An online updating approach for testing the proportional hazards assumption with streams of survival data

The Cox model—which remains the first choice for analyzing time‐to‐event data, even for large data sets—relies on the proportional hazards (PH) assumption. When survival data arrive sequentially in chunks, a fast and minimally storage intensive approach to test the PH assumption is desirable. We pro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biometrics 2020-03, Vol.76 (1), p.171-182
Hauptverfasser: Xue, Yishu, Wang, HaiYing, Yan, Jun, Schifano, Elizabeth D.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 182
container_issue 1
container_start_page 171
container_title Biometrics
container_volume 76
creator Xue, Yishu
Wang, HaiYing
Yan, Jun
Schifano, Elizabeth D.
description The Cox model—which remains the first choice for analyzing time‐to‐event data, even for large data sets—relies on the proportional hazards (PH) assumption. When survival data arrive sequentially in chunks, a fast and minimally storage intensive approach to test the PH assumption is desirable. We propose an online updating approach that updates the standard test statistic as each new block of data becomes available and greatly lightens the computational burden. Under the null hypothesis of PH, the proposed statistic is shown to have the same asymptotic distribution as the standard version computed on an entire data stream with the data blocks pooled into one data set. In simulation studies, the test and its variant based on most recent data blocks maintain their sizes when the PH assumption holds and have substantial power to detect different violations of the PH assumption. We also show in simulation that our approach can be used successfully with “big data” that exceed a single computer's computational resources. The approach is illustrated with the survival analysis of patients with lymphoma cancer from the Surveillance, Epidemiology, and End Results Program. The proposed test promptly identified deviation from the PH assumption, which was not captured by the test based on the entire data.
doi_str_mv 10.1111/biom.13137
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2275951200</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2375892207</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3577-d5137e94e176c8aa83a2506d2b2017092fc745cf7c2a0f3f8bebf2623cd8b09c3</originalsourceid><addsrcrecordid>eNp9kctOwzAQRS0EoqWw4QOQJTYIKcWPuE6WpeJRqagbkNhFjmNTV0kc7KRV-XrcByxYMJvRXB1dzcwF4BKjIQ51lxtbDTHFlB-BPmYxjlBM0DHoI4RGEY3xew-ceb8MY8oQOQU9imMSh6EPzLiGti5NrWDXFKI19QcUTeOskAuorYOt8juxXSgY5Ma61thalHAhvoQrPBTed1WzFeHatAvoW6dE5aHV0HduZVaBDcbiHJxoUXp1cegD8Pb48Dp5jmbzp-lkPIskZZxHBQt3qDRWmI9kIkRCBWFoVJCcIMxRSrTkMZOaSyKQpjrJVa7JiFBZJDlKJR2Am71v2PazC9tnlfFSlaWole18RghnKcMEoYBe_0GXtnPhuEBRzpKUEMQDdbunpLPeO6WzxplKuE2GUbYNINsGkO0CCPDVwbLLK1X8oj8fDwDeA2tTqs0_Vtn9dP6yN_0Ga1SRdA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2375892207</pqid></control><display><type>article</type><title>An online updating approach for testing the proportional hazards assumption with streams of survival data</title><source>Access via Wiley Online Library</source><source>Oxford University Press Journals All Titles (1996-Current)</source><creator>Xue, Yishu ; Wang, HaiYing ; Yan, Jun ; Schifano, Elizabeth D.</creator><creatorcontrib>Xue, Yishu ; Wang, HaiYing ; Yan, Jun ; Schifano, Elizabeth D.</creatorcontrib><description>The Cox model—which remains the first choice for analyzing time‐to‐event data, even for large data sets—relies on the proportional hazards (PH) assumption. When survival data arrive sequentially in chunks, a fast and minimally storage intensive approach to test the PH assumption is desirable. We propose an online updating approach that updates the standard test statistic as each new block of data becomes available and greatly lightens the computational burden. Under the null hypothesis of PH, the proposed statistic is shown to have the same asymptotic distribution as the standard version computed on an entire data stream with the data blocks pooled into one data set. In simulation studies, the test and its variant based on most recent data blocks maintain their sizes when the PH assumption holds and have substantial power to detect different violations of the PH assumption. We also show in simulation that our approach can be used successfully with “big data” that exceed a single computer's computational resources. The approach is illustrated with the survival analysis of patients with lymphoma cancer from the Surveillance, Epidemiology, and End Results Program. The proposed test promptly identified deviation from the PH assumption, which was not captured by the test based on the entire data.