Home > Research > Publications & Outputs > Point estimation for adaptive trial designs I

Links

Text available via DOI:

View graph of relations

Point estimation for adaptive trial designs I: A methodological review

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Point estimation for adaptive trial designs I: A methodological review. / Robertson, David S.; Choodari‐Oskooei, Babak; Dimairo, Munya et al.
In: Statistics in Medicine, Vol. 42, No. 2, 30.01.2023, p. 122-145.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Robertson, DS, Choodari‐Oskooei, B, Dimairo, M, Flight, L, Pallmann, P & Jaki, T 2023, 'Point estimation for adaptive trial designs I: A methodological review', Statistics in Medicine, vol. 42, no. 2, pp. 122-145. https://doi.org/10.1002/sim.9605

APA

Robertson, D. S., Choodari‐Oskooei, B., Dimairo, M., Flight, L., Pallmann, P., & Jaki, T. (2023). Point estimation for adaptive trial designs I: A methodological review. Statistics in Medicine, 42(2), 122-145. https://doi.org/10.1002/sim.9605

Vancouver

Robertson DS, Choodari‐Oskooei B, Dimairo M, Flight L, Pallmann P, Jaki T. Point estimation for adaptive trial designs I: A methodological review. Statistics in Medicine. 2023 Jan 30;42(2):122-145. Epub 2022 Nov 30. doi: 10.1002/sim.9605

Author

Robertson, David S. ; Choodari‐Oskooei, Babak ; Dimairo, Munya et al. / Point estimation for adaptive trial designs I : A methodological review. In: Statistics in Medicine. 2023 ; Vol. 42, No. 2. pp. 122-145.

Bibtex

@article{e99f916837e5480e877b8ec1ca1ba213,
title = "Point estimation for adaptive trial designs I: A methodological review",
abstract = "Recent FDA guidance on adaptive clinical trial designs defines bias as “a systematic tendency for the estimate of treatment effect to deviate from its true value,” and states that it is desirable to obtain and report estimates of treatment effects that reduce or remove this bias. The conventional end‐of‐trial point estimates of the treatment effects are prone to bias in many adaptive designs, because they do not take into account the potential and realized trial adaptations. While much of the methodological developments on adaptive designs have tended to focus on control of type I error rates and power considerations, in contrast the question of biased estimation has received relatively less attention. This article is the first in a two‐part series that studies the issue of potential bias in point estimation for adaptive trials. Part I provides a comprehensive review of the methods to remove or reduce the potential bias in point estimation of treatment effects for adaptive designs, while part II illustrates how to implement these in practice and proposes a set of guidelines for trial statisticians. The methods reviewed in this article can be broadly classified into unbiased and bias‐reduced estimation, and we also provide a classification of estimators by the type of adaptive design. We compare the proposed methods, highlight available software and code, and discuss potential methodological gaps in the literature.",
keywords = "RESEARCH ARTICLE, RESEARCH ARTICLES, adaptive design, bias‐correction, conditional bias, flexible design, point estimation",
author = "Robertson, {David S.} and Babak Choodari‐Oskooei and Munya Dimairo and Laura Flight and Philip Pallmann and Thomas Jaki",
year = "2023",
month = jan,
day = "30",
doi = "10.1002/sim.9605",
language = "English",
volume = "42",
pages = "122--145",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

RIS

TY - JOUR

T1 - Point estimation for adaptive trial designs I

T2 - A methodological review

AU - Robertson, David S.

AU - Choodari‐Oskooei, Babak

AU - Dimairo, Munya

AU - Flight, Laura

AU - Pallmann, Philip

AU - Jaki, Thomas

PY - 2023/1/30

Y1 - 2023/1/30

N2 - Recent FDA guidance on adaptive clinical trial designs defines bias as “a systematic tendency for the estimate of treatment effect to deviate from its true value,” and states that it is desirable to obtain and report estimates of treatment effects that reduce or remove this bias. The conventional end‐of‐trial point estimates of the treatment effects are prone to bias in many adaptive designs, because they do not take into account the potential and realized trial adaptations. While much of the methodological developments on adaptive designs have tended to focus on control of type I error rates and power considerations, in contrast the question of biased estimation has received relatively less attention. This article is the first in a two‐part series that studies the issue of potential bias in point estimation for adaptive trials. Part I provides a comprehensive review of the methods to remove or reduce the potential bias in point estimation of treatment effects for adaptive designs, while part II illustrates how to implement these in practice and proposes a set of guidelines for trial statisticians. The methods reviewed in this article can be broadly classified into unbiased and bias‐reduced estimation, and we also provide a classification of estimators by the type of adaptive design. We compare the proposed methods, highlight available software and code, and discuss potential methodological gaps in the literature.

AB - Recent FDA guidance on adaptive clinical trial designs defines bias as “a systematic tendency for the estimate of treatment effect to deviate from its true value,” and states that it is desirable to obtain and report estimates of treatment effects that reduce or remove this bias. The conventional end‐of‐trial point estimates of the treatment effects are prone to bias in many adaptive designs, because they do not take into account the potential and realized trial adaptations. While much of the methodological developments on adaptive designs have tended to focus on control of type I error rates and power considerations, in contrast the question of biased estimation has received relatively less attention. This article is the first in a two‐part series that studies the issue of potential bias in point estimation for adaptive trials. Part I provides a comprehensive review of the methods to remove or reduce the potential bias in point estimation of treatment effects for adaptive designs, while part II illustrates how to implement these in practice and proposes a set of guidelines for trial statisticians. The methods reviewed in this article can be broadly classified into unbiased and bias‐reduced estimation, and we also provide a classification of estimators by the type of adaptive design. We compare the proposed methods, highlight available software and code, and discuss potential methodological gaps in the literature.

KW - RESEARCH ARTICLE

KW - RESEARCH ARTICLES

KW - adaptive design

KW - bias‐correction

KW - conditional bias

KW - flexible design

KW - point estimation

U2 - 10.1002/sim.9605

DO - 10.1002/sim.9605

M3 - Journal article

C2 - 36451173

VL - 42

SP - 122

EP - 145

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 2

ER -