Sampling of alternatives in Logit Mixture models

Employing a strategy of sampling of alternatives is necessary for various transportation models that have to deal with large choice-sets. In this article, we propose a method to obtain consistent, asymptotically normal and relatively efficient estimators for Logit Mixture models while sampling alternatives. Our method is an extension of previous results for Logit and MEV models. We show that the practical application of the proposed method for Logit Mixture can result in a Naïve approach, in which the kernel is replaced by the usual sampling correction for Logit. We give theoretical support for previous applications of the Naïve approach, showing not only that it yields consistent estimators, but also providing its asymptotic distribution for proper hypothesis testing. We illustrate the proposed method using Monte Carlo experimentation and real data. Results provide further evidence that the Naïve approach is suitable and practical. The article concludes by summarizing the findings of this research, assessing their potential impact, and suggesting extensions of the research in this area.     

New insights on random regret minimization models

This paper develops new methodological insights on Random Regret Minimization (RRM) models. It starts by showing that the classical RRM model is not scale-invariant, and that – as a result – the degree of regret minimization behavior imposed by the classical RRM model depends crucially on the sizes of the estimated taste parameters in combination with the distribution of attribute-values in the data. Motivated by this insight, this paper makes three methodological contributions: (1) it clarifies how the estimated taste parameters and the decision rule are related to one another; (2) it introduces the notion of “profundity of regret”, and presents a formal measure of this concept; and (3) it proposes two new family members of random regret minimization models: the μRRM model, and the Pure-RRM model. These new methodological insights are illustrated by re-analyzing 10 datasets which have been used to compare linear-additive RUM and classical RRM models in recently published papers. Our re-analyses reveal that the degree of regret minimizing behavior imposed by the classical RRM model is generally very limited. This insight explains the small differences in model fit that have previously been reported in the literature between the classical RRM model and the linear-additive RUM model. Furthermore, we find that on 4 out of 10 datasets the μRRM model improves model fit very substantially as compared to the RUM and the classical RRM model.     

Three-dimensional conflict count models for unstructured and layered airspace designs

This paper presents analytical models that describe the safety of unstructured and layered en route airspace designs. Here, ‘unstructured airspace’ refers to airspace designs that offer operators complete freedom in path planning, whereas ‘layered airspace’ refers to airspace concepts that utilize heading-altitude rules to vertically separate cruising aircraft based on their travel directions. With a focus on the intrinsic safety provided by an airspace design, the models compute instantaneous conflict counts as a function of traffic demand and airspace design parameters, such as traffic separation requirements and the permitted heading range per flight level. While previous studies have focused primarily on conflicts between cruising aircraft, the models presented here also take into account conflicts involving climbing and descending traffic. Fast-time simulation experiments used to validate the modeling approach indicate that the models estimate instantaneous conflict counts with high accuracy for both airspace designs. The simulation results also show that climbing and descending traffic caused the majority of conflicts for layered airspaces with a narrow heading range per flight level, highlighting the importance of including all aircraft flight phases for a comprehensive safety analysis. Because such trends could be accurately predicted by the three-dimensional models derived here, these analytical models can be used as tools for airspace design applications as they provide a detailed understanding of the relationships between the parameters that influence the safety of unstructured and layered airspace designs.     

Distribution models for start-up lost time and effective departure flow rate

Due to its importance, lots of investigations had been carried out in the last four decades to study the relationship between phase duration and vehicle departure amount. In this paper, we aim to build appropriate distribution models for start-up lost time and effective departure flow rate, by considering their relations with the frequently mentioned departure headway distributions. The motivation behind is that distribution models could provide richer information than the conventional mean value models and thus better serve the need of traffic simulation and signal timing planning. To reach this goal, we first check empirical data collected in Beijing, China. Tests show that the departure headways at each position in a discharging queue are very weakly dependent or almost independent. Based on this new finding, two distribution models are proposed for start-up lost time and effective flow rate, respectively. We also examine the dependences of departure headways that are generated by three popular traffic simulation software: VISSIM, PARAMICS and TransModeler. Results suggest that in VISSIM, the departure headways at different positions are almost deterministically dependent and may not be in accordance with empirical observations. Finally, we discuss how the dependence of departure headways may influence traffic simulation and signal timing planning.     

