Analyzing Factors Contributing to Real-time Train Arrival Delays using Seemingly Unrelated Regression Models
Tiong, Kah Yong LU ; Ma, Zhenliang and Palmqvist, Carl-William LU
(2023)
In Transportation Research, Part A: Policy and Practice
174.
- Abstract
- Understanding the impact of various factors on train arrival delays is a prerequisite for effectiverailway traffic operating control and management. Existing studies analyze the train delayfactors using a single, generic regression equation, restricting their capability in accounting forheterogeneous impacts of spatiotemporal factors on arrival delays as the train travels along itsroute. The paper proposes a set of equations conditional on the train location for analyzing trainarrival delay factors at stations. We develop a seemingly unrelated regression equation (SURE)model to estimate the coefficients simultaneously while considering potential correlationsbetween regression residuals caused by shared unobserved variables among equations.... (More)
- Understanding the impact of various factors on train arrival delays is a prerequisite for effectiverailway traffic operating control and management. Existing studies analyze the train delayfactors using a single, generic regression equation, restricting their capability in accounting forheterogeneous impacts of spatiotemporal factors on arrival delays as the train travels along itsroute. The paper proposes a set of equations conditional on the train location for analyzing trainarrival delay factors at stations. We develop a seemingly unrelated regression equation (SURE)model to estimate the coefficients simultaneously while considering potential correlationsbetween regression residuals caused by shared unobserved variables among equations. Therailway data from 2017 to 2020 in Sweden are used to validate the proposed model andexplore the effects of various factors on train arrival delays. The results confirm the necessity ofdeveloping a set of station-specific train arrival delay models to understand the heterogeneousimpact of explanatory variables. The results show that the significant factors impacting trainarrival delays are primarily train operations, including dwell times, running times, and operationdelays from previous trains and upstream stations. The factors of the calendar, weather, andmaintenance are also significant in impacting delays. Importantly, different train operatingmanagement strategies should be targeted at different stations since the impacts of these factorscould vary depending on where the station is. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4000a59c-8ad7-43ff-9d7d-879a53a2b2cf
- author
- Tiong, Kah Yong
LU
; Ma, Zhenliang
and Palmqvist, Carl-William
LU
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Transportation Research, Part A: Policy and Practice
- volume
- 174
- article number
- 103751
- publisher
- Elsevier
- external identifiers
-
- scopus:85164274665
- ISSN
- 0965-8564
- DOI
- 10.1016/j.tra.2023.103751
- language
- English
- LU publication?
- yes
- id
- 4000a59c-8ad7-43ff-9d7d-879a53a2b2cf
- date added to LUP
- 2023-07-16 16:00:46
- date last changed
- 2024-04-05 21:11:52
@article{4000a59c-8ad7-43ff-9d7d-879a53a2b2cf,
abstract = {{Understanding the impact of various factors on train arrival delays is a prerequisite for effectiverailway traffic operating control and management. Existing studies analyze the train delayfactors using a single, generic regression equation, restricting their capability in accounting forheterogeneous impacts of spatiotemporal factors on arrival delays as the train travels along itsroute. The paper proposes a set of equations conditional on the train location for analyzing trainarrival delay factors at stations. We develop a seemingly unrelated regression equation (SURE)model to estimate the coefficients simultaneously while considering potential correlationsbetween regression residuals caused by shared unobserved variables among equations. Therailway data from 2017 to 2020 in Sweden are used to validate the proposed model andexplore the effects of various factors on train arrival delays. The results confirm the necessity ofdeveloping a set of station-specific train arrival delay models to understand the heterogeneousimpact of explanatory variables. The results show that the significant factors impacting trainarrival delays are primarily train operations, including dwell times, running times, and operationdelays from previous trains and upstream stations. The factors of the calendar, weather, andmaintenance are also significant in impacting delays. Importantly, different train operatingmanagement strategies should be targeted at different stations since the impacts of these factorscould vary depending on where the station is.}},
author = {{Tiong, Kah Yong and Ma, Zhenliang and Palmqvist, Carl-William}},
issn = {{0965-8564}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Transportation Research, Part A: Policy and Practice}},
title = {{Analyzing Factors Contributing to Real-time Train Arrival Delays using Seemingly Unrelated Regression Models}},
url = {{http://dx.doi.org/10.1016/j.tra.2023.103751}},
doi = {{10.1016/j.tra.2023.103751}},
volume = {{174}},
year = {{2023}},
}