7. Systematic Patterns of Zero Exposures in Event-History Analysis
Identifieur interne : 009F51 ( Main/Exploration ); précédent : 009F50; suivant : 009F527. Systematic Patterns of Zero Exposures in Event-History Analysis
Auteurs : Jan M. HoemSource :
- Sociological Methodology [ 0081-1750 ] ; 2000.
English descriptors
- Teeft :
- Andersson, Baseline, Baseline group, Baseline hazard, Baseline intensity, Baseline level, Binary, Binary regressors, Birth cohort, Birth cohorts, Calendar period, Calendar year, Categorical covariates, Cause problems, Certain combinations, Childless, Childless women, Cohabitation, Cohabitational unions, Cohort, Consensual union, Corresponding estimator, Corresponding exposures, Current motherhood status, Diagnostic tool, Disruption, Divorce risk, Divorce risks, Educational attainment, Educational level, Empirical results, Empty cells, Estimator, European journal, Event history analysis, Exponential representation, Exposure matrices, Exposure matrix, Female students, First child, First marriage, First panel, First union, Hoem, Ijkm, Impossible combinations, Intensity function, Introductory example, Life segments, Marriage formation, Matrix, Meaningful combinations, Meaningful parameter, Multiplicative, Multiplicative model, Nonmarital, Nonmarital union, Nonmarital unions, Observational design, Other combinations, Other factors, Parameter, Parameter estimates, Parity, Positive exposures, Pregnant women, Premarital cohabitation, Regression coefficient, Regressors, Relative risk, Relative risks, Second child, Second pregnancy, Second union, Single child, Single deviation, Skilled workers, Social background, Social class, Social origin, Statistical texts, Statistics sweden, Stockholm research reports, Such analysis, Swedish women, Systematic patterns, Transition intensities, Union disruption, Union formation, Unskilled workers, Young people, Younger ages, Youngest child.
Abstract
Users of intensity-regression techniques in event-history analysis based on occurrence and exposure matrices frequently encounter zero-valued exposures where there is no observation for selected combinations of factor levels, either because they are logically impossible or because the observational design leaves them out. For example, higher educational levels cannot be attained at very young ages, and observations collected over a given calendar period cannot contain data for older birth cohorts at younger ages or data for younger cohorts at older ages. Unless the exposure matrix is too badly full of zeros, this does not necessarily cause problems for the estimation of regression parameters, but interpretation of results may have to be carried out with extra care. In this paper, we discuss why this is so and show how deft handling of systematic patterns of zero exposures can facilitate analysis.
Url:
DOI: 10.1111/0081-1750.00080
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 001B11
- to stream Istex, to step Curation: 001A91
- to stream Istex, to step Checkpoint: 002204
- to stream Main, to step Merge: 00A532
- to stream Main, to step Curation: 009F51
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">7. Systematic Patterns of Zero Exposures in Event-History Analysis</title>
<author wicri:is="90%"><name sortKey="Hoem, Jan M" sort="Hoem, Jan M" uniqKey="Hoem J" first="Jan M." last="Hoem">Jan M. Hoem</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:75AA29DA4F68823BE8C196BA0F40E3EB78740A7D</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1111/0081-1750.00080</idno>
<idno type="url">https://api.istex.fr/ark:/67375/M70-8NGCX773-8/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">001B11</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">001B11</idno>
<idno type="wicri:Area/Istex/Curation">001A91</idno>
<idno type="wicri:Area/Istex/Checkpoint">002204</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">002204</idno>
<idno type="wicri:doubleKey">0081-1750:2000:Hoem J:systematic:patterns:of</idno>
<idno type="wicri:Area/Main/Merge">00A532</idno>
<idno type="wicri:Area/Main/Curation">009F51</idno>
<idno type="wicri:Area/Main/Exploration">009F51</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">7. Systematic Patterns of Zero Exposures in Event-History Analysis</title>
<author wicri:is="90%"><name sortKey="Hoem, Jan M" sort="Hoem, Jan M" uniqKey="Hoem J" first="Jan M." last="Hoem">Jan M. Hoem</name>
<affiliation><wicri:noCountry code="no comma">Max-Planck Institute for Demographic Research</wicri:noCountry>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Sociological Methodology</title>
<idno type="ISSN">0081-1750</idno>
<idno type="eISSN">1467-9531</idno>
