Approximate Bayesian computation (ABC) gives exact results under the assumption of model error
Open accessThe DOI matches its Crossref record; 40 of the 41 references it cites were found in a registry or an index.
Abstract
Approximate Bayesian computation (ABC) or likelihood-free inference algorithms are used to find approximations to posterior distributions without making explicit use of the likelihood function, depending instead on simulation of sample data sets from the model. In this paper we show that under the assumption of the existence of a uniform additive model error term, ABC algorithms give exact results when sufficient summaries are used. This interpretation allows the approximation made in many previous application papers to be understood, and should guide the choice of metric and tolerance in future work. ABC algorithms can be generalized by replacing the 0-1 cut-off with an acceptance probability that varies with the distance of the simulated data from the observed data. The acceptance density gives the distribution of the error term, enabling the uniform error usually used to be replaced by a general distribution. This generalization can also be applied to approximate Markov chain Monte Carlo algorithms. In light of this work, ABC algorithms can be seen as calibration techniques for implicit stochastic models, inferring parameter values in light of the computer model, data, prior beliefs about the parameter values, and any measurement or model errors.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The key strength of ABC approaches is that they can be applied to problems with intractable likelihoods35,36 (for example, complex stochastic models).”
From A framework for parameter estimation and model selection from experimental data in systems biology using approximate Bayesian computation (2014) · cites this paper as [35]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Kass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Approximate Bayesian computation in population genetics
Beaumont, M. A., Zhang, W., & Balding, D. J. (2002) · Genetics · doi:10.1093/genetics/162.4.2025 · Cited by 2,932
Monte Carlo Strategies in Scientific Computing
Liu, J. S. (2004) · Springer Series in Statistics · doi:10.1007/978-0-387-76371-2 · Cited by 2,690
Toni, T., Welch, D., Strelkowa, N., Ipsen, A., & Stumpf, M. P. H. (2009) · Journal of The Royal Society Interface · doi:10.1098/rsif.2008.0172 · Cited by 1,498
Monte Carlo Strategies in Scientific Computing
Hesterberg, T. (2002) · Technometrics · doi:10.1198/tech.2002.s85 · Cited by 1,409
Markov chain Monte Carlo without likelihoods
Marjoram, P., Molitor, J., Plagnol, V., & Tavaré, S. (2003) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0306899100 · Cited by 1,199
Population growth of human Y chromosomes: a study of Y chromosome microsatellites
Pritchard, J. K., Seielstad, M. T., Perez-Lezaun, A., & Feldman, M. W. (1999) · Molecular Biology and Evolution · doi:10.1093/oxfordjournals.molbev.a026091 · Cited by 1,080
Computer Model Calibration Using High-Dimensional Output
Higdon, D., Gattiker, J., Williams, B., & Rightley, M. (2008) · Journal of the American Statistical Association · doi:10.1198/016214507000000888 · Cited by 867
Sequential Monte Carlo without likelihoods
Sisson, S. A., Fan, Y., & Tanaka, M. M. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0607208104 · Cited by 856
Cornuet, J.-M., Santos, F., Beaumont, M. A., Robert, C. P., Marin, J.-M., Balding, D. J., Guillemaud, T., & Estoup, A. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn514 · Cited by 690
Research works printed but not linked: 33
- Wilkinson, 2007, Bayesian inference of primate divergence times Ph thesis University of
- Nunes, M. A., Balding, D. J., 2010. On optimal selection of summary statistics for approximate Bayesian computation. Stat. Appl. Genet. Mo. B. 9, Article 34. · DOI · Paper page
- Blum, M., Tran, V., 2010. HIV with contact tracing: a case study in approximate Bayesian computation. Biostatistics 11 (4), 644-660. · DOI
- Shibata, 2008, Siegmund Marjoram Modeling DNA methylation in apopulation of cancer cells article, Stat Appl Genet Mo B, 18
- Plagnol, 2004, Approximate Bayesian computation and In Proceedings of Monte Carlo and Quasi - Monte Carlo Verlag, Methods, 99
- Ratmann, 2007, Using likelihood - free inference to compare evolutionary dynamics of the protein networks ofH pyloriandP falciparum, Comput Biol, 2266
- Fearnhead, P., Prangle, D., 2012. Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. J. Roy. Stat. Soc. Ser. B 74, 419-474. · DOI · Paper page
- Kennedy, M., O'Hagan, A., 2001. Bayesian calibration of computer models (with discussion). J. R. Statist. Soc. Ser. B 63, 425-464.
