Title

ABC random forests for Bayesian parameter inferenceuse asterix (*) to get italics

Authors

Louis Raynal, Jean-Michel Marin, Pierre Pudlo, Mathieu Ribatet, Christian P. Robert, Arnaud EstoupPlease use the format "First name initials family name" as in "Marie S. Curie, Niels H. D. Bohr, Albert Einstein, John R. R. Tolkien, Donna T. Strickland"

Year

2017

Picture

Abstract

This preprint has been reviewed and recommended by Peer Community In Evolutionary Biology (http:// dx.doi.org/ 10.24072/ pci.evolbiol.100036). Approximate Bayesian computation (ABC) has grown into a standard methodology that manages Bayesian inference for models associated with intractable likelihood functions. Most ABC implementations require the preliminary selection of a vector of infor- mative statistics summarizing raw data. Furthermore, in almost all existing implementations, the toler- ance level that separates acceptance from rejection of simulated parameter values needs to be calibrated. We propose to conduct likelihood-free Bayesian inferences about parameters with no prior selection of the relevant components of the summary statistics and bypassing the derivation of the associated toler- ance level. The approach relies on the random forest methodology of Breiman (2001) applied in a (non parametric) regression setting. We advocate the derivation of a new random forest for each component of the parameter vector of interest. When compared with earlier ABC solutions, this method offers sig- nificant gains in terms of robustness to the choice of the summary statistics, does not depend on any type of tolerance level, and is a good trade-off in term of quality of point estimator precision and credible interval estimations for a given computing time. We illustrate the performance of our methodological proposal and compare it with earlier ABC methods on a Normal toy example and a population genetics example dealing with human population evolution. All methods designed here have been incorporated in the R package abcrf (version 1.7) available on CRAN.

Indicate the full web address (DOI or URL) giving public access to these data (if you have any problems with the deposit of your data, please contact contact@evolbiol.peercommunityin.org). In case all raw data are included in the preprint, indicate the DOI or URL of the preprint.

You should fill this box only if you chose 'All or part of the results presented in this preprint are based on data'. URL must start with http:// or https://

Indicate the full web address (DOI or URL) giving public access to these scripts (if you have any problems with the deposit of your scripts, please contact contact@evolbiol.peercommunityin.org). In case all raw scripts are included in the preprint, indicate the DOI or URL of the preprint.

You should fill this box only if you chose 'Scripts were used to obtain or analyze the results'. URL must start with http:// or https://

Indicate the full web address (DOI, SWHID or URL) giving public access to these codes (if you have any problems with the deposit of your codes, please contact contact@evolbiol.peercommunityin.org). In case all raw codes are included in the preprint, indicate the DOI or URL of the preprint.

You should fill this box only if you chose 'Codes have been used in this study'. URL must start with http:// or https://

Keywords

Approximate Bayesian computation, Bayesian inference, likelihood-free methods, parameter inference, random forests

Methods that require specific expertise (optional)

NonePlease indicate the methods that may require specialised expertise during the peer review process (use a comma to separate various required expertises).

Thematic fields

Bioinformatics & Computational Biology, Evolutionary Applications, Other, Population Genetics / Genomics

Suggested reviewers - Suggest up to 10 reviewers (provide names and Email addresses). (Optional)

No need for them to be recommenders of PCIEvolBiol. Please do not suggest reviewers for whom there might be a conflict of interest. Reviewers are not allowed to review preprints written by close colleagues (with whom they have published in the last four years, with whom they have received joint funding in the last four years, or with whom they are currently writing a manuscript, or submitting a grant proposal), or by family members, friends, or anyone for whom bias might affect the nature of the review - see the code of conduct

Opposed reviewers - Suggest up to 5 people not to invite as reviewers. (Optional)

e.g. John Doe [john@doe.com]

Submission date

2017-07-06 07:42:00

Recommender

Michael Blum

Reviewers

or Register
Submit a preprint

MANAGING BOARD

Guillaume Achaz
Juan Arroyo
Trine Bilde
Dustin Brisson
Marianne Elias
Inês Fragata
Matteo Fumagalli
Tatiana Giraud
Frédéric Guillaume
Ruth Hufbauer
Sara Magalhaes
Caroline Nieberding
Michael David Pirie
Tanja Pyhäjärvi

Fernando Racimo
Tanja Schwander
Alejandro Gonzalez Voyer

RECOMMENDERS

MANAGING BOARD

MEMBER OF

INDEXED BY