Measuring the contribution of randomness, exposure, weather, and daylight to the variation in road accident counts

Lasse Fridström, Jan Ifver, Siv Ingebrigtsen, Risto Kulmala, Lars Thomsen

Research output: Contribution to journalArticleScientificpeer-review

232 Citations (Scopus)

Abstract

Road accident counts are influenced by random variation as well as by various systematic, causal factors.
To study these issues, a four-country, segmented data base has been compiled, each segment consisting of monthly accident counts, along with candidate explanatory factors, in the various counties (provinces) of Denmark, Finland, Norway, or Sweden. Using a generalized Poisson regression model, we are able to decompose the variation in accident counts into parts attributable to randomness, exposure, weather, daylight, or changing reporting routines and speed limits.
To this purpose, a set of specialized goodness-of-fit measures have been developed, taking explicit account of the inevitable amount of random variation that would be present in any set of accident counts, no matter how well known the accident generating Poisson process.
Pure randomness is seen to “explain” a major part of the variation in smaller accident counts (e.g. fatal accidents per county per month), while exposure is the dominant systematic determinant. The relationship between exposure and injury accidents appears to be almost proportional, while it is less than proportional in the case of fatal accidents or death victims. Together, randomness and exposure account for 80% to 90% of the observable variation in our data sets.
A surprisingly large share of the variation in road casualty counts is thus explicable in terms of factors not ordinarily within the realm of traffic safety policy.
In view of this observation, it may seem unlikely that very substantial reductions in the accident toll can be achieved without a decrease in the one most important systematic determinant: the traffic volume.
Original languageEnglish
Pages (from-to)1-20
JournalAccident Analysis and Prevention
Volume27
Issue number1
DOIs
Publication statusPublished - 1995
MoE publication typeA1 Journal article-refereed

Fingerprint

Highway accidents
Weather
Accidents
accident
road
determinants
speed limit
traffic volume
traffic safety
Denmark
Finland
Norway
Sweden
candidacy
Databases
death
Safety
regression

Cite this

Fridström, Lasse ; Ifver, Jan ; Ingebrigtsen, Siv ; Kulmala, Risto ; Thomsen, Lars. / Measuring the contribution of randomness, exposure, weather, and daylight to the variation in road accident counts. In: Accident Analysis and Prevention. 1995 ; Vol. 27, No. 1. pp. 1-20.
@article{82a127f895aa4eaa9bbfb810f2e6f018,
title = "Measuring the contribution of randomness, exposure, weather, and daylight to the variation in road accident counts",
abstract = "Road accident counts are influenced by random variation as well as by various systematic, causal factors. To study these issues, a four-country, segmented data base has been compiled, each segment consisting of monthly accident counts, along with candidate explanatory factors, in the various counties (provinces) of Denmark, Finland, Norway, or Sweden. Using a generalized Poisson regression model, we are able to decompose the variation in accident counts into parts attributable to randomness, exposure, weather, daylight, or changing reporting routines and speed limits. To this purpose, a set of specialized goodness-of-fit measures have been developed, taking explicit account of the inevitable amount of random variation that would be present in any set of accident counts, no matter how well known the accident generating Poisson process. Pure randomness is seen to “explain” a major part of the variation in smaller accident counts (e.g. fatal accidents per county per month), while exposure is the dominant systematic determinant. The relationship between exposure and injury accidents appears to be almost proportional, while it is less than proportional in the case of fatal accidents or death victims. Together, randomness and exposure account for 80{\%} to 90{\%} of the observable variation in our data sets. A surprisingly large share of the variation in road casualty counts is thus explicable in terms of factors not ordinarily within the realm of traffic safety policy. In view of this observation, it may seem unlikely that very substantial reductions in the accident toll can be achieved without a decrease in the one most important systematic determinant: the traffic volume.",
author = "Lasse Fridstr{\"o}m and Jan Ifver and Siv Ingebrigtsen and Risto Kulmala and Lars Thomsen",
note = "Project code: TGL8165",
year = "1995",
doi = "10.1016/0001-4575(94)E0023-E",
language = "English",
volume = "27",
pages = "1--20",
journal = "Accident Analysis and Prevention",
issn = "0001-4575",
publisher = "Elsevier",
number = "1",

}

Measuring the contribution of randomness, exposure, weather, and daylight to the variation in road accident counts. / Fridström, Lasse; Ifver, Jan; Ingebrigtsen, Siv; Kulmala, Risto; Thomsen, Lars.

In: Accident Analysis and Prevention, Vol. 27, No. 1, 1995, p. 1-20.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Measuring the contribution of randomness, exposure, weather, and daylight to the variation in road accident counts

AU - Fridström, Lasse

AU - Ifver, Jan

AU - Ingebrigtsen, Siv

AU - Kulmala, Risto

AU - Thomsen, Lars

N1 - Project code: TGL8165

PY - 1995

Y1 - 1995

N2 - Road accident counts are influenced by random variation as well as by various systematic, causal factors. To study these issues, a four-country, segmented data base has been compiled, each segment consisting of monthly accident counts, along with candidate explanatory factors, in the various counties (provinces) of Denmark, Finland, Norway, or Sweden. Using a generalized Poisson regression model, we are able to decompose the variation in accident counts into parts attributable to randomness, exposure, weather, daylight, or changing reporting routines and speed limits. To this purpose, a set of specialized goodness-of-fit measures have been developed, taking explicit account of the inevitable amount of random variation that would be present in any set of accident counts, no matter how well known the accident generating Poisson process. Pure randomness is seen to “explain” a major part of the variation in smaller accident counts (e.g. fatal accidents per county per month), while exposure is the dominant systematic determinant. The relationship between exposure and injury accidents appears to be almost proportional, while it is less than proportional in the case of fatal accidents or death victims. Together, randomness and exposure account for 80% to 90% of the observable variation in our data sets. A surprisingly large share of the variation in road casualty counts is thus explicable in terms of factors not ordinarily within the realm of traffic safety policy. In view of this observation, it may seem unlikely that very substantial reductions in the accident toll can be achieved without a decrease in the one most important systematic determinant: the traffic volume.

AB - Road accident counts are influenced by random variation as well as by various systematic, causal factors. To study these issues, a four-country, segmented data base has been compiled, each segment consisting of monthly accident counts, along with candidate explanatory factors, in the various counties (provinces) of Denmark, Finland, Norway, or Sweden. Using a generalized Poisson regression model, we are able to decompose the variation in accident counts into parts attributable to randomness, exposure, weather, daylight, or changing reporting routines and speed limits. To this purpose, a set of specialized goodness-of-fit measures have been developed, taking explicit account of the inevitable amount of random variation that would be present in any set of accident counts, no matter how well known the accident generating Poisson process. Pure randomness is seen to “explain” a major part of the variation in smaller accident counts (e.g. fatal accidents per county per month), while exposure is the dominant systematic determinant. The relationship between exposure and injury accidents appears to be almost proportional, while it is less than proportional in the case of fatal accidents or death victims. Together, randomness and exposure account for 80% to 90% of the observable variation in our data sets. A surprisingly large share of the variation in road casualty counts is thus explicable in terms of factors not ordinarily within the realm of traffic safety policy. In view of this observation, it may seem unlikely that very substantial reductions in the accident toll can be achieved without a decrease in the one most important systematic determinant: the traffic volume.

U2 - 10.1016/0001-4575(94)E0023-E

DO - 10.1016/0001-4575(94)E0023-E

M3 - Article

VL - 27

SP - 1

EP - 20

JO - Accident Analysis and Prevention

JF - Accident Analysis and Prevention

SN - 0001-4575

IS - 1

ER -