- Robert, C. P., Cornuet, J. M., Marin, J. M., Pillai, N. S., 2011. Lack of confidence in approximate Bayesian computation model choice. P. Natl. Acad. Sci. USA 108, 15112-15117.
- Toni, T., Welch, D., Strelkowa, N., Ipsen, A., Stumpf, M. P. H., 2009. Approximate Bayesian Computation scheme for parameter inference and model selection in dynamical systems. J. R. Soc. Interface 6 (31), 187-202. · DOI · Paper page
- Campbell, 2006, Statistical calibration of computer simulations, Eng Syst Safe, 1358, 10.1016/j.ress.2005.11.032 · DOI
- Sunnaker, M., Busetto, A. G., Numminen, E., Corander, J., Foll, M., Dessimoz, C., 2013. Approximate bayesian computation. PLoS Comput Biol 9, e1002803.
- Cornuet, 2008, Inferring population history with DIY ABC a user - friendly approach to approximate Bayesian computation, Bioinformatics, 24, 2713, 10.1093/bioinformatics/btn514 · DOI · Paper page
- Beaumont, 2002, Balding Approximate Bayesian computatation in population genetics, Genetics, 162
- Barnes, 2012, Considerate approaches to constructing summary statistics for ABC model selection, Stat Comput, 22, 1181, 10.1007/s11222-012-9335-7 · DOI · Paper page
- Murray, I., Ghahramani, Z., MacKay, D. J. C., 2006. MCMC for doublyintractable distributions. In: Proceedings of the 22nd Annual Conference on Uncertainty in Artificial Intelligence. UAI.
- Marjoram, P., Molitor, J., Plagnol, V ., Tavar´ e, S., 2003. Markov chain Monte Carlo without likelihoods. P. Natl. Acad. Sci. USA 100 (26), 15324-15328.
- Pritchard, J. K., Seielstad, M. T., Perez-Lezaun, A., Feldman, M. W., 1999. Population growth of human Y chromosomes: a study of Y chromosome microsatellites. Mol. Biol. Evol. 16 (12), 1791-1798. · DOI · Paper page
- Goldstein, 2009, Bayesian modelling and inference for physical systems, Stat Plan Infer, 139
- Sisson, S. A., Fan, Y., Tanaka, M. M., 2007. Sequential Monte Carlo without likelihoods. Proc. Natl. Acad. Sci. USA 104 (6), 1760-1765. · DOI · Paper page
- Wilkinson, R. D., 2007. Bayesian inference of primate divergence times. Ph.D. thesis, University of Cambridge.
- Higdon, 2008, model calibration using high - dimensional output, Computer Am Assoc, 103
- Peters, 2012, On sequential Monte Carlo partial rejection control and approximate Bayesian computation, Stat Comput, 22, 1209, 10.1007/s11222-012-9315-y · DOI · Paper page
- Hamilton, 2005, Bayesian estimation of recent migration rates after a spatial expansion, Genetics, 170
- Doucet, 2012, Del Moral An adaptive sequential Monte Carlo method for approximate Bayesian computation, Stat Comput, 22, 1009, 10.1007/s11222-011-9271-y · DOI · Paper page
- Foll, 2008, An approximate Bayesian computation approach to overcome biases that arise when using amplifed fragment length polymorphism markers to study population structure, Genetics, 179
- Kass, 1995, factors, Am Assoc, 773, 10.1080/01621459.1995.10476572 · DOI · Paper page
- Joyce, 2008, Marjoram Approximately sufficient Bayesian computation article, statistics Stat Appl Genet Mo B, 26
- Kennedy, 2001, Bayesian calibration of computer models with discussion, Statist, 425
- Tanaka, M. M., Francis, A. R., Luciani, F., Sisson, S. A., 2006. Using approximate Bayesian computation to estimate tuberculosis transmission parameters from genotype data. Genetics 173, 1511-1520.
