TY - JOUR
T1 - Multiple discrete-continuous choice models with bounds on consumptions
AU - Saxena, Shobhit
AU - Pinjari, Abdul Rawoof
AU - Roy, Ananya
AU - Paleti, Rajesh
N1 - Funding Information:
The methodological work in this paper was carried out as part of a project titled “A connected Intermediate Public Transport Mobility-as-a-service (IPTMaaS) solution for the last mile connectivity and multi-modal integration problems of public transit” sponsored by the Ministry of Education (MoE) and the Department of Science and Technology (DST) of the Government of India. Three anonymous reviewers provided valuable comments on earlier versions of the paper.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/7
Y1 - 2021/7
N2 - This paper derives a multiple discrete–continuous (MDC) choice model formulation with constraints that specify upper bounds on consumption. To do so, considering the conventional utility maximization problem of a consumer, the Karush-Kuhn-Tucker (KKT) conditions are laid out for the MDC model with a general set of linear constraints that include inequalities. Subsequently, we derive a model with constraints that accommodate upper bounds on consumptions and an additive utility structure that accommodates lower bounds on consumptions. The likelihood expression for the proposed model takes a closed form. Furthermore, we extend the formulation to impose bounds on an MDC choice model with activity episode-level choice alternatives that accommodates a logical ordering among different episodes of an activity. The proposed models are derived for two different specifications of the outside good utility – (1) nonlinear utility with respect to consumption and (2) linear utility with respect to consumption. The proposed models are applied to an empirical context to analyze activity-level as well as episode-level activity participation and time allocation while considering bounds on time allocations. Empirical results suggest that the models that consider upper bounds on consumption offer a better fit to data, avoid predictions of unrealistically large time allocations, and result in overall better predictions than those from models without bounds. The proposed models are useful in situations, such as microsimulation models of travel demand, where it is crucial to avoid unrealistically large predictions.
AB - This paper derives a multiple discrete–continuous (MDC) choice model formulation with constraints that specify upper bounds on consumption. To do so, considering the conventional utility maximization problem of a consumer, the Karush-Kuhn-Tucker (KKT) conditions are laid out for the MDC model with a general set of linear constraints that include inequalities. Subsequently, we derive a model with constraints that accommodate upper bounds on consumptions and an additive utility structure that accommodates lower bounds on consumptions. The likelihood expression for the proposed model takes a closed form. Furthermore, we extend the formulation to impose bounds on an MDC choice model with activity episode-level choice alternatives that accommodates a logical ordering among different episodes of an activity. The proposed models are derived for two different specifications of the outside good utility – (1) nonlinear utility with respect to consumption and (2) linear utility with respect to consumption. The proposed models are applied to an empirical context to analyze activity-level as well as episode-level activity participation and time allocation while considering bounds on time allocations. Empirical results suggest that the models that consider upper bounds on consumption offer a better fit to data, avoid predictions of unrealistically large time allocations, and result in overall better predictions than those from models without bounds. The proposed models are useful in situations, such as microsimulation models of travel demand, where it is crucial to avoid unrealistically large predictions.
UR - http://www.scopus.com/inward/record.url?scp=85107037500&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107037500&partnerID=8YFLogxK
U2 - 10.1016/j.tra.2021.03.016
DO - 10.1016/j.tra.2021.03.016
M3 - Article
AN - SCOPUS:85107037500
VL - 149
SP - 237
EP - 265
JO - Transportation Research, Part A: Policy and Practice
JF - Transportation Research, Part A: Policy and Practice
SN - 0965-8564
ER -