The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias
Although randomized controlled trials are considered the ‘gold standard’ for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We...
Gespeichert in:
| Veröffentlicht in: | Statistics in medicine 2013-09, Vol.32 (20), p.3552-3568 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3568 |
|---|---|
| container_issue | 20 |
| container_start_page | 3552 |
| container_title | Statistics in medicine |
| container_volume | 32 |
| creator | Pressler, Taylor R. Kaizar, Eloise E. |
| description | Although randomized controlled trials are considered the ‘gold standard’ for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We propose to use observational data to estimate the bias due to enrollment restrictions, which we term generalizability bias. In this paper, we introduce a class of estimators for the generalizability bias and use simulation to study its properties in the presence of non‐constant treatment effects. We find the surprising result that our estimators can be unbiased for the true generalizability bias even when all potentially confounding variables are not measured. In addition, our proposed doubly robust estimator performs well even for mis‐specified models. Copyright © 2013 John Wiley & Sons, Ltd. |
| doi_str_mv | 10.1002/sim.5802 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3967586</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1424323630</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4762-d76900656e630809de41d47e20326971deb92d1c47d36816d714ee10a81b05fb3</originalsourceid><addsrcrecordid>eNp1kV1PFDEUhhsjkRVN_AWmiTfeDPZj2s7cmBgiiAJ-YbxsOtOzUOxMl7YDLL_eLqzrR-JVT9InT95zXoSeUbJLCWGvkht2RUPYAzSjpFUVYaJ5iGaEKVVJRcU2epzSBSGUCqYeoW3GheBc8Rm6PD0HPCXAYY4XMSxgTC4vcepDhITNaHHoEsQrk10YjcfWZINzwJCyG0wGHAsTBncLFvdhzDF4X8YcXYHPYIRovLs1nfMrbedMeoK25sYneLp-d9C3_bene--qo48Hh3tvjqq-VpJVVsmWECkkSE4a0lqoqa0VMMKZbBW10LXM0gJbLhsqraI1ACWmoR0R847voNf33sXUDWB7KOGM14tYcselDsbpv39Gd67PwpXmrVSikUXwci2I4XIqC-vBpR68NyOEKWlas5ozXuIV9MU_6EWYYrnXHSWpVJK0v4V9DClFmG_CUKJXPerSo171WNDnf4bfgL-KK0B1D1w7D8v_ivTXw-O1cM27lOFmw5v4Q0vFldDfTw70-w_q0z798lm3_Cf0f7e1</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1426167609</pqid></control><display><type>article</type><title>The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias</title><source>MEDLINE</source><source>Wiley Online Library Journals Frontfile Complete</source><creator>Pressler, Taylor R. ; Kaizar, Eloise E.</creator><creatorcontrib>Pressler, Taylor R. ; Kaizar, Eloise E.</creatorcontrib><description>Although randomized controlled trials are considered the ‘gold standard’ for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We propose to use observational data to estimate the bias due to enrollment restrictions, which we term generalizability bias. In this paper, we introduce a class of estimators for the generalizability bias and use simulation to study its properties in the presence of non‐constant treatment effects. We find the surprising result that our estimators can be unbiased for the true generalizability bias even when all potentially confounding variables are not measured. In addition, our proposed doubly robust estimator performs well even for mis‐specified models. Copyright © 2013 John Wiley & Sons, Ltd.</description><identifier>ISSN: 0277-6715</identifier><identifier>EISSN: 1097-0258</identifier><identifier>DOI: 10.1002/sim.5802</identifier><identifier>PMID: 23553373</identifier><identifier>CODEN: SMEDDA</identifier><language>eng</language><publisher>England: Blackwell Publishing Ltd</publisher><subject>Bias ; causal effect ; Cause & effect diagrams ; Clinical trials ; Computer Simulation ; Confounding Factors (Epidemiology) ; Data Interpretation, Statistical ; Extraction, Obstetrical - instrumentation ; Female ; Humans ; Medical errors ; Medicine ; Models, Statistical ; observational studies ; Propensity Score ; randomized controlled trials ; Randomized Controlled Trials as Topic - methods ; sample selection error ; Samples ; Statistical methods ; Treatment Outcome</subject><ispartof>Statistics in medicine, 2013-09, Vol.32 (20), p.3552-3568</ispartof><rights>Copyright © 2013 John Wiley & Sons, Ltd.