A comparison of data-driven and model-based approaches to quantifying railway risk

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This paper presents some of the results of a project sponsored by the UK Railway Safety and Standards Board (RSSB). An earlier statistical evaluation of a previous version of the RSSB Safety Risk Model (SRM), a combined Fault/Event Tree, conducted by Prof Andrew Evans had concluded that the model was unduly pessimistic. We have constructed a hypothesis test based on the relative likelihood techniques using the most recent version of the SRM as the null hypothesis. The results support the SRM being consistent with the historical data. Two significant differences between these two studies are the statistical methods employed to support the analysis and the removal of certain significant conservative assumptions from updating the versions of the SRM.

The paper discusses the demands that different model purposes place on these models, and explores the question of whether or not it is meaningful to compare their outputs. The use of expected fatalities as a metric for expressing risk in both models is questioned because of the heavy-tailed form of the distribution for fatality numbers given a fatal accident.
LanguageEnglish
Title of host publicationProbabilistic Safety Assessment and Management
EditorsCornelia Spitzer, Ulrich Schmocker, Vinh N. Dang
Place of PublicationLondon
PublisherSpringer-Verlag
Pages2765-2771
ISBN (Print)9781852338275
DOIs
Publication statusPublished - 2004

Fingerprint

Safety
Railway
Statistical methods
Accidents
Risk model
Fatality
Fault
Hypothesis test
Evaluation

Keywords

  • UK Railway Safety and Standards Board
  • reliability
  • system performance
  • Safety Risk Model
  • RSSB

Cite this

Bedford, T. J., Quigley, J. L., & French, S. (2004). A comparison of data-driven and model-based approaches to quantifying railway risk. In C. Spitzer, U. Schmocker, & V. N. Dang (Eds.), Probabilistic Safety Assessment and Management (pp. 2765-2771). London: Springer-Verlag. https://doi.org/10.1007/978-0-85729-410-4_443
Bedford, T.J. ; Quigley, J.L. ; French, S. / A comparison of data-driven and model-based approaches to quantifying railway risk. Probabilistic Safety Assessment and Management. editor / Cornelia Spitzer ; Ulrich Schmocker ; Vinh N. Dang. London : Springer-Verlag, 2004. pp. 2765-2771
@inbook{df92a565e6004346a5b42c7f88699f64,
title = "A comparison of data-driven and model-based approaches to quantifying railway risk",
abstract = "This paper presents some of the results of a project sponsored by the UK Railway Safety and Standards Board (RSSB). An earlier statistical evaluation of a previous version of the RSSB Safety Risk Model (SRM), a combined Fault/Event Tree, conducted by Prof Andrew Evans had concluded that the model was unduly pessimistic. We have constructed a hypothesis test based on the relative likelihood techniques using the most recent version of the SRM as the null hypothesis. The results support the SRM being consistent with the historical data. Two significant differences between these two studies are the statistical methods employed to support the analysis and the removal of certain significant conservative assumptions from updating the versions of the SRM.The paper discusses the demands that different model purposes place on these models, and explores the question of whether or not it is meaningful to compare their outputs. The use of expected fatalities as a metric for expressing risk in both models is questioned because of the heavy-tailed form of the distribution for fatality numbers given a fatal accident.",
keywords = "UK Railway Safety and Standards Board, reliability, system performance, Safety Risk Model, RSSB",
author = "T.J. Bedford and J.L. Quigley and S. French",
note = "Also presented at: International Conference on Probabalistic Safety Assessment and Management (PSAM), Hotel Inter-Continental Berlin, Germany, 14-18 June, 2004.",
year = "2004",
doi = "10.1007/978-0-85729-410-4_443",
language = "English",
isbn = "9781852338275",
pages = "2765--2771",
editor = "Cornelia Spitzer and Ulrich Schmocker and Dang, {Vinh N.}",
booktitle = "Probabilistic Safety Assessment and Management",
publisher = "Springer-Verlag",

}

Bedford, TJ, Quigley, JL & French, S 2004, A comparison of data-driven and model-based approaches to quantifying railway risk. in C Spitzer, U Schmocker & VN Dang (eds), Probabilistic Safety Assessment and Management. Springer-Verlag, London, pp. 2765-2771. https://doi.org/10.1007/978-0-85729-410-4_443

A comparison of data-driven and model-based approaches to quantifying railway risk. / Bedford, T.J.; Quigley, J.L.; French, S.

Probabilistic Safety Assessment and Management. ed. / Cornelia Spitzer; Ulrich Schmocker; Vinh N. Dang. London : Springer-Verlag, 2004. p. 2765-2771.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - A comparison of data-driven and model-based approaches to quantifying railway risk

AU - Bedford, T.J.

AU - Quigley, J.L.

AU - French, S.

N1 - Also presented at: International Conference on Probabalistic Safety Assessment and Management (PSAM), Hotel Inter-Continental Berlin, Germany, 14-18 June, 2004.

PY - 2004

Y1 - 2004

N2 - This paper presents some of the results of a project sponsored by the UK Railway Safety and Standards Board (RSSB). An earlier statistical evaluation of a previous version of the RSSB Safety Risk Model (SRM), a combined Fault/Event Tree, conducted by Prof Andrew Evans had concluded that the model was unduly pessimistic. We have constructed a hypothesis test based on the relative likelihood techniques using the most recent version of the SRM as the null hypothesis. The results support the SRM being consistent with the historical data. Two significant differences between these two studies are the statistical methods employed to support the analysis and the removal of certain significant conservative assumptions from updating the versions of the SRM.The paper discusses the demands that different model purposes place on these models, and explores the question of whether or not it is meaningful to compare their outputs. The use of expected fatalities as a metric for expressing risk in both models is questioned because of the heavy-tailed form of the distribution for fatality numbers given a fatal accident.

AB - This paper presents some of the results of a project sponsored by the UK Railway Safety and Standards Board (RSSB). An earlier statistical evaluation of a previous version of the RSSB Safety Risk Model (SRM), a combined Fault/Event Tree, conducted by Prof Andrew Evans had concluded that the model was unduly pessimistic. We have constructed a hypothesis test based on the relative likelihood techniques using the most recent version of the SRM as the null hypothesis. The results support the SRM being consistent with the historical data. Two significant differences between these two studies are the statistical methods employed to support the analysis and the removal of certain significant conservative assumptions from updating the versions of the SRM.The paper discusses the demands that different model purposes place on these models, and explores the question of whether or not it is meaningful to compare their outputs. The use of expected fatalities as a metric for expressing risk in both models is questioned because of the heavy-tailed form of the distribution for fatality numbers given a fatal accident.

KW - UK Railway Safety and Standards Board

KW - reliability

KW - system performance

KW - Safety Risk Model

KW - RSSB

UR - http://www.springer.com/computer/hardware/book/978-1-85233-827-5

UR - http://www.psam7.org/

U2 - 10.1007/978-0-85729-410-4_443

DO - 10.1007/978-0-85729-410-4_443

M3 - Chapter

SN - 9781852338275

SP - 2765

EP - 2771

BT - Probabilistic Safety Assessment and Management

A2 - Spitzer, Cornelia

A2 - Schmocker, Ulrich

A2 - Dang, Vinh N.

PB - Springer-Verlag

CY - London

ER -

Bedford TJ, Quigley JL, French S. A comparison of data-driven and model-based approaches to quantifying railway risk. In Spitzer C, Schmocker U, Dang VN, editors, Probabilistic Safety Assessment and Management. London: Springer-Verlag. 2004. p. 2765-2771 https://doi.org/10.1007/978-0-85729-410-4_443