</description><identifier>ISSN: 0006-341X</identifier><identifier>EISSN: 1541-0420</identifier><identifier>DOI: 10.1111/biom.13137</identifier><identifier>PMID: 31424095</identifier><language>eng</language><publisher>United States: Blackwell Publishing Ltd</publisher><subject>Computer applications ; Computer simulation ; Cox model ; Data transmission ; Datasets ; diagnostics ; Epidemiology ; Hazards ; Internet ; Lymphoma ; Schoenfeld residuals ; Survival ; Survival analysis</subject><ispartof>Biometrics, 2020-03, Vol.76 (1), p.171-182</ispartof><rights>2019 The International Biometric Society</rights><rights>2019 The International Biometric Society.</rights><rights>2020 The International Biometric Society</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3577-d5137e94e176c8aa83a2506d2b2017092fc745cf7c2a0f3f8bebf2623cd8b09c3</citedby><cites>FETCH-LOGICAL-c3577-d5137e94e176c8aa83a2506d2b2017092fc745cf7c2a0f3f8bebf2623cd8b09c3</cites><orcidid>0000-0002-9660-6087 ; 0000-0001-7729-0243 ; 0000-0002-9793-332X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1111%2Fbiom.13137$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1111%2Fbiom.13137$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31424095$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Xue, Yishu</creatorcontrib><creatorcontrib>Wang, HaiYing</creatorcontrib><creatorcontrib>Yan, Jun</creatorcontrib><creatorcontrib>Schifano, Elizabeth D.</creatorcontrib><title>An online updating approach for testing the proportional hazards assumption with streams of survival data</title><title>Biometrics</title><addtitle>Biometrics</addtitle><description>The Cox model—which remains the first choice for analyzing time‐to‐event data, even for large data sets—relies on the proportional hazards (PH) assumption. When survival data arrive sequentially in chunks, a fast and minimally storage intensive approach to test the PH assumption is desirable. We propose an online updating approach that updates the standard test statistic as each new block of data becomes available and greatly lightens the computational burden. Under the null hypothesis of PH, the proposed statistic is shown to have the same asymptotic distribution as the standard version computed on an entire data stream with the data blocks pooled into one data set. In simulation studies, the test and its variant based on most recent data blocks maintain their sizes when the PH assumption holds and have substantial power to detect different violations of the PH assumption. We also show in simulation that our approach can be used successfully with “big data” that exceed a single computer's computational resources. The approach is illustrated with the survival analysis of patients with lymphoma cancer from the Surveillance, Epidemiology, and End Results Program. The proposed test promptly identified deviation from the PH assumption, which was not captured by the test based on the entire data.</description><subject>Computer applications</subject><subject>Computer simulation</subject><subject>Cox model</subject><subject>Data transmission</subject><subject>Datasets</subject><subject>diagnostics</subject><subject>Epidemiology</subject><subject>Hazards</subject><subject>Internet</subject><subject>Lymphoma</subject><subject>Schoenfeld residuals</subject><subject>Survival</subject><subject>Survival analysis</subject><issn>0006-341X</issn><issn>1541-0420</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kctOwzAQRS0EoqWw4QOQJTYIKcWPuE6WpeJRqagbkNhFjmNTV0kc7KRV-XrcByxYMJvRXB1dzcwF4BKjIQ51lxtbDTHFlB-BPmYxjlBM0DHoI4RGEY3xew-ceb8MY8oQOQU9imMSh6EPzLiGti5NrWDXFKI19QcUTeOskAuorYOt8juxXSgY5Ma61thalHAhvoQrPBTed1WzFeHatAvoW6dE5aHV0HduZVaBDcbiHJxoUXp1cegD8Pb48Dp5jmbzp-lkPIskZZxHBQt3qDRWmI9kIkRCBWFoVJCcIMxRSrTkMZOaSyKQpjrJVa7JiFBZJDlKJR2Am71v2PazC9tnlfFSlaWole18RghnKcMEoYBe_0GXtnPhuEBRzpKUEMQDdbunpLPeO6WzxplKuE2GUbYNINsGkO0CCPDVwbLLK1X8oj8fDwDeA2tTqs0_Vtn9dP6yN_0Ga1SRdA</recordid><startdate>202003</startdate><enddate>202003</enddate><creator>Xue, Yishu</creator><creator>Wang, HaiYing</creator><creator>Yan, Jun</creator><creator>Schifano, Elizabeth D.