- Beaumont, 2009, for ABC algorithms the ABC, Biometrika, 983, 10.1093/biomet/asp052 · DOI · Paper page
- Wilkinson, R. D., Tavar´ e, S., 2009. Estimating primate divergence times by using conditioned birth-and-death processes. Theor. Popul. Biol. 75, 278-285. · DOI
- Drovandi, 2011, Faddy Approximate Bayesian computation using indirect inference, Stat Soc, 317
Cited by
Items 301–334 of 334
Bayesian algorithms for multiple target tracking with binary sensors on particle filterPreprint
Milton, R., Guetierrez, A., Bradbury, B., Cherry, S., & Cummings, B. (2020) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/4zh3g
Modelling extremes using approximate Bayesian ComputationPreprint
Erhardt, R. J., & Sisson, S. A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.1451
“choices of kernel Kh will produce continuous weights. 9 The resulting weighted samples (w(i),θ(i),y(i)) are then draws from πABC h (θ,y|yobs) ∝ Kh(ky − yobsk)L(y|θ)p(θ) (5) (Reeves and Pettitt, 2005; Wilkinson, 2008). Distribution (5) is the joint posterior distribution of model parameter θ and auxiliary dataset y suc…”
BackgroundEfficient Data Mosaicing with Simulation-based InferencePreprint
Gambardella, A., Choi, Y., Choi, D., & Lee, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.14602
“In ABC, multiple traces of the simulator are aggregated into an empirical posterior, with traces being accepted or given high weight when their observed variables align closely with a target observation (where “closeness” is defined via a tolerance hyperparameter), and rejected or given low weight otherwise.”
MethodBayesian uncertainty quantification to identify population level vaccine hesitancy behaviours
Warne, D. J., Varghese, A., Brewster, A., Browning, A. P., Krell, M. M., Drovandi, C., Hu, W., Mira, A., Mengersen, K. L., & Jenner, A. L. (2026) · PLoS ONE · doi:10.1371/journal.pone.0349499
“While this assumption will almost certainly not hold in practice, our approach to Bayesian inference (See S2 Appendix) has well-establish properties for natural robustness to misspecification and accounts for model uncertainty [56–58].”
Asymptotics of ABCPreprint
Fearnhead, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.07712
“ional Gaussian random variable with covariance matrix A( 0). Furthermore, for close to 0 the prior will be well approximated by a uniform prior. For the following we assume that D 0 is of rank p. Wilkinson (2013) shows that the eect of the approximation in ABC, whereby we accept simulated summaries which are similar,…”
MethodBayesian learning of the optimal action-value function in a Markov decision processPreprint
Guo, J., Ho, C., & Singh, S. S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.01859
A Comparison of Kernels for ABC-SMCPreprint
Prangle, D., Viscardi, C., & Ragy, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.06351
Uncertainty in model-informed precision dosing: predicting what you can and what you cannot predict
Augustin, D. (2024) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-7e8mmwwa1
Bayesian methods for interpretable and scalable modelling of population dynamics
Rotous, I. (2024) · Kent Academic Repository (University of Kent) · doi:10.22024/unikent/01.02.107803
Improved approximate Bayesian computation methods for censored and uncensored data
Dmitrieva, T. (2018) · Huskie Commons (Northern Illinois University)
Markov Chain Monte Carlo Methods and Applications in Neuroscience
Milinanni, F. (2023) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
Mitigating Model Misspecification with Variational Bayesian Inference
Krissaane, I. (2024) · Nottingham ePrints (University of Nottingham)
Bayesian statistical methods in evolutionary genomics
Zwaenepoel, A. (2022) · Ghent University Academic Bibliography (Ghent University)
Singh, S. S., Sedki, M. A., Jasra, A., Pudlo, P., Robert, C. P., Lee, A., Marin, J., Kosmidis, I., Girolami, M., Andrieu, C., et al. (2012) · Base Institutionnelle de Recherche de l'université Paris-Dauphine (BIRD) (University Paris-Dauphine)
Approximate Methods For Otherwise Intractable Problems
RICHARDS, K. (2023) · Durham e-Theses (Durham University)
Simpson, M. J., Bennett, J. S., & Baker, R. E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.04891
Enhanced bridge damage detection with utility function framework
Turkomany, M., AbdelLatef, A. I., & Uddin, N. (2026) · Measurement · doi:10.1016/j.measurement.2026.120858
Méthodes d'inférence statistique pour champs de Gibbs
Stoehr, J. (2015) · theses.fr (ABES) · doi:10.70675/e11b3c43zd4d5z468dz91c3zc0e88793e2a9
Structural Health Monitoring Optimization
Geara, C. (2021) · theses.fr (ABES) · doi:10.70675/cc4a7ceez24d2z4c98z810cz6ddbb2fae4f6
SBI in Dynamic Data Analysis of a Multichannel Imaging Detector
Сараев, Р. Е., & Sharakin, S. A. (2025) · Moscow University Physics Bulletin · doi:10.3103/s0027134925702844
Bayesian learning for the stochastic shortest path problemPreprint
Ho, C. W., Singh, S. S., & Guo, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.04845
Cottom, J. P., & Olsson, E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.09594
“…( θ, u ) represents a physical discrepancy or model-error observation with a specified noise law, as in calibration, ABC/model-error interpretations, or residual-noise physics-constrained generative modelling, then the determinant factor in (27) is part of the intended Bayesian model [64, 65, 45].”
