Examining the difference between park and ride and kiss and ride station choices using a spatially weighted error correlation (SWEC) discrete choice model

This paper presents a novel discrete choice model formulation: the spatially weighted error correlation (SWEC) logit model for spatial location choices. This model captures both the correlation between spatially distinct alternatives based on the relative distance between them and the heteroskedasticity of the errors of the alternative as a function of their relative distance to the decision maker. The SWEC model is applied for the estimation of models of transit station choice for P-and-R as well as kiss and ride (dropped off at transit station) transit commuters in the Greater Toronto and Hamilton Area (GTHA). The kiss and ride model has particular relevance due to its ability to capture household tradeoffs made by both the driver and the passenger. The tradeoffs are captured by utilizing the subsequent trip made by the driver in the utility function specification. The proposed model structure provides additional insights into how station choice occurs for such complex trips. Finally, the application of the SWEC model for both choice contexts provides a fundamental improvement over conventional approaches, as it is able to capture non-proportional substitution patterns and heteroskedasticity inherent with spatial choices.     

Welfare calculations in discrete choice settings: An exploratory analysis of error term correlation with finite populations

A difference in logsum terms (also known as inclusive values) is becoming a standard practice for anticipating the welfare impacts of transport policy when choice alternatives are discrete and behavior is (assumed to be) random-utility maximizing. However, this calculation is only an approximation when the population under study is finite. This paper examines the effect of error term correlations in such welfare analyses with finite samples, recognizing that individual preferences and unobserved attributes influencing choice are unlikely to change much, if at all, across scenarios or across alternatives. Such measures appear reasonably robust to deviations in assumptions of correlation. Nevertheless, we identify cases when the synthetic population samples need to be quite large for the average logsum to be realized. Another finding in these results is the substantial variation that emerges across synthetic populations, suggesting that policies that appear welfare-improving (when evaluated with average welfare formulations) may well be welfare-reducing (or vice versa) for a wide variety of actual, finite populations.     

Incorporating needs-satisfaction in a discrete choice model of leisure activities

In this paper we extend the behavioural scope of discrete choice models for leisure activity-travel choices. More specifically, we investigate to what extent choices for leisure activities and related travels are driven by the satisfaction of needs. In addition to conventional attributes (such as activity costs), our regret based discrete choice model incorporates latent variables representing the anticipated level of individual needs-satisfaction by a particular leisure activity. The latent variables are calibrated with the help of subjective indicators of needs-satisfaction associated with the leisure activities. Results show that needs-satisfaction allows us to decompose a substantial share of the unobserved heterogeneity in leisure activity-travel decisions across respondents. Identifying the structural drivers of anticipated needs-satisfaction also enables a better prediction of leisure activity choice.     

A two-stage residential location and transport mode choice model with exposure to traffic-induced air pollution

Air pollution is an increasing concern to urban residents. In response, residents are beginning to adapt their travel behaviour and to consider local air quality when choosing a home. We study implications of such behaviour for the morphology of cities and population exposure to traffic-induced air pollution. To do so, we propose a spatially explicit and integrated residential location and transport mode choice model for a city with traffic-induced air pollution. Intra-urban spatial patterns of population densities, transport mode choices, and resulting population exposure are analysed for urban settings of varying levels of health concern and air pollution information available to residents. Numerical analysis of the feedback between residential location choice and transport mode choice, and between residents' choices and the subsequent potential impact on their own health suggests that increased availability of information on spatially variable traffic-induced health concerns shifts population towards suburban areas with availability of public transport. Thus, health benefits result from reduced population densities close to urban centres in this context. To mitigate population exposure, our work highlights the need for spatially explicit information on peoples' air pollution concerns and, on this basis, spatially differentiated integrated land use and transport measures.     

The decision-making process of and the decisive factors in accommodation choice

This study examines tourists’ decision-making process of and highlights the decisive factors in accommodation choice, employing the discrete choice (multinomial logit and nested logit) models and using the international tourist data of Taiwan. The results of this study may be indicative of the hierarchical nature of tourists’ decision-making process of accommodation choice. In addition, we find that price is a significant factor in accommodation choice, whereas income has only limited explanatory power. The results also indicate that tourists with a longer length of stay tend to choose hotels of lower quality, and, in contrast, elder people prefer better accommodations.     

