TRB Pubsindex
Text Size:
x

« Prev Next »

Return to Results | New Search

Bookmark and Share

Title:

Analysis of Travel Activity Determinants Using Robust Statistics

Accession Number:

01593542

Record Type:

Component

Abstract:

This study investigates travel behavior determinants based on a multiday travel survey that was conducted in Ghent region, Belgium. Due to limited data reliability of the data sample, robust principal component analysis (ROBPCA) is employed in order to reveal the explanatory variables responsible for most of the variance. Comparison of classical PCA (CPCA) and ROBPCA proves critical influence of outliers which in turn makes CPCA infeasible for application. Although similar issues are common to many data resources and estimation techniques used in the transportation domain, the authors are not aware of any study that would thoroughly treat input data by applying robust statistical methods. Moreover, the interpretation of results is eased by utilizing sparse robust PCA (ROSPCA). This paper demonstrates the very first application of ROBPCA and ROSPCA to travel behavior data. Among others, these results suggest a key role of variable categories such as journey purpose-related impedance and journey inherent constraints. Surprisingly, the variables associated with journey timing turn out to be less important. The explanatory analysis of the result is considerably eased with the application of ROSPCA that reveals 6 distinct principal components where each is determined by a few variables. Finally, the findings reveal the critical role of outliers in travel behavior analysis. This suggests that a systematic understanding of how outliers contribute to observed mobility behavior patterns, as derived from travel surveys, is needed. In this regard, the proposed methods serve for processing raw data typically used in activity-based modelling.

Supplemental Notes:

This paper was sponsored by TRB committee ADB10 Standing Committee on Traveler Behavior and Values.

Monograph Accession #:

01584066

Report/Paper Numbers:

16-3763

Language:

English

Corporate Authors:

Transportation Research Board

500 Fifth Street, NW
Washington, DC 20001 United States

Authors:

Plevka, Václav
Segaert, Pieter
Tampère, Chris M J
Hubert, Mia

Pagination:

14p

Publication Date:

2016

Conference:

Transportation Research Board 95th Annual Meeting

Location: Washington DC, United States
Date: 2016-1-10 to 2016-1-14
Sponsors: Transportation Research Board

Media Type:

Digital/other

Features:

Figures; References; Tables

Geographic Terms:

Ghent (Belgium)

Subject Areas:

Planning and Forecasting; Transportation (General)

Source Data:

Transportation Research Board Annual Meeting 2016 Paper #16-3763

Files:

TRIS, TRB, ATRI

Created Date:

Jan 12 2016 5:38PM