A hybrid choice model with a nonlinear utility function and bounded distribution for latent variables: application to purchase intention decisions of electric cars

Kim, Jinhee; Rasouli, Soora; Timmermans, Hjp Harry

doi:10.1080/23249935.2016.1193567

Cited by 22 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alongside numerous empirical applications, further refinements of the model framework have taken place, looking at the specification of the measurement model (Daly et al, 2012), how and where to incorporate the latent variables into the choice model (Bahamonde-Birke et al, 2017) and testing for non-linearity and distributional assumptions (Kim et al, 2016). Substantial efforts have also gone into improved estimation techniques for the model and proper identification (Bhat & Dubey, 2014;Daziano, 2015;Raveau et al, 2012;Vij & Walker, 2014).…”

Section: Introductionmentioning

confidence: 99%

Analysis of mode choice for intercity travel: Application of a hybrid choice model to two distinct US corridors

Hess

Spitz

Bradley

et al. 2018

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

With growing concerns about greenhouse gas emissions and traffic congestion, there is an emphasis on encouraging shifts to public transport, for both short and long distance travel. Major differences exist across countries in how successful these efforts are, and the United States is often used as the key example of a country with a strong resistance to shifting away from private car use. Even within the United States however, there is strong heterogeneity across regions and across different types of travellers. This paper seeks to add empirical evidence to understand the drivers of mode choice for intercity travel, using stated choice data from two major US intercity corridors: the Northeast Corridor (NEC) and the Cascade Corridor. We develop a hybrid choice model that allows for deterministic and random variations across travellers in their preferences, some of which can be linked to underlying attitudinal constructs. Our results highlight extensive heterogeneity and provide interesting insights into the drivers of behaviour, and the relationship between attitudes and actual choices. As an example, we see that for some groups, notably West Coast respondents, a stronger anti-car attitude is counteracted by a reduced utility for non-car modes when making choices, possibly due quality of public transport provision. Similarly, for other groups, such as older and female travellers, a reduced concern for privacy, which would benefit public transport, is counteracted by a stronger pro-car attitude. These findings highlight the complex way in which attitudes can influence choices and provide insights for targeted policy interventions. Through scenario testing, we also show how future modal split might change depending on how these patterns of heterogeneity evolve over time, noting that the way this might happen is of course unknown at present.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of mode choice for intercity travel: Application of a hybrid choice model to two distinct US corridors

Hess

Spitz

Bradley

et al. 2018

Transportation Research Part A: Policy and Practice

View full text Add to dashboard Cite

show abstract

“…The physician's valuation of profit, patient health benefit, and patient consumption opportunity is captured by the preference parameters β π , β B and β C , respectively. The functional form of utility functions has been discussed in other economic applications (Keane & Moffitt, 1998;Kim et al, 2016;Koppelman, 1981;Van Soest, 1995), but less attention has been paid to the specifications of utility in the discrete choice literature within the health domain. In health economic applications, the most commonly assumed utility specification is linear additive in all choice attributes as in specification (3).…”

Section: A Model Of Discrete Treatment Choicementioning

confidence: 99%

Exploring physician agency under demand‐side cost sharing—An experimental approach

