Show simple item record

dc.contributor.advisorBhat, Chandra R. (Chandrasekhar R.), 1964-en
dc.creatorFerdous, Nazneenen
dc.date.accessioned2011-11-04T21:05:46Zen
dc.date.available2011-11-04T21:05:46Zen
dc.date.issued2011-08en
dc.date.submittedAugust 2011en
dc.identifier.urihttp://hdl.handle.net/2152/ETD-UT-2011-08-4224en
dc.descriptiontexten
dc.description.abstractThe research in the field of travel demand modeling is driven by the need to understand individuals’ behavior in the context of travel-related decisions as accurately as possible. In this regard, the activity-based approach to modeling travel demand has received substantial attention in the past decade, both in the research arena as well as in practice. At the same time, recent efforts have been focused on more fully realizing the potential of activity-based models by explicitly recognizing the multi-dimensional nature of activity-travel decisions. However, as more behavioral elements/dimensions are added, the dimensionality of the model systems tends to explode, making the estimation of such models all but infeasible using traditional inference methods. As a result, analysts and practitioners often trade-off between recognizing attributes that will make a model behaviorally more representative (from a theoretical viewpoint) and being able to estimate/implement a model (from a practical viewpoint). An alternative approach to deal with the estimation complications arising from multi-dimensional choice situations is the technique of composite marginal likelihood (CML). This is an estimation technique that is gaining substantial attention in the statistics field, though there has been relatively little coverage of this method in transportation and other fields. The CML approach is a conceptually and pedagogically simpler simulation-free procedure (relative to traditional approaches that employ simulation techniques), and has the advantage of reproducibility of the results. Under the usual regularity assumptions, the CML estimator is consistent, unbiased, and asymptotically normally distributed. The discussion above indicates that the CML approach has the potential to contribute in the area of travel demand modeling in a significant way. For example, the approach can be used to develop conceptually and behaviorally more appealing models to examine individuals’ travel decisions in a joint framework. The overarching goal of the current research work is to demonstrate the applicability of the CML approach in the area of activity-travel demand modeling and to highlight the enhanced features of the choice models estimated using the CML approach. The goal of the dissertation is achieved in three steps as follows: (1) by evaluating the performance of the CML approach in multivariate situations, (2) by developing multidimensional choice models using the CML approach, and (3) by demonstrating applications of the multidimensional choice models developed in the current dissertation.en
dc.format.mimetypeapplication/pdfen
dc.language.isoengen
dc.subjectComposite marginal likelihooden
dc.subjectMultivariate ordered-response model systemen
dc.subjectMaximum simulated likelihooden
dc.subjectPairwise marginal likelihooden
dc.subjectStatistical efficiencyen
dc.subjectSocial interactionsen
dc.subjectActivity-based modelingen
dc.subjectWalkingen
dc.subjectBicyclingen
dc.subjectActivity durationen
dc.subjectHazard functionen
dc.subjectSpatial interactionen
dc.subjectNormal scale mixtureen
dc.subjectSpatial econometricsen
dc.subjectPanel dataen
dc.subjectRandom coefficientsen
dc.subjectUrban land development intensityen
dc.titleA new estimation approach for modeling activity-travel behavior : applications of the composite marginal likelihood approach in modeling multidimensional choicesen
dc.date.updated2011-11-04T21:06:01Zen
dc.identifier.slug2152/ETD-UT-2011-08-4224en
dc.contributor.committeeMemberMachemehl, Randyen
dc.contributor.committeeMemberAbrevaya, Jasonen
dc.contributor.committeeMemberWaller, Stevenen
dc.contributor.committeeMemberStolp, Chandleren
dc.description.departmentCivil, Architectural, and Environmental Engineeringen
dc.type.genrethesisen
thesis.degree.departmentCivil, Architectural, and Environmental Engineeringen
thesis.degree.disciplineCivil Engineeringen
thesis.degree.grantorUniversity of Texas at Austinen
thesis.degree.levelDoctoralen
thesis.degree.nameDoctor of Philosophyen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record