Evaluating and addressing the effects of regression to the mean phenomenon in estimating collision frequencies on urban high collision concentration locations

Jinwoo Lee, Koohong Chung, Seungmo Kang

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Two different methods for addressing the regression to the mean phenomenon (RTM) were evaluated using empirical data: 1 The Empirical Bayes (EB) method, which combines observed collision data and Safety Performance Functions (SPF) to estimate expected collision frequency of a site.2 Continuous Risk Profile (CRP), which estimates true collision profile constructed after filtering out the noise.Data from 110 miles of freeway located in California were used to evaluate the performance of the EB and CRP methods in addressing RTM. CRP outperformed the EB method in estimating collision frequencies in selected high collision concentration locations (HCCLs). Findings indicate that the performance of the EB method can be markedly affected when SPF is biased, while the performance of CRP remains much less affected. The CRP method was more effective in addressing RTM.

Original languageEnglish
Pages (from-to)49-56
Number of pages8
JournalAccident Analysis and Prevention
Volume97
DOIs
Publication statusPublished - 2016 Dec 1

Fingerprint

empirical method
regression
performance
Highway systems
Safety
Noise

Keywords

  • Continuous risk profile
  • Empirical bayes method
  • Random noise
  • Safety performance function
  • The regression to the mean

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Safety, Risk, Reliability and Quality
  • Public Health, Environmental and Occupational Health
  • Law

Cite this

@article{a9272c2c2f3443d9b29f903e8f83e881,
title = "Evaluating and addressing the effects of regression to the mean phenomenon in estimating collision frequencies on urban high collision concentration locations",
abstract = "Two different methods for addressing the regression to the mean phenomenon (RTM) were evaluated using empirical data: 1 The Empirical Bayes (EB) method, which combines observed collision data and Safety Performance Functions (SPF) to estimate expected collision frequency of a site.2 Continuous Risk Profile (CRP), which estimates true collision profile constructed after filtering out the noise.Data from 110 miles of freeway located in California were used to evaluate the performance of the EB and CRP methods in addressing RTM. CRP outperformed the EB method in estimating collision frequencies in selected high collision concentration locations (HCCLs). Findings indicate that the performance of the EB method can be markedly affected when SPF is biased, while the performance of CRP remains much less affected. The CRP method was more effective in addressing RTM.",
keywords = "Continuous risk profile, Empirical bayes method, Random noise, Safety performance function, The regression to the mean",
author = "Jinwoo Lee and Koohong Chung and Seungmo Kang",
year = "2016",
month = "12",
day = "1",
doi = "10.1016/j.aap.2016.08.019",
language = "English",
volume = "97",
pages = "49--56",
journal = "Accident Analysis and Prevention",
issn = "0001-4575",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Evaluating and addressing the effects of regression to the mean phenomenon in estimating collision frequencies on urban high collision concentration locations

AU - Lee, Jinwoo

AU - Chung, Koohong

AU - Kang, Seungmo

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Two different methods for addressing the regression to the mean phenomenon (RTM) were evaluated using empirical data: 1 The Empirical Bayes (EB) method, which combines observed collision data and Safety Performance Functions (SPF) to estimate expected collision frequency of a site.2 Continuous Risk Profile (CRP), which estimates true collision profile constructed after filtering out the noise.Data from 110 miles of freeway located in California were used to evaluate the performance of the EB and CRP methods in addressing RTM. CRP outperformed the EB method in estimating collision frequencies in selected high collision concentration locations (HCCLs). Findings indicate that the performance of the EB method can be markedly affected when SPF is biased, while the performance of CRP remains much less affected. The CRP method was more effective in addressing RTM.

AB - Two different methods for addressing the regression to the mean phenomenon (RTM) were evaluated using empirical data: 1 The Empirical Bayes (EB) method, which combines observed collision data and Safety Performance Functions (SPF) to estimate expected collision frequency of a site.2 Continuous Risk Profile (CRP), which estimates true collision profile constructed after filtering out the noise.Data from 110 miles of freeway located in California were used to evaluate the performance of the EB and CRP methods in addressing RTM. CRP outperformed the EB method in estimating collision frequencies in selected high collision concentration locations (HCCLs). Findings indicate that the performance of the EB method can be markedly affected when SPF is biased, while the performance of CRP remains much less affected. The CRP method was more effective in addressing RTM.

KW - Continuous risk profile

KW - Empirical bayes method

KW - Random noise

KW - Safety performance function

KW - The regression to the mean

UR - http://www.scopus.com/inward/record.url?scp=84983462293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983462293&partnerID=8YFLogxK

U2 - 10.1016/j.aap.2016.08.019

DO - 10.1016/j.aap.2016.08.019

M3 - Article

C2 - 27566957

AN - SCOPUS:84983462293

VL - 97

SP - 49

EP - 56

JO - Accident Analysis and Prevention

JF - Accident Analysis and Prevention

SN - 0001-4575

ER -