Optimization of Wiedemann and Fritzsche car-following models for emission estimation

Recent studies have provided that the vehicle trajectories generated by car-following models may not represent the real driving characteristics, thus leading to significant emission estimation errors. In this paper, two of the most widely used car-following models, Wiedemann and Fritzsche models, were selected and analyzed based on the massive field car-following trajectories in Beijing. A numerical simulation method was designed to generate the following car’s trajectories by using the field trajectories as the input. By comparing the simulated and the filed data, the representativeness of the simulated regime fractions and VSP distributions were evaluated. Then, the mechanism of car-following models was investigated from the aspects of regime determination and the acceleration rule in each regime. Further, the regime threshold parameters and acceleration model were optimized for emission estimations. This study found that the “Following” regime threshold of SDX and the maximum acceleration in “Free Driving” regime are critical parameters for Wiedemann model. The differences between the Wiedemann simulated VSP distribution and the field one can be reduced separately by applying the optimized SDX and maximum acceleration model individually. However, a much sharper reduction was observed by optimizing both parameters simultaneously, and the emission estimation errors were further reduced, which were less than 4% in the case studies. Fritzsche model generated more realistic VSP distributions and emissions, while the maximum accelerations could be further optimized for high speed conditions.     

Some features of non-linear travel time models for dynamic traffic assignment

Abstract

This paper investigates some features of non-linear travel time models for dynamic traffic assignment (DTA) that adopt traffic on the link as the sole determinant for the calculation of travel time and have explicit relationships between travel time and traffic on the link. Analytical proofs and numerical examples are provided to show first-in-first-out (FIFO) violation and the behaviour of decreasing outflow with increasing traffic in non-linear travel time models. It is analytically shown that any non-linear travel time model could violate FIFO in some circumstances, especially when inflow drops sharply, and some convex non-linear travel time models could show behaviour with outflow decreasing as traffic increases. It is also shown that the linear travel time model does not show these behaviours. A non-linear travel time model in general form was used for analytical proofs and several existing non-linear travel time models were adopted for numerical examples. Considering the features addressed in this study, non-linear travel time models seem to have limitations for use in DTA in practical terms and care should be taken when they are used for modelling time-varying transportation networks.     

A review of port devolution and governance models with compound eyes approach

Port devolution and port governance are focal issues in port studies. This paper argues that the previous typology of port devolution and port governance, including port function matrix models, might have to be modified, in particular for Asian port cases, because they have not considered socio, economic, and political systems and historical aspects behind the port devolution continuum. This paper uses the “compound eyes” approach comprising of many similar, closely-packed facets called ommatidia, with a multiple angle view, to revisit and review previous port devolution and governance models. The paper aims to identify the limitations and rectify fallacies in previous port studies by conducting a critical review and taking a couple of Asian container port cases as examples. This paper contributes to the literature of port devolution and governance, illuminating crucial gaps that the previous studies have not addressed.     

Essential elements in tactical planning models for container liner shipping

Tactical planning models for liner shipping problems such as network design and fleet deployment usually minimize the total cost or maximize the total profit subject to constraints including ship availability, service frequency, ship capacity, and transshipment. Most models in the literature do not consider slot-purchasing, multi-type containers, empty container repositioning, or ship repositioning, and they formulate the numbers of containers to transport as continuous variables. This paper develops a mixed-integer linear programming model that captures all these elements. It further examines from the theoretical point of view the additional computational burden introduced by incorporating these elements in the planning model. Extensive numerical experiments are conducted to evaluate the effects of the elements on tactical planning decisions. Results demonstrate that slot-purchasing and empty container repositioning have the largest impact on tactical planning decisions and relaxing the numbers of containers as continuous variables has little impact on the decisions.     

