Modeling unobserved heterogeneity using finite mixture random parameters for spatially correlated discrete count data

Road segments with identical site-specific attributes often exhibit significantly different crash counts due to unobserved reasons. The extent of unobserved heterogeneity associated with a road feature is to be estimated prior to selecting the relevant safety treatment. Moreover, crash count data is often over-dispersed and spatially correlated. This paper proposes a spatial negative binomial specification with random parameters for modeling crash counts of contiguous road segments. The unobserved heterogeneity is incorporated using a finite multi-variate normal mixture prior on the random parameters; this allows for non-normality, skewness in the distribution of the random parameters, facilitates correlation across the random parameters, and relaxes any distributional assumptions. The model extracts the inherent groups of road segments with crash counts that are equally sensitive to the road attributes on an average; the heterogeneity within these groups is also allowed in the proposed framework. The specification simultaneously accounts for potential spatial correlation of the crash counts from neighboring road segments. A Gibbs sampling framework is proposed that leverages recent theoretical developments on data-augmentation algorithms, and elegantly sidesteps many of the computational difficulties usually associated with Bayesian inference of count models. Empirical results suggests the presence of two latent groups and spatial correlation within the study road network. Road features with significantly different effect on crash counts across two latent groups of road segments were identified.     

A joint flexible econometric model system of household residential location and vehicle fleet composition/usage choices

Modeling the interaction between the built environment and travel behavior is of much interest to transportation planning professionals due to the desire to curb vehicular travel demand through modifications to built environment attributes. However, such models need to take into account self-selection effects in residential location choice, wherein households choose to reside in neighborhoods and built environments that are conducive to their lifestyle preferences and attitudes. This phenomenon, well-recognized in the literature, calls for the specification and estimation of joint models of multi-dimensional land use and travel choice processes. However, the estimation of such model systems that explicitly account for the presence of unobserved factors that jointly impact multiple choice dimensions is extremely complex and computationally intensive. This paper presents a joint GEV-based logit regression model of residential location choice, vehicle count by type choice, and vehicle usage (vehicle miles of travel) using a copula-based framework that facilitates the estimation of joint equations systems with error dependence structures within a simple and flexible closed-form analytic framework. The model system is estimated on a sample derived from the 2000 San Francisco Bay Area Household Travel Survey. Estimation results show that there is significant dependency among the choice dimensions and that self-selection effects cannot be ignored when modeling land use-travel behavior interactions.     

Comparisons of the environmental footprint of heavy vehicles in the UK and Switzerland

The European Union project Eureka Logchain Footprint is an ongoing project to identify road and rail vehicles by means of their environmental footprint as characterised by dynamic load, noise, ground borne vibrations and gaseous emissions induced by the vehicle. Part of the project involves the installation of road and rail footprint monitoring stations throughout Europe. This paper presents results of the road stations in Switzerland and the UK. Individual vehicle data from weigh-in-motion and noise are compared. The results indicate that a significant number of vehicles surpass the limits set in both countries. It was shown that the UK sites are generating higher noise levels than their Swiss counterparts; in part due to the much coarser aggregate embedded in the running course of the pavement employed in the UK. Such data can be used to create an incentive for vehicle types with a low footprint and a penalty for vehicles with a large footprint.     

Estimation of road traffic noise emissions: The influence of speed and acceleration

This paper relies on vehicle trajectory collection on a corridor, to compare different traffic representations used for the estimation of the sound power of light vehicles and the resulting sound pressure levels. Four noise emission models are tested. The error introduced when the emissions are calculated based on speeds measured at regular intervals along the road network are quantified and explained. The current noise emission models might in particular misestimate noise levels under congestion. This bias can be reduced by introducing additional traffic variables in the modeling. In addition, significant differences within the models are highlighted, especially concerning their accounting of vehicle accelerations. Models that rely on a binary representation of acceleration regimes (a vehicle or a road segment is accelerating or not) can lead to errors in practice. Models under use in Europe have a very low sensitivity to acceleration values. These results help underlying the further required improvements of dynamic road traffic noise models.     