</creator><general>Blackwell Publishing Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-9660-6087</orcidid><orcidid>https://orcid.org/0000-0001-7729-0243</orcidid><orcidid>https://orcid.org/0000-0002-9793-332X</orcidid></search><sort><creationdate>202003</creationdate><title>An online updating approach for testing the proportional hazards assumption with streams of survival data</title><author>Xue, Yishu ; Wang, HaiYing ; Yan, Jun ; Schifano, Elizabeth D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3577-d5137e94e176c8aa83a2506d2b2017092fc745cf7c2a0f3f8bebf2623cd8b09c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer applications</topic><topic>Computer simulation</topic><topic>Cox model</topic><topic>Data transmission</topic><topic>Datasets</topic><topic>diagnostics</topic><topic>Epidemiology</topic><topic>Hazards</topic><topic>Internet</topic><topic>Lymphoma</topic><topic>Schoenfeld residuals</topic><topic>Survival</topic><topic>Survival analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Xue, Yishu</creatorcontrib><creatorcontrib>Wang, HaiYing</creatorcontrib><creatorcontrib>Yan, Jun</creatorcontrib><creatorcontrib>Schifano, Elizabeth D.</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><collection>MEDLINE - Academic</collection><jtitle>Biometrics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xue, Yishu</au><au>Wang, HaiYing</au><au>Yan, Jun</au><au>Schifano, Elizabeth D.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An online updating approach for testing the proportional hazards assumption with streams of survival data</atitle><jtitle>Biometrics</jtitle><addtitle>Biometrics</addtitle><date>2020-03</date><risdate>2020</risdate><volume>76</volume><issue>1</issue><spage>171</spage><epage>182</epage><pages>171-182</pages><issn>0006-341X</issn><eissn>1541-0420</eissn><abstract>The Cox model—which remains the first choice for analyzing time‐to‐event data, even for large data sets—relies on the proportional hazards (PH) assumption. When survival data arrive sequentially in chunks, a fast and minimally storage intensive approach to test the PH assumption is desirable. We propose an online updating approach that updates the standard test statistic as each new block of data becomes available and greatly lightens the computational burden. Under the null hypothesis of PH, the proposed statistic is shown to have the same asymptotic distribution as the standard version computed on an entire data stream with the data blocks pooled into one data set. In simulation studies, the test and its variant based on most recent data blocks maintain their sizes when the PH assumption holds and have substantial power to detect different violations of the PH assumption. We also show in simulation that our approach can be used successfully with “big data” that exceed a single computer's computational resources. The approach is illustrated with the survival analysis of patients with lymphoma cancer from the Surveillance, Epidemiology, and End Results Program. The proposed test promptly identified deviation from the PH assumption, which was not captured by the test based on the entire data.</abstract><cop>United States</cop><pub>Blackwell Publishing Ltd</pub><pmid>31424095</pmid><doi>10.1111/biom.13137</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-9660-6087</orcidid><orcidid>https://orcid.org/0000-0001-7729-0243</orcidid><orcidid>https://orcid.org/0000-0002-9793-332X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0006-341X
ispartof Biometrics, 2020-03, Vol.76 (1), p.171-182
issn 0006-341X
1541-0420
language eng
recordid cdi_proquest_miscellaneous_2275951200
source Access via Wiley Online Library; Oxford University Press Journals All Titles (1996-Current)
subjects Computer applications
Computer simulation
Cox model
Data transmission
Datasets
diagnostics
Epidemiology
Hazards
Internet
Lymphoma
Schoenfeld residuals
Survival
Survival analysis
title An online updating approach for testing the proportional hazards assumption with streams of survival data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T23%3A26%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20online%20updating%20approach%20for%20testing%20the%20proportional%20hazards%20assumption%20with%20streams%20of%20survival%20data&rft.jtitle=Biometrics&rft.au=Xue,%20Yishu&rft.date=2020-03&rft.volume=76&rft.issue=1&rft.spage=171&rft.epage=182&rft.pages=171-182&rft.issn=0006-341X&rft.eissn=1541-0420&rft_id=info:doi/10.1111/biom.13137&rft_dat=%3Cproquest_cross%3E2375892207%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2375892207&rft_id=info:pmid/31424095&rfr_iscdi=true