File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Article: Identifying crash-prone locations with quantile regression
  • Basic View
  • Metadata View
  • XML View
TitleIdentifying crash-prone locations with quantile regression
 
AuthorsQin, X1
Ng, M3
Reyes, PE2
 
KeywordsConfidence interval
Heterogeneity
Poisson-gamma
Quantile regression
 
Issue Date2010
 
PublisherElsevier Ltd. The Journal's web site is located at http://www.elsevier.com/wps/find/journaldescription.cws_home/336/description#description
 
CitationAccident Analysis And Prevention, 2010, v. 42 n. 6, p. 1531-1537 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.aap.2010.03.009
 
AbstractIdentifying locations that exhibit the greatest potential for safety improvements is becoming more and more important because of competing needs and a tightening safety improvement budget. Current crash modeling practices mainly target changes at the mean level. However, crash data often have skewed distributions and exhibit substantial heterogeneity. Changes at mean level do not adequately represent patterns present in the data. This study employs a regression technique known as the quantile regression. Quantile regression offers the flexibility of estimating trends at different quantiles. It is particularly useful for summarizing data with heterogeneity. Here, we consider its application for identifying intersections with severe safety issues. Several classic approaches for determining risk-prone intersections are also compared. Our findings suggest that relative to other methods, quantile regression yields a sensible and much more refined subset of risk-prone locations.
 
ISSN0001-4575
2012 Impact Factor: 1.964
2012 SCImago Journal Rankings: 1.228
 
DOIhttp://dx.doi.org/10.1016/j.aap.2010.03.009
 
ISI Accession Number IDWOS:000282240500002
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorQin, X
 
dc.contributor.authorNg, M
 
dc.contributor.authorReyes, PE
 
dc.date.accessioned2011-03-28T09:27:38Z
 
dc.date.available2011-03-28T09:27:38Z
 
dc.date.issued2010
 
dc.description.abstractIdentifying locations that exhibit the greatest potential for safety improvements is becoming more and more important because of competing needs and a tightening safety improvement budget. Current crash modeling practices mainly target changes at the mean level. However, crash data often have skewed distributions and exhibit substantial heterogeneity. Changes at mean level do not adequately represent patterns present in the data. This study employs a regression technique known as the quantile regression. Quantile regression offers the flexibility of estimating trends at different quantiles. It is particularly useful for summarizing data with heterogeneity. Here, we consider its application for identifying intersections with severe safety issues. Several classic approaches for determining risk-prone intersections are also compared. Our findings suggest that relative to other methods, quantile regression yields a sensible and much more refined subset of risk-prone locations.
 
dc.description.natureLink_to_subscribed_fulltext
 
dc.identifier.citationAccident Analysis And Prevention, 2010, v. 42 n. 6, p. 1531-1537 [How to Cite?]
DOI: http://dx.doi.org/10.1016/j.aap.2010.03.009
 
dc.identifier.citeulike7109686
 
dc.identifier.doihttp://dx.doi.org/10.1016/j.aap.2010.03.009
 
dc.identifier.epage1537
 
dc.identifier.hkuros186132
 
dc.identifier.isiWOS:000282240500002
 
dc.identifier.issn0001-4575
2012 Impact Factor: 1.964
2012 SCImago Journal Rankings: 1.228
 
dc.identifier.issue6
 
dc.identifier.openurl
 
dc.identifier.pmid20728599
 
dc.identifier.scopuseid_2-s2.0-77955983203
 
dc.identifier.spage1531
 
dc.identifier.urihttp://hdl.handle.net/10722/132664
 
dc.identifier.volume42
 
dc.languageeng
 
dc.publisherElsevier Ltd. The Journal's web site is located at http://www.elsevier.com/wps/find/journaldescription.cws_home/336/description#description
 
