Multinomial Probit with Structured Covariance for Choice Situations with Similar Alternatives

The estimatability of the multinomial probit (MNP) model has been improved greatly by the modeling of the error structure. A modeling idea for travelers’ choice behaviors using the MNP with structured covariances (MNPSC) model is proposed. Choice of route, destination, and time of day are considered. The covariance of the error term of the utility function is structured by introducing the overlapped length between any two routes and the overlapped time length between any two departure times. Simultaneous models such as route and train class, route and mode, and time of day and mode choice model also are introduced by applying the MNPSC modeling idea. These are formulated easily by assuming that the error is generated independently between two choices. An empirical study for a route and train class choice model was conducted by using the passenger survey data in the Tokyo metropolitan region, and its estimatability and applicability are examined.

Download Full-text

Semiparametric specification of the utility function in a travel mode choice model

Transportation ◽

10.1007/s11116-009-9253-5 ◽

2009 ◽

Vol 37 (2) ◽

pp. 221-238 ◽

Cited By ~ 13

Author(s):

Daisuke Fukuda ◽

Tetsuo Yai

Keyword(s):

Utility Function ◽

Choice Model ◽

Mode Choice ◽

Travel Mode ◽

Travel Mode Choice ◽

Mode Choice Model

Download Full-text

Estimating a mode choice model with incomplete data

Canadian Journal of Civil Engineering ◽

10.1139/l89-135 ◽

1989 ◽

Vol 16 (6) ◽

pp. 917-923

Author(s):

Gerald Brown ◽

Siovache Kahkeshan

Keyword(s):

Survey Data ◽

Incomplete Data ◽

Choice Model ◽

Mode Choice ◽

Synthetic Data ◽

Level Of Service ◽

Data Simulation ◽

Data Set ◽

Policy Model ◽

Mode Choice Model

This study develops and uses a synthetic data base to calibrate a logit mode choice model of work trips in metropolitan Vancouver. Missing survey data entries for perceived measures of travel time and waiting time by bus, as well as operating and parking cost by car, are calculated using statistical methods to increase the survey sample of 275 complete cases to 621 usable cases. The synthesized data set is used to specify random utility functions for two planning assumptions. The short-term policy specification using only level of service variables does not produce a usable model, but the specification based on a long-term planning assumption using a combination of level of service and socioeconomic variables produces plausible results. The inconclusive results from the policy model could be due to survey data problems, data simulation, and (or) the lack of conceptual validity of perceived measures of transportation attributes. The planning model provides insight into mode split prediction and transportation management for cities that are undergoing dynamic demographic and social changes. Key words: mode choice, incomplete data, socioeconomic factors, logit model.

Download Full-text

Exploring Travel Mode Preference of External Trips for Smart City Transportation Planning: Sejong, Korea

Sustainability ◽

10.3390/su14020630 ◽

2022 ◽

Vol 14 (2) ◽

pp. 630

Author(s):

Jin-Ki Eom ◽

Kwang-Sub Lee ◽

Sangpil Ko ◽

Jun Lee

Keyword(s):

Survey Data ◽

Smart City ◽

Choice Model ◽

Smart Cities ◽

Mode Choice ◽

Driving Ability ◽

Planning Stage ◽

Major Mode ◽

Mode Choice Model ◽

Living Area

In the face of growing concerns about urban problems, smart cities have emerged as a promising solution to address the challenges, for future sustainable societies in cities. Since the early 2000s, 67 local governments in Korea have been participating in smart city projects, as of 2019. The Sejong 5-1 Living Area smart city was selected as one of two pilot national demonstration smart cities. The main objectives of this study are to introduce the Sejong 5-1 Living Area smart city project that is currently in the planning stage, present travel and mode preferences focusing on external trips in a smart city context to be built, and analyze a mode choice model according to the socioeconomic characteristics of individual travelers. One of the distinguishing features of the Sejong smart city is its transportation design concept of designating a sharing car-only district within the city to limit private vehicle ownership to about one-third of residents, while bus rapid transit (BRT) plays a central role in mobility for external trips among four transport modes including private cars, BRT, carsharing, and ridesharing. This study was analyzed using the stated preference survey data under hypothetical conditions by reflecting the unique characteristics of the Sejong smart city transportation policy. Approximately two-thirds of respondents in the survey preferred to spend less than 1.25 USD, traveling less than 35 min on BRT trips. On the basis of the survey data, we developed a mixed logit mode choice model and found the overall model estimates to be statistically significant and reasonable. All people-specific variables examined in this study were associated with mode choices for external commuting trips, including age, income, household size, major mode, driving ability, and presence of preschoolers.

Download Full-text

Development of a New Toll Mode-Choice Modeling System for Florida’s Turnpike Enterprise

Transportation Research Record Journal of the Transportation Research Board ◽

10.3141/1858-02 ◽

2003 ◽

Vol 1858 (1) ◽

pp. 9-17 ◽

Cited By ~ 3

Author(s):

Youssef Dehghani ◽

Thomas Adler ◽

Michael W. Doherty ◽

Randy Fox

Keyword(s):

Travel Time ◽

Choice Model ◽

Mode Choice ◽

Model Development ◽

Time Of Day ◽

Choice Modeling ◽

Fort Lauderdale ◽

Trip Purpose ◽

Mode Choice Model ◽

Mode Choice Modeling

The Florida Department of Transportation Turnpike Enterprise’s recent toll mode-choice model development activities are described. Because the simple toll travel forecasting analysis methods used were not adequate for reliably addressing contemporary toll study issues, there was a need for toll modeling innovations that address trip makers’ toll route decisions as a mode-choice step sensitive to changes in service levels by time of day, trip purpose, and socioeconomic attributes. Innovations developed for Florida’s turnpike began with data-collection efforts and toll model development for the Central Florida (Orlando) region. This represents the next generation of modeling system. Similar efforts are under way for the Miami–Fort Lauderdale area. The Orlando region toll mode-choice model, which is in its final validation phase, includes a statistically estimated nested mode-choice modeling system with a discrete choice for toll travel. The models were developed for a combination of four periods and four trip purposes, including visitor trips. Other key features are ( a) a pre-mode-choice time-of-day process; ( b) a generalized cost-assignment procedure that uses travel time and costs by time of day (rather than travel time alone); ( c) production of zone-to-zone travel time and costs consistent with travel paths; and ( d) a feedback loop process that uses an iterative successive averaging procedure to estimate travel times.

Download Full-text