Fitting generalized linear models to retrospectively sampled clusters with categorical responses
We use simulations based on data on injury severity in car accidents to compare methods for the analysis of very large data sets containing clusters of individuals for which the measured response is polytomous. Retrospective sampling of clusters is used to expedite the analysis of the large data set...
Gespeichert in:
Veröffentlicht in: | Canadian journal of statistics 1997-06, Vol.25 (2), p.159-174 |
---|---|
1. Verfasser: | |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 174 |
---|---|
container_issue | 2 |
container_start_page | 159 |
container_title | Canadian journal of statistics |
container_volume | 25 |
creator | Hines, R.J. O'Hara |
description | We use simulations based on data on injury severity in car accidents to compare methods for the analysis of very large data sets containing clusters of individuals for which the measured response is polytomous. Retrospective sampling of clusters is used to expedite the analysis of the large data set while at the same time obtaining information about rare, but important, outcomes. An additional complication in the analysis of such data sets is that there can be two types of covariates: those which vary within a cluster and those which vary only among clusters. Weighted generalized estimating equations are developed to obtain consistent estimates of the regression coefficients in a proportional-odds model, along with a weighted robust covariance matrix to estimate the variabilities of these estimated coefficients. /// Nous utilisons des simulations fondées sur des données de sévérité de blessure lors d'accidents de voiture pour comparer les méthodes d'analyse de très grands ensembles de données contenant des grappes d'invidus pour lesquels la réponse mesurée est polytomique. L'échantillonage rétroactif des grappes est utilisé dans le but d'accélérer l'analyse des grands ensembles de données tout en obtenant de l'information sur des résultats rares mais importants. Une complication supplémentaire de l'analyse de ces types d'ensembles de données est qu'il peut y avoir deux types de covariables: celles qui varient à l'intérieur d'une grappe et celles qui ne varient que d'une grappe à l'autre. Nous développons des équations d'estimation pondérées généralisées pour obtenir des estimations convergentes des coefficients de régression dans un modèle de chances proportionelles, ainsi qu'une matrice de covariance robuste pondérée pour estimer les variabilités de ces coefficients estimés. |
doi_str_mv | 10.2307/3315729 |
format | Article |
fullrecord | <record><control><sourceid>jstor_cross</sourceid><recordid>TN_cdi_crossref_primary_10_2307_3315729</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><jstor_id>3315729</jstor_id><sourcerecordid>3315729</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3189-3fa2e823061639120f6f3fa373b7e98657ebbe656e589b05767e0b79e579afc23</originalsourceid><addsrcrecordid>eNp1kM1OwzAQhC0EEqUgXoBDbhxQwI5rOz6iQlugggO_4mKcdFNc3CSyDaU8PalSlROnlWa-He0OQocEnyYUizNKCROJ3EIdInAayx572UYdTImMG723i_a8n2FMGSFJB70NTAimnEZTKMFpa35gEllTgnbRvJqA9VGoIgfBVb6GPJgvsMvI63ltGzC3nz6A89HChPco1wGmlTO5ts2Gr6vSg99HO4W2Hg7Ws4seB5cP_VE8vhte9c_HcU5JKmNa6ATS5gFOOJUkwQUvGo0KmgmQKWcCsgw448BSmWEmuACcCQlMSF3kCe2i4zY3by71DgpVOzPXbqkIVqti1LqYhjxpyYWxsPwPU_3re8JW9FFLz3yo3Ib-C4tb2zRFfG9s7T4UF1Qw9Xw7VOQVj_qDpxt1QX8BbRp8hA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Fitting generalized linear models to retrospectively sampled clusters with categorical responses</title><source>Wiley Journals</source><source>JSTOR Mathematics & Statistics</source><source>JSTOR Archive Collection A-Z Listing</source><creator>Hines, R.J. O'Hara</creator><creatorcontrib>Hines, R.J. O'Hara</creatorcontrib><description>We use simulations based on data on injury severity in car accidents to compare methods for the analysis of very large data sets containing clusters of individuals for which the measured response is polytomous. Retrospective sampling of clusters is used to expedite the analysis of the large data set while at the same time obtaining information about rare, but important, outcomes. An additional complication in the analysis of such data sets is that there can be two types of covariates: those which vary within a cluster and those which vary only among clusters. Weighted generalized estimating equations are developed to obtain consistent estimates of the regression coefficients in a proportional-odds model, along with a weighted robust covariance matrix to estimate the variabilities of these estimated coefficients. /// Nous utilisons des simulations fondées sur des données de sévérité de blessure lors d'accidents de voiture pour comparer les méthodes d'analyse de très grands ensembles de données contenant des grappes d'invidus pour lesquels la réponse mesurée est polytomique. L'échantillonage rétroactif des grappes est utilisé dans le but d'accélérer l'analyse des grands ensembles de données tout en obtenant de l'information sur des résultats rares mais importants. Une complication supplémentaire de l'analyse de ces types d'ensembles de données est qu'il peut y avoir deux types de covariables: celles qui varient à l'intérieur d'une grappe et celles qui ne varient que d'une grappe à l'autre. Nous développons des équations d'estimation pondérées généralisées pour obtenir des estimations convergentes des coefficients de régression dans un modèle de chances proportionelles, ainsi qu'une matrice de covariance robuste pondérée pour estimer les variabilités de ces coefficients estimés.