Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness
The generalized estimating equation (GEE) has been a popular tool for marginal regression analysis with longitudinal data, and its extension, the weighted GEE approach, can further accommodate data that are missing at random (MAR). Model selection methodologies for GEE, however, have not been system...
Gespeichert in:
| Veröffentlicht in: | Biometrics 2012-12, Vol.68 (4), p.1046-1054 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1054 |
|---|---|
| container_issue | 4 |
| container_start_page | 1046 |
| container_title | Biometrics |
| container_volume | 68 |
| creator | Shen, Chung‐Wei Chen, Yi‐Hau |
| description | The generalized estimating equation (GEE) has been a popular tool for marginal regression analysis with longitudinal data, and its extension, the weighted GEE approach, can further accommodate data that are missing at random (MAR). Model selection methodologies for GEE, however, have not been systematically developed to allow for missing data. We propose the missing longitudinal information criterion (MLIC) for selection of the mean model, and the MLIC for correlation (MLICC) for selection of the correlation structure in GEE when the outcome data are subject to dropout/monotone missingness and are MAR. Our simulation results reveal that the MLIC and MLICC are effective for variable selection in the mean model and selecting the correlation structure, respectively. We also demonstrate the remarkable drawbacks of naively treating incomplete data as if they were complete and applying the existing GEE model selection method. The utility of proposed method is further illustrated by two real applications involving missing longitudinal outcome data. |
| doi_str_mv | 10.1111/j.1541-0420.2012.01758.x |
| format | Article |
| fullrecord | <record><control><sourceid>jstor_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_1273115415</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>41806023</jstor_id><sourcerecordid>41806023</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4828-2c8bb540f0ca5044ceae3cf4663b0ce06fbc873240cbae72d4de19aac1fb31643</originalsourceid><addsrcrecordid>eNqNkEtv1DAUhS0EokPhJwCR2LBJuH7EyWyQ2jIdKnWmiz5gZznOTZWQxFM7EVN-PQ4ps2CFN_b1-e659iEkopDQsD41CU0FjUEwSBhQlgDN0jzZPyOLg_CcLABAxlzQ70fklfdNKJcpsJfkiDEhOSyXC3K3sSW20TW2aIba9lFlXbTGHp1u619YRis_1J0e6v4-Wj2MemJ8dGKM7TpbzvdfnN3ZcYg2tfeh7tH71-RFpVuPb572Y3J7vro5-xpfXq0vzk4uYyNylsfM5EWRCqjA6BSEMKiRm0pIyQswCLIqTJ5xJsAUGjNWihLpUmtDq4JTKfgx-Tj77px9GNEPqqu9wbbVPdrRK8oyTqdI0oB--Adt7Oj68LpACcYklWwyzGfKOOu9w0rtXPi_e1QU1JS9atTkp6aI1ZS9-pO92ofWd08DxqLD8tD4N-wAfJ6Bn3WLj_9trE4vrjbTMRi8nQ0aP1h3MBA0BwmMBz2e9doPuD_o2v1QMuNZqr5t12p7t75JM9iq88C_n_lKW6XvXe3V7XUYnQJQkQMI_hvaWLTJ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1242261624</pqid></control><display><type>article</type><title>Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness</title><source>MEDLINE</source><source>Wiley Online Library Journals Frontfile Complete</source><source>JSTOR Mathematics & Statistics</source><source>Jstor Complete Legacy</source><source>Oxford University Press Journals All Titles (1996-Current)</source><creator>Shen, Chung‐Wei ; Chen, Yi‐Hau</creator><creatorcontrib>Shen, Chung‐Wei ; Chen, Yi‐Hau</creatorcontrib><description>The generalized estimating equation (GEE) has been a popular tool for marginal regression analysis with longitudinal data, and its extension, the weighted GEE approach, can further accommodate data that are missing at random (MAR). Model selection methodologies for GEE, however, have not been systematically developed to allow for missing data. We propose the missing longitudinal information criterion (MLIC) for selection of the mean model, and the MLIC for correlation (MLICC) for selection of the correlation structure in GEE when the outcome data are subject to dropout/monotone missingness and are MAR. Our simulation results reveal that the MLIC and MLICC are effective for variable selection in the mean model and selecting the correlation structure, respectively. We also demonstrate the remarkable drawbacks of naively treating incomplete data as if they were complete and applying the existing GEE model selection method. The utility of proposed method is further illustrated by two real applications involving missing longitudinal outcome data.