<imprint><publisher>SAGE Publications</publisher>
<pubPlace>Sage CA: Los Angeles, CA</pubPlace>
<date type="published" when="2000">2000</date>
<biblScope unit="volume">30</biblScope>
<biblScope unit="issue">1</biblScope>
<biblScope unit="page" from="237">237</biblScope>
<biblScope unit="page" to="259">259</biblScope>
</imprint>
<idno type="ISSN">0081-1750</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0081-1750</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>Andersson</term>
<term>Baseline</term>
<term>Baseline group</term>
<term>Baseline hazard</term>
<term>Baseline intensity</term>
<term>Baseline level</term>
<term>Binary</term>
<term>Binary regressors</term>
<term>Birth cohort</term>
<term>Birth cohorts</term>
<term>Calendar period</term>
<term>Calendar year</term>
<term>Categorical covariates</term>
<term>Cause problems</term>
<term>Certain combinations</term>
<term>Childless</term>
<term>Childless women</term>
<term>Cohabitation</term>
<term>Cohabitational unions</term>
<term>Cohort</term>
<term>Consensual union</term>
<term>Corresponding estimator</term>
<term>Corresponding exposures</term>
<term>Current motherhood status</term>
<term>Diagnostic tool</term>
<term>Disruption</term>
<term>Divorce risk</term>
<term>Divorce risks</term>
<term>Educational attainment</term>
<term>Educational level</term>
<term>Empirical results</term>
<term>Empty cells</term>
<term>Estimator</term>
<term>European journal</term>
<term>Event history analysis</term>
<term>Exponential representation</term>
<term>Exposure matrices</term>
<term>Exposure matrix</term>
<term>Female students</term>
<term>First child</term>
<term>First marriage</term>
<term>First panel</term>
<term>First union</term>
<term>Hoem</term>
<term>Ijkm</term>
<term>Impossible combinations</term>
<term>Intensity function</term>
<term>Introductory example</term>
<term>Life segments</term>
<term>Marriage formation</term>
<term>Matrix</term>
<term>Meaningful combinations</term>
<term>Meaningful parameter</term>
<term>Multiplicative</term>
<term>Multiplicative model</term>
<term>Nonmarital</term>
<term>Nonmarital union</term>
<term>Nonmarital unions</term>
<term>Observational design</term>
<term>Other combinations</term>
<term>Other factors</term>
<term>Parameter</term>
<term>Parameter estimates</term>
<term>Parity</term>
<term>Positive exposures</term>
<term>Pregnant women</term>
<term>Premarital cohabitation</term>
<term>Regression coefficient</term>
<term>Regressors</term>
<term>Relative risk</term>
<term>Relative risks</term>
<term>Second child</term>
<term>Second pregnancy</term>
<term>Second union</term>
<term>Single child</term>
<term>Single deviation</term>
<term>Skilled workers</term>
<term>Social background</term>
<term>Social class</term>
<term>Social origin</term>
<term>Statistical texts</term>
<term>Statistics sweden</term>
<term>Stockholm research reports</term>
<term>Such analysis</term>
<term>Swedish women</term>
<term>Systematic patterns</term>
<term>Transition intensities</term>
<term>Union disruption</term>
<term>Union formation</term>
<term>Unskilled workers</term>
<term>Young people</term>
<term>Younger ages</term>
<term>Youngest child</term>
</keywords>
</textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Users of intensity-regression techniques in event-history analysis based on occurrence and exposure matrices frequently encounter zero-valued exposures where there is no observation for selected combinations of factor levels, either because they are logically impossible or because the observational design leaves them out. For example, higher educational levels cannot be attained at very young ages, and observations collected over a given calendar period cannot contain data for older birth cohorts at younger ages or data for younger cohorts at older ages. Unless the exposure matrix is too badly full of zeros, this does not necessarily cause problems for the estimation of regression parameters, but interpretation of results may have to be carried out with extra care. In this paper, we discuss why this is so and show how deft handling of systematic patterns of zero exposures can facilitate analysis.</div>
</front>
</TEI>
<affiliations><list></list>
<tree><noCountry><name sortKey="Hoem, Jan M" sort="Hoem, Jan M" uniqKey="Hoem J" first="Jan M." last="Hoem">Jan M. Hoem</name>
</noCountry>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 009F51 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 009F51 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:75AA29DA4F68823BE8C196BA0F40E3EB78740A7D |texte= 7. Systematic Patterns of Zero Exposures in Event-History Analysis }}
This area was generated with Dilib version V0.6.33. |