Application of a nested trivariate copula structure in a competing duration hazard-based vehicle transaction decision model

Abstract

Vehicle ownership has been the subject of numerous transportation studies, which typically have adopted a variety of econometric frameworks at both aggregate and disaggregate choice modeling levels. These models have covered various aspects of vehicle ownership, including vehicle transaction behavior, number of vehicles held, vehicle type choice, and vehicle use. Vehicle transaction models have been developed in both static and dynamic paradigms. However, traditionally transaction timing has been overlooked in static vehicle ownership models despite the significant role that it plays in explaining vehicle ownership behavior. The decision about transaction type is typically assumed to be independently made; therefore, independent timing models are developed for each transaction type. This study aims to introduce a joint transaction type and timing model at the disaggregate level of individuals using a discrete competing proportional hazard model. The inter-correlation among multiple transaction types is modeled in this study by utilizing a set of multivariate Archimedean copula density functions to approximate the multivariate probability density function for the error terms of transaction types in a fully nested structure. ARTICLE HISTORY

Dependence analysis of social contact behaviors under the impacts of COVID-19 based on a copula approach

“…Moreover, compared with other multivariate correlation methods (e.g., Pearson, Kendall's tau, Spearman's rho), copulas can obtain nonlinear central dependence and tail dependence in both symmetric and asymmetric forms ( Frey et al, 2001 ; Trivedi and Zimmer, 2007 ). Because of the flexibility of choosing marginal distributions, the copula-based approach allows complex dependence structures between discrete variables ( Huang et al, 2022 ; Seyedabrishami and Izadi, 2019 ; Rashidi and Mohammadian, 2016 ), continuous variables ( Sener et al, 2010 ; Wali et al, 2022 ; Zilko et al, 2016 ; Kuwano et al, 2011 ), and ordered variables ( Eluru et al, 2010 ; Laman et al, 2018 ; Wang et al, 2015 ). Only the copula approach allows such combinations with different types of marginal distributions ( Bhat and Eluru, 2009 ; Zhang et al, 2012 ; Habib et al, 2009 ; Spissu et al, 2009 ; Irannezhad et al, 2017 ; Nguyen et al, 2017 ; Rith et al, 2019 ; Shabanpour et al, 2017 ).…”

Private Car Ownership in Presence of Shared Autonomous Vehicles, Case of Tehran

“…Clark et al (2016) investigated the impact of factors on change in the level of ownership over time and, as Dargay and Hanly (2007) noted, found that factors such as a family member reaching the legal driving age, marriage, and retirement significantly influence the changes in the level of car ownership. The household car ownership level, the role of each person in a household, as well as age and education, are other socioeconomic factors that affect car ownership level (Clark, 2012;Hossein Rashidi & Mohammadian, 2016). In addition to socioeconomic factors, transportation system network also influences household car ownership (Shaygan et al, 2017).…”

The Effects of Life Course Events on Car Ownership and Sustainable Mobility Tools Adoption Decisions: Results of an Error Component Random Parameter Logit Model

“…Changes in residence, education, and employment were found to increase the probability of changes in car ownership. On the basis of the hazard model, the competing risks model, which considered the type of car transactions, was applied in several studies [10][11][12]. The influence of changes in household size, education, employment, and house type has been analyzed and estimated using revealed preference data in these studies.…”