EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A burn-in(g) question: How long should an initial equal randomization stage be before Bayesian response-adaptive randomization?

Edwin Yn Tang iD, Stef Baas iD, Daniel Kaddaj, Lukas Pin iD, David S Robertson iD, Sofía S Villar iD

Statistical Methods in Medical Research · 2026-11 · 35 (11) · 2320-2340

DOI: 10.1177/09622802251411538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistical Methods in Medical Research, online erschienen am 19.01.2026. Verfasst von Edwin Yn Tang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Statistics, University of Warwick, Coventry, UK. Hauptthemen laut MEDLINE: Randomized Controlled Trials as Topic. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MRC Biostatistics Unit Core Studentship, Cusanuswerk e.V., Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Response-adaptive randomization (RAR) can increase participant benefit in clinical trials, but also complicates statistical analysis. The burn-in period—a non-adaptive initial stage—is commonly used to mitigate this disadvantage, yet guidance on its optimal duration is scarce. To address this critical gap, this paper introduces an exact evaluation approach to investigate how the burn-in length impacts statistical operating characteristics of two-arm binary Bayesian RAR (BRAR) designs. We show that (1) commonly used calibration and asymptotic tests show substantial type I error rate inflation for BRAR designs without a burn-in period, and increasing the total burn-in length to more than half the trial size reduces but does not fully mitigate type I error rate inflation, necessitating exact tests; (2) exact tests conditioning on total successes show the highest average and minimum power up to large burn-in lengths; (3) the burn-in length substantially influences power and participant benefit, which are often not maximized at the maximum or minimum possible burn-in length; (4) the test statistic influences the type I error rate and power; (5) estimation bias decreases quicker in the burn-in length for larger treatment effects and increases for larger trial sizes under the same burn-in length. Our approach is illustrated by re-designing the ARREST trial.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Randomized Controlled Trials as TopicBayes TheoremHumansRandom AllocationModels, StatisticalResearch Design

Stichwörter der Autor:innen

Conditional exact testbinary outcomesexact operating characteristicstwo-arm trialunconditional exact test

Autor:innen und Institutionen

  • Department of Statistics, University of Warwick, Coventry, UK.
  • MRC Biostatistics Unit, University of Cambridge, Cambridge, UK.
  • Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, Cambridge, UK.

ORCID-Profile: Edwin Yn Tang, Stef Baas, Lukas Pin, David S Robertson, Sofía S Villar

Förderung

  • MRC Biostatistics Unit Core Studentship
  • Cusanuswerk e.V.
  • Medical Research Council

Zitieren

APA

Tang, E. Y., Baas, S., Kaddaj, D., Pin, L., Robertson, D. S., & Villar, S. S. (2026). A burn-in(g) question: How long should an initial equal randomization stage be before Bayesian response-adaptive randomization?. Statistical Methods in Medical Research, 35(11), 2320-2340. https://doi.org/10.1177/09622802251411538

Vancouver

Tang EY, Baas S, Kaddaj D, Pin L, Robertson DS, Villar SS. A burn-in(g) question: How long should an initial equal randomization stage be before Bayesian response-adaptive randomization?. Statistical Methods in Medical Research. 2026;35(11):2320-2340. doi:10.1177/09622802251411538

BibTeX
@article{Tang2026,
  author = {Tang, Edwin Yn and Baas, Stef and Kaddaj, Daniel and Pin, Lukas and Robertson, David S and Villar, Sofía S},
  title = {A burn-in(g) question: How long should an initial equal randomization stage be before Bayesian response-adaptive randomization?},
  journal = {Statistical Methods in Medical Research},
  year = {2026},
  volume = {35},
  number = {11},
  pages = {2320--2340},
  doi = {10.1177/09622802251411538}
}
Kostenlos starten →