Effects of incorporating latent and attitudinal information in mode choice models

Abstract

Hybrid choice modelling approaches allow latent variables in mode choice utility functions to be addressed. However, defining attitude and behavior as latent variables is influenced by the researcher's assumptions. Therefore, it is better to capture the effects of latent behavioral and attitudinal factors as latent variables than defining behaviors and attitudes per se. This article uses a hybrid choice model for capturing such latent effects, which will herein be referred to as modal captivity effects in commuting mode choice. Latent modal captivity refers to the unobserved and apparently unexplained attraction towards a specific mode of transportation that is resulting from latent attitude and behavior of passengers in addition to the urban transportation system. In empirical models, the latent modal captivity variables are explained as functions of different observed variables. Empirical models show significant improvement in fitting observed data as well as improved understanding of travel behavior.     

Bike route choice modeling using GPS data without choice sets of paths

Concerned by the nuisances of motorized travel on urban life, policy makers are faced with the challenge of making cycling a more attractive alternative for everyday transportation. Route choice models can help achieve this objective by gaining insights into the trade-offs cyclists make when choosing their routes and by allowing the effect of infrastructure improvements to be analyzed. We estimate a link-based bike route choice model from a sample of GPS observations in the city of Eugene on a network comprising over 40,000 links. The so-called recursive logit (RL) model (Fosgerau et al., 2013) does not require to sample any choice set of paths. We show the advantages of this approach in the context of prediction by focusing on two applications of the model: link flows and accessibility measures. Compared to the path-based approach which requires to generate choice sets, the RL model proves to make significant gains in computational time and to avoid paradoxical accessibility measure results discussed in previous works, e.g. Nassir et al. (2014).     

Mode choice decision process models: A comparison of compensatory and non-compensatory structures

Transportation planners use models which involve the construction of linear combinations of travel mode attributes to predict mode choice behavior. Psychologists, marketing researchers, and decision theorists, however, have identified a number of other types of choice models. Previous research has indicated that many of these models provide more accurate predictions of consumer choices than simple additive models. It is therefore suggested that mode choice decisions may involve a number of different choice mechanisms. Empirical results showing that conjunctive, lexicographic, and conjunctive-lexicographic models of mode choice outperform additive models are presented, and directions for future research are discussed.     

Dynamic travel time prediction using data clustering and genetic programming

The current state-of-practice for predicting travel times assumes that the speeds along the various roadway segments remain constant over the duration of the trip. This approach produces large prediction errors, especially when the segment speeds vary temporally. In this paper, we develop a data clustering and genetic programming approach for modeling and predicting the expected, lower, and upper bounds of dynamic travel times along freeways. The models obtained from the genetic programming approach are algebraic expressions that provide insights into the spatiotemporal interactions. The use of an algebraic equation also means that the approach is computationally efficient and suitable for real-time applications. Our algorithm is tested on a 37-mile freeway section encompassing several bottlenecks. The prediction error is demonstrated to be significantly lower than that produced by the instantaneous algorithm and the historical average averaged over seven weekdays (p-value <0.0001). Specifically, the proposed algorithm achieves more than a 25% and 76% reduction in the prediction error over the instantaneous and historical average, respectively on congested days. When bagging is used in addition to the genetic programming, the results show that the mean width of the travel time interval is less than 5 min for the 60–80 min trip.     

A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data

Traffic crashes occurring on freeways/expressways are considered to relate closely to previous traffic conditions, which are time-varying. Meanwhile, most studies use volume/occupancy/speed parameters to predict the likelihood of crashes, which are invalid for roads where the traffic conditions are estimated using speed data extracted from sampled floating cars or smart phones. Therefore, a dynamic Bayesian network (DBN) model of time sequence traffic data has been proposed to investigate the relationship between crash occurrence and dynamic speed condition data. Moreover, the traffic conditions near the crash site were identified as several state combinations according to the level of congestion and included in the DBN model. Based on 551 crashes and corresponding speed information collected on expressways in Shanghai, China, DBN models were built with time series speed condition data and different state combinations. A comparative analysis of the DBN model using flow detector data and a static Bayesian network model was also conducted. The results show that, with only speed condition data and nine traffic state combinations, the DBN model can achieve a crash prediction accuracy of 76.4% with a false alarm rate of 23.7%. In addition, the results of transferability testing imply that the DBN models are applicable to other similar expressways with 67.0% crash prediction accuracy.     