Towards data-driven car-following models

Car following models have been studied with many diverse approaches for decades. Nowadays, technological advances have significantly improved our traffic data collection capabilities. Conventional car following models rely on mathematical formulas and are derived from traffic flow theory; a property that often makes them more restrictive. On the other hand, data-driven approaches are more flexible and allow the incorporation of additional information to the model; however, they may not provide as much insight into traffic flow theory as the traditional models. In this research, an innovative methodological framework based on a data-driven approach is proposed for the estimation of car-following models, suitable for incorporation into microscopic traffic simulation models. An existing technique, i.e. locally weighted regression (loess), is defined through an optimization problem and is employed in a novel way. The proposed methodology is demonstrated using data collected from a sequence of instrumented vehicles in Naples, Italy. Gipps’ model, one of the most extensively used car-following models, is calibrated against the same data and used as a reference benchmark. Optimization issues are raised in both cases. The obtained results suggest that data-driven car-following models could be a promising research direction.     

The validity of using activity type to structure tour-based scheduling models

A unique set of activity scheduling data is utilized in this paper to provide much needed empirical analysis of the sequence in which activities are planned in everyday life. This is used to assess the validity of the assumption that activities are planned in accordance to a fixed hierarchy of activity types: mandatory activities first (work/school), followed by joint maintenance, joint discretionary, allocated maintenance, and individual discretionary activities. Such an assumption is typical of current generation activity and tour-based travel demand models. However, the empirical results clearly do not support such assumptions. For instance, fewer than 50% of mandatory activities were actually planned first in related out-of-home tours; remaining activity types also did not take any particular precedence in the planning sequence. Given this, a search was made for the more salient attributes of activities (beyond activity type) that would better predict how they are planned within tours. Several ordered response choice models for different tour sizes were developed for this purpose, predicting the choice order of the 1st, 2nd, 3rd, etc. planned activity in the tour as a function of activity type, activity characteristics (duration, frequency, travel time, and involved persons), and individual characteristics. Activity duration played the most significant role in the models compared to any other single variable, wherein longer duration activities tended to be planned much earlier in tours. This strongly suggests that the amount of time-use, rather than the nature of the event as indicated by activity type, is a primary driver of within-tour planning order and offers potential for a much improved and valid fit.     

Can scale and coefficient heterogeneity be separated in random coefficients models?

There is growing interest in the notion that a significant component of the heterogeneity retrieved in random coefficients models may actually relate to variations in absolute sensitivities, a phenomenon referred to as scale heterogeneity. As a result, a number of authors have tried to explicitly model such scale heterogeneity, which is shared across coefficients, and separate it from heterogeneity in individual coefficients. This direction of work has in part motivated the development of specialised modelling tools such as the G-MNL model. While not disagreeing with the notion that scale heterogeneity across respondents exists, this paper argues that attempts in the literature to disentangle scale heterogeneity from heterogeneity in individual coefficients in discrete choice models are misguided. In particular, we show how the various model specifications can in fact simply be seen as different parameterisations, and that any gains in fit obtained in random scale models are the result of using more flexible distributions, rather than an ability to capture scale heterogeneity. We illustrate our arguments through an empirical example and show how the conclusions from past work are based on misinterpretations of model results.     

An investigation of tour generation models combining two waves of household travel surveys through pooled models

This paper presents a study that examines two waves of travel survey data through a pooled model structure. The pooled model structure provides a means to take advantage of multiple data sources which will lead to a better estimate and understanding of travel behavior. In particular, it accounts for the difference in data variance and therefore allows for the comparison of the true impacts of the model parameters on travelers’ tour-making behavior. Larger variance is found in the 1998 data than in the 2010 data. Comparison between model parameters reveals significant behavioral changes among several socio-economic and demographic groups. In terms of common variables, the magnitude of the coefficient values has generally decreased, which conforms to the overall decreasing trend in traveling. Overall, the model equality tests indicate that the models developed based on the two data sources do not have equal taste parameters, thus the transferability hypothesis is rejected. The results of this study are expected to have implications for the application of models based on cross-sectional data, especially over long time periods.     

Statistical models of discrete choice processes

A number of problems studied in the transportation literature, such as automobile choice, motorist route choice, and transportation mode choice, involve an agent who makes a series of discrete choices over time. This paper presents statistical models and estimation methods for such discrete choice processes, and illustrates potential applications of these methods to the transportation literature.     