</rights><rights>Copyright Wiley Subscription Services, Inc. Sep 10, 2013</rights><rights>Copyright © 0000 John Wiley & Sons, Ltd.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4762-d76900656e630809de41d47e20326971deb92d1c47d36816d714ee10a81b05fb3</citedby><cites>FETCH-LOGICAL-c4762-d76900656e630809de41d47e20326971deb92d1c47d36816d714ee10a81b05fb3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fsim.5802$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fsim.5802$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>230,314,776,780,881,1411,27903,27904,45553,45554</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/23553373$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Pressler, Taylor R.</creatorcontrib><creatorcontrib>Kaizar, Eloise E.</creatorcontrib><title>The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias</title><title>Statistics in medicine</title><addtitle>Statist. Med</addtitle><description>Although randomized controlled trials are considered the ‘gold standard’ for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We propose to use observational data to estimate the bias due to enrollment restrictions, which we term generalizability bias. In this paper, we introduce a class of estimators for the generalizability bias and use simulation to study its properties in the presence of non‐constant treatment effects. We find the surprising result that our estimators can be unbiased for the true generalizability bias even when all potentially confounding variables are not measured. In addition, our proposed doubly robust estimator performs well even for mis‐specified models. Copyright © 2013 John Wiley & Sons, Ltd.</description><subject>Bias</subject><subject>causal effect</subject><subject>Cause & effect diagrams</subject><subject>Clinical trials</subject><subject>Computer Simulation</subject><subject>Confounding Factors (Epidemiology)</subject><subject>Data Interpretation, Statistical</subject><subject>Extraction, Obstetrical - instrumentation</subject><subject>Female</subject><subject>Humans</subject><subject>Medical errors</subject><subject>Medicine</subject><subject>Models, Statistical</subject><subject>observational studies</subject><subject>Propensity Score</subject><subject>randomized controlled trials</subject><subject>Randomized Controlled Trials as Topic - methods</subject><subject>sample selection error</subject><subject>Samples</subject><subject>Statistical methods</subject><subject>Treatment Outcome</subject><issn>0277-6715</issn><issn>1097-0258</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2013</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp1kV1PFDEUhhsjkRVN_AWmiTfeDPZj2s7cmBgiiAJ-YbxsOtOzUOxMl7YDLL_eLqzrR-JVT9InT95zXoSeUbJLCWGvkht2RUPYAzSjpFUVYaJ5iGaEKVVJRcU2epzSBSGUCqYeoW3GheBc8Rm6PD0HPCXAYY4XMSxgTC4vcepDhITNaHHoEsQrk10YjcfWZINzwJCyG0wGHAsTBncLFvdhzDF4X8YcXYHPYIRovLs1nfMrbedMeoK25sYneLp-d9C3_bene--qo48Hh3tvjqq-VpJVVsmWECkkSE4a0lqoqa0VMMKZbBW10LXM0gJbLhsqraI1ACWmoR0R847voNf33sXUDWB7KOGM14tYcselDsbpv39Gd67PwpXmrVSikUXwci2I4XIqC-vBpR68NyOEKWlas5ozXuIV9MU_6EWYYrnXHSWpVJK0v4V9DClFmG_CUKJXPerSo171WNDnf4bfgL-KK0B1D1w7D8v_ivTXw-O1cM27lOFmw5v4Q0vFldDfTw70-w_q0z798lm3_Cf0f7e1</recordid><startdate>20130910</startdate><enddate>20130910</enddate><creator>Pressler, Taylor R.</creator><creator>Kaizar, Eloise E.</creator><general>Blackwell Publishing Ltd</general><general>Wiley Subscription Services, Inc</general><scope>BSCLL</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>K9.</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20130910</creationdate><title>The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias</title><author>Pressler, Taylor R. ; Kaizar, Eloise E.