Door-to-door travel times in RP departure time choice models: An approximation method using GPS data

A common way to determine values of travel time and schedule delay is to estimate departure time choice models, using stated preference (SP) or revealed preference (RP) data. The latter are used less frequently, mainly because of the difficulties to collect the data required for the model estimation. One main requirement is knowledge of the (expected) travel times for both chosen and unchosen departure time alternatives. As the availability of such data is limited, most RP-based scheduling models only take into account travel times on trip segments rather than door-to-door travel times, or use very rough measures of door-to-door travel times. We show that ignoring the temporal and spatial variation of travel times, and, in particular, the correlation of travel times across links may lead to biased estimates of the value of time (VOT). To approximate door-to-door travel times for which no complete measurement is possible, we develop a method that relates travel times on links with continuous speed measurements to travel times on links where relatively infrequent GPS-based speed measurements are available. We use geographically weighted regression to estimate the location-specific relation between the speeds on these two types of links, which is then used for travel time prediction at different locations, days, and times of the day. This method is not only useful for the approximation of door-to-door travel times in departure time choice models, but is generally relevant for predicting travel times in situations where continuous speed measurements can be enriched with GPS data.     

Development of destination choice model with pairwise district-level constants using taxi GPS data

In this paper, a destination choice model with pairwise district-level constants is proposed for trip distribution based on a nearly complete OD trip matrix in a region. It is found that the coefficients are weakly identified in a destination choice model with pairwise zone-level constants. Thus, a destination choice model with pairwise district-level constants is then proposed and an iterative algorithm is developed for model estimation. Herein, the “district” means a spatial aggregation of a number of zones. The proposed model is demonstrated through simulation experiments. Then, destination choice models with and without pairwise district-level constants are estimated based on GPS data of taxi passenger trips collected during morning peak hours within the Inner Ring Road of Shanghai, China. The datasets comprise 504,187 trip records and a sample of 10,000 taxi trips for model development. The zones used in the study are actually 961 residents’ committees while the districts are 52 residential districts that are spatial aggregations and upper-level administrative units of residents’ committees. It is found that the estimated value of time dramatically drops after the involvement of district-level constants, indicating that the traditional model tends to overestimate the value of time when ignoring pairwise associations between two zones in trip distribution. The proposed destination choice model can ensure its predicted trip OD matrix to match the observed one at district level. Thus, the proposed model has potential to be widely applied for trip distribution under the situation where a complete OD trip matrix can be observed.     

Modelling shopping destination choice behaviour using the basic multinomial logit model and some of its extensions

This paper reviews basic multinomial logit (MNL) models of shopping destination choice and some extensions to the basic MNL model. Issues include the identification and form of inclusion of measures of destination attractiveness, identification of the appropriate destination choice set, modelling multidestination tours and choices over time, and linking destination choice models with activity measures. The paper begins with a discussion of modelling philosophy and forecasting‐related informational needs and concludes with a summary of areas requiring further research.     

Route choice stickiness of public transport passengers: Measuring habitual bus ridership behaviour using smart card data

This paper explores how we can use smart card data for bus passengers to reveal individual and aggregate travel behaviour. More specifically, we measure the extent to which both individual and bus routes exhibit habitual behaviour. To achieve this, we introduce a metric called Stickiness Index to quantify the range of preferences of users that always select to travel on the same route (high stickiness) to those with a more varied patterns of route selection (low stickiness). Adopting a visual analytic and modelling approach using a suite of regression models we find evidence to suggest that stickiness varies across the metropolitan area and over a 24-h period wherein higher stickiness is associated with high frequency users where there is substantial variability of route travel times across all alternatives. We argue that our findings are important in their capacity to contribute to a new evidence base with the potential to inform the (re)-design and scheduling of a public transit systems through unveiling the complexities of transit behaviour.     

