DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Making Steppingstones out of Stumbling Blocks: A Bayesian Model Evidence Estimator with Application to Groundwater Transport Model Selection

Abstract

Bayesian model evidence (BME) is a measure of the average fit of a model to observation data given all the parameter values that the model can assume. By accounting for the trade-off between goodness-of-fit and model complexity, BME is used for model selection and model averaging purposes. For strict Bayesian computation, the theoretically unbiased Monte Carlo based numerical estimators are preferred over semi-analytical solutions. This study examines five BME numerical estimators and asks how accurate estimation of the BME is important for penalizing model complexity. The limiting cases for numerical BME estimators are the prior sampling arithmetic mean estimator (AM) and the posterior sampling harmonic mean (HM) estimator, which are straightforward to implement, yet they result in underestimation and overestimation, respectively. We also consider the path sampling methods of thermodynamic integration (TI) and steppingstone sampling (SS) that sample multiple intermediate distributions that link the prior and the posterior. Although TI and SS are theoretically unbiased estimators, they could have a bias in practice arising from numerical implementation. For example, sampling errors of some intermediate distributions can introduce bias. We propose a variant of SS, namely the multiple one-steppingstone sampling (MOSS) that is less sensitive to sampling errors. We evaluate thesemore » five estimators using a groundwater transport model selection problem. SS and MOSS give the least biased BME estimation at an efficient computational cost. If the estimated BME has a bias that covariates with the true BME, this would not be a problem because we are interested in BME ratios and not their absolute values. On the contrary, the results show that BME estimation bias can be a function of model complexity. Thus, biased BME estimation results in inaccurate penalization of more complex models, which changes the model ranking. This was less observed with SS and MOSS as with the three other methods.« less

Authors:
 [1];  [2]
  1. Univ. of Hawaii at Manoa, Honolulu, HI (United States)
  2. Florida State Univ., Tallahassee, FL (United States)
Publication Date:
Research Org.:
Florida State Univ., Tallahassee, FL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER); National Science Foundation (NSF)
OSTI Identifier:
1611030
Grant/Contract Number:  
SC0008272; SC0019438; OIA-1557349; EAR-1552329
Resource Type:
Accepted Manuscript
Journal Name:
Water (Basel)
Additional Journal Information:
Journal Name: Water (Basel); Journal Volume: 11; Journal Issue: 8; Journal ID: ISSN 2073-4441
Publisher:
MDPI
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; groundwater transport; Bayesian; model selection; Bayesian model averaging; modeling; model complexity; Bayesian model evidence; marginal likelihood