Rebound effects in UK road freight transport

This paper analyses aggregate time-series data to estimate the direct rebound effect in UK road freight over the period 1970–2014. We investigate 25 different model specifications, conduct a comprehensive set of diagnostic tests to evaluate the robustness of these specifications and estimate the rebound effect using three different elasticities. Using the mean of the statistically significant estimates from these specifications, we estimate a direct rebound effect of 61% - which is larger than previous estimates in the literature and almost twice as large as the consensus estimate of direct rebound effects in road passenger transport. Using the mean of the estimates from our most robust models, we estimate a slightly lower direct rebound effect of 49%. Our estimates are fairly consistent between different model specifications and different metrics, although individual estimates range from 21% to 137%. We also find that an increasing proportion of UK road freight is being undertaken by foreign registered vehicles, and that increases in the vehicle weight limits have encouraged more freight activity. We highlight the significant limitations imposed by the use of aggregate time series data and recommend that further studies in this area employ data from vehicle use surveys.     

A nonparametric approach to the incorporation of heterogeneity into repeated polytomous choice models of urban shopping behaviour

Longitudinal discrete choice models which use a mixing distribution to control for unobserved heterogeneity, and which are estimated by a nonparametric maximum likelihood mass point procedure, have so far been restricted to the analysis of dichotomous choices. This paper extends mass point methods to the case of polytomous choice problems and in so doing makes an important contribution to the analysis of longitudinal data and dynamic discrete choice models. The paper concludes with an empirical assessment of the performance of mass point methods in the analysis of urban shopping behaviour, using short-term panel data from the Cardiff Consumer Panel.     

Modelling acceleration decisions in traffic streams with weak lane discipline: A latent leader approach

Acceleration is an important driving manoeuvre that has been modelled for decades as a critical element of the microscopic traffic simulation tools. The state-of-the art acceleration models have however primarily focused on lane based traffic. In lane based traffic, every driver has a single distinct lead vehicle in the front and the acceleration of the driver is typically modelled as a function of the relative speed, position and/or type of the corresponding leader. On the contrary, in a traffic stream with weak lane discipline, the subject driver may have multiple vehicles in the front. The subject driver is therefore subjected to multiple sources of stimulus for acceleration and reacts to the stimulus from the governing leader. However, only the applied accelerations are observed in the trajectory data, and the governing leader is unobserved or latent. The state-of-the-art models therefore cannot be directly applied to traffic streams with weak lane discipline.This prompts the current research where we present a latent leader acceleration model. The model has two components: a random utility based dynamic class membership model (latent leader component) and a class-specific acceleration model (acceleration component). The parameters of the model have been calibrated using detailed trajectory data collected from Dhaka, Bangladesh. Results indicate that the probability of a given front vehicle of being the governing leader can depend on the type of the lead vehicle and the extent of lateral overlap with the subject driver. The estimation results are compared against a simpler acceleration model (where the leader is determined deterministically) and a significant improvement in the goodness-of-fit is observed. The proposed models, when implemented in microscopic traffic simulation tools, are expected to result more realistic representation of traffic streams with weak lane discipline.     

A dynamic analysis of household car ownership

This paper examines the determinants of household car ownership, using Irish longitudinal data for the period 1995–2001. This was a period of rapid economic and social change in Ireland, with the proportion of households with one or more cars growing from 74.6% to 80.8%. Understanding the determinants of household car ownership, a key determinant of household travel behaviour more generally, is particularly important in the context of current policy developments which seek to encourage more sustainable means of travel. In this paper, we use longitudinal data to estimate dynamic models of household car ownership, controlling for unobserved heterogeneity and state dependence. We find income and previous car ownership to be the strongest determinants of differences in household car ownership, with the effect of permanent income having a stronger and more significant effect on the probability of household car ownership than current income. In addition, income elasticities differ by previous car ownership status, with income elasticities higher for those households with no car in the initial period. Other important influences include household composition (in particular, the presence of young children) and lifecycle effects, which create challenges for policymakers in seeking to change travel behaviour.     

Does winter road maintenance help reduce air emissions and fuel consumption?

Winter road maintenance (WRM) has been shown to have significant benefits of improving road safety and reducing traffic delay caused by adverse weather conditions. It has also been suggested that WRM is also beneficial in terms of reducing vehicular air emissions and fuel consumptions because snow and ice on road surface often cause the drivers to reduce their vehicle speeds or to switch to high gears, thus decreasing fuel combustion efficiency. However, there has been very limited information about the underlying relationship, which is important for quantifying this particular benefit of a winter road maintenance program. This research is focused on establishing a quantitative relationship between winter road surface conditions and vehicular air emissions. Speed distribution models are developed for the selected Ontario highways using data from 22 road sites across the province of Ontario, Canada. The vehicular air emissions under different road surface conditions are calculated by coupling the speed models with the engine emission models integrated in the emission estimation model - MOVES. It was found that, on the average, a 10% improvement in road surface conditions could result in approximately 0.6–2% reduction in air emissions. Application of the proposed methodology is demonstrated through a case study to analyse the air emission and energy consumption effects under specific weather events.     