</description><identifier>ISSN: 0006-341X</identifier><identifier>EISSN: 1541-0420</identifier><identifier>DOI: 10.1111/j.1541-0420.2012.01758.x</identifier><identifier>PMID: 22463099</identifier><identifier>CODEN: BIOMA5</identifier><language>eng</language><publisher>Malden, USA: Blackwell Publishing Inc</publisher><subject>Algorithms ; Analytical estimating ; BIOMETRIC METHODOLOGY ; Biometrics ; biometry ; Biometry - methods ; Clinical outcomes ; Correlations ; Data Interpretation, Statistical ; Drug design ; Epidemiologic Methods ; equations ; Estimating techniques ; Longitudinal data ; Longitudinal Studies ; Missing data ; Modeling ; Models, Statistical ; Parametric models ; Regression Analysis ; Repeated measures ; Sample Size ; School dropouts</subject><ispartof>Biometrics, 2012-12, Vol.68 (4), p.1046-1054</ispartof><rights>2012 The International Biometric Society</rights><rights>2012, The International Biometric Society</rights><rights>2012, The International Biometric Society.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4828-2c8bb540f0ca5044ceae3cf4663b0ce06fbc873240cbae72d4de19aac1fb31643</citedby><cites>FETCH-LOGICAL-c4828-2c8bb540f0ca5044ceae3cf4663b0ce06fbc873240cbae72d4de19aac1fb31643</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/41806023$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/41806023$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>314,776,780,799,828,1411,27903,27904,45553,45554,57996,58000,58229,58233</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/22463099$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Shen, Chung‐Wei</creatorcontrib><creatorcontrib>Chen, Yi‐Hau</creatorcontrib><title>Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness</title><title>Biometrics</title><addtitle>Biometrics</addtitle><description>The generalized estimating equation (GEE) has been a popular tool for marginal regression analysis with longitudinal data, and its extension, the weighted GEE approach, can further accommodate data that are missing at random (MAR). Model selection methodologies for GEE, however, have not been systematically developed to allow for missing data. We propose the missing longitudinal information criterion (MLIC) for selection of the mean model, and the MLIC for correlation (MLICC) for selection of the correlation structure in GEE when the outcome data are subject to dropout/monotone missingness and are MAR. Our simulation results reveal that the MLIC and MLICC are effective for variable selection in the mean model and selecting the correlation structure, respectively. We also demonstrate the remarkable drawbacks of naively treating incomplete data as if they were complete and applying the existing GEE model selection method. The utility of proposed method is further illustrated by two real applications involving missing longitudinal outcome data.</description><subject>Algorithms</subject><subject>Analytical estimating</subject><subject>BIOMETRIC METHODOLOGY</subject><subject>Biometrics</subject><subject>biometry</subject><subject>Biometry - methods</subject><subject>Clinical outcomes</subject><subject>Correlations</subject><subject>Data Interpretation, Statistical</subject><subject>Drug design</subject><subject>Epidemiologic Methods</subject><subject>equations</subject><subject>Estimating techniques</subject><subject>Longitudinal data</subject><subject>Longitudinal Studies</subject><subject>Missing data</subject><subject>Modeling</subject><subject>Models, Statistical</subject><subject>Parametric models</subject><subject>Regression Analysis</subject><subject>Repeated measures</subject><subject>Sample Size</subject><subject>School dropouts</subject><issn>0006-341X</issn><issn>1541-0420</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNqNkEtv1DAUhS0EokPhJwCR2LBJuH7EyWyQ2jIdKnWmiz5gZznOTZWQxFM7EVN-PQ4ps2CFN_b1-e659iEkopDQsD41CU0FjUEwSBhQlgDN0jzZPyOLg_CcLABAxlzQ70fklfdNKJcpsJfkiDEhOSyXC3K3sSW20TW2aIba9lFlXbTGHp1u619YRis_1J0e6v4-Wj2MemJ8dGKM7TpbzvdfnN3ZcYg2tfeh7tH71-RFpVuPb572Y3J7vro5-xpfXq0vzk4uYyNylsfM5EWRCqjA6BSEMKiRm0pIyQswCLIqTJ5xJsAUGjNWihLpUmtDq4JTKfgx-Tj77px9GNEPqqu9wbbVPdrRK8oyTqdI0oB--Adt7Oj68LpACcYklWwyzGfKOOu9w0rtXPi_e1QU1JS9atTkp6aI1ZS9-pO92ofWd08DxqLD8tD4N-wAfJ6Bn3WLj_9trE4vrjbTMRi8nQ0aP1h3MBA0BwmMBz2e9doPuD_o2v1QMuNZqr5t12p7t75JM9iq88C_n_lKW6XvXe3V7XUYnQJQkQMI_hvaWLTJ</recordid><startdate>201212</startdate><enddate>201212</enddate><creator>Shen, Chung‐Wei</creator><creator>Chen, Yi‐Hau</creator><general>Blackwell Publishing Inc</general><general>Wiley-Blackwell</general><general>Blackwell Publishing