Citation Formats

Elshall, Ahmed S., and Ye, Ming. Making Steppingstones out of Stumbling Blocks: A Bayesian Model Evidence Estimator with Application to Groundwater Transport Model Selection. United States: N. p., 2019. Web. doi:10.3390/w11081579.
Elshall, Ahmed S., & Ye, Ming. Making Steppingstones out of Stumbling Blocks: A Bayesian Model Evidence Estimator with Application to Groundwater Transport Model Selection. United States. https://doi.org/10.3390/w11081579
Elshall, Ahmed S., and Ye, Ming. Tue . "Making Steppingstones out of Stumbling Blocks: A Bayesian Model Evidence Estimator with Application to Groundwater Transport Model Selection". United States. https://doi.org/10.3390/w11081579. https://www.osti.gov/servlets/purl/1611030.
@article{osti_1611030,
title = {Making Steppingstones out of Stumbling Blocks: A Bayesian Model Evidence Estimator with Application to Groundwater Transport Model Selection},
author = {Elshall, Ahmed S. and Ye, Ming},
abstractNote = {Bayesian model evidence (BME) is a measure of the average fit of a model to observation data given all the parameter values that the model can assume. By accounting for the trade-off between goodness-of-fit and model complexity, BME is used for model selection and model averaging purposes. For strict Bayesian computation, the theoretically unbiased Monte Carlo based numerical estimators are preferred over semi-analytical solutions. This study examines five BME numerical estimators and asks how accurate estimation of the BME is important for penalizing model complexity. The limiting cases for numerical BME estimators are the prior sampling arithmetic mean estimator (AM) and the posterior sampling harmonic mean (HM) estimator, which are straightforward to implement, yet they result in underestimation and overestimation, respectively. We also consider the path sampling methods of thermodynamic integration (TI) and steppingstone sampling (SS) that sample multiple intermediate distributions that link the prior and the posterior. Although TI and SS are theoretically unbiased estimators, they could have a bias in practice arising from numerical implementation. For example, sampling errors of some intermediate distributions can introduce bias. We propose a variant of SS, namely the multiple one-steppingstone sampling (MOSS) that is less sensitive to sampling errors. We evaluate these five estimators using a groundwater transport model selection problem. SS and MOSS give the least biased BME estimation at an efficient computational cost. If the estimated BME has a bias that covariates with the true BME, this would not be a problem because we are interested in BME ratios and not their absolute values. On the contrary, the results show that BME estimation bias can be a function of model complexity. Thus, biased BME estimation results in inaccurate penalization of more complex models, which changes the model ranking. This was less observed with SS and MOSS as with the three other methods.},
doi = {10.3390/w11081579},
journal = {Water (Basel)},
number = 8,
volume = 11,
place = {United States},
year = {Tue Jul 30 00:00:00 EDT 2019},
month = {Tue Jul 30 00:00:00 EDT 2019}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 4 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Bayesian calibration of groundwater models with input data uncertainty: CALIBRATING WITH INPUT DATA UNCERTAINTY
journal, April 2017

  • Xu, Tianfang; Valocchi, Albert J.; Ye, Ming
  • Water Resources Research, Vol. 53, Issue 4
  • DOI: 10.1002/2016WR019512

Bayes Factors
journal, June 1995


Estimating the Dimension of a Model
journal, March 1978


Maximum likelihood Bayesian averaging of spatial variability models in unsaturated fractured tuff: MAXIMUM LIKELIHOOD BAYESIAN MODEL AVERAGING
journal, May 2004

  • Ye, Ming; Neuman, Shlomo P.; Meyer, Philip D.
  • Water Resources Research, Vol. 40, Issue 5
  • DOI: 10.1029/2003WR002557

Improving parameter estimation for column experiments by multi-model evaluation and comparison
journal, October 2009


CXTFIT/Excel–A modular adaptable code for parameter estimation, sensitivity analysis and uncertainty analysis for laboratory or field tracer experiments
journal, September 2010


Repeated pig manure applications modify nitrate and chloride competition and fluxes in a Nitisol
journal, April 2015


Marginal likelihood estimation via power posteriors
journal, July 2008

  • Friel, N.; Pettitt, A. N.
  • Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 70, Issue 3
  • DOI: 10.1111/j.1467-9868.2007.00650.x

Simulating normalizing constants: from importance sampling to bridge sampling to path sampling
journal, May 1998


A bayesian approach to testing the arbitrage pricing theory
journal, July 1991


Nested sampling algorithm for subsurface flow model selection, uncertainty quantification, and nonlinear calibration: NESTED SAMPLING FOR SUBSURFACE FLOW MODELS
journal, December 2013

  • Elsheikh, A. H.; Wheeler, M. F.; Hoteit, I.
  • Water Resources Research, Vol. 49, Issue 12
  • DOI: 10.1002/2012WR013406

Properties of nested sampling
journal, June 2010


Model Averaging Techniques for Quantifying Conceptual Model Uncertainty
journal, August 2010


Accelerating Markov Chain Monte Carlo Simulation by Differential Evolution with Self-Adaptive Randomized Subspace Sampling
journal, January 2009

  • Vrugt, J. A.; ter Braak, C. J. F.; Diks, C. G. H.
  • International Journal of Nonlinear Sciences and Numerical Simulation, Vol. 10, Issue 3
  • DOI: 10.1515/IJNSNS.2009.10.3.273

