Joint model of weekend discretionary activity participation and episode duration

Kathryn Born, Shamsunnahar Yasmin, Daehyun You, Naveen Eluru, Chandra Bhat, Ram Pendyala

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Research on travel demand modeling has primarily focused on weekday activity-travel patterns. However, weekend activities and travel constitute a major component of individuals' overall weekly activity-travel participation. This paper describes a modeling effort that focuses on weekend activity-travel demand for discretionary events. This study bridges the gap in the literature by modeling participation in discretionary types of events, the duration of participation, and accompaniment type jointly in a simultaneous equations model system. A joint discrete-continuous modeling framework is formulated for analysis of these dimensions as a choice bundle. Specifically, the combination of event type and accompaniment type constitutes the discrete component, whereas the duration of participation constitutes the continuous component. The model uses a copula-based sample selection approach that ties the discrete choice error component with the duration error component in a flexible manner. The data used in the paper are drawn from the 2008-2009 National Household Travel Survey sample of the greater Phoenix metropolitan area in Arizona. The results from the estimation process highlight the presence of sample selection in the joint modeling context. Furthermore, the results also highlight the flexibility of copula models in capturing such sample selection. The best copula model results are used to generate hazard profiles for various alternative related duration intervals. The generated profiles highlight the inaccurate predictions obtained by the use of approaches that ignore the presence of sample selection.

Original languageEnglish (US)
Pages (from-to)34-44
Number of pages11
JournalTransportation Research Record
Issue number2413
DOIs
StatePublished - Dec 1 2014

Fingerprint

Hazards

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Joint model of weekend discretionary activity participation and episode duration. / Born, Kathryn; Yasmin, Shamsunnahar; You, Daehyun; Eluru, Naveen; Bhat, Chandra; Pendyala, Ram.

In: Transportation Research Record, No. 2413, 01.12.2014, p. 34-44.

Research output: Contribution to journalArticle

Born, Kathryn ; Yasmin, Shamsunnahar ; You, Daehyun ; Eluru, Naveen ; Bhat, Chandra ; Pendyala, Ram. / Joint model of weekend discretionary activity participation and episode duration. In: Transportation Research Record. 2014 ; No. 2413. pp. 34-44.
@article{1bc6fc68bc59473e91ac12a13aa783b8,
title = "Joint model of weekend discretionary activity participation and episode duration",
abstract = "Research on travel demand modeling has primarily focused on weekday activity-travel patterns. However, weekend activities and travel constitute a major component of individuals' overall weekly activity-travel participation. This paper describes a modeling effort that focuses on weekend activity-travel demand for discretionary events. This study bridges the gap in the literature by modeling participation in discretionary types of events, the duration of participation, and accompaniment type jointly in a simultaneous equations model system. A joint discrete-continuous modeling framework is formulated for analysis of these dimensions as a choice bundle. Specifically, the combination of event type and accompaniment type constitutes the discrete component, whereas the duration of participation constitutes the continuous component. The model uses a copula-based sample selection approach that ties the discrete choice error component with the duration error component in a flexible manner. The data used in the paper are drawn from the 2008-2009 National Household Travel Survey sample of the greater Phoenix metropolitan area in Arizona. The results from the estimation process highlight the presence of sample selection in the joint modeling context. Furthermore, the results also highlight the flexibility of copula models in capturing such sample selection. The best copula model results are used to generate hazard profiles for various alternative related duration intervals. The generated profiles highlight the inaccurate predictions obtained by the use of approaches that ignore the presence of sample selection.",
author = "Kathryn Born and Shamsunnahar Yasmin and Daehyun You and Naveen Eluru and Chandra Bhat and Ram Pendyala",
year = "2014",
month = "12",
day = "1",
doi = "10.3141/2413-04",
language = "English (US)",
pages = "34--44",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "2413",

}

TY - JOUR

T1 - Joint model of weekend discretionary activity participation and episode duration

AU - Born, Kathryn

AU - Yasmin, Shamsunnahar

AU - You, Daehyun

AU - Eluru, Naveen

AU - Bhat, Chandra

AU - Pendyala, Ram

PY - 2014/12/1

Y1 - 2014/12/1

N2 - Research on travel demand modeling has primarily focused on weekday activity-travel patterns. However, weekend activities and travel constitute a major component of individuals' overall weekly activity-travel participation. This paper describes a modeling effort that focuses on weekend activity-travel demand for discretionary events. This study bridges the gap in the literature by modeling participation in discretionary types of events, the duration of participation, and accompaniment type jointly in a simultaneous equations model system. A joint discrete-continuous modeling framework is formulated for analysis of these dimensions as a choice bundle. Specifically, the combination of event type and accompaniment type constitutes the discrete component, whereas the duration of participation constitutes the continuous component. The model uses a copula-based sample selection approach that ties the discrete choice error component with the duration error component in a flexible manner. The data used in the paper are drawn from the 2008-2009 National Household Travel Survey sample of the greater Phoenix metropolitan area in Arizona. The results from the estimation process highlight the presence of sample selection in the joint modeling context. Furthermore, the results also highlight the flexibility of copula models in capturing such sample selection. The best copula model results are used to generate hazard profiles for various alternative related duration intervals. The generated profiles highlight the inaccurate predictions obtained by the use of approaches that ignore the presence of sample selection.

AB - Research on travel demand modeling has primarily focused on weekday activity-travel patterns. However, weekend activities and travel constitute a major component of individuals' overall weekly activity-travel participation. This paper describes a modeling effort that focuses on weekend activity-travel demand for discretionary events. This study bridges the gap in the literature by modeling participation in discretionary types of events, the duration of participation, and accompaniment type jointly in a simultaneous equations model system. A joint discrete-continuous modeling framework is formulated for analysis of these dimensions as a choice bundle. Specifically, the combination of event type and accompaniment type constitutes the discrete component, whereas the duration of participation constitutes the continuous component. The model uses a copula-based sample selection approach that ties the discrete choice error component with the duration error component in a flexible manner. The data used in the paper are drawn from the 2008-2009 National Household Travel Survey sample of the greater Phoenix metropolitan area in Arizona. The results from the estimation process highlight the presence of sample selection in the joint modeling context. Furthermore, the results also highlight the flexibility of copula models in capturing such sample selection. The best copula model results are used to generate hazard profiles for various alternative related duration intervals. The generated profiles highlight the inaccurate predictions obtained by the use of approaches that ignore the presence of sample selection.

UR - http://www.scopus.com/inward/record.url?scp=84907009878&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907009878&partnerID=8YFLogxK

U2 - 10.3141/2413-04

DO - 10.3141/2413-04

M3 - Article

SP - 34

EP - 44

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 2413

ER -