dc.publisher.placeUnited Kingdom
 
dc.relation.ispartofAccident Analysis and Prevention
 
dc.relation.referencesReferences in Scopus
 
dc.subject.meshAccidents, Traffic - prevention and control - statistics and numerical data - trends
 
dc.subject.meshCity Planning - organization and administration - trends
 
dc.subject.meshEnvironment Design - trends
 
dc.subject.meshForecasting
 
dc.subject.meshSafety Management - organization and administration - trends
 
dc.subjectConfidence interval
 
dc.subjectHeterogeneity
 
dc.subjectPoisson-gamma
 
dc.subjectQuantile regression
 
dc.titleIdentifying crash-prone locations with quantile regression
 
dc.typeArticle
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Qin, X</contributor.author>
<contributor.author>Ng, M</contributor.author>
<contributor.author>Reyes, PE</contributor.author>
<date.accessioned>2011-03-28T09:27:38Z</date.accessioned>
<date.available>2011-03-28T09:27:38Z</date.available>
<date.issued>2010</date.issued>
<identifier.citation>Accident Analysis And Prevention, 2010, v. 42 n. 6, p. 1531-1537</identifier.citation>
<identifier.issn>0001-4575</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/132664</identifier.uri>
<description.abstract>Identifying locations that exhibit the greatest potential for safety improvements is becoming more and more important because of competing needs and a tightening safety improvement budget. Current crash modeling practices mainly target changes at the mean level. However, crash data often have skewed distributions and exhibit substantial heterogeneity. Changes at mean level do not adequately represent patterns present in the data. This study employs a regression technique known as the quantile regression. Quantile regression offers the flexibility of estimating trends at different quantiles. It is particularly useful for summarizing data with heterogeneity. Here, we consider its application for identifying intersections with severe safety issues. Several classic approaches for determining risk-prone intersections are also compared. Our findings suggest that relative to other methods, quantile regression yields a sensible and much more refined subset of risk-prone locations.</description.abstract>
<language>eng</language>
<publisher>Elsevier Ltd. The Journal&apos;s web site is located at http://www.elsevier.com/wps/find/journaldescription.cws_home/336/description#description</publisher>
<relation.ispartof>Accident Analysis and Prevention</relation.ispartof>
<subject>Confidence interval</subject>
<subject>Heterogeneity</subject>
<subject>Poisson-gamma</subject>
<subject>Quantile regression</subject>
<subject.mesh>Accidents, Traffic - prevention and control - statistics and numerical data - trends</subject.mesh>
<subject.mesh>City Planning - organization and administration - trends</subject.mesh>
<subject.mesh>Environment Design - trends</subject.mesh>
<subject.mesh>Forecasting</subject.mesh>
<subject.mesh>Safety Management - organization and administration - trends</subject.mesh>
<title>Identifying crash-prone locations with quantile regression</title>
<type>Article</type>
<identifier.openurl>http://library.hku.hk:4550/resserv?sid=HKU:IR&amp;issn=0001-4575&amp;volume=42&amp;issue=6&amp;spage=1531&amp;epage=1537&amp;date=2010&amp;atitle=Identifying+crash-prone+locations+with+quantile+regression</identifier.openurl>
<description.nature>Link_to_subscribed_fulltext</description.nature>
<identifier.doi>10.1016/j.aap.2010.03.009</identifier.doi>
<identifier.pmid>20728599</identifier.pmid>
<identifier.scopus>eid_2-s2.0-77955983203</identifier.scopus>
<identifier.hkuros>186132</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-77955983203&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.volume>42</identifier.volume>
<identifier.issue>6</identifier.issue>
<identifier.spage>1531</identifier.spage>
<identifier.epage>1537</identifier.epage>
<identifier.isi>WOS:000282240500002</identifier.isi>
<publisher.place>United Kingdom</publisher.place>
<identifier.citeulike>7109686</identifier.citeulike>
</item>
Author Affiliations
  1. South Dakota State University
  2. University of Wisconsin Madison
  3. University of Washington Seattle