Markov Chain Sampling Methods for Dirichlet Process Mixture Models
journal, June 2000


Bayesian inference and predictive performance of soil respiration models in the presence of model discrepancy
journal, January 2019

  • Elshall, Ahmed S.; Ye, Ming; Niu, Guo-Yue
  • Geoscientific Model Development, Vol. 12, Issue 5
  • DOI: 10.5194/gmd-12-2009-2019

Annealed importance sampling
journal, April 2001


Hydrological model selection: A Bayesian alternative: HYDROLOGICAL MODEL SELECTION
journal, October 2005

  • Marshall, Lucy; Nott, David; Sharma, Ashish
  • Water Resources Research, Vol. 41, Issue 10
  • DOI: 10.1029/2004WR003719

Bayesian Phylogenetic Model Selection Using Reversible Jump Markov Chain Monte Carlo
journal, February 2004


Improving power posterior estimation of statistical evidence
journal, May 2013


Critical Assessment of Models for Transport of Engineered Nanoparticles in Saturated Porous Media
journal, October 2014

  • Goldberg, Eli; Scheringer, Martin; Bucheli, Thomas D.
  • Environmental Science & Technology, Vol. 48, Issue 21
  • DOI: 10.1021/es502044k

On the optimal design of experiments for conceptual and predictive discrimination of hydrologic system models: CONCEPTUAL AND PREDICTIVE DISCRIMINATION
journal, June 2015

  • Kikuchi, C. P.; Ferré, T. P. A.; Vrugt, J. A.
  • Water Resources Research, Vol. 51, Issue 6
  • DOI: 10.1002/2014WR016795

Degassing, gas retention and release in Fe(0) permeable reactive barriers
journal, April 2014


Data‐Worth Assessment for a Three‐Dimensional Optimal Design in Nonlinear Groundwater Systems
journal, December 2018

  • Safi, Amir; Vilhelmsen, Troels N.; Alameddine, Ibrahim
  • Groundwater, Vol. 57, Issue 4
  • DOI: 10.1111/gwat.12835

Climate informed flood frequency analysis and prediction in Montana using hierarchical Bayesian modeling
journal, January 2008

  • Kwon, Hyun-Han; Brown, Casey; Lall, Upmanu
  • Geophysical Research Letters, Vol. 35, Issue 5
  • DOI: 10.1029/2007GL032220

Bayesian experimental design for identification of model propositions and conceptual model uncertainty reduction
journal, September 2015


A multimodel data assimilation framework via the ensemble Kalman filter
journal, May 2014


Assessment of parametric uncertainty for groundwater reactive transport modeling
journal, May 2014

  • Shi, Xiaoqing; Ye, Ming; Curtis, Gary P.
  • Water Resources Research, Vol. 50, Issue 5
  • DOI: 10.1002/2013WR013755

Identification of TCE and PCE sorption and biodegradation parameters in a sandy aquifer for fate and transport modelling: batch and column studies
journal, February 2015

  • Kret, E.; Kiecak, A.; Malina, G.
  • Environmental Science and Pollution Research, Vol. 22, Issue 13
  • DOI: 10.1007/s11356-015-4156-9

Hydrogeological conceptual model building and testing: A review
journal, February 2019


Assessing five evolving microbial enzyme models against field measurements from a semiarid savannah-What are the mechanisms of soil respiration pulses?
journal, September 2014

  • Zhang, Xia; Niu, Guo-Yue; Elshall, Ahmed S.
  • Geophysical Research Letters, Vol. 41, Issue 18
  • DOI: 10.1002/2014GL061399

Uncertainty evaluation of mass discharge estimates from a contaminated site using a fully Bayesian framework: QUANTIFYING MASS DISCHARGE
journal, December 2010

  • Troldborg, Mads; Nowak, Wolfgang; Tuxen, Nina
  • Water Resources Research, Vol. 46, Issue 12
  • DOI: 10.1029/2010WR009227