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4762-d76900656e630809de41d47e20326971deb92d1c47d36816d714ee10a81b05fb3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Bias</topic><topic>causal effect</topic><topic>Cause & effect diagrams</topic><topic>Clinical trials</topic><topic>Computer Simulation</topic><topic>Confounding Factors (Epidemiology)</topic><topic>Data Interpretation, Statistical</topic><topic>Extraction, Obstetrical - instrumentation</topic><topic>Female</topic><topic>Humans</topic><topic>Medical errors</topic><topic>Medicine</topic><topic>Models, Statistical</topic><topic>observational studies</topic><topic>Propensity Score</topic><topic>randomized controlled trials</topic><topic>Randomized Controlled Trials as Topic - methods</topic><topic>sample selection error</topic><topic>Samples</topic><topic>Statistical methods</topic><topic>Treatment Outcome</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Pressler, Taylor R.</creatorcontrib><creatorcontrib>Kaizar, Eloise E.</creatorcontrib><collection>Istex</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Statistics in medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Pressler, Taylor R.</au><au>Kaizar, Eloise E.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias</atitle><jtitle>Statistics in medicine</jtitle><addtitle>Statist. Med</addtitle><date>2013-09-10</date><risdate>2013</risdate><volume>32</volume><issue>20</issue><spage>3552</spage><epage>3568</epage><pages>3552-3568</pages><issn>0277-6715</issn><eissn>1097-0258</eissn><coden>SMEDDA</coden><abstract>Although randomized controlled trials are considered the ‘gold standard’ for clinical studies, the use of exclusion criteria may impact the external validity of the results. It is unknown whether estimators of effect size are biased by excluding a portion of the target population from enrollment. We propose to use observational data to estimate the bias due to enrollment restrictions, which we term generalizability bias. In this paper, we introduce a class of estimators for the generalizability bias and use simulation to study its properties in the presence of non‐constant treatment effects. We find the surprising result that our estimators can be unbiased for the true generalizability bias even when all potentially confounding variables are not measured. In addition, our proposed doubly robust estimator performs well even for mis‐specified models. Copyright © 2013 John Wiley & Sons, Ltd.</abstract><cop>England</cop><pub>Blackwell Publishing Ltd</pub><pmid>23553373</pmid><doi>10.1002/sim.5802</doi><tpages>17</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0277-6715 |
| ispartof | Statistics in medicine, 2013-09, Vol.32 (20), p.3552-3568 |
| issn | 0277-6715 1097-0258 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3967586 |
| source | MEDLINE; Wiley Online Library Journals Frontfile Complete |
| subjects | Bias causal effect Cause & effect diagrams Clinical trials Computer Simulation Confounding Factors (Epidemiology) Data Interpretation, Statistical Extraction, Obstetrical - instrumentation Female Humans Medical errors Medicine Models, Statistical observational studies Propensity Score randomized controlled trials Randomized Controlled Trials as Topic - methods sample selection error Samples Statistical methods Treatment Outcome |
| title | The use of propensity scores and observational data to estimate randomized controlled trial generalizability bias |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T17%3A13%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20use%20of%20propensity%20scores%20and%20observational%20data%20to%20estimate%20randomized%20controlled%20trial%20generalizability%20bias&rft.jtitle=Statistics%20in%20medicine&rft.au=Pressler,%20Taylor%20R.&rft.date=2013-09-10&rft.volume=32&rft.issue=20&rft.spage=3552&rft.epage=3568&rft.pages=3552-3568&rft.issn=0277-6715&rft.eissn=1097-0258&rft.coden=SMEDDA&rft_id=info:doi/10.1002/sim.5802&rft_dat=%3Cproquest_pubme%3E1424323630%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1426167609&rft_id=info:pmid/23553373&rfr_iscdi=true |