nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2020‒11‒09
four papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks By Shenhao Wang; Baichuan Mo; Jinhua Zhao
  2. Representing travel cost variation in large-scale models of long-distance passenger transport By Kristoffersson, Ida; Daly, Andrew; Algers, Staffan; Svalgård-Jarcem, Stehn
  3. The relationship between driving volatility in time to collision and crash injury severity in a naturalistic driving environment By Behram Wali; Asad Khattak; Thomas Karnowski
  4. Electric Street Car as a Clean Public Transport Alternative: A Choice Experiment Approach By Oindrila Dey; Debalina Chakravarty

  1. By: Shenhao Wang; Baichuan Mo; Jinhua Zhao
    Abstract: Researchers often treat data-driven and theory-driven models as two disparate or even conflicting methods in travel behavior analysis. However, the two methods are highly complementary because data-driven methods are more predictive but less interpretable and robust, while theory-driven methods are more interpretable and robust but less predictive. Using their complementary nature, this study designs a theory-based residual neural network (TB-ResNet) framework, which synergizes discrete choice models (DCMs) and deep neural networks (DNNs) based on their shared utility interpretation. The TB-ResNet framework is simple, as it uses a ($\delta$, 1-$\delta$) weighting to take advantage of DCMs' simplicity and DNNs' richness, and to prevent underfitting from the DCMs and overfitting from the DNNs. This framework is also flexible: three instances of TB-ResNets are designed based on multinomial logit model (MNL-ResNets), prospect theory (PT-ResNets), and hyperbolic discounting (HD-ResNets), which are tested on three data sets. Compared to pure DCMs, the TB-ResNets provide greater prediction accuracy and reveal a richer set of behavioral mechanisms owing to the utility function augmented by the DNN component in the TB-ResNets. Compared to pure DNNs, the TB-ResNets can modestly improve prediction and significantly improve interpretation and robustness, because the DCM component in the TB-ResNets stabilizes the utility functions and input gradients. Overall, this study demonstrates that it is both feasible and desirable to synergize DCMs and DNNs by combining their utility specifications under a TB-ResNet framework. Although some limitations remain, this TB-ResNet framework is an important first step to create mutual benefits between DCMs and DNNs for travel behavior modeling, with joint improvement in prediction, interpretation, and robustness.
    Date: 2020–10
  2. By: Kristoffersson, Ida (Research Programme in Transport Economics); Daly, Andrew (University of Leeds); Algers, Staffan (TPMod); Svalgård-Jarcem, Stehn (WSP Advisory)
    Abstract: In this paper we show that travel cost variation for long-distance travel is often substantial, even within a given mode, and we discuss why it is likely to increase further in the future. Thus, the current praxis in large-scale models to set one single travel cost for a combination of origin, destination, mode, and purpose, has potential for improvement. To tackle this issue, we develop ways of accounting for cost variation in model estimation and forecasting. For public transport, two methods are developed, where the first method focuses on improving the average fare, whereas the second method incorporates a submodel for choice of fare alternative within a demand model structure. Only the second method is consistent with random utility theory. For car, cost variation is related to long run decisions such as car type choice and employment location. Handling car cost variation therefore implies considering car type choice and workplace choice rather than different options related to a specific trip. These long-term choices can be considered using a car fleet model.
    Keywords: Long-distance travel; Travel cost; Travel fare; Large-scale model; Demand model
    JEL: R40
    Date: 2020–10–28
  3. By: Behram Wali; Asad Khattak; Thomas Karnowski
    Abstract: As a key indicator of unsafe driving, driving volatility characterizes the variations in microscopic driving decisions. This study characterizes volatility in longitudinal and lateral driving decisions and examines the links between driving volatility in time to collision and crash injury severity. By using a unique real-world naturalistic driving database from the 2nd Strategic Highway Research Program (SHRP), a test set of 671 crash events featuring around 0.2 million temporal samples of real world driving are analyzed. Based on different driving performance measures, 16 different volatility indices are created. To explore the relationships between crash-injury severity outcomes and driving volatility, the volatility indices are then linked with individual crash events including information on crash severity, drivers' pre crash maneuvers and behaviors, secondary tasks and durations, and other factors. As driving volatility prior to crash involvement can have different components, an indepth analysis is conducted using the aggregate as well as segmented (based on time to collision) real world driving data. To account for the issues of observed and unobserved heterogeneity, fixed and random parameter logit models with heterogeneity in parameter means and variances are estimated. The empirical results offer important insights regarding how driving volatility in time to collision relates to crash severity outcomes. Overall, statistically significant positive correlations are found between the aggregate (as well as segmented) volatility measures and crash severity outcomes. The findings suggest that greater driving volatility (both in longitudinal and lateral direction) in time to collision increases the likelihood of police reportable or most severe crash events... ...
    Date: 2020–10
  4. By: Oindrila Dey (Indian Institute of Foreign Trade (IIFT)); Debalina Chakravarty (Indian Institute of Management (IIM) Calcutta)
    Abstract: Electric Street Car (ESC) has established itself as an ideal public transport system for urban agglomeration by offering better safety, minimum pollution and conservation of fossil fuel. Yet, India envisions going all-electric by 2030 by procuring electric buses (e-buses) rather than ESCs. The crucial question is, why not upgrade the existing ESC considering that the e-buses need a profound infrastructural development in India. This paper studies the potential uptake rate of ESC over e-buses using stratified sampling data from 1226 daily public transport commuters of Kolkata, the only Indian city having an operational ESCs. We identify the demographic, psychometric and socio-economic factors influencing the probabilistic uptake of ESC over e-buses using a random utility choice model. It estimates that 38% of the commuters demand ESC over e-buses given the alternatives’ comparative details. ESC can be a model electric public transport if there is an improvement in factors, like frequent availability of ESCs and technological upgradation. By promoting the ESC services over e-buses, the government can potentially save on public investment and reach a low carbon pathway cost-effectively. The findings have crucial implications in exploration of the operational feasibility of ESC in the small and medium-sized cities of developing economies like India.
    Keywords: Public Transport, Electric Bus, Electric Street Car, Sustainability, Urban Area
    JEL: R58 R49 Q56 Q40
    Date: 2020–10

This nep-dcm issue is ©2020 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.