BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood

Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: An, Ziwen, South, Leah F, Drovandi, Christopher
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator An, Ziwen
South, Leah F
Drovandi, Christopher
description Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of a judiciously chosen summary statistic of the data via model simulation and density estimation. Compared to alternative methods such as approximate Bayesian computation (ABC), BSL requires little tuning and requires less model simulations than ABC when the chosen summary statistic is high-dimensional. The original synthetic likelihood relies on a multivariate normal approximation of the intractable likelihood, where the mean and covariance are estimated by simulation. An extension of BSL considers replacing the sample covariance with a penalised covariance estimator to reduce the number of required model simulations. Further, a semi-parametric approach has been developed to relax the normality assumption. In this paper, we present an R package called BSL that amalgamates the aforementioned methods and more into a single, easy-to-use and coherent piece of software. The R package also includes several examples to illustrate how to use the package and demonstrate the utility of the methods.
doi_str_mv 10.48550/arxiv.1907.10940
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1907_10940</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1907_10940</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-c113d98e64364e04ed6300ff5f3aaf0677c5989d165eb5c46e19ed49918fe55b3</originalsourceid><addsrcrecordid>eNotj8tOwzAURL1hgQofwAr_QIItPxKza6rykIJApPvo1r6mVvNAjqnI31MCq9GMRqM5hNxwlstSKXYH8Tuccm5YkXNmJLsksWrqe7oe6Dt9A3uED6R-jHTrfbABh3ROI_SY8JxNKfSQwjgslSb0X91iswomdPRldNhN9BSAVjDjFGCgzTykA6ZgaR2O2IXDOLorcuGhm_D6X1dk97DdbZ6y-vXxebOuM9AFyyznwpkStRRaIpPotGDMe-UFgGe6KKwypXFcK9wrKzVyg04aw0uPSu3Fitz-zS7Q7Wc8n49z-wvfLvDiB5CMVQU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood</title><source>arXiv.org</source><creator>An, Ziwen ; South, Leah F ; Drovandi, Christopher</creator><creatorcontrib>An, Ziwen ; South, Leah F ; Drovandi, Christopher</creatorcontrib><description>Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of a judiciously chosen summary statistic of the data via model simulation and density estimation. Compared to alternative methods such as approximate Bayesian computation (ABC), BSL requires little tuning and requires less model simulations than ABC when the chosen summary statistic is high-dimensional. The original synthetic likelihood relies on a multivariate normal approximation of the intractable likelihood, where the mean and covariance are estimated by simulation. An extension of BSL considers replacing the sample covariance with a penalised covariance estimator to reduce the number of required model simulations. Further, a semi-parametric approach has been developed to relax the normality assumption. In this paper, we present an R package called BSL that amalgamates the aforementioned methods and more into a single, easy-to-use and coherent piece of software. The R package also includes several examples to illustrate how to use the package and demonstrate the utility of the methods.</description><identifier>DOI: 10.48550/arxiv.1907.10940</identifier><language>eng</language><subject>Statistics - Applications ; Statistics - Computation ; Statistics - Machine Learning</subject><creationdate>2019-07</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1907.10940$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1907.10940$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>An, Ziwen</creatorcontrib><creatorcontrib>South, Leah F</creatorcontrib><creatorcontrib>Drovandi, Christopher</creatorcontrib><title>BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood</title><description>Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of a judiciously chosen summary statistic of the data via model simulation and density estimation. Compared to alternative methods such as approximate Bayesian computation (ABC), BSL requires little tuning and requires less model simulations than ABC when the chosen summary statistic is high-dimensional. The original synthetic likelihood relies on a multivariate normal approximation of the intractable likelihood, where the mean and covariance are estimated by simulation. An extension of BSL considers replacing the sample covariance with a penalised covariance estimator to reduce the number of required model simulations. Further, a semi-parametric approach has been developed to relax the normality assumption. In this paper, we present an R package called BSL that amalgamates the aforementioned methods and more into a single, easy-to-use and coherent piece of software. The R package also includes several examples to illustrate how to use the package and demonstrate the utility of the methods.</description><subject>Statistics - Applications</subject><subject>Statistics - Computation</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAURL1hgQofwAr_QIItPxKza6rykIJApPvo1r6mVvNAjqnI31MCq9GMRqM5hNxwlstSKXYH8Tuccm5YkXNmJLsksWrqe7oe6Dt9A3uED6R-jHTrfbABh3ROI_SY8JxNKfSQwjgslSb0X91iswomdPRldNhN9BSAVjDjFGCgzTykA6ZgaR2O2IXDOLorcuGhm_D6X1dk97DdbZ6y-vXxebOuM9AFyyznwpkStRRaIpPotGDMe-UFgGe6KKwypXFcK9wrKzVyg04aw0uPSu3Fitz-zS7Q7Wc8n49z-wvfLvDiB5CMVQU</recordid><startdate>20190725</startdate><enddate>20190725</enddate><creator>An, Ziwen</creator><creator>South, Leah F</creator><creator>Drovandi, Christopher</creator><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190725</creationdate><title>BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood</title><author>An, Ziwen ; South, Leah F ; Drovandi, Christopher</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-c113d98e64364e04ed6300ff5f3aaf0677c5989d165eb5c46e19ed49918fe55b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Statistics - Applications</topic><topic>Statistics - Computation</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>An, Ziwen</creatorcontrib><creatorcontrib>South, Leah F</creatorcontrib><creatorcontrib>Drovandi, Christopher</creatorcontrib><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>An, Ziwen</au><au>South, Leah F</au><au>Drovandi, Christopher</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood</atitle><date>2019-07-25</date><risdate>2019</risdate><abstract>Bayesian synthetic likelihood (BSL) is a popular method for estimating the parameter posterior distribution for complex statistical models and stochastic processes that possess a computationally intractable likelihood function. Instead of evaluating the likelihood, BSL approximates the likelihood of a judiciously chosen summary statistic of the data via model simulation and density estimation. Compared to alternative methods such as approximate Bayesian computation (ABC), BSL requires little tuning and requires less model simulations than ABC when the chosen summary statistic is high-dimensional. The original synthetic likelihood relies on a multivariate normal approximation of the intractable likelihood, where the mean and covariance are estimated by simulation. An extension of BSL considers replacing the sample covariance with a penalised covariance estimator to reduce the number of required model simulations. Further, a semi-parametric approach has been developed to relax the normality assumption. In this paper, we present an R package called BSL that amalgamates the aforementioned methods and more into a single, easy-to-use and coherent piece of software. The R package also includes several examples to illustrate how to use the package and demonstrate the utility of the methods.</abstract><doi>10.48550/arxiv.1907.10940</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.1907.10940
ispartof
issn
language eng
recordid cdi_arxiv_primary_1907_10940
source arXiv.org
subjects Statistics - Applications
Statistics - Computation
Statistics - Machine Learning
title BSL: An R Package for Efficient Parameter Estimation for Simulation-Based Models via Bayesian Synthetic Likelihood
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T08%3A13%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=BSL:%20An%20R%20Package%20for%20Efficient%20Parameter%20Estimation%20for%20Simulation-Based%20Models%20via%20Bayesian%20Synthetic%20Likelihood&rft.au=An,%20Ziwen&rft.date=2019-07-25&rft_id=info:doi/10.48550/arxiv.1907.10940&rft_dat=%3Carxiv_GOX%3E1907_10940%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true