The design and analysis of vaccine trials for COVID-19 for the purpose of estimating efficacy

Stephen Senn

doi:10.1002/pst.2226

The design and analysis of vaccine trials for COVID-19 for the purpose of estimating efficacy

Stephen Senn^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Research › peer-review

Abstract

After a preliminary explanation as to how I came to know Andy Grieve and some remarks about his career and mine and how they have intersected, I consider the design and analysis of trials of vaccines for COVID-19 for the purpose of estimating efficacy. Five large trials, run by the sponsors Pfizer/BioNTech, AstraZeneca/Oxford University, Moderna, Novavax and J&J Janssen are considered briefly. Frequentist approaches to analysis were used for four of the trials but Pfizer/BioNTech nominated a Bayesian approach. The design and analysis of this trial is considered in some detail, in particular as regards the choice of prior distribution. I conclude by drawing some general lessons.

Original language	English
Pages (from-to)	790-807
Number of pages	18
Journal	Pharmaceutical Statistics
Volume	21
Issue number	4
DOIs	https://doi.org/10.1002/pst.2226
Publication status	Published - 1 Jul 2022
Externally published	Yes

Keywords

Bayesian
conditional inference
design of experiments
frequentist
sequential design
vaccine efficacy

Access to Document

10.1002/pst.2226

Cite this

@article{c0241103e41340cfa3a6f42228a1373e,

title = "The design and analysis of vaccine trials for COVID-19 for the purpose of estimating efficacy",

abstract = "After a preliminary explanation as to how I came to know Andy Grieve and some remarks about his career and mine and how they have intersected, I consider the design and analysis of trials of vaccines for COVID-19 for the purpose of estimating efficacy. Five large trials, run by the sponsors Pfizer/BioNTech, AstraZeneca/Oxford University, Moderna, Novavax and J&J Janssen are considered briefly. Frequentist approaches to analysis were used for four of the trials but Pfizer/BioNTech nominated a Bayesian approach. The design and analysis of this trial is considered in some detail, in particular as regards the choice of prior distribution. I conclude by drawing some general lessons.",

keywords = "Bayesian, conditional inference, design of experiments, frequentist, sequential design, vaccine efficacy",

author = "Stephen Senn",

note = "Funding Information: I am grateful to Val Fedorov for helpful comments on an earlier draft, to Anders Huitfeldt for discussions on scales and to two referees and the associate editor for further comments that substantially improved this paper. Publisher Copyright: {\textcopyright} 2022 The Author. Pharmaceutical Statistics published by John Wiley & Sons Ltd.",

year = "2022",

month = jul,

day = "1",

doi = "10.1002/pst.2226",

language = "English",

volume = "21",

pages = "790--807",

journal = "Pharmaceutical Statistics",

issn = "1539-1604",

publisher = "John Wiley and Sons Ltd",

number = "4",

}

TY - JOUR

T1 - The design and analysis of vaccine trials for COVID-19 for the purpose of estimating efficacy

AU - Senn, Stephen

N1 - Funding Information: I am grateful to Val Fedorov for helpful comments on an earlier draft, to Anders Huitfeldt for discussions on scales and to two referees and the associate editor for further comments that substantially improved this paper. Publisher Copyright: © 2022 The Author. Pharmaceutical Statistics published by John Wiley & Sons Ltd.

PY - 2022/7/1

Y1 - 2022/7/1

N2 - After a preliminary explanation as to how I came to know Andy Grieve and some remarks about his career and mine and how they have intersected, I consider the design and analysis of trials of vaccines for COVID-19 for the purpose of estimating efficacy. Five large trials, run by the sponsors Pfizer/BioNTech, AstraZeneca/Oxford University, Moderna, Novavax and J&J Janssen are considered briefly. Frequentist approaches to analysis were used for four of the trials but Pfizer/BioNTech nominated a Bayesian approach. The design and analysis of this trial is considered in some detail, in particular as regards the choice of prior distribution. I conclude by drawing some general lessons.

AB - After a preliminary explanation as to how I came to know Andy Grieve and some remarks about his career and mine and how they have intersected, I consider the design and analysis of trials of vaccines for COVID-19 for the purpose of estimating efficacy. Five large trials, run by the sponsors Pfizer/BioNTech, AstraZeneca/Oxford University, Moderna, Novavax and J&J Janssen are considered briefly. Frequentist approaches to analysis were used for four of the trials but Pfizer/BioNTech nominated a Bayesian approach. The design and analysis of this trial is considered in some detail, in particular as regards the choice of prior distribution. I conclude by drawing some general lessons.

KW - Bayesian

KW - conditional inference

KW - design of experiments

KW - frequentist

KW - sequential design

KW - vaccine efficacy

UR - http://www.scopus.com/inward/record.url?scp=85133755666&partnerID=8YFLogxK

U2 - 10.1002/pst.2226

DO - 10.1002/pst.2226

M3 - Article

C2 - 35819115

AN - SCOPUS:85133755666

SN - 1539-1604

VL - 21

SP - 790

EP - 807

JO - Pharmaceutical Statistics

JF - Pharmaceutical Statistics

IS - 4

ER -

The design and analysis of vaccine trials for COVID-19 for the purpose of estimating efficacy

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this