Ltd</general><scope>FBQ</scope><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>JQ2</scope><scope>7X8</scope></search><sort><creationdate>201212</creationdate><title>Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness</title><author>Shen, Chung‐Wei ; Chen, Yi‐Hau</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4828-2c8bb540f0ca5044ceae3cf4663b0ce06fbc873240cbae72d4de19aac1fb31643</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Algorithms</topic><topic>Analytical estimating</topic><topic>BIOMETRIC METHODOLOGY</topic><topic>Biometrics</topic><topic>biometry</topic><topic>Biometry - methods</topic><topic>Clinical outcomes</topic><topic>Correlations</topic><topic>Data Interpretation, Statistical</topic><topic>Drug design</topic><topic>Epidemiologic Methods</topic><topic>equations</topic><topic>Estimating techniques</topic><topic>Longitudinal data</topic><topic>Longitudinal Studies</topic><topic>Missing data</topic><topic>Modeling</topic><topic>Models, Statistical</topic><topic>Parametric models</topic><topic>Regression Analysis</topic><topic>Repeated measures</topic><topic>Sample Size</topic><topic>School dropouts</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shen, Chung‐Wei</creatorcontrib><creatorcontrib>Chen, Yi‐Hau</creatorcontrib><collection>AGRIS</collection><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 Computer Science Collection</collection><collection>MEDLINE - Academic</collection><jtitle>Biometrics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shen, Chung‐Wei</au><au>Chen, Yi‐Hau</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness</atitle><jtitle>Biometrics</jtitle><addtitle>Biometrics</addtitle><date>2012-12</date><risdate>2012</risdate><volume>68</volume><issue>4</issue><spage>1046</spage><epage>1054</epage><pages>1046-1054</pages><issn>0006-341X</issn><eissn>1541-0420</eissn><coden>BIOMA5</coden><abstract>The generalized estimating equation (GEE) has been a popular tool for marginal regression analysis with longitudinal data, and its extension, the weighted GEE approach, can further accommodate data that are missing at random (MAR). Model selection methodologies for GEE, however, have not been systematically developed to allow for missing data. We propose the missing longitudinal information criterion (MLIC) for selection of the mean model, and the MLIC for correlation (MLICC) for selection of the correlation structure in GEE when the outcome data are subject to dropout/monotone missingness and are MAR. Our simulation results reveal that the MLIC and MLICC are effective for variable selection in the mean model and selecting the correlation structure, respectively. We also demonstrate the remarkable drawbacks of naively treating incomplete data as if they were complete and applying the existing GEE model selection method. The utility of proposed method is further illustrated by two real applications involving missing longitudinal outcome data.</abstract><cop>Malden, USA</cop><pub>Blackwell Publishing Inc</pub><pmid>22463099</pmid><doi>10.1111/j.1541-0420.2012.01758.x</doi><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0006-341X |
| ispartof | Biometrics, 2012-12, Vol.68 (4), p.1046-1054 |
| issn | 0006-341X 1541-0420 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1273115415 |
| source | MEDLINE; Wiley Online Library Journals Frontfile Complete; JSTOR Mathematics & Statistics; Jstor Complete Legacy; Oxford University Press Journals All Titles (1996-Current) |
| subjects | Algorithms Analytical estimating BIOMETRIC METHODOLOGY Biometrics biometry Biometry - methods Clinical outcomes Correlations Data Interpretation, Statistical Drug design Epidemiologic Methods equations Estimating techniques Longitudinal data Longitudinal Studies Missing data Modeling Models, Statistical Parametric models Regression Analysis Repeated measures Sample Size School dropouts |
| title | Model Selection for Generalized Estimating Equations Accommodating Dropout Missingness |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T02%3A29%3A42IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Model%20Selection%20for%20Generalized%20Estimating%20Equations%20Accommodating%20Dropout%20Missingness&rft.jtitle=Biometrics&rft.au=Shen,%20Chung%E2%80%90Wei&rft.date=2012-12&rft.volume=68&rft.issue=4&rft.spage=1046&rft.epage=1054&rft.pages=1046-1054&rft.issn=0006-341X&rft.eissn=1541-0420&rft.coden=BIOMA5&rft_id=info:doi/10.1111/j.1541-0420.2012.01758.x&rft_dat=%3Cjstor_proqu%3E41806023%3C/jstor_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1242261624&rft_id=info:pmid/22463099&rft_jstor_id=41806023&rfr_iscdi=true |