A Model-Averaging Method for Assessing Groundwater Conceptual Model Uncertainty
journal, August 2010


Climate change impacts on extreme floods I: combining imperfect deterministic simulations and non-stationary frequency analysis
journal, December 2011


Maximum likelihood Bayesian model averaging and its predictive analysis for groundwater reactive transport models
journal, October 2015


Sequential Monte Carlo samplers
journal, June 2006

  • Del Moral, Pierre; Doucet, Arnaud; Jasra, Ajay
  • Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 68, Issue 3
  • DOI: 10.1111/j.1467-9868.2006.00553.x

Importance of reversible attachment in predicting E. coli transport in saturated aquifers from column experiments
journal, January 2014


Estimating the evidence - a review
journal, January 2012


Model selection on solid ground: Rigorous comparison of nine ways to evaluate Bayesian model evidence
journal, December 2014

  • Schöniger, Anneli; Wöhling, Thomas; Samaniego, Luis
  • Water Resources Research, Vol. 50, Issue 12
  • DOI: 10.1002/2014WR016062

Improved Nested Sampling and Surrogate-Enabled Comparison With Other Marginal Likelihood Estimators
journal, February 2018

  • Zeng, Xiankui; Ye, Ming; Wu, Jichun
  • Water Resources Research, Vol. 54, Issue 2
  • DOI: 10.1002/2017WR020782

Multimodel Ranking and Inference in Ground Water Modeling
journal, July 2005


Sworn testimony of the model evidence: Gaussian Mixture Importance (GAME) sampling: SWORN TESTIMONY OF THE MODEL EVIDENCE
journal, July 2017

  • Volpi, Elena; Schoups, Gerrit; Firmani, Giovanni
  • Water Resources Research, Vol. 53, Issue 7
  • DOI: 10.1002/2016WR020167

Conjunctive management of surface and groundwater resources under projected future climate change scenarios
journal, September 2016


A hypothesis-driven approach to optimize field campaigns: HYPOTHESIS-DRIVEN FIELD CAMPAIGNS
journal, June 2012

  • Nowak, Wolfgang; Rubin, Yoram; de Barros, Felipe P. J.
  • Water Resources Research, Vol. 48, Issue 6
  • DOI: 10.1029/2011WR011016

Computing Bayes Factors Using Thermodynamic Integration
journal, April 2006


Water movement through an aggregated, gravelly oxisol from cameroon
journal, March 1990


Relative model score: a scoring rule for evaluating ensemble simulations with application to microbial soil respiration modeling
journal, August 2018

  • Elshall, Ahmed S.; Ye, Ming; Pei, Yongzhen
  • Stochastic Environmental Research and Risk Assessment, Vol. 32, Issue 10
  • DOI: 10.1007/s00477-018-1592-3

Evaluating model structure adequacy: The case of the Maggia Valley groundwater system, southern Switzerland: Evaluating Model Structure Adequacy
journal, January 2013

  • Foglia, L.; Mehl, S. W.; Hill, M. C.
  • Water Resources Research, Vol. 49, Issue 1
  • DOI: 10.1029/2011WR011779

Maximum likelihood Bayesian averaging of uncertain model predictions
journal, November 2003

  • Neuman, S. P.
  • Stochastic Environmental Research and Risk Assessment (SERRA), Vol. 17, Issue 5
  • DOI: 10.1007/s00477-003-0151-7

On model selection criteria in multimodel analysis: ON MODEL SELECTION CRITERIA IN MULTIMODEL ANALYSIS
journal, March 2008

  • Ye, Ming; Meyer, Philip D.; Neuman, Shlomo P.
  • Water Resources Research, Vol. 44, Issue 3
  • DOI: 10.1029/2008WR006803

Differential Evolution Markov Chain with snooker updater and fewer chains
journal, October 2008


Nested sampling for general Bayesian computation
journal, December 2006


A Primer for Model Selection: The Decisive Role of Model Complexity
journal, March 2018