Latent class nested logit model for analyzing high-speed rail access mode choice

This paper explores access mode choice behavior, using a survey data collected in Taiwan. The latent class nested logit model is used to capture flexible substitution patterns among alternatives and preference heterogeneity across individuals while simultaneously identifying the number, sizes, and characteristics of market segments. The results indicate that a four-segment latent class nested logit model with individual characteristics in segment membership functions is the most preferred specification. Most high-speed rail travelers were cost-sensitive to access modes, and thus strategies that reduce the access costs can be more effective than reducing the access times.     

Air itinerary choice in a low-frequency market: A decision rule approach

This paper focuses on low frequency airline service patronage using the data from a survey conducted at Imam Khomeini International Airport in Tehran, Iran. It uses Dominance-based Rough Set Approach (DRSA) for modeling passengers’ choices. We compare the method with discrete choice models using a prediction potential measure. Unlike discrete choice methods, it can use qualitative and categorized data without having to transform them into dummy variables. It is found that the prediction accuracy of the proposed technique is better than that of the discrete choice model for the case under consideration.     

Modeling air travelers’ choice of flight departure and return dates on long holiday weekends

Air travel demand is typically high on long holidays. Understanding factors that influence the choice of air travelers with respect to their departure and return dates on long holidays can help airlines make effective decisions on pricing, ticket sales, and scheduling. We conduct a stated preference survey to examine the preferences of low-cost airline travelers on a particular holiday weekend. A temporally correlated logit model is developed to account for the temporal correlation of day-of-the-week alternatives. The results indicate that airfare is the key variable affecting air travel date choices. The utility of day alternatives decreases when more leave days are required before the holiday begins. Departure dates before the beginning of the holiday weekend and return dates after the end of the holiday are highly substitutable. The low-fare strategy comprising early departures and late returns can effectively increase the load factor of off-peak flights on long holiday weekends.     

Domestic tourism destination choices — a choice modelling analysis

Tourism destinations compete with each other to attract visitors. Although international tourism has received a lot of attention, domestic tourism remains the mainstay for many destinations. To inform the basis on which destinations compete, an understanding of the determinants of destination choices is required. In this paper, the discrete choice modelling method is applied to investigate the determining factors underlying the short‐break holiday destination choices of prospective tourists from Melbourne, Australia. The results from an estimated nested logit model indicate the relative importance of a number of destination and trip attributes and respondent characteristics. The model results are used to simulate the effects on destinations' market shares resulting from various changes in attributes and tourist characteristics. Copyright © 2003 John Wiley & Sons, Ltd.     

Location of logistics companies: a stated preference study to disentangle the impact of accessibility

Due to the globalization and the fragmentation of industrial production processes, the logistics sector, organizing the linkages between different production plants and the market, is growing fast. This results in an increasing demand for suitable new business locations. Previous research has indicated that accessibility is a key factor in the location decision making process. Though the literature on this subject is extensive, little research has been done to quantify the impact of the different dimensions of accessibility on the location decision process of logistics companies. This paper aims to fill this void in the literature by means of a revealed preference study (using a Geographic Information System (GIS) analysis) and a stated preference study (using a designed discrete choice experiment) in Flanders (Belgium). The results of the revealed preference study served as input to the design of the choice situations in the stated preference study. In the stated preference study, the respondents were confronted with a series of choice situations described by means of accessibility variables as well as land rent information. An analysis of the resulting data by means of discrete choice modeling revealed that land rent is the most important factor in the location choice of logistics companies in Flanders. Access to a port is the second most important factor, followed by access to a motorway, the location in a business park and an inland navigation terminal, which are all about equally important. Access to a rail terminal plays no significant role in the location choice of logistics companies in Flanders.     

Passengers' airport choice and airports' catchment area analysis in cross-border Upper Adriatic multi-airport region

