Evaluating the predictive abilities of mixed logit models with unobserved inter- and intra-individual heterogeneity

Krueger, Rico; Bierlaire, Michel; Daziano, Ricardo A.; Rashidi, Taha Hossein; Bansal, Prateek

doi:10.1016/j.jocm.2021.100323

Cited by 21 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the maintained conditions in this research is that individual parameters are considered constant across a set of replications. This restriction can of course be removed, as suggested by Swait et al (2016) for latent class (mixture) models, and more recently, by Kreuger et al (2021) for the Mixed Logit model. Both allow for intra-person variation in preference parameters, over and above inter-personal preference heterogeneity.…”

Section: Discussionmentioning

confidence: 99%

Distribution-free estimation of individual parameter logit (IPL) models using combined evolutionary and optimization algorithms

Swait́

2023

Journal of Choice Modelling

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Distribution-free estimation of individual parameter logit (IPL) models using combined evolutionary and optimization algorithms

Swait́

2023

Journal of Choice Modelling

View full text Add to dashboard Cite

“…where C n is the choice set; X it is the observed variable vector for mode i in scenario t; β ni is the corresponding coefficient vector for traveler n; and ε nit is the unobserved part of utility and is assumed to be independently and identically distributed according to Gumbel (0, 1) across travelers, choice scenarios, and modes. The Gumbel distribution of ε nit is different from the normal distribution of error term in traditional regression models (e.g., generalized linear models and CD production function) (Elahi et al, 2021;Krueger et al, 2021;Elahi et al, 2022;McFadden, 2022;Yang Y. et al, 2022).…”

Section: Model Specificationmentioning

confidence: 91%

Exploring the Role of Shared Mobility in Alleviating Private Car Dependence and On-Road Carbon Emissions in the Context of COVID-19

Zhang

Shao

Wang

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Shared mobility is becoming increasingly popular worldwide, and travelers show more complex choice preferences during the post-pandemic era. This study explored the role of shared mobility in the context of coronavirus disease (COVID-19) by comparing the travel mode choice behavior with and without shared mobility. Considering the shared mobility services of ride-hailing, ride-sharing, car-sharing, and bike-sharing, the stated preference survey was designed, and the mixed logit model with panel data was applied. The results show that if shared mobility is absent, approximately 50% of motorized mobility users and 84.62% of bike-sharing adopters will switch to using private car and public transport, respectively. The perceived pandemic severity positively affects the usage of car-sharing and bike-sharing, while it negatively affects the ride-sharing usage. Under different pandemic severity levels, the average probabilities of private car choice with and without shared mobility are 38.70 and 57.77%, respectively; thus, shared mobility would alleviate the dependence on private car in post-pandemic future. It also helps to decrease the on-road carbon emissions when the pandemic severity is lower than 53. These findings suggest policymakers to maintain the shared mobility ridership and simultaneously contain the pandemic. Additionally, pricing discount and safety enhancement are more effective than reducing detour time to protect ride-sharing against COVID-19.

show abstract

“…For instance, if the EM takes 1000 iterations to converge, the estimation of DLCM involves the estimation of 1000 mixed logit models. For this reason, we rely on the Broyden‐Fletcher–Goldfarb–Shanno (BFGS) algorithm with analytical gradients to optimize these functions in Python (see appendix of Krueger et al, 2021, for analytical gradients).…”

Section: Model Estimationmentioning

confidence: 99%

A Dynamic Choice Model to Estimate the User Cost of Crowding with Large-Scale Transit Data

Bansal

Hörcher

Graham

2022

Journal of the Royal Statistical Society Series A: Statistics in Society

Self Cite

View full text Add to dashboard Cite

Efficient mass transit provision should be responsive to the behaviour of passengers. Operators often conduct surveys to elicit passenger perspectives, but these can be expensive to administer and can suffer from hypothetical biases. With the advent of smart card and automated vehicle location data, operators have reliable sources of revealed preference (RP) data that can be utilized to estimate transit riders' valuation of service attributes. To date, effective use of RP data has been limited due to modelling complexities. We propose a dynamic choice model (DCM) for population‐level longitudinal RP data to address prominent challenges. In the DCM, riders are assumed to follow different decision rules (compensatory and inertia/habit) and temporal switching between decision rules based on experience‐based learning is also formulated. We develop an expectation–maximization algorithm to estimate the DCM and apply our model to estimate passenger valuation of crowding. Using large‐scale data of 2 months with over four million daily trips by an Asian metro, our DCM estimates show an increase of 47% in passenger's valuation of travel time under extremely crowded conditions. Furthermore, the average passenger follows the compensatory rule on only 25.5% or fewer trips. These results are valuable for supply‐side decisions of transit operators.

show abstract

Evaluating the predictive abilities of mixed logit models with unobserved inter- and intra-individual heterogeneity

Cited by 21 publications

References 33 publications

Distribution-free estimation of individual parameter logit (IPL) models using combined evolutionary and optimization algorithms

Distribution-free estimation of individual parameter logit (IPL) models using combined evolutionary and optimization algorithms

Exploring the Role of Shared Mobility in Alleviating Private Car Dependence and On-Road Carbon Emissions in the Context of COVID-19

A Dynamic Choice Model to Estimate the User Cost of Crowding with Large-Scale Transit Data

Contact Info

Product

Resources

About