Multistate nonhomogeneous semi-markov model of daily activity type, timing, and duration sequence

T.-Y. Ma, C. Raux, E. Cornelis, I. Joly

Research output: Contribution to journalArticle

Abstract

Understanding travelers' daily travel activity pattern formation is an important issue for activity-based travel-demand analysis. The activity pattern formation concerns not only complex interrelations between household members and individuals' sociodemographic characteristics but also urban form and transport system settings. To investigate the effects of these attributes and the interrelationship between conducted activities, a multistate semi-Markov model is applied. The underlying assumption of the proposed model is that the state transition probability depends on its adjoining states. The statistical tests of significance affirm that the duration of activity depends not only on its beginning time of day but also on the duration of travel or activity previously conducted. An empirical study based on the Belgian mobility survey is conducted to estimate individuals' daily activity durations of different episodes and provides useful insight for the effects of sociodemographic characteristics, urban and transportation system settings on the activity pattern formation.
Original languageEnglish
Pages (from-to)123-134
Number of pages12
JournalTransportation Research Record (TRR)
Issue number2134
DOIs
Publication statusPublished - 1 Jan 2009

Fingerprint

Statistical tests

Cite this

@article{a7ea089d35264d17919fb5c7d533c2db,
title = "Multistate nonhomogeneous semi-markov model of daily activity type, timing, and duration sequence",
abstract = "Understanding travelers' daily travel activity pattern formation is an important issue for activity-based travel-demand analysis. The activity pattern formation concerns not only complex interrelations between household members and individuals' sociodemographic characteristics but also urban form and transport system settings. To investigate the effects of these attributes and the interrelationship between conducted activities, a multistate semi-Markov model is applied. The underlying assumption of the proposed model is that the state transition probability depends on its adjoining states. The statistical tests of significance affirm that the duration of activity depends not only on its beginning time of day but also on the duration of travel or activity previously conducted. An empirical study based on the Belgian mobility survey is conducted to estimate individuals' daily activity durations of different episodes and provides useful insight for the effects of sociodemographic characteristics, urban and transportation system settings on the activity pattern formation.",
author = "T.-Y. Ma and C. Raux and E. Cornelis and I. Joly",
note = "Copyright 2010 Elsevier B.V., All rights reserved.",
year = "2009",
month = "1",
day = "1",
doi = "10.3141/2134-15",
language = "English",
pages = "123--134",
journal = "Transportation Research Record (TRR)",
issn = "0361-1981",
publisher = "US National Research Council",
number = "2134",

}

Multistate nonhomogeneous semi-markov model of daily activity type, timing, and duration sequence. / Ma, T.-Y.; Raux, C.; Cornelis, E.; Joly, I.

In: Transportation Research Record (TRR), No. 2134, 01.01.2009, p. 123-134.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multistate nonhomogeneous semi-markov model of daily activity type, timing, and duration sequence

AU - Ma, T.-Y.

AU - Raux, C.

AU - Cornelis, E.

AU - Joly, I.

N1 - Copyright 2010 Elsevier B.V., All rights reserved.

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Understanding travelers' daily travel activity pattern formation is an important issue for activity-based travel-demand analysis. The activity pattern formation concerns not only complex interrelations between household members and individuals' sociodemographic characteristics but also urban form and transport system settings. To investigate the effects of these attributes and the interrelationship between conducted activities, a multistate semi-Markov model is applied. The underlying assumption of the proposed model is that the state transition probability depends on its adjoining states. The statistical tests of significance affirm that the duration of activity depends not only on its beginning time of day but also on the duration of travel or activity previously conducted. An empirical study based on the Belgian mobility survey is conducted to estimate individuals' daily activity durations of different episodes and provides useful insight for the effects of sociodemographic characteristics, urban and transportation system settings on the activity pattern formation.

AB - Understanding travelers' daily travel activity pattern formation is an important issue for activity-based travel-demand analysis. The activity pattern formation concerns not only complex interrelations between household members and individuals' sociodemographic characteristics but also urban form and transport system settings. To investigate the effects of these attributes and the interrelationship between conducted activities, a multistate semi-Markov model is applied. The underlying assumption of the proposed model is that the state transition probability depends on its adjoining states. The statistical tests of significance affirm that the duration of activity depends not only on its beginning time of day but also on the duration of travel or activity previously conducted. An empirical study based on the Belgian mobility survey is conducted to estimate individuals' daily activity durations of different episodes and provides useful insight for the effects of sociodemographic characteristics, urban and transportation system settings on the activity pattern formation.

UR - http://www.scopus.com/inward/record.url?scp=76149100210&partnerID=8YFLogxK

U2 - 10.3141/2134-15

DO - 10.3141/2134-15

M3 - Article

SP - 123

EP - 134

JO - Transportation Research Record (TRR)

JF - Transportation Research Record (TRR)

SN - 0361-1981

IS - 2134

ER -