</description><identifier>ISSN: 0319-5724</identifier><identifier>EISSN: 1708-945X</identifier><identifier>DOI: 10.2307/3315729</identifier><language>eng</language><publisher>Hoboken: Wiley-Blackwell</publisher><subject>Automobile accidents ; Automobiles ; choice-based sampling ; Coefficients ; Covariance ; Covariance matrices ; Datasets ; Estimation methods ; Estimators ; individual and cluster covariates ; marginal models ; Physical trauma ; population-averaged models ; Regression coefficients ; Response-based sampling ; weighted generalized estimating equations</subject><ispartof>Canadian journal of statistics, 1997-06, Vol.25 (2), p.159-174</ispartof><rights>Copyright 1997 Statistical Society of Canada / Société Statistique du Canada</rights><rights>Copyright © 1997 Statistical Society of Canada</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3189-3fa2e823061639120f6f3fa373b7e98657ebbe656e589b05767e0b79e579afc23</citedby><cites>FETCH-LOGICAL-c3189-3fa2e823061639120f6f3fa373b7e98657ebbe656e589b05767e0b79e579afc23</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.jstor.org/stable/pdf/3315729$$EPDF$$P50$$Gjstor$$H</linktopdf><linktohtml>$$Uhttps://www.jstor.org/stable/3315729$$EHTML$$P50$$Gjstor$$H</linktohtml><link.rule.ids>314,780,784,803,832,1417,27924,27925,45574,45575,58017,58021,58250,58254</link.rule.ids></links><search><creatorcontrib>Hines, R.J. O'Hara</creatorcontrib><title>Fitting generalized linear models to retrospectively sampled clusters with categorical responses</title><title>Canadian journal of statistics</title><addtitle>Can J Statistics</addtitle><description>We use simulations based on data on injury severity in car accidents to compare methods for the analysis of very large data sets containing clusters of individuals for which the measured response is polytomous. Retrospective sampling of clusters is used to expedite the analysis of the large data set while at the same time obtaining information about rare, but important, outcomes. An additional complication in the analysis of such data sets is that there can be two types of covariates: those which vary within a cluster and those which vary only among clusters. Weighted generalized estimating equations are developed to obtain consistent estimates of the regression coefficients in a proportional-odds model, along with a weighted robust covariance matrix to estimate the variabilities of these estimated coefficients. /// Nous utilisons des simulations fondées sur des données de sévérité de blessure lors d'accidents de voiture pour comparer les méthodes d'analyse de très grands ensembles de données contenant des grappes d'invidus pour lesquels la réponse mesurée est polytomique. L'échantillonage rétroactif des grappes est utilisé dans le but d'accélérer l'analyse des grands ensembles de données tout en obtenant de l'information sur des résultats rares mais importants. Une complication supplémentaire de l'analyse de ces types d'ensembles de données est qu'il peut y avoir deux types de covariables: celles qui varient à l'intérieur d'une grappe et celles qui ne varient que d'une grappe à l'autre. Nous développons des équations d'estimation pondérées généralisées pour obtenir des estimations convergentes des coefficients de régression dans un modèle de chances proportionelles, ainsi qu'une matrice de covariance robuste pondérée pour estimer les variabilités de ces coefficients estimés.</description><subject>Automobile accidents</subject><subject>Automobiles</subject><subject>choice-based sampling</subject><subject>Coefficients</subject><subject>Covariance</subject><subject>Covariance matrices</subject><subject>Datasets</subject><subject>Estimation methods</subject><subject>Estimators</subject><subject>individual and cluster covariates</subject><subject>marginal models</subject><subject>Physical trauma</subject><subject>population-averaged models</subject><subject>Regression coefficients</subject><subject>Response-based sampling</subject><subject>weighted generalized estimating equations</subject><issn>0319-5724</issn><issn>1708-945X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1997</creationdate><recordtype>article</recordtype><recordid>eNp1kM1OwzAQhC0EEqUgXoBDbhxQwI5rOz6iQlugggO_4mKcdFNc3CSyDaU8PalSlROnlWa-He0OQocEnyYUizNKCROJ3EIdInAayx572UYdTImMG723i_a8n2FMGSFJB70NTAimnEZTKMFpa35gEllTgnbRvJqA9VGoIgfBVb6GPJgvsMvI63ltGzC3nz6A89HChPco1wGmlTO5ts2Gr6vSg99HO4W2Hg7Ws4seB5cP_VE8vhte9c_HcU5JKmNa6ATS5gFOOJUkwQUvGo0KmgmQKWcCsgw448BSmWEmuACcCQlMSF3kCe2i4zY3by71DgpVOzPXbqkIVqti1LqYhjxpyYWxsPwPU_3re8JW9FFLz3yo3Ib-C4tb2zRFfG9s7T4UF1Qw9Xw7VOQVj_qDpxt1QX8BbRp8hA</recordid><startdate>199706</startdate><enddate>199706</enddate><creator>Hines, R.J. O'Hara</creator><general>Wiley-Blackwell</general><general>Statistical