Back

A Simplified Bayesian Analysis Method for Vaccine Efficacy

Graziani, C.

2020-12-11 public and global health
10.1101/2020.12.07.20244954 medRxiv
Show abstract

We describe a simplified Bayesian analysis of vaccine trial data, in which a reparametrization of the Poisson likelihood leads to a factorization in which the protective vaccine efficacy VES and the nuisance parameter appear in different factors. As a consequence the posterior density acquires a factorized form, and marginalization over the nuisance parameter is trivial. Estimates of VES accordingly become a matter of simple manipulations of one-dimensional posterior probability densities. We demonstrate the method using the publically-released data on the efficacy of three vaccines agains SARS-CoV-2: the final Phase III data from the Pfizer/BioNTech and Moderna mRNA vaccines and the interim data released for the Sputnik V adenovirus-based vaccine.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

1
PLOS ONE
● 5266 papers in training set
Top 12%
15.3%
Similar papers in this journal
2
Vaccine
○ 203 papers in training set
Top 0.5%
6.8%
Similar papers in this journal
3
BMC Medical Research Methodology
○ 47 papers in training set
Top 0.1%
6.8%
Similar papers in this journal
4
Statistics in Medicine
○ 40 papers in training set
Top 0.1%
5.6%
Similar papers in this journal
5
Epidemiology and Infection
◐ 89 papers in training set
Top 0.2%
4.9%
Similar papers in this journal
6
Vaccines
○ 198 papers in training set
Top 0.7%
4.5%
7
Frontiers in Artificial Intelligence
○ 20 papers in training set
Top 0.1%
4.1%
8
Biostatistics
◐ 24 papers in training set
Top 0.1%
3.3%
50% of probability mass above
9
Statistical Methods in Medical Research
○ 11 papers in training set
Top 0.1%
2.8%
10
Journal of Medical Internet Research
◐ 87 papers in training set
Top 1.0%
2.7%
11
Clinical Trials
○ 11 papers in training set
Top 0.1%
2.1%
12
Scientific Reports
○ 3612 papers in training set
Top 45%
2.1%
13
Clinical Infectious Diseases
◐ 235 papers in training set
Top 1%
2.1%
14
PLOS Computational Biology
● 1863 papers in training set
Top 12%
2.1%
15
Infectious Disease Modelling
○ 54 papers in training set
Top 0.7%
1.8%
16
Trials
○ 29 papers in training set
Top 0.5%
1.8%
17
Research Synthesis Methods
○ 20 papers in training set
Top 0.2%
1.5%
18
F1000Research
○ 88 papers in training set
Top 2%
1.4%
19
eLife
● 5828 papers in training set
Top 58%
1.1%
20
Frontiers in Public Health
○ 148 papers in training set
Top 5%
1.1%
21
Journal of Theoretical Biology
○ 162 papers in training set
Top 2%
1.0%
22
Annals of Internal Medicine
● 28 papers in training set
Top 0.5%
1.0%
23
Frontiers in Neurology
○ 102 papers in training set
Top 3%
0.9%
24
Cureus
○ 68 papers in training set
Top 4%
0.9%
25
BMC Infectious Diseases
○ 133 papers in training set
Top 4%
0.9%
26
Royal Society Open Science
● 214 papers in training set
Top 6%
0.9%
27
Medical Decision Making
○ 12 papers in training set
Top 0.4%
0.6%
28
Epidemiology
○ 32 papers in training set
Top 0.7%
0.6%
29
PeerJ
◐ 308 papers in training set
Top 12%
0.6%
30
Journal of Clinical Epidemiology
○ 31 papers in training set
Top 0.9%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.