Learning the distance for ABC and localized neural posterior estimationPreprint
Wang, Y., & Nott, D. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.22981
“In ABC, the kernel can be interpreted as a model error term (Wilkinson, 2013) and it is commonly defined through a distance and one-dimensional kernel.”
A New Sampling Method via Approximate Bayesian Computation with Correlated Random Numbers
Qian, H. (2026) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2026.2705296
Robust Methods for Simulation-based Inference under Model Misspecification
Kelly, R. (2026) · Queensland University of Technology · doi:10.5204/thesis.eprints.266874
Kim, K. (2026) · eScholarship (California Digital Library)
Efficient approximate Bayesian inference for large, heterogeneous biological datasetsPreprint
Zanussi, J., & Miles, C. E. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.10.05.756786
“Wilkin-son [28] interprets the hard cutoff as adding a uniform error on [ − ϵ, ϵ ].”
Kumar, S., Prakash, S., & Kumar, H. (2026) · Journal of Statistical Computation and Simulation · doi:10.1080/00949655.2026.2751567
Simulation-free approximate Bayesian computation for stochastic reaction networksPreprint
Li, Z., Barahona, M., & Thomas, P. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.10.19.760104
Herold, J., Götz, M., & Schug, A. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.29506
Two-Phase Rapid Simulation-Based Inference with Differentiable SimulatorsPreprint
Zivanovic, U., Srinivasan, R., Trotta, R., & Scaffidi, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.12422
An agent-based model of Epstein-Barr virus transmission and vaccinationPreprint
Amoako, B., Huang, Z., Thommes, E. W., Hare, W., & Cojocaru, M. G. (2026) · medRxiv · doi:10.64898/2026.11.10.26367734
Metadata
- Authors
- Wilkinson, R. D.
- Affiliations
- University of Nottingham (GB)
- Corresponding author
- Wilkinson, Richard David
- Venue
- Statistical Applications in Genetics and Molecular Biology
- Publisher
- Walter de Gruyter GmbH
- Published
- 2013-01-06
- Volume
- 12
- Issue
- 2
- Pages
- 129-41
- ISSN
- 1544-6115 (ISSN-L)
- 2194-6302
- OpenAlex
- W2053332694
- Cited by
- 247
- References
- 41
- Citations by year
- 2026: 6 · 2025: 9 · 2024: 8 · 2023: 8 · 2022: 9 · 2021: 13 · 2020: 30 · 2019: 16 · 2018: 26 · 2017: 13 · 2016: 17 · 2015: 24 · 2014: 17 · 2013: 16
- FWCI
- 21.70
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Statistical Applications in Genetics and Molecular Biology (publishedVersion)
- PubMed (publishedVersion)
- White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Markov Chains and Monte Carlo Methods
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Gaussian Processes and Bayesian Inference
- Keywords
- approximate Bayesian computation, model error, simulation-based inference, acceptance probability, model calibration
- MeSH terms
- Algorithms, Bayes Theorem, Computer Simulation, Markov Chains, Monte Carlo Method, Models, Statistical, Likelihood Functions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.