Time-varying dependencies among mobility decisions and key life course events: an application of dynamic Bayesian decision networks

Jia Guo; Tao Feng; Harry J.P. Timmermans

doi:10.1016/j.tra.2019.09.008

Time-varying dependencies among mobility decisions and key life course events: an application of dynamic Bayesian decision networks

Jia Guo, Tao Feng (Corresponding author), Harry J.P. Timmermans

Urban Planning and Transportation

Research output: Contribution to journal › Article › Academic › peer-review

13 Citations (Scopus)

105 Downloads (Pure)

Abstract

People's long-term mobility decisions depend on their current situation, past history and/or future plans. Consequently, models of long-term mobility decisions should take lagged, concurrent and/or lead effects into account. Contributing to the literature on long-term mobility analysis, this study develops an integrated framework for modeling the temporally interdependent choices related to residential change, job change and car purchasing decisions. Using retrospective life trajectory data collected through a Web-based survey, a dynamic Bayesian network model is estimated. Results show that different life domains are highly interdependent. Concurrent, as well as lagged and lead effects are observed.

Original language	English
Pages (from-to)	82-92
Number of pages	11
Journal	Transportation Research. Part A: Policy and Practice
Volume	130
DOIs	https://doi.org/10.1016/j.tra.2019.09.008
Publication status	Published - 1 Dec 2019

Funding

This research was supported by the China Scholarship Council (CSC). We would like to thank the China Scholarship Council for providing the funding for this PhD study. Appendix A

Keywords

Concurrent
Dynamic Bayesian network
Lagged and lead effects
Life events

Access to Document

10.1016/j.tra.2019.09.008

published versionFinal published version, 874 KBLicence: TAVERNE

Cite this

@article{46305a4d5b154c0292bf7c909330b3b3,

title = "Time-varying dependencies among mobility decisions and key life course events: an application of dynamic Bayesian decision networks",

abstract = "People's long-term mobility decisions depend on their current situation, past history and/or future plans. Consequently, models of long-term mobility decisions should take lagged, concurrent and/or lead effects into account. Contributing to the literature on long-term mobility analysis, this study develops an integrated framework for modeling the temporally interdependent choices related to residential change, job change and car purchasing decisions. Using retrospective life trajectory data collected through a Web-based survey, a dynamic Bayesian network model is estimated. Results show that different life domains are highly interdependent. Concurrent, as well as lagged and lead effects are observed.",

keywords = "Concurrent, Dynamic Bayesian network, Lagged and lead effects, Life events",

author = "Jia Guo and Tao Feng and Timmermans, {Harry J.P.}",

year = "2019",

month = dec,

day = "1",

doi = "10.1016/j.tra.2019.09.008",

language = "English",

volume = "130",

pages = "82--92",

journal = "Transportation Research. Part A: Policy and Practice",

issn = "0965-8564",

publisher = "Elsevier",

}

Time-varying dependencies among mobility decisions and key life course events: an application of dynamic Bayesian decision networks. / Guo, Jia; Feng, Tao (Corresponding author); Timmermans, Harry J.P.
In: Transportation Research. Part A: Policy and Practice, Vol. 130, 01.12.2019, p. 82-92.

Research output: Contribution to journal › Article › Academic › peer-review

TY - JOUR

T1 - Time-varying dependencies among mobility decisions and key life course events

T2 - an application of dynamic Bayesian decision networks

AU - Guo, Jia

AU - Feng, Tao

AU - Timmermans, Harry J.P.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - People's long-term mobility decisions depend on their current situation, past history and/or future plans. Consequently, models of long-term mobility decisions should take lagged, concurrent and/or lead effects into account. Contributing to the literature on long-term mobility analysis, this study develops an integrated framework for modeling the temporally interdependent choices related to residential change, job change and car purchasing decisions. Using retrospective life trajectory data collected through a Web-based survey, a dynamic Bayesian network model is estimated. Results show that different life domains are highly interdependent. Concurrent, as well as lagged and lead effects are observed.

AB - People's long-term mobility decisions depend on their current situation, past history and/or future plans. Consequently, models of long-term mobility decisions should take lagged, concurrent and/or lead effects into account. Contributing to the literature on long-term mobility analysis, this study develops an integrated framework for modeling the temporally interdependent choices related to residential change, job change and car purchasing decisions. Using retrospective life trajectory data collected through a Web-based survey, a dynamic Bayesian network model is estimated. Results show that different life domains are highly interdependent. Concurrent, as well as lagged and lead effects are observed.

KW - Concurrent

KW - Dynamic Bayesian network

KW - Lagged and lead effects

KW - Life events

UR - http://www.scopus.com/inward/record.url?scp=85072574167&partnerID=8YFLogxK

U2 - 10.1016/j.tra.2019.09.008

DO - 10.1016/j.tra.2019.09.008

M3 - Article

AN - SCOPUS:85072574167

SN - 0965-8564

VL - 130

SP - 82

EP - 92

JO - Transportation Research. Part A: Policy and Practice

JF - Transportation Research. Part A: Policy and Practice

ER -

Time-varying dependencies among mobility decisions and key life course events: an application of dynamic Bayesian decision networks

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this