The accuracy of proxy responses in a stated choice setting: A re-examination and some controversial conclusions

Data is typically gathered from an individual respondent who represents the group or the household. This individual is often identified as the “primary decision maker” and is asked to provide responses as a proxy for the group given that the cost of interviewing each member individually is impractical and/or expensive. The collection of joint preferences is rarely undertaken, with the use of proxy responses not uncommon in travel behaviour research. Under such a framework, there exists an assumption that the primary decision maker has perfect knowledge of other group member preferences, and bargaining behaviour, and is able to synthesise this information when providing a response on their behalf. The validity of such an assumption however remains an open question, with recent research calling the reliability of proxy responses into account (Bateman and Munro, 2009). In this paper, using three models estimated in willingness to pay space, we examine the accuracy of proxy responses in a stated choice experiment. We find that there is overlap between a proxy response and the own preferences of the individual providing the proxy choice, but while the proxy responses fail to represent the full preference heterogeneity that exists in the actual choices made by individuals, the proxy responses in aggregate provide a suitable replacement for actual data, subject to a number of caveats.     

Assessment of the transit ridership prediction errors using AVL/APC data

Transportation - The disparity between actual and forecasted transit ridership has been an important area of study and a concern for researchers for several decades. In order to decrease the...     

Estimation of a route choice model for urban public transport using smart card data

This paper describes a logit model of route choice for urban public transport and explains how the archived data from a smart card-based fare payment system can be used for the choice set generation and model estimation. It demonstrates the feasibility and simplicity of applying a trip-chaining method to infer passenger journeys from smart card transactions data. Not only origins and destinations of passenger journeys can be inferred but also the interchanges between the segments of a linked journey can be recognised. The attributes of the corresponding routes, such as in-vehicle travel time, transfer walking time and to get from alighting stop to trip destination, the need to change, and the time headway of the first transportation line, can be determined by the combination of smart card data with other data sources, such as a street map and timetable. The smart card data represent a large volume of revealed preference data that allows travellers' behaviour to be modelled with higher accuracy than by using traditional survey data. A multinomial route choice model is proposed and estimated by the maximum likelihood method, using urban public transport in ?ilina, the Slovak Republic, as a case study     

Using ordered attitudinal indicators in a latent variable choice model: a study of the impact of security on rail travel behaviour

There is growing interest in the use of models that recognise the role of individuals’ attitudes and perceptions in choice behaviour. Rather than relying on simple linear approaches or a potentially bias-inducing deterministic approach based on incorporating stated attitudinal indicators directly in the choice model, researchers have recently recognised the latent nature of attitudes. The uptake of such latent attitude models in applied work has however been slow, while a number of overly simplistic assumptions are also commonly made. In this article, we present an application of jointly estimated attitudinal and choice models to a real-world transport study, looking at the role of latent attitudes in a rail travel context. Our results show the impact that concern with privacy, liberty and security, and distrust of business, technology and authority have on the desire for rail travel in the face of increased security measures, as well as for universal security checks. Alongside demonstrating the applicability of the model in applied work, we also address a number of theoretical issues. We first show the equivalence of two different normalisations discussed in the literature. Unlike many other latent attitude studies, we explicitly recognise the repeated choice nature of the data. Finally, the main methodological contribution comes in replacing the typically used continuous model for attitudinal response by an ordered logit structure which more correctly accounts for the ordinal nature of the indicators.     

Mode choice and travel distance joint models in school trips

We test a copula-based joint discrete–continuous model to unravel mode choice and travel distance decisions in a joint framework for school trips. This framework explicitly accounts for common unobserved factors that may affect both the mode choice and travel distance. Joint estimation of the models makes a significant difference in the effect of travel distance on willingness to walk to school. The absolute value of the travel distance coefficient in the mode choice model increases by 22% when a joint formulation is adopted instead of the conventional single estimations. We find a significant decrease of 19% in the coefficient of travel safety perception in the joint mode choice model compared to the single model. This underscores the impact of model specification, in terms of the variable effect interpretation and policy assessments. The effect magnitude of several policy-sensitive variables is discussed and compared with previous studies. Particularly, we indicate that the probability of walking is reduced by 0.85% due to a 1% increase in travel distance; accordingly, it propels parents to select non-active modes, particularly school bus. This study also demonstrates how addressing parental concerns about travel safety could double the propensity to walk to school.     

