An Integrated Choice and Latent Variable Model quantifying the Impact of Physical Activity Propensity, Environmental and Safety Consciousness on Mode-to-School Choice Behavior

