Bayesian and frequentist models: Legitimate choices for different purposes of clinical research

Research output: Contribution to journalArticle

Abstract

Objective Bayesian and frequentist approaches to statistical modelling in epidemiology are often pitted against each other as if they represented diametrically opposing philosophies. However, both approaches have a role to play in clinical epidemiology and the evaluation of clinical practice. Methods Here I present an overview of the philosophical underpinnings of the Bayesian and frequentist approaches, showing that each model has its place depending on the philosophical and evaluative needs of the user. Results If the user's approach to a clinical problem places an emphasis on identifying causal relationships, a frequentist approach might be best suited. On the other hand, if the user takes an approach in which estimating a priori probabilities is appropriate, a Bayesian approach might be more appropriate. One could imagine both approaches used for the same study. Conclusions Bayesian and frequentist approaches are complementary tools in the clinical evaluator's toolkit.

Original languageEnglish (US)
Pages (from-to)1045-1047
Number of pages3
JournalJournal of Evaluation in Clinical Practice
Volume16
Issue number6
DOIs
StatePublished - Dec 2010

Fingerprint

Bayes Theorem
Research
Epidemiology

Keywords

  • Bayesianism
  • causality
  • estimation
  • frequentism
  • modelling
  • probability
  • statistics

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health
  • Health Policy

Cite this

@article{5db4f49e069a4253907e995c78d69eef,
title = "Bayesian and frequentist models: Legitimate choices for different purposes of clinical research",
abstract = "Objective Bayesian and frequentist approaches to statistical modelling in epidemiology are often pitted against each other as if they represented diametrically opposing philosophies. However, both approaches have a role to play in clinical epidemiology and the evaluation of clinical practice. Methods Here I present an overview of the philosophical underpinnings of the Bayesian and frequentist approaches, showing that each model has its place depending on the philosophical and evaluative needs of the user. Results If the user's approach to a clinical problem places an emphasis on identifying causal relationships, a frequentist approach might be best suited. On the other hand, if the user takes an approach in which estimating a priori probabilities is appropriate, a Bayesian approach might be more appropriate. One could imagine both approaches used for the same study. Conclusions Bayesian and frequentist approaches are complementary tools in the clinical evaluator's toolkit.",
keywords = "Bayesianism, causality, estimation, frequentism, modelling, probability, statistics",
author = "Zackary Berger",
year = "2010",
month = "12",
doi = "10.1111/j.1365-2753.2009.01247.x",
language = "English (US)",
volume = "16",
pages = "1045--1047",
journal = "Journal of Evaluation in Clinical Practice",
issn = "1356-1294",
publisher = "Wiley-Blackwell",
number = "6",

}

TY - JOUR

T1 - Bayesian and frequentist models

T2 - Legitimate choices for different purposes of clinical research

AU - Berger, Zackary

PY - 2010/12

Y1 - 2010/12

N2 - Objective Bayesian and frequentist approaches to statistical modelling in epidemiology are often pitted against each other as if they represented diametrically opposing philosophies. However, both approaches have a role to play in clinical epidemiology and the evaluation of clinical practice. Methods Here I present an overview of the philosophical underpinnings of the Bayesian and frequentist approaches, showing that each model has its place depending on the philosophical and evaluative needs of the user. Results If the user's approach to a clinical problem places an emphasis on identifying causal relationships, a frequentist approach might be best suited. On the other hand, if the user takes an approach in which estimating a priori probabilities is appropriate, a Bayesian approach might be more appropriate. One could imagine both approaches used for the same study. Conclusions Bayesian and frequentist approaches are complementary tools in the clinical evaluator's toolkit.

AB - Objective Bayesian and frequentist approaches to statistical modelling in epidemiology are often pitted against each other as if they represented diametrically opposing philosophies. However, both approaches have a role to play in clinical epidemiology and the evaluation of clinical practice. Methods Here I present an overview of the philosophical underpinnings of the Bayesian and frequentist approaches, showing that each model has its place depending on the philosophical and evaluative needs of the user. Results If the user's approach to a clinical problem places an emphasis on identifying causal relationships, a frequentist approach might be best suited. On the other hand, if the user takes an approach in which estimating a priori probabilities is appropriate, a Bayesian approach might be more appropriate. One could imagine both approaches used for the same study. Conclusions Bayesian and frequentist approaches are complementary tools in the clinical evaluator's toolkit.

KW - Bayesianism

KW - causality

KW - estimation

KW - frequentism

KW - modelling

KW - probability

KW - statistics

UR - http://www.scopus.com/inward/record.url?scp=78650603954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650603954&partnerID=8YFLogxK

U2 - 10.1111/j.1365-2753.2009.01247.x

DO - 10.1111/j.1365-2753.2009.01247.x

M3 - Article

C2 - 20860579

AN - SCOPUS:78650603954

VL - 16

SP - 1045

EP - 1047

JO - Journal of Evaluation in Clinical Practice

JF - Journal of Evaluation in Clinical Practice

SN - 1356-1294

IS - 6

ER -