Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation

Bayesian inference affords scientists powerful tools for testing hypotheses. One of these tools is the Bayes factor, which indexes the extent to which support for one hypothesis over another is updated after seeing the data. Part of the hesitance to adopt this approach may stem from an unfamiliarity...

Full description

Saved in:
Bibliographic Details
Published in:Biometrical letters 2018-06, Vol.55 (1), p.31-43
Main Author: Faulkenberry, Thomas J
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c2041-5ca602b8bfd0e95338090d75747d96fa9f4a51d0117fe610342311c2f26f01523
cites
container_end_page 43
container_issue 1
container_start_page 31
container_title Biometrical letters
container_volume 55
creator Faulkenberry, Thomas J
description Bayesian inference affords scientists powerful tools for testing hypotheses. One of these tools is the Bayes factor, which indexes the extent to which support for one hypothesis over another is updated after seeing the data. Part of the hesitance to adopt this approach may stem from an unfamiliarity with the computational tools necessary for computing Bayes factors. Previous work has shown that closed-form approximations of Bayes factors are relatively easy to obtain for between-groups methods, such as an analysis of variance or t-test. In this paper, I extend this approximation to develop a formula for the Bayes factor that directly uses information that is typically reported for ANOVAs (e.g., the F ratio and degrees of freedom). After giving two examples of its use, I report the results of simulations which show that even with minimal input, this approximate Bayes factor produces similar results to existing software solutions.
doi_str_mv 10.2478/bile-2018-0003
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3156128153</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3156128153</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2041-5ca602b8bfd0e95338090d75747d96fa9f4a51d0117fe610342311c2f26f01523</originalsourceid><addsrcrecordid>eNotT89LwzAYDaLgmLt6DniO5kvaJvG2FZ2DgRcFbyNrv2jHmtQmlfnfG9HT4_Ee7wch18BvRaH03b47IhMcNOOcyzMyE2AMK5V6Oycz0KZiUgNckkWMh-yAsuIAakaaOvTDlDr_Tlf2GyN1tklhjDQF2qON04gUv7oWfYPUjaGneBpw7Hr0Kd7Tpc88oY9d8DQ4mj6QrjY1tcMwhlPX25SFK3Lh7DHi4h_n5PXx4aV-Ytvn9aZeblkjeAGsbGzFxV7vXcvRlFJqbnirSlWo1lTOGlfYEtrf3Q4r4LIQEqARTlQuHxJyTm7-cnP354Qx7Q5hGn2u3Ml8GISGnPoD0RZX3Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3156128153</pqid></control><display><type>article</type><title>Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation</title><source>Publicly Available Content Database</source><creator>Faulkenberry, Thomas J</creator><creatorcontrib>Faulkenberry, Thomas J</creatorcontrib><description>Bayesian inference affords scientists powerful tools for testing hypotheses. One of these tools is the Bayes factor, which indexes the extent to which support for one hypothesis over another is updated after seeing the data. Part of the hesitance to adopt this approach may stem from an unfamiliarity with the computational tools necessary for computing Bayes factors. Previous work has shown that closed-form approximations of Bayes factors are relatively easy to obtain for between-groups methods, such as an analysis of variance or t-test. In this paper, I extend this approximation to develop a formula for the Bayes factor that directly uses information that is typically reported for ANOVAs (e.g., the F ratio and degrees of freedom). After giving two examples of its use, I report the results of simulations which show that even with minimal input, this approximate Bayes factor produces similar results to existing software solutions.</description><identifier>ISSN: 1896-3811</identifier><identifier>EISSN: 2199-577X</identifier><identifier>DOI: 10.2478/bile-2018-0003</identifier><language>eng</language><publisher>Poznan: De Gruyter Poland</publisher><ispartof>Biometrical letters, 2018-06, Vol.55 (1), p.31-43</ispartof><rights>2018. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2041-5ca602b8bfd0e95338090d75747d96fa9f4a51d0117fe610342311c2f26f01523</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3156128153?