Godager

Wang

2022

Health Economics

View full text Add to dashboard Cite

Demand-side cost sharing in the health sector occurs when a patient is required to pay for a portion of medical treatment costs. Out-of-pocket payments by patients can take the form of co-payments according to a fixed fee schedule or specific co-insurance rates. Demand-side cost sharing can be the result of national policy in single-payer systems such as in the Scandinavian countries, where out-of pocket payments for various health services are set by the government. In markets where consumers may choose from several health insurance plans, the amount and specific features of demand-side cost sharing will typically vary substantially between plans, and plans with less cost sharing will necessarily imply higher premiums. Consumers purchasing health insurance in the United States can choose between alternative health insurance plans with different levels of demand-side cost sharing, and consumers may acquire health insurance with relatively low premiums in exchange for greater cost sharing (Pauly, 2017).The aim of our study is to contribute to knowledge on physician behavior in the context of demand-side cost sharing. Under demand-side cost sharing, the choice of treatment will influence both health benefits and consumption opportunities for patients. The optimal calibration of supply-and demand-side cost sharing has been shown to depend on physician preferences. This paper contributes to the literature on physician preferences in several respects: We acquire data by conducting a laboratory experiment where we attach real monetary incentives to three separate choice attributes. In addition to determining subjects' profit, the choices in the experiment determine the health benefits and the future consumption opportunity of a real patient admitted to the nearest hospital. To the best of our knowledge, this is the first

show abstract

“…Alongside numerous applications of SEM, HCM has been employed to account for a variety of attitudes in research on key decisions in the public transport context, such as mode choice (Atasoy et al 2013;Hess et al 2018;Kamargianni et al 2014;Roberts et al 2018;Song et al 2018;Tran et al 2020) and departure time choice (Thorhauge et al 2016). Additionally, substantial effort has been devoted to further refinement of the HCM framework in studies exploring the proper way to accommodate latent variables in choice models (Bahamonde-Birke et al 2017), testing non-linearity and distributional assumptions (Kim et al 2016), and seeking to improve estimation techniques (Bhat and Dubey 2014;Daziano 2015;Raveau et al 2012). To reveal the roles of SQ, OI, EA and SC in our research context, a detailed factor analysis is conducted in the data section to seek rational structures for these four attitudinal variables, as well as an HCM-based analytical framework for interpreting commuters' behavioural responses to metro TDM strategies.…”

Section: Literature Reviewmentioning

confidence: 99%

Understanding the effects of travel demand management on metro commuters’ behavioural loyalty: a hybrid choice modelling approach

2021

View full text Add to dashboard Cite

As part of efforts to promote sustainable mobility, many cities are currently experiencing the rapid expansion of their metro network. The consequent growth in ridership motivates a broad range of travel demand management (TDM) policies, both in terms of passenger flow control and dynamic pricing strategies. This work aims to reveal the impact of TDM on metro commuters' behavioural loyalty using stated preference data collected in Guangzhou, China. Commuters' behavioural response to TDM strategies is investigated in terms of the possible shift in departure time and travel mode. A hybrid choice model framework is used to incorporate four latent variables of interest, i.e., service quality, overall impression, external attractiveness and switching cost, into the discrete choice model and thereby capture the relationships between the attitudinal factors and observed variables. The model estimation results indicate that the four latent variables all prove useful in interpreting commuters' behavioural loyalty. Commuters' perceived service quality and overall impression both show a positive effect on their willingness to continue travelling by metro and are thus instructive for ridership retention. External attractiveness is found to be significant only in the case of the tendency to shift to a private car. Switching costs reveal commuters' emotional attachment to their already developed commuting habit. These insights into commuters' behavioural change intention enable metro operators to enhance commuters' loyalty to their service and develop more effective TDM strategies in future practice. Keywords behavioural change • nested logit model • attitude • factor analysis • SP-off-RP survey • urban rail transitSection 5 reports the model estimation results and discusses the policy implications. In the last section, the conclusions drawn from the above content are summarised, and directions for future work are discussed.

show abstract

A hybrid choice model with a nonlinear utility function and bounded distribution for latent variables: application to purchase intention decisions of electric cars

Cited by 22 publications

References 43 publications

Analysis of mode choice for intercity travel: Application of a hybrid choice model to two distinct US corridors

Analysis of mode choice for intercity travel: Application of a hybrid choice model to two distinct US corridors

Exploring physician agency under demand‐side cost sharing—An experimental approach

Understanding the effects of travel demand management on metro commuters’ behavioural loyalty: a hybrid choice modelling approach

Contact Info

Product

Resources

About