Although much research has been performed on passengers' origin airport choice, there is little research on airports' catchment area size and even less on airports' catchment areas in cross-border regions. This paper addresses passengers' airport choice and analyzes airports' catchment area size and its homogeneity in the Upper Adriatic region. Using the results of passengers' survey at three regional airports (Ljubljana Jože Pučnik Airport (LJU), Venice Marco Polo Airport (VCE) and Trieste Pietro Savorgnan di Brazza Airport (TRS)) we have estimated the airports' catchment areas and airports market shares therein using multinomial logit (MNL) model structure. To additionally explore the passengers' airport choice behavior considering the different sensitivity across travellers to regional, demographic and airports attributes and account for preference heterogeneity in airport choice a mixed logit model was used. The results indicated that the three airports have relatively small core catchment areas and that the market share rapidly decreases with the increasing access time to airport. Partially, the results reinforced earlier findings showing that access time to airport is the most important determinant in airport choice for all segments (business/leisure and cross-border/domestic), however the sensitivity to access time is more pronounced in business and domestic group. Additionally, the results indicated pronounced loyalty to domestic airports and generally low importance of ticket prices, and show that in market conditions where all airports in the region have a low-cost carrier (LCC) the effect of LCC on airport choice is limited. Finally, the results indicated that the borders might have an influence on airport choice and that overall, in the cross-border regions the passengers’ airport choice process is even more complex than in non cross-border regions.     

A study on passengers' airport choice behavior using hybrid choice model: A case study of Seoul metropolitan area,South Korea

Improving explanatory power is significantly important to understand variables that affect attitudes and perceptions in the decision process. This paper estimates not only tangible attributes but also intangible perceptions and attitudes using a hybrid-choice model to study air passengers' flight choice behavior. The empirical study was conducted for the choice behavior of air passengers at Seoul Metropolitan Area, South Korea. The analysis uses a two-level Nested Logit model in order to examine which factors have more effect on passengers’ choice of airport and airline simultaneously by using airport and airline choice attributes. The study also estimated the parameters in the equations relating the latent variable by using Structural Equation Model (SEM). The results indicate that the models with latent variables have improved Goodness-of-Fit when compared to classical discrete choice models and effectively capture psychological factors that affect choice behavior of passengers.     

A GIS-based toolkit for route choice analysis

This paper develops and applies the route choice analysis (RCA) toolkit. This GIS-based toolkit generates a suite of over 40 variables describing route characteristics such as distance, travel time, speed statistics, number of intersections, number of turns, number of stop signs/stop lights, and a measure of route circuity, to name a few. The input to the toolkit is one or more routes, which can be obtained from global positioning system (GPS) data or some other means (e.g., shortest path). While the toolkit is designed to support route choice modeling by generating variables that have been tested in previous modeling efforts, we demonstrate its utility by testing the hypothesis that workers choose routes to minimize either travel time or distance between home and work. A GPS-enhanced data set of 237 observed routes for home-to-work trips collected for auto drivers in Halifax, Nova Scotia, Canada is used in our analysis. We find that the null hypothesis is refuted - that is, a comparison of observed routes to their shortest-path alternatives based on time and distance via inferential statistics indicates that observed routes are significantly longer compared to their alternatives. This finding suggests that workers may choose routes based on other route attributes. The attributes generated by the RCA toolkit for observed, shortest time, and shortest distance routes are compared and significant differences are noted.     

The role of perceived acceptability of alternatives in identifying and assessing choice set processing strategies in stated choice settings: The case of road pricing reform

In designing choice experiments, it is common to present a number of alternatives to a respondent and have them choose the most preferred alternative. However, respondents may ignore one or more alternatives which they deem unacceptable for various reasons. This possibility aligns with the idea of the ‘consideration set’ which influences the choice of an alternative given the choice set of interest. This paper uses an endogenous choice set model to investigate the influence that contextual effects and socioeconomic characteristics play in explaining variations in the choice sets considered by respondents when they reveal their preferences.     

Valuation of travel time for international long-distance travel – results from the Fehmarn Belt stated choice experiment

The geographical scope of travel varies from short distances in urban areas to long distances across cities and countries. While urban travel has been widely analysed in the literature, travel over longer distances and particularly across countries, has received much less attention. While this may be justified due to the number of travellers it cannot be justified when looking at the mileage consumption and its resulting environmental impacts. In this paper, we investigate international long-distance travel preferences related to travel between Scandinavia and Central Europe with particular focus on the Fehmarn Belt fixed link between Germany and Denmark to be opened in 2021. To facilitate long-term demand forecasts for the future fixed link, stated preference data were collected in 2011. Based on these data a discrete choice model for long-distance travellers was developed in order to estimate the value of travel time savings (VTTS). The final model, which was formulated as a nested logit model and included Box–Cox transformed travel time and cost attributes, revealed several interesting findings. Firstly, we found damping effects in both cost and time – most strongly in cost. Secondly, we found significant interactions among travel cost and time, and journey characteristics, such as distance and duration. This had direct impact on the VTTS, which was shown to decrease with distance and duration. Thirdly, we found that air travel implies a higher average VTTS, which is to be expected but rarely supported by empirical evidence.     