  • Höge, Marvin; Wöhling, Thomas; Nowak, Wolfgang
  • Water Resources Research, Vol. 54, Issue 3
  • DOI: 10.1002/2017WR021902

Bayesian model averaging to explore the worth of data for soil‐plant model selection and prediction
journal, April 2015

  • Wöhling, Thomas; Schöniger, Anneli; Gayler, Sebastian
  • Water Resources Research, Vol. 51, Issue 4
  • DOI: 10.1002/2014WR016292

Make the most of your samples: Bayes factor estimators for high-dimensional models of sequence evolution
journal, March 2013

  • Baele, Guy; Lemey, Philippe; Vansteelandt, Stijn
  • BMC Bioinformatics, Vol. 14, Issue 1
  • DOI: 10.1186/1471-2105-14-85

Phylogenetic Inference via Sequential Monte Carlo
journal, January 2012

  • Bouchard-Côté, Alexandre; Sankararaman, Sriram; Jordan, Michael I.
  • Systematic Biology, Vol. 61, Issue 4
  • DOI: 10.1093/sysbio/syr131

Transport of U(VI) through sediments amended with phosphate to induce in situ uranium immobilization
journal, February 2015


Improving Marginal Likelihood Estimation for Bayesian Phylogenetic Model Selection
journal, December 2010


Marginal Likelihood From the Metropolis–Hastings Output
journal, March 2001

  • Chib, Siddhartha; Jeliazkov, Ivan
  • Journal of the American Statistical Association, Vol. 96, Issue 453
  • DOI: 10.1198/016214501750332848

Approximate Bayesian Inference with the Weighted Likelihood Bootstrap
journal, January 1994


Optimal Choice of AR and MA Parts in Autoregressive Moving Average Models
journal, March 1982

  • Kashyap, Rangasami L.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-4, Issue 2
  • DOI: 10.1109/TPAMI.1982.4767213

A path sampling identity for computing the Kullback–Leibler and J divergences
journal, July 2010

  • Lefebvre, Geneviève; Steele, Russell; Vandal, Alain C.
  • Computational Statistics & Data Analysis, Vol. 54, Issue 7
  • DOI: 10.1016/j.csda.2010.01.018

Estimating Bayes factors via thermodynamic integration and population MCMC
journal, October 2009


A statistical concept to assess the uncertainty in Bayesian model weights and its impact on model ranking: ASSESSING THE UNCERTAINTY IN BAYESIAN MODEL WEIGHTS
journal, September 2015

  • Schöniger, Anneli; Wöhling, Thomas; Nowak, Wolfgang
  • Water Resources Research, Vol. 51, Issue 9
  • DOI: 10.1002/2015WR016918

Impacts of prior parameter distributions on Bayesian evaluation of groundwater model complexity
journal, April 2018


Hydrogeological Bayesian Hypothesis Testing through Trans-Dimensional Sampling of a Stochastic Water Balance Model
journal, July 2019

  • Enemark, Trine; Peeters, Luk JM; Mallants, Dirk
  • Water, Vol. 11, Issue 7
  • DOI: 10.3390/w11071463

Bayesian Chance-Constrained Hydraulic Barrier Design under Geological Structure Uncertainty: Ground Water xx, no. xx: xx-xx
journal, December 2014

  • Chitsazan, Nima; Pham, Hai V.; Tsai, Frank T. -C.
  • Groundwater, Vol. 53, Issue 6
  • DOI: 10.1111/gwat.12304

Model complexity control for hydrologic prediction: MODEL COMPLEXITY CONTROL
journal, August 2008

  • Schoups, G.; van de Giesen, N. C.; Savenije, H. H. G.
  • Water Resources Research, Vol. 44, Issue 12
  • DOI: 10.1029/2008WR006836

Dependence of Bayesian Model Selection Criteria and Fisher Information Matrix on Sample Size
journal, October 2011


Finding the right balance between groundwater model complexity and experimental effort via Bayesian model selection
journal, December 2015


The hydrologist’s guide to Bayesian model selection, averaging and combination
journal, May 2019