Alternative Modeling Approaches Used for Examining Automobile Ownership: A Comprehensive Review

Abstract

Household vehicle ownership, and the associated dimensions including fleet size, vehicle type and usage, has been one of the most researched transport topics. This paper endeavors to provide a critical overview of the wide-ranging methodological approaches employed in vehicle ownership modeling depending on the ownership representation over the past two decades. The studies in the existing literature based on the vehicle ownership representation are classified as: exogenous static, exogenous dynamic, endogenous static and endogenous dynamic models. The methodological approaches applied range from simple linear regressions to complex econometrics formulations taking into account a rich set of covariates. In spite of the steady advancement and impressive evolution in terms of methodological approaches to examine the decision process, we identify complex issues that pose a formidable challenge to address the evolution of vehicle ownership in the coming years. Specifically, we discuss challenges with data availability and methodological framework selection. In light of these discussions, we provide a decision matrix for aiding researchers/practitioners in determining appropriate model frameworks for conducting vehicle ownership analysis.     

A finite mixture model of vehicle-to-vehicle and day-to-day variability of traffic network travel times

This study proposes an approach to modeling the effects of daily roadway conditions on travel time variability using a finite mixture model based on the Gamma–Gamma (GG) distribution. The GG distribution is a compound distribution derived from the product of two Gamma random variates, which represent vehicle-to-vehicle and day-to-day variability, respectively. It provides a systematic way of investigating different variability dimensions reflected in travel time data. To identify the underlying distribution of each type of variability, this study first decomposes a mixture of Gamma–Gamma models into two separate Gamma mixture modeling problems and estimates the respective parameters using the Expectation–Maximization (EM) algorithm. The proposed methodology is demonstrated using simulated vehicle trajectories produced under daily scenarios constructed from historical weather and accident data. The parameter estimation results suggest that day-to-day variability exhibits clear heterogeneity under different weather conditions: clear versus rainy or snowy days, whereas the same weather conditions have little impact on vehicle-to-vehicle variability. Next, a two-component Gamma–Gamma mixture model is specified. The results of the distribution fitting show that the mixture model provides better fits to travel delay observations than the standard (one-component) Gamma–Gamma model. The proposed method, the application of the compound Gamma distribution combined with a mixture modeling approach, provides a powerful and flexible tool to capture not only different types of variability—vehicle-to-vehicle and day-to-day variability—but also the unobserved heterogeneity within these variability types, thereby allowing the modeling of the underlying distributions of individual travel delays across different days with varying roadway disruption levels in a more effective and systematic way.     

Modeling the choice continuum: an integrated model of residential location,auto ownership,bicycle ownership,and commute tour mode choice decisions

The integrated modeling of land use and transportation choices involves analyzing a continuum of choices that characterize people’s lifestyles across temporal scales. This includes long-term choices such as residential and work location choices that affect land-use, medium-term choices such as vehicle ownership, and short-term choices such as travel mode choice that affect travel demand. Prior research in this area has been limited by the complexities associated with the development of integrated model systems that combine the long-, medium- and short-term choices into a unified analytical framework. This paper presents an integrated simultaneous multi-dimensional choice model of residential location, auto ownership, bicycle ownership, and commute tour mode choices using a mixed multidimensional choice modeling methodology. Model estimation results using the San Francisco Bay Area highlight a series of interdependencies among the multi-dimensional choice processes. The interdependencies include: (1) self-selection effects due to observed and unobserved factors, where households locate based on lifestyle and mobility preferences, (2) endogeneity effects, where any one choice dimension is not exogenous to another, but is endogenous to the system as a whole, (3) correlated error structures, where common unobserved factors significantly and simultaneously impact multiple choice dimensions, and (4) unobserved heterogeneity, where decision-makers show significant variation in sensitivity to explanatory variables due to unobserved factors. From a policy standpoint, to be able to forecast the “true” causal influence of activity-travel environment changes on residential location, auto/bicycle ownership, and commute mode choices, it is necessary to capture the above-identified interdependencies by jointly modeling the multiple choice dimensions in an integrated framework.     