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,25731,27901,27902,36989,44566</link.rule.ids></links><search><creatorcontrib>Faulkenberry, Thomas J</creatorcontrib><title>Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation</title><title>Biometrical letters</title><description>Bayesian inference affords scientists powerful tools for testing hypotheses. One of these tools is the Bayes factor, which indexes the extent to which support for one hypothesis over another is updated after seeing the data. Part of the hesitance to adopt this approach may stem from an unfamiliarity with the computational tools necessary for computing Bayes factors. Previous work has shown that closed-form approximations of Bayes factors are relatively easy to obtain for between-groups methods, such as an analysis of variance or t-test. In this paper, I extend this approximation to develop a formula for the Bayes factor that directly uses information that is typically reported for ANOVAs (e.g., the F ratio and degrees of freedom). After giving two examples of its use, I report the results of simulations which show that even with minimal input, this approximate Bayes factor produces similar results to existing software solutions.</description><issn>1896-3811</issn><issn>2199-577X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNotT89LwzAYDaLgmLt6DniO5kvaJvG2FZ2DgRcFbyNrv2jHmtQmlfnfG9HT4_Ee7wch18BvRaH03b47IhMcNOOcyzMyE2AMK5V6Oycz0KZiUgNckkWMh-yAsuIAakaaOvTDlDr_Tlf2GyN1tklhjDQF2qON04gUv7oWfYPUjaGneBpw7Hr0Kd7Tpc88oY9d8DQ4mj6QrjY1tcMwhlPX25SFK3Lh7DHi4h_n5PXx4aV-Ytvn9aZeblkjeAGsbGzFxV7vXcvRlFJqbnirSlWo1lTOGlfYEtrf3Q4r4LIQEqARTlQuHxJyTm7-cnP354Qx7Q5hGn2u3Ml8GISGnPoD0RZX3Q</recordid><startdate>20180601</startdate><enddate>20180601</enddate><creator>Faulkenberry, Thomas J</creator><general>De Gruyter Poland</general><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope></search><sort><creationdate>20180601</creationdate><title>Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation</title><author>Faulkenberry, Thomas J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2041-5ca602b8bfd0e95338090d75747d96fa9f4a51d0117fe610342311c2f26f01523</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Faulkenberry, Thomas J</creatorcontrib><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Biometrical letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Faulkenberry, Thomas J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation</atitle><jtitle>Biometrical letters</jtitle><date>2018-06-01</date><risdate>2018</risdate><volume>55</volume><issue>1</issue><spage>31</spage><epage>43</epage><pages>31-43</pages><issn>1896-3811</issn><eissn>2199-577X</eissn><abstract>Bayesian inference affords scientists powerful tools for testing hypotheses. One of these tools is the Bayes factor, which indexes the extent to which support for one hypothesis over another is updated after seeing the data. Part of the hesitance to adopt this approach may stem from an unfamiliarity with the computational tools necessary for computing Bayes factors. Previous work has shown that closed-form approximations of Bayes factors are relatively easy to obtain for between-groups methods, such as an analysis of variance or t-test. In this paper, I extend this approximation to develop a formula for the Bayes factor that directly uses information that is typically reported for ANOVAs (e.g., the F ratio and degrees of freedom). After giving two examples of its use, I report the results of simulations which show that even with minimal input, this approximate Bayes factor produces similar results to existing software solutions.</abstract><cop>Poznan</cop><pub>De Gruyter Poland</pub><doi>10.2478/bile-2018-0003</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1896-3811
ispartof Biometrical letters, 2018-06, Vol.55 (1), p.31-43
issn 1896-3811
2199-577X
language eng
recordid cdi_proquest_journals_3156128153
source Publicly Available Content Database
title Computing Bayes factors to measure evidence from experiments: An extension of the BIC approximation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T21%3A20%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Computing%20Bayes%20factors%20to%20measure%20evidence%20from%20experiments:%20An%20extension%20of%20the%20BIC%20approximation&rft.jtitle=Biometrical%20letters&rft.au=Faulkenberry,%20Thomas%20J&rft.date=2018-06-01&rft.volume=55&rft.issue=1&rft.spage=31&rft.epage=43&rft.pages=31-43&rft.issn=1896-3811&rft.eissn=2199-577X&rft_id=info:doi/10.2478/bile-2018-0003&rft_dat=%3Cproquest%3E3156128153%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c2041-5ca602b8bfd0e95338090d75747d96fa9f4a51d0117fe610342311c2f26f01523%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3156128153&rft_id=info:pmid/&rfr_iscdi=true