Society of Canada</general><general>Wiley‐Blackwell</general><scope>BSCLL</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>199706</creationdate><title>Fitting generalized linear models to retrospectively sampled clusters with categorical responses</title><author>Hines, R.J. O'Hara</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3189-3fa2e823061639120f6f3fa373b7e98657ebbe656e589b05767e0b79e579afc23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1997</creationdate><topic>Automobile accidents</topic><topic>Automobiles</topic><topic>choice-based sampling</topic><topic>Coefficients</topic><topic>Covariance</topic><topic>Covariance matrices</topic><topic>Datasets</topic><topic>Estimation methods</topic><topic>Estimators</topic><topic>individual and cluster covariates</topic><topic>marginal models</topic><topic>Physical trauma</topic><topic>population-averaged models</topic><topic>Regression coefficients</topic><topic>Response-based sampling</topic><topic>weighted generalized estimating equations</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hines, R.J. O'Hara</creatorcontrib><collection>Istex</collection><collection>CrossRef</collection><jtitle>Canadian journal of statistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hines, R.J. O'Hara</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fitting generalized linear models to retrospectively sampled clusters with categorical responses</atitle><jtitle>Canadian journal of statistics</jtitle><addtitle>Can J Statistics</addtitle><date>1997-06</date><risdate>1997</risdate><volume>25</volume><issue>2</issue><spage>159</spage><epage>174</epage><pages>159-174</pages><issn>0319-5724</issn><eissn>1708-945X</eissn><abstract>We use simulations based on data on injury severity in car accidents to compare methods for the analysis of very large data sets containing clusters of individuals for which the measured response is polytomous. Retrospective sampling of clusters is used to expedite the analysis of the large data set while at the same time obtaining information about rare, but important, outcomes. An additional complication in the analysis of such data sets is that there can be two types of covariates: those which vary within a cluster and those which vary only among clusters. Weighted generalized estimating equations are developed to obtain consistent estimates of the regression coefficients in a proportional-odds model, along with a weighted robust covariance matrix to estimate the variabilities of these estimated coefficients. /// Nous utilisons des simulations fondées sur des données de sévérité de blessure lors d'accidents de voiture pour comparer les méthodes d'analyse de très grands ensembles de données contenant des grappes d'invidus pour lesquels la réponse mesurée est polytomique. L'échantillonage rétroactif des grappes est utilisé dans le but d'accélérer l'analyse des grands ensembles de données tout en obtenant de l'information sur des résultats rares mais importants. Une complication supplémentaire de l'analyse de ces types d'ensembles de données est qu'il peut y avoir deux types de covariables: celles qui varient à l'intérieur d'une grappe et celles qui ne varient que d'une grappe à l'autre. Nous développons des équations d'estimation pondérées généralisées pour obtenir des estimations convergentes des coefficients de régression dans un modèle de chances proportionelles, ainsi qu'une matrice de covariance robuste pondérée pour estimer les variabilités de ces coefficients estimés.</abstract><cop>Hoboken</cop><pub>Wiley-Blackwell</pub><doi>10.2307/3315729</doi><tpages>16</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0319-5724 |
ispartof | Canadian journal of statistics, 1997-06, Vol.25 (2), p.159-174 |
issn | 0319-5724 1708-945X |
language | eng |
recordid | cdi_crossref_primary_10_2307_3315729 |
source | Wiley Journals; JSTOR Mathematics & Statistics; JSTOR Archive Collection A-Z Listing |
subjects | Automobile accidents Automobiles choice-based sampling Coefficients Covariance Covariance matrices Datasets Estimation methods Estimators individual and cluster covariates marginal models Physical trauma population-averaged models Regression coefficients Response-based sampling weighted generalized estimating equations |
title | Fitting generalized linear models to retrospectively sampled clusters with categorical responses |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T00%3A17%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-jstor_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fitting%20generalized%20linear%20models%20to%20retrospectively%20sampled%20clusters%20with%20categorical%20responses&rft.jtitle=Canadian%20journal%20of%20statistics&rft.au=Hines,%20R.J.%20O'Hara&rft.date=1997-06&rft.volume=25&rft.issue=2&rft.spage=159&rft.epage=174&rft.pages=159-174&rft.issn=0319-5724&rft.eissn=1708-945X&rft_id=info:doi/10.2307/3315729&rft_dat=%3Cjstor_cross%3E3315729%3C/jstor_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_jstor_id=3315729&rfr_iscdi=true |