Estimation of infrastructure performance models using state-space specifications of time series models

We consider state-space specifications of autoregressive moving average models (ARMA) and structural time series models as a framework to formulate and estimate inspection and deterioration models for transportation infrastructure facilities. The framework provides a rigorous approach to exploit the abundance and breadth of condition data generated by advanced inspection technologies. From a managerial perspective, the framework is attractive because the ensuing models can be used to forecast infrastructure condition in a manner that is useful to support maintenance and repair optimization, and thus they constitute an alternative to Markovian transition probabilities. To illustrate the methodology, we develop performance models for asphalt pavements. Pressure and deflection measurements generated by pressure sensors and a falling weight deflectometer, respectively, are represented as manifestations of the pavement’s elasticity/load-bearing capacity. The numerical results highlight the advantages of the two classes of models; that is, ARMA models have superior data-fitting capabilities, while structural time series models are parsimonious and provide a framework to identify components, such as trend, seasonality and random errors. We use the numerical examples to show how the framework can accommodate missing values, and also to discuss how the results can be used to evaluate and select between inspection technologies.     

The construction and use of continuous autoregressive models for traffic indices

This article discusses the use of continuous autoregressive models to describe the behavior of traffic indices. From discretely sampled data, second-order differential equation models are constructed to represent dynamic traffic fluctuations as the response of a linear system to a stochastic forcing function. The results are compared to the more common M/G/∞ queueing model approach, and the analysis is demonstrated on time series of aircraft concentration in thirty-one enroute air traffic control sectors.     

Comparison and evaluation of several mobile-source and line-source models in Israel

This study compares several transportation-related air quality models. Two line-source models were used: Caline4 (California Department of Transportation) and Hiway2 (US Environmental Protection Agency). Two mobile-source models, Mobile5b (US Environmental Protection Agency) and COPERT3 (European Environment Agency), along with real-world emission factors were used and evaluated as well. Model predictions of NO_x concentrations were compared to measured values at two sites in Israel, differing by fleet composition and physical layout (‘at-grade’ and a ‘cut/depressed’ road sections). The process indicated that emission factors generated by COPERT3 are the most appropriate for free flowing traffic situations in Israel. Predictions by both line-source models were similar when applied to ‘at-grade’ road sections. When applied to ‘cut/depressed’ sections, Hiway2 better predicted concentrations during unstable conditions, while Caline4 better predicted concentrations during stable conditions and peak concentrations.     

City delineation in European applications of LUTI models: review and tests

This paper stresses the lack of attention paid to the geographical definitions of cities in LUTI models as one key detrimental aspect to transferring and generalising LUTI results. First, the argumentation develops from a meta-analysis of peer-reviewed publications about LUTI applications in European cities. We show that most authors do not assess findings against potential geographical biases. Second, theoretical simulations are conducted with UrbanSim applied to a synthetic urban area. By varying the geographical limits of the system and population endowments, our simulations confirm that the absence of control on city delineation weakens the results. Finally, the paper suggests methodological guidelines to improve the comparability of LUTI applications and push forward their theoretical agenda.     

Recovery of inter- and intra-personal heterogeneity using mixed logit models

Most applications of discrete choice models in transportation now utilise a random coefficient specification, such as mixed logit, to represent taste heterogeneity. However, little is known about the ability of these models to capture the heterogeneity in finite samples (as opposed to asymptotically). Also, due to the computational intensity of the standard estimation procedures, several alternative, less demanding methods have been proposed, and yet the relative accuracy of these methods has not been investigated. This is especially true in the context of work looking at joint inter-respondent and intra-respondent variation. This paper presents an overview of the various different estimators, gives insights into some of the theoretical properties, and analyses their performance in a large scale study on simulated data. In particular, we specify 31 different forms of heterogeneity, with multiple versions of each dataset, and with results from over 16,000 mixed logit estimation runs. The findings suggest that variation in tastes over consumers is captured by all the methods, including the simpler versions, at least when sample size is sufficiently large. When tastes vary over choice situations for each consumer, as well as over consumers, the ability of the methods to capture and differentiate the two sources of heterogeneity becomes more tenuous. Only the most computationally intensive approach is able to capture adequately the two sources of variation, but at the cost of very high run times. Our results highlight the difficulty of retrieving taste heterogeneity with only cross-sectional data, providing further evidence of the benefits of repeated choice data. Our findings also suggest that the data requirements of random coefficients models may be more substantial than is commonly assumed, further reinforcing concerns about small sample issues.