Traveler perceptions and airline choice: A multivariate probit approach

We investigate the factors that affect passenger decisions regarding airline choice. Three Multivariate Probit (MP) models are developed to analyze data for a sample of 853 respondents. This methodology allows for modeling the simultaneous, yet separate, consideration of airline choice determinants. Fare, safety and reliability, and friendly-and-helpful staff during flight are the most important determinants of airline choice. In-flight entertainment and frequent flyer program are considered to be less important. Results clearly depict differences in the significance of these factors among passengers with different socio-demographic and trip characteristics.     

Determinants and spatial variability of after-school travel by teenagers

This research work targeted teenagers to investigate after-school travel patterns and factors affecting their modal choice characteristics in Okinawa, Japan, where teenagers are not allowed to drive. The analysis is based on the cross-sectional data collected for discrete choice modeling of students’ travel in the prefecture. In this study, high school students’ trips from school to home have been analysed using a multinomial logit model. This has revealed the impact of individual, modal, and spatial variables on the mode choice decisions and return trip patterns. A comparative analysis made of downtown and suburb schools exposed differences in travel patterns induced by spatial factors and some existing constraints in modal choice options.     

Route choice behavior in a radial structured urban network: Do people choose the orbital or the route through the city center?

We use a license plate survey to study route choice through the city center of a medium-sized Dutch city, in which car drivers can basically choose between the orbital and center ring. For a sample of 1397 trips, we fitted a multinomial logit regression model. According to this model, route choice is relatively little influenced by actual travel time. This corresponds with the fact that many drivers did not choose the shortest time route. Travel distance in combination with one “route type velocity” for all orbital routes, and one route type velocity for all center routes is the most decisive factor. The route type velocity indicates how fast and attractive routes of that type are (being perceived). The results support the hypothesis that orbital routes are more attractive as these routes avoid the busy city center. This effect is however partly offset by the fact that drivers also prefer routes in the direction of their destination. These direct routes are mainly center routes. The results show the importance of considering complete routes in relation to their location and not only as a set of links and nodes when modeling route choice.     

Latent class models of international air carrier choice

This paper uses a market segmentation approach to identify airline passengers’ potential segments and preferences toward international air carriers. The modeling approaches consist of the stated preference method and the latent class model. The stated choice experiments were designed based on service attributes in the international airline choice context. Empirical data was collected from airline passengers who have flown from Taipei to Tokyo or from Taipei to Hong Kong. The latent class model accommodating preference heterogeneity outperforms the multinomial logit model as indication of a better approach to analyze airline choice behavior. The latent class model with individual socioeconomic and trip characteristics in segment membership functions also improved model fit relative to the corresponding latent class model without individual characteristics. The values of willingness to pay for service attribute improvements vary across international air routes and segments. Passengers are willing to pay more for better service quality. In order to develop effective marketing and operational strategies for the international air travel market, this study highlights the importance of exploring airline choice behaviors by routes and segments.     

Market segmentation analysis for airport access mode choice modeling with mixed logit

Accessing airports can be considered as a crucial issue since passengers need not miss their flights. This issue makes the mode choice to access the airports important to study on and develop policies regarding it. Many studies show destination type as domestic or international affects the airport access mode choice, along with other factors. In this study, we investigate the effect of destination type of mode choice using mixed logit, using market segmentation approach. Market segmentation regarding destination type as domestic or international is a first in airport access mode choice modeling. Revealed-preference data was collected by face-to-face passenger surveys at Ataturk International Airport in Istanbul, Turkey, in 2015. We did market segmentation analysis for Multinomial Logit (MNL) and Mixed Logit (ML) models. When MNL and ML models were compared, it was observed that ML was superior to MNL. Further, results of market segmentation analysis revealed that using segmented models produced more accurate results than using the pooled model; both in MNL and ML. This finding was also supported by the value of time estimates; there were significant differences between domestic and international travel markets in terms of airport access mode choice. These results showed that different transportation policies may be introduced for domestic and international traveler segments, which also were explained.