Home > Research > Publications & Outputs > Effects of Allocation Method and Time Trends on...

Electronic data

Links

Text available via DOI:

View graph of relations

Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials. / Berry, Lindsay R; Lorenzi, Elizabeth; Berry, Nicholas S et al.
In: Statistics in Biopharmaceutical Research, Vol. 16, No. 4, 23.01.2024, p. 512-525.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Berry, LR, Lorenzi, E, Berry, NS, Crawford, AM, Jacko, P & Viele, K 2024, 'Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials', Statistics in Biopharmaceutical Research, vol. 16, no. 4, pp. 512-525. https://doi.org/10.1080/19466315.2023.2298961

APA

Berry, L. R., Lorenzi, E., Berry, N. S., Crawford, A. M., Jacko, P., & Viele, K. (2024). Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials. Statistics in Biopharmaceutical Research, 16(4), 512-525. https://doi.org/10.1080/19466315.2023.2298961

Vancouver

Berry LR, Lorenzi E, Berry NS, Crawford AM, Jacko P, Viele K. Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials. Statistics in Biopharmaceutical Research. 2024 Jan 23;16(4):512-525. Epub 2024 Jan 2. doi: 10.1080/19466315.2023.2298961

Author

Berry, Lindsay R ; Lorenzi, Elizabeth ; Berry, Nicholas S et al. / Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials. In: Statistics in Biopharmaceutical Research. 2024 ; Vol. 16, No. 4. pp. 512-525.

Bibtex

@article{334a0ee85b26480c993705531d3da07b,
title = "Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials",
abstract = "Many trial designs, such as dose-finding trials, shared-control designs, or adaptive platform trials, investigate multiple therapies simultaneously. Often these trials seek to identify the best arm and compare it to a control. Adaptive trials are commonly considered in this space, focusing on methods that drop arms or adjust allocation in response to accumulating information. These methods continue to be compared in the literature, most recently with an emphasis on the effect of time trends during the experiment. Here we compare several methods, considering their performance with and without time trends present. The four procedures are: (a) fixed allocation, (b) arm dropping based on p-values (two variants), (c) arm dropping based on the posterior probability each arm is best (two variants), and (d) response-adaptive randomization. These procedures are compared in terms of their ability to identify the best arm, statistical power, accuracy of estimation, and potential benefit to participants inside the trial. We find arm dropping based on the probability each arm is best and RAR among the best options from the methods considered. Arm dropping based on p-values performs moderately worse, and fixed allocation is much worse on all metrics within this context.",
keywords = "Pharmaceutical Science, Statistics and Probability",
author = "Berry, {Lindsay R} and Elizabeth Lorenzi and Berry, {Nicholas S} and Crawford, {Amy M} and Peter Jacko and Kert Viele",
year = "2024",
month = jan,
day = "23",
doi = "10.1080/19466315.2023.2298961",
language = "English",
volume = "16",
pages = "512--525",
journal = "Statistics in Biopharmaceutical Research",
issn = "1946-6315",
publisher = "Taylor and Francis Ltd.",
number = "4",

}

RIS

TY - JOUR

T1 - Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-arm Trials

AU - Berry, Lindsay R

AU - Lorenzi, Elizabeth

AU - Berry, Nicholas S

AU - Crawford, Amy M

AU - Jacko, Peter

AU - Viele, Kert

PY - 2024/1/23

Y1 - 2024/1/23

N2 - Many trial designs, such as dose-finding trials, shared-control designs, or adaptive platform trials, investigate multiple therapies simultaneously. Often these trials seek to identify the best arm and compare it to a control. Adaptive trials are commonly considered in this space, focusing on methods that drop arms or adjust allocation in response to accumulating information. These methods continue to be compared in the literature, most recently with an emphasis on the effect of time trends during the experiment. Here we compare several methods, considering their performance with and without time trends present. The four procedures are: (a) fixed allocation, (b) arm dropping based on p-values (two variants), (c) arm dropping based on the posterior probability each arm is best (two variants), and (d) response-adaptive randomization. These procedures are compared in terms of their ability to identify the best arm, statistical power, accuracy of estimation, and potential benefit to participants inside the trial. We find arm dropping based on the probability each arm is best and RAR among the best options from the methods considered. Arm dropping based on p-values performs moderately worse, and fixed allocation is much worse on all metrics within this context.

AB - Many trial designs, such as dose-finding trials, shared-control designs, or adaptive platform trials, investigate multiple therapies simultaneously. Often these trials seek to identify the best arm and compare it to a control. Adaptive trials are commonly considered in this space, focusing on methods that drop arms or adjust allocation in response to accumulating information. These methods continue to be compared in the literature, most recently with an emphasis on the effect of time trends during the experiment. Here we compare several methods, considering their performance with and without time trends present. The four procedures are: (a) fixed allocation, (b) arm dropping based on p-values (two variants), (c) arm dropping based on the posterior probability each arm is best (two variants), and (d) response-adaptive randomization. These procedures are compared in terms of their ability to identify the best arm, statistical power, accuracy of estimation, and potential benefit to participants inside the trial. We find arm dropping based on the probability each arm is best and RAR among the best options from the methods considered. Arm dropping based on p-values performs moderately worse, and fixed allocation is much worse on all metrics within this context.

KW - Pharmaceutical Science

KW - Statistics and Probability

U2 - 10.1080/19466315.2023.2298961

DO - 10.1080/19466315.2023.2298961

M3 - Journal article

VL - 16

SP - 512

EP - 525

JO - Statistics in Biopharmaceutical Research

JF - Statistics in Biopharmaceutical Research

SN - 1946-6315

IS - 4

ER -