confidence intervals for both the difference and the ratio to control for proving either superiority or at least noninferiority is demonstrated by real data examples. Relevant and relatively straightforward software is available for biostatistical analysis and can also be used to aid design. In summary, referring to published, well-designed experimental studies can help to assist with ensuring the quality of future investigations.",
keywords = "comparison, Confidence interval for the ratio, Ibanthonate, Many-to-one, Minimum-effective dose, Osteoporosis, Pharmacological study",
author = "Hothorn, {Ludwig A.} and Frieder Bauss",
year = "2004",
month = dec,
day = "20",
doi = "10.1177/009286150403800107",
language = "English",
volume = "38",
pages = "47--56",
journal = "Therapeutic Innovation & Regulatory Science",
issn = "2168-4790",
publisher = "SAGE Publications Inc.",
number = "1",

}

Download

TY - JOUR

T1 - Biostatistical Design and Analyses of Long-Term Animal Studies Simulating Human Postmenopausal Osteoporosis

AU - Hothorn, Ludwig A.

AU - Bauss, Frieder

PY - 2004/12/20

Y1 - 2004/12/20

N2 - Using three well-designed experimental studies as illustration, we demonstrate that the biostatistical design and analysis of long-term animal studies simulating human osteoporosis should be analogous to the design and analysis of randomized clinical trials. This principal is in accordance with the recommendations from the International Conference on Harmonisation guidelines concerning statistical principles in clinical trials (1). An important element of biostatistical study design is sample size. The three studies that are described herein used an a-priori sample size estimation for the one-way layout that included controls and several treatment and dose groups. In these k-sample designs, with at least one control group, both the multiple comparison procedure and trend tests within procedures for identification of the minimal-effective dose are recommended. Although p-values in pharmacology are quite common, confidence intervals should be used according to their interpretation for both statistical significance and clinical relevance. The use of one-sided confidence intervals for both the difference and the ratio to control for proving either superiority or at least noninferiority is demonstrated by real data examples. Relevant and relatively straightforward software is available for biostatistical analysis and can also be used to aid design. In summary, referring to published, well-designed experimental studies can help to assist with ensuring the quality of future investigations.

AB - Using three well-designed experimental studies as illustration, we demonstrate that the biostatistical design and analysis of long-term animal studies simulating human osteoporosis should be analogous to the design and analysis of randomized clinical trials. This principal is in accordance with the recommendations from the International Conference on Harmonisation guidelines concerning statistical principles in clinical trials (1). An important element of biostatistical study design is sample size. The three studies that are described herein used an a-priori sample size estimation for the one-way layout that included controls and several treatment and dose groups. In these k-sample designs, with at least one control group, both the multiple comparison procedure and trend tests within procedures for identification of the minimal-effective dose are recommended. Although p-values in pharmacology are quite common, confidence intervals should be used according to their interpretation for both statistical significance and clinical relevance. The use of one-sided confidence intervals for both the difference and the ratio to control for proving either superiority or at least noninferiority is demonstrated by real data examples. Relevant and relatively straightforward software is available for biostatistical analysis and can also be used to aid design. In summary, referring to published, well-designed experimental studies can help to assist with ensuring the quality of future investigations.

KW - comparison

KW - Confidence interval for the ratio

KW - Ibanthonate

KW - Many-to-one

KW - Minimum-effective dose

KW - Osteoporosis

KW - Pharmacological study

UR - http://www.scopus.com/inward/record.url?scp=84993730749&partnerID=8YFLogxK

U2 - 10.1177/009286150403800107

DO - 10.1177/009286150403800107

M3 - Article

AN - SCOPUS:84993730749

VL - 38

SP - 47

EP - 56

JO - Therapeutic Innovation & Regulatory Science

JF - Therapeutic Innovation & Regulatory Science

SN - 2168-4790

IS - 1

ER -