Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem

Abstract Bayesian model selection (BMS) and Bayesian model justifiability analysis (BMJ) provide a statistically rigorous framework for comparing competing models through the use of Bayesian model evidence (BME). However, a BME‐based analysis has two main limitations: (a) it does not account for a m...

Full description

Saved in:
Bibliographic Details
Main Authors: Maria Fernanda Morales Oreamuno, Sergey Oladyshkin, Wolfgang Nowak
Format: Article
Language:English
Published: Wiley 2023-07-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2022WR033711
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849706669699760128
author Maria Fernanda Morales Oreamuno
Sergey Oladyshkin
Wolfgang Nowak
author_facet Maria Fernanda Morales Oreamuno
Sergey Oladyshkin
Wolfgang Nowak
author_sort Maria Fernanda Morales Oreamuno
collection DOAJ
description Abstract Bayesian model selection (BMS) and Bayesian model justifiability analysis (BMJ) provide a statistically rigorous framework for comparing competing models through the use of Bayesian model evidence (BME). However, a BME‐based analysis has two main limitations: (a) it does not account for a model's posterior predictive performance after using the data for calibration and (b) it leads to biased results when comparing models that use different subsets of the observations for calibration. To address these limitations, we propose augmenting BMS and BMJ analyses with additional information‐theoretic measures: expected log‐predictive density (ELPD), relative entropy (RE) and information entropy (IE). Exploring the connection between Bayesian inference and information theory, we explicitly link BME and ELPD together with RE and IE to highlight the information flow in BMS and BMJ analyses. We show how to compute and interpret these scores alongside BME, and apply the framework to a controlled 2D groundwater setup featuring five models, one of which uses a subset of the data for calibration. Our results show how the information‐theoretic scores complement BME by providing a more complete picture concerning the Bayesian updating process. Additionally, we demonstrate how both RE and IE can be used to objectively compare models that feature different data sets for calibration. Overall, the introduced Bayesian information‐theoretic framework can lead to a better‐informed decision by incorporating a model's post‐calibration predictive performance, by allowing to work with different subsets of the data and by considering the usefulness of the data in the Bayesian updating process.
format Article
id doaj-art-813899107a944056a296c7dc2dbf4da6
institution DOAJ
issn 0043-1397
1944-7973
language English
publishDate 2023-07-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-813899107a944056a296c7dc2dbf4da62025-08-20T03:16:07ZengWileyWater Resources Research0043-13971944-79732023-07-01597n/an/a10.1029/2022WR033711Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater ProblemMaria Fernanda Morales Oreamuno0Sergey Oladyshkin1Wolfgang Nowak2Department of Stochastic Simulation and Safety Research for Hydrosystems Institute for Modelling Hydraulic and Environmental Systems University of Stuttgart Stuttgart GermanyDepartment of Stochastic Simulation and Safety Research for Hydrosystems Institute for Modelling Hydraulic and Environmental Systems University of Stuttgart Stuttgart GermanyDepartment of Stochastic Simulation and Safety Research for Hydrosystems Institute for Modelling Hydraulic and Environmental Systems University of Stuttgart Stuttgart GermanyAbstract Bayesian model selection (BMS) and Bayesian model justifiability analysis (BMJ) provide a statistically rigorous framework for comparing competing models through the use of Bayesian model evidence (BME). However, a BME‐based analysis has two main limitations: (a) it does not account for a model's posterior predictive performance after using the data for calibration and (b) it leads to biased results when comparing models that use different subsets of the observations for calibration. To address these limitations, we propose augmenting BMS and BMJ analyses with additional information‐theoretic measures: expected log‐predictive density (ELPD), relative entropy (RE) and information entropy (IE). Exploring the connection between Bayesian inference and information theory, we explicitly link BME and ELPD together with RE and IE to highlight the information flow in BMS and BMJ analyses. We show how to compute and interpret these scores alongside BME, and apply the framework to a controlled 2D groundwater setup featuring five models, one of which uses a subset of the data for calibration. Our results show how the information‐theoretic scores complement BME by providing a more complete picture concerning the Bayesian updating process. Additionally, we demonstrate how both RE and IE can be used to objectively compare models that feature different data sets for calibration. Overall, the introduced Bayesian information‐theoretic framework can lead to a better‐informed decision by incorporating a model's post‐calibration predictive performance, by allowing to work with different subsets of the data and by considering the usefulness of the data in the Bayesian updating process.https://doi.org/10.1029/2022WR033711Bayesian model selectionBayesian model evidenceinformation theoryrelative entropyBayesian model similarity
spellingShingle Maria Fernanda Morales Oreamuno
Sergey Oladyshkin
Wolfgang Nowak
Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
Water Resources Research
Bayesian model selection
Bayesian model evidence
information theory
relative entropy
Bayesian model similarity
title Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
title_full Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
title_fullStr Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
title_full_unstemmed Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
title_short Information‐Theoretic Scores for Bayesian Model Selection and Similarity Analysis: Concept and Application to a Groundwater Problem
title_sort information theoretic scores for bayesian model selection and similarity analysis concept and application to a groundwater problem
topic Bayesian model selection
Bayesian model evidence
information theory
relative entropy
Bayesian model similarity
url https://doi.org/10.1029/2022WR033711
work_keys_str_mv AT mariafernandamoralesoreamuno informationtheoreticscoresforbayesianmodelselectionandsimilarityanalysisconceptandapplicationtoagroundwaterproblem
AT sergeyoladyshkin informationtheoreticscoresforbayesianmodelselectionandsimilarityanalysisconceptandapplicationtoagroundwaterproblem
AT wolfgangnowak informationtheoreticscoresforbayesianmodelselectionandsimilarityanalysisconceptandapplicationtoagroundwaterproblem