Understanding suburban travel demand: Flexible modelling with revealed and stated choice data

We analyse the choice of mode in suburban corridors using nested logit specifications with revealed and stated preference data. The latter were obtained from a choice experiment between car and bus, which allowed for interactions among the main policy variables: travel cost, travel time and frequency. The experiment also included parking cost and comfort attributes. The attribute levels in the experiment were adapted to travellers’ experience using their revealed preference information. Different model specifications were tested accounting for the presence of income effect, systematic taste variation, and incorporating the effect of latent variables. We also derived willingness-to-pay measures, such as the subjective value of time, that vary among individuals as well as elasticity values. Finally, we analysed the demand response to various policy scenarios that favour public transport use by considering improvements in level-of-service, fare reductions and/or increases in parking costs. In general, demand was shown to be more sensitive to policies that penalise the private car than those improving public transport.     

A sequential approach to exploiting the combined strengths of SP and RP data: Application to freight shipper choice

The possibility of and procedure for pooling RP and SP data have been discussed in recent research work. In that literature, the RP data has been viewed as the yardstick against which the SP data must be compared. In this paper we take a fresh look at the two data types. Based on the peculiar strengths and weaknesses of each we propose a new, sequential approach to exploiting the strengths and avoiding the weaknesses of each data source. This approach is based on the premise that SP data, characterized by a well-conditioned design matrix and a less constrained decision environment than the real world, is able to capture respondents' tradeoffs more robustly than is possible in RP data. (This, in turn, results in more robust estimates of share changes due to changes in independent variables.) The RP data, however, represent the current market situation better than the SP data, hence should be used to establish the aggregate equilibrium level represented by the final model. The approachfixes the RP parameters for independent variables at the estimated SP parameters but uses the RP data to establish alternative-specific constants. Simultaneously, the RP data are rescaled to correct for error-in-variables problems in the RP design matrixvis-à- vis the SP design matrix. All specifications tested are Multinomial Logit (MNL) models.The approach is tested with freight shippers' choice of carrier in three major North American cities. It is shown that the proposed sequential approach to using SP and RP data has the same or better predictive power as the model calibrated solely on the RP data (which is the best possible model for that data, in terms of goodness-of-fit figures of merit), when measured in terms of Pearson's Chi-squared ratio and the percent correctly predicted statistic. The sequential approach is also shown to produce predictions with lower error than produced by the more usual method of pooling the RP and SP data.     

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

Neural networks have been extensively applied to short-term traffic prediction in the past years. This study proposes a novel architecture of neural networks, Long Short-Term Neural Network (LSTM NN), to capture nonlinear traffic dynamic in an effective manner. The LSTM NN can overcome the issue of back-propagated error decay through memory blocks, and thus exhibits the superior capability for time series prediction with long temporal dependency. In addition, the LSTM NN can automatically determine the optimal time lags. To validate the effectiveness of LSTM NN, travel speed data from traffic microwave detectors in Beijing are used for model training and testing. A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.     

Context-dependent influence of road attributes and pricing policies on route choice behavior of truck drivers: results of a conjoint choice experiment

In this paper, we report the results of a stated choice experiment, which was conducted to examine truck drivers?? route choice behavior. Of particular interest are the questions (i) what is the relative importance of road accessibility considerations via-a-vis traditional factors influencing route choice behavior, (ii) what are the influences of particular personal and situational variables on the evaluation of route attributes, (iii) how sensitive are truck drivers for possible pricing policies, and (iv) is there a difference in impact if environmental concerns are framed as a bonus or as a pricing instrument. The main findings indicate that road accessibility characteristics have a substantial impact on route preferences which is of the same order of magnitude as variation in travel times. This suggests that provision of adequate travel information in itself can be an effective instrument to prevent negative externalities of good transport associated with shortest routes. Furthermore, the results indicate that truck drivers/route planners when choosing a route are relatively sensitive to road pricing schemes and rather insensitive to environmental bonuses.