Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.

Biomedical research often utilizes Cox regression for the analysis of time-to-event data. The pervasive use of frequentist inference for these analyses implicates that the evidence for or against the presence (or absence) of an effect cannot be directly compared and that researchers must adhere to a...

Full description

Saved in:
Bibliographic Details
Main Authors: Maximilian Linde, Laura Jochim, Jorge N Tendeiro, Don van Ravenzwaaij
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0322144
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731710904696832
author Maximilian Linde
Laura Jochim
Jorge N Tendeiro
Don van Ravenzwaaij
author_facet Maximilian Linde
Laura Jochim
Jorge N Tendeiro
Don van Ravenzwaaij
author_sort Maximilian Linde
collection DOAJ
description Biomedical research often utilizes Cox regression for the analysis of time-to-event data. The pervasive use of frequentist inference for these analyses implicates that the evidence for or against the presence (or absence) of an effect cannot be directly compared and that researchers must adhere to a predefined sampling plan. As an alternative, the use of Bayes factors improves upon these limitations, which is especially important for costly and time-consuming biomedical studies. However, Bayes factors involve their own difficulty of specifying priors for the parameters of the statistical model. In this article, we develop data-driven priors centered around zero for Cox regression tailored to nine subfields in biomedicine. To this end, we extracted hazard ratios and associated [Formula: see text] confidence intervals from the abstracts of large corpora of already existing studies within the nine biomedical subfields. We used these extracted data to inform priors for the nine subfields. All of our suggested priors are Normal distributions with means of 0 and standard deviations closely scattered around 1. We propose that researchers use these priors as reasonable starting points for their analyses.
format Article
id doaj-art-af7442efc2684a5ea0dce5db3e359724
institution DOAJ
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-af7442efc2684a5ea0dce5db3e3597242025-08-20T03:08:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032214410.1371/journal.pone.0322144Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.Maximilian LindeLaura JochimJorge N TendeiroDon van RavenzwaaijBiomedical research often utilizes Cox regression for the analysis of time-to-event data. The pervasive use of frequentist inference for these analyses implicates that the evidence for or against the presence (or absence) of an effect cannot be directly compared and that researchers must adhere to a predefined sampling plan. As an alternative, the use of Bayes factors improves upon these limitations, which is especially important for costly and time-consuming biomedical studies. However, Bayes factors involve their own difficulty of specifying priors for the parameters of the statistical model. In this article, we develop data-driven priors centered around zero for Cox regression tailored to nine subfields in biomedicine. To this end, we extracted hazard ratios and associated [Formula: see text] confidence intervals from the abstracts of large corpora of already existing studies within the nine biomedical subfields. We used these extracted data to inform priors for the nine subfields. All of our suggested priors are Normal distributions with means of 0 and standard deviations closely scattered around 1. We propose that researchers use these priors as reasonable starting points for their analyses.https://doi.org/10.1371/journal.pone.0322144
spellingShingle Maximilian Linde
Laura Jochim
Jorge N Tendeiro
Don van Ravenzwaaij
Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
PLoS ONE
title Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
title_full Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
title_fullStr Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
title_full_unstemmed Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
title_short Data-driven prior elicitation for Bayes factors in Cox regression for nine subfields in biomedicine.
title_sort data driven prior elicitation for bayes factors in cox regression for nine subfields in biomedicine
url https://doi.org/10.1371/journal.pone.0322144
work_keys_str_mv AT maximilianlinde datadrivenpriorelicitationforbayesfactorsincoxregressionforninesubfieldsinbiomedicine
AT laurajochim datadrivenpriorelicitationforbayesfactorsincoxregressionforninesubfieldsinbiomedicine
AT jorgentendeiro datadrivenpriorelicitationforbayesfactorsincoxregressionforninesubfieldsinbiomedicine
AT donvanravenzwaaij datadrivenpriorelicitationforbayesfactorsincoxregressionforninesubfieldsinbiomedicine