Modelling the dynamics of bus use in a changing travel environment using panel data

Panel data offers the potential to represent the influence on travel choices of changing circumstances, past history and persistent individual differences (unobserved heterogeneity). A four-wave panel survey collected data on the travel choices of residents before and after the introduction of a new bus rapid transit service. The data shows gradual changes to bus use over the four waves, implying time was required for residents to become aware of the new service and to adapt to it. Ordered response models are estimated for bus use over the survey period. The results show that the influence of level of service (LOS) is underestimated if unobserved heterogeneity is not taken into account. The delayed response to the new service is able to be well represented by including LOS as a lagged variable. Current bus use is found to be conditioned on past bus use, but with additional influence of lagged LOS and unobserved heterogeneity. It is shown how different model specifications generate different evolution patterns with the most realistic predictions arising from a model which takes into account lagged responses to change in LOS and unobserved heterogeneity. The paper demonstrates the feasibility of developing panel data models that can be applied to forecasting the effect of interventions in the travel environment. Longer panels—encompassing periods of both stability and change—are required to support future efforts at modelling travel choice dynamics.     

Estimating automobile utilisation with panel data: An investigation of alternative assumptions for the initial conditions and error covariances

This paper illustrates how recent developments in the econometrics of panel data analysis can be implemented in the study of the dynamics of continuous choice. Adopting the household's annual use of automobiles as the empirical setting with the data defined as a four-wave panel, we outline alternative assumptions for representing the role of unobserved heterogeneity, in particular the initial conditions, and the correlational structure between the observed and unobserved influences on choice. We show the importance of treating the initial conditions as endogenous. With the growing interest in integrating discrete and continuous choice models, typically through the application of the idea of selectivity, more thought has to be given to the error structure of the continuous choice module when the panel is short, as is so often the empirical reality. The simple application of econometric methods developed for long time series can be quite misleading.     

Improved vehicle classification from dual-loop detectors in congested traffic

Vehicle classification is an important traffic parameter for transportation planning and infrastructure management. Length-based vehicle classification from dual loop detectors is among the lowest cost technologies commonly used for collecting these data. Like many vehicle classification technologies, the dual loop approach works well in free flow traffic. Effective vehicle lengths are measured from the quotient of the detector dwell time and vehicle traversal time between the paired loops. This approach implicitly assumes that vehicle acceleration is negligible, but unfortunately at low speeds this assumption is invalid and length-based classification performance degrades in congestion.To addresses this problem, we seek a solution that relies strictly on the measured effective vehicle length and measured speed. We analytically evaluate the feasible range of true effective vehicle lengths that could underlie a given combination of measured effective vehicle length, measured speed, and unobserved acceleration at a dual loop detector. From this analysis we find that there are small uncertainty zones where the measured length class can differ from the true length class, depending on the unobserved acceleration. In other words, a given combination of measured speed and measured effective vehicle length falling in the uncertainty zones could arise from vehicles with different true length classes. Outside of the uncertainty zones, any error in the measured effective vehicle length due to acceleration will not lead to an error in the measured length class. Thus, by mapping these uncertainty zones, most vehicles can be accurately sorted to a single length class, while the few vehicles that fall within the uncertainty zones are assigned to two or more classes. We find that these uncertainty zones remain small down to about 10 mph and then grow exponentially as speeds drop further.Using empirical data from stop-and-go traffic at a well-tuned loop detector station the best conventional approach does surprisingly well; however, our new approach does even better, reducing the classification error rate due to acceleration by at least a factor of four relative to the best conventional method. Meanwhile, our approach still assigns over 98% of the vehicles to a single class.     

Analysis of vehicle ownership evolution in Montreal,Canada using pseudo panel analysis

This paper employs a pseudo-panel approach to study vehicle ownership evolution in Montreal region, Canada using cross-sectional origin–destination survey datasets of 1998, 2003 and 2008. Econometric modeling approaches that simultaneously accommodate the influence of observed and unobserved attributes on the vehicle ownership decision framework are implemented. Specifically, we estimate generalized versions of the ordered response model—including the generalized, scaled- and mixed-generalized ordered logit models. Socio-demographic variables that impact household’s decision to own multiple cars include number of full and part-time working adults, license holders, middle aged adults, retirees, male householders, and presence of children. Increased number of bus stops, longer bus and metro lengths within the household residential location buffer area decrease vehicle fleet size of households. The observed results also varied across years as manifested by the significance of the interaction terms of some of the variables with the time elapsed since 1998 variable. Moreover, variation due to unobserved factors are captured for part-time working adults, number of bus stops, and length of metro lines. In terms of the effect of location of households, we found that some neighborhoods exhibited distinct car ownership temporal dynamics over the years.     

The joint analysis of injury severity of drivers in two-vehicle crashes accommodating seat belt use endogeneity

The current study contributes to the existing injury severity modeling literature by developing a multivariate probit model of injury severity and seat belt use decisions of both drivers involved in two-vehicle crashes. The modeling approach enables the joint modeling of the injury severity of multiple individuals involved in a crash, while also recognizing the endogeneity of seat belt use in predicting injury severity levels as well as accommodating unobserved heterogeneity in the effects of variables. The proposed model is applied to analyze the injury severity of drivers involved in two-vehicle road crashes in Denmark.The empirical analysis provides strong support for the notion that people offset the restraint benefits of seat belt use by driving more aggressively. Also, men and those individuals driving heavy vehicles have a lower injury risk than women and those driving lighter vehicles, respectively. At the same time, men and individuals driving heavy vehicles pose more of a danger to other drivers on the roadway when involved in a crash. Other important determinants of injury severity include speed limit on roadways where crash occurs, the presence (or absence) of center dividers (median barriers), and whether the crash involves a head-on collision. These and other results are discussed, along with implications for countermeasures to reduce injury severities in crashes. The analysis also underscores the importance of considering injury severity at a crash level, while accommodating seat belt endogeneity effects and unobserved heterogeneity effects.     

Explaining light vehicle demand evolution in interurban toll roads: a dynamic panel data analysis in Spain

Tolls have increasingly become a common mechanism to fund road projects in recent decades. Therefore, improving knowledge of demand behavior constitutes a key aspect for stakeholders dealing with the management of toll roads. However, the literature concerning demand elasticity estimates for interurban toll roads is still limited due to their relatively scarce number in the international context. Furthermore, existing research has left some aspects to be investigated, among others, the choice of GDP as the most common socioeconomic variable to explain traffic growth over time. This paper intends to determine the variables that better explain the evolution of light vehicle demand in toll roads throughout the years. To that end, we establish a dynamic panel data methodology aimed at identifying the key socioeconomic variables explaining changes in light vehicle demand over time. The results show that, despite some usefulness, GDP does not constitute the most appropriate explanatory variable, while other parameters such as employment or GDP per capita lead to more stable and consistent results. The methodology is applied to Spanish toll roads for the 1990–2011 period, which constitutes a very interesting case on variations in toll road use, as road demand has experienced a significant decrease since the beginning of the economic crisis in 2008.     

Estimating a model of dynamic activity generation based on one-day observations: Method and results

In this paper we develop and explore an approach to estimate dynamic models of activity generation on one-day travel-diary data. Dynamic models predict multi-day activity patterns of individuals taking into account dynamic needs as well as day-varying preferences and time-budgets. We formulate an ordered-logit model of dynamic activity-agenda-formation decisions and show how one-day observation probabilities can be derived from the model as a function of the model’s parameters and, with that, how parameters can be estimated using standard loglikelihood estimation. A scale parameter cannot be identified because information on within-person variability is lacking in one-day data. An application of the method to data from a national travel survey illustrates the method. A test on simulated data indicates that, given a pre-set scale, the parameters can be identified and that estimates are robust for a source of heterogeneity not captured in the model. This result indicates that dynamic activity-based models of the kind considered here can be estimated from data that are less costly to collect and that support the large sample sizes typically required for travel-demand modeling. We conclude therefore that the proposed approach opens up a way to develop large-scale dynamic activity-based models of travel demand.     

Recent developments in the econometrics of panel data analysis

The present paper surveys different issues related to the econometric analysis of panel data. It discusses the controversy over fixed effects vs. random effects models, specification error tests with panel data, the problem of specification of the distribution of initial values in dynamic models, maximum-likelihood estimation of dynamic models, tests for serial correlation with panel data, serial correlation vs. state dependence, multiple equation models with panel data, and errors in variables in panel data. References are also given for certain other miscellaneous problems involving panel data.