Home > Research > Publications & Outputs > A Benchmark for Dose Finding Studies with Unkno...

Electronic data

  • Combo-Benchmark-Final

    Rights statement: This is a pre-copy-editing, author-produced PDF of an article accepted for publication in British Journal for the Philosophy of Science following peer review. The definitive publisher-authenticated version Pavel Mozgunov, Xavier Paoletti, Thomas Jaki, A benchmark for dose-finding studies with unknown ordering, Biostatistics, Volume 23, Issue 3, July 2022, Pages 721–737 is available online at: https://academic.oup.com/biostatistics/article/23/3/721/6066695

    Accepted author manuscript, 363 KB, PDF document

    Embargo ends: 4/01/23

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

A Benchmark for Dose Finding Studies with Unknown Ordering

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A Benchmark for Dose Finding Studies with Unknown Ordering. / Mozgunov, Pavel; Paoletti, Xavier; Jaki, Thomas.

In: Biostatistics, Vol. 23, No. 3, 31.07.2022, p. 721-737.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Mozgunov P, Paoletti X, Jaki T. A Benchmark for Dose Finding Studies with Unknown Ordering. Biostatistics. 2022 Jul 31;23(3):721-737. Epub 2021 Jan 4. doi: 10.1093/biostatistics/kxaa054

Author

Mozgunov, Pavel ; Paoletti, Xavier ; Jaki, Thomas. / A Benchmark for Dose Finding Studies with Unknown Ordering. In: Biostatistics. 2022 ; Vol. 23, No. 3. pp. 721-737.

Bibtex

@article{85655ed70fe94a5987898ef6913d0633,
title = "A Benchmark for Dose Finding Studies with Unknown Ordering",
abstract = "An important tool to evaluate the performance of a dose finding design is the non-parametric optimal benchmark that provides an upper bound on the performance of a design under a given scenario. A fundamental assumption of the benchmark is that the investigator can arrange doses in monotonically increasing toxicity order. While the benchmark can be still applied to combination studies in which not all dose combinations can be ordered, it does not account for the uncertainty in the ordering. In this work, we propose a generalization of the benchmark that accounts for this uncertainty and, as a result, provides a sharper upper bound on the performance. The benchmark assesses how probable the occurrence of each ordering is, given the complete information abouteach patient. The proposed approach can also be applied to trials with an arbitrary number of endpoints with discrete or continuous distributions. We illustrate the utility of the benchmark using recently proposed dose finding designs for Phase I combination trials with a binary toxicity endpoint and Phase I/II combination trials with binary toxicity and continuous efficacy endpoints.",
author = "Pavel Mozgunov and Xavier Paoletti and Thomas Jaki",
note = "This is a pre-copy-editing, author-produced PDF of an article accepted for publication in British Journal for the Philosophy of Science following peer review. The definitive publisher-authenticated version Pavel Mozgunov, Xavier Paoletti, Thomas Jaki, A benchmark for dose-finding studies with unknown ordering, Biostatistics, Volume 23, Issue 3, July 2022, Pages 721–737 is available online at: https://academic.oup.com/biostatistics/article/23/3/721/6066695",
year = "2022",
month = jul,
day = "31",
doi = "10.1093/biostatistics/kxaa054",
language = "English",
volume = "23",
pages = "721--737",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "3",

}

RIS

TY - JOUR

T1 - A Benchmark for Dose Finding Studies with Unknown Ordering

AU - Mozgunov, Pavel

AU - Paoletti, Xavier

AU - Jaki, Thomas

N1 - This is a pre-copy-editing, author-produced PDF of an article accepted for publication in British Journal for the Philosophy of Science following peer review. The definitive publisher-authenticated version Pavel Mozgunov, Xavier Paoletti, Thomas Jaki, A benchmark for dose-finding studies with unknown ordering, Biostatistics, Volume 23, Issue 3, July 2022, Pages 721–737 is available online at: https://academic.oup.com/biostatistics/article/23/3/721/6066695

PY - 2022/7/31

Y1 - 2022/7/31

N2 - An important tool to evaluate the performance of a dose finding design is the non-parametric optimal benchmark that provides an upper bound on the performance of a design under a given scenario. A fundamental assumption of the benchmark is that the investigator can arrange doses in monotonically increasing toxicity order. While the benchmark can be still applied to combination studies in which not all dose combinations can be ordered, it does not account for the uncertainty in the ordering. In this work, we propose a generalization of the benchmark that accounts for this uncertainty and, as a result, provides a sharper upper bound on the performance. The benchmark assesses how probable the occurrence of each ordering is, given the complete information abouteach patient. The proposed approach can also be applied to trials with an arbitrary number of endpoints with discrete or continuous distributions. We illustrate the utility of the benchmark using recently proposed dose finding designs for Phase I combination trials with a binary toxicity endpoint and Phase I/II combination trials with binary toxicity and continuous efficacy endpoints.

AB - An important tool to evaluate the performance of a dose finding design is the non-parametric optimal benchmark that provides an upper bound on the performance of a design under a given scenario. A fundamental assumption of the benchmark is that the investigator can arrange doses in monotonically increasing toxicity order. While the benchmark can be still applied to combination studies in which not all dose combinations can be ordered, it does not account for the uncertainty in the ordering. In this work, we propose a generalization of the benchmark that accounts for this uncertainty and, as a result, provides a sharper upper bound on the performance. The benchmark assesses how probable the occurrence of each ordering is, given the complete information abouteach patient. The proposed approach can also be applied to trials with an arbitrary number of endpoints with discrete or continuous distributions. We illustrate the utility of the benchmark using recently proposed dose finding designs for Phase I combination trials with a binary toxicity endpoint and Phase I/II combination trials with binary toxicity and continuous efficacy endpoints.

U2 - 10.1093/biostatistics/kxaa054

DO - 10.1093/biostatistics/kxaa054

M3 - Journal article

C2 - 33409536

VL - 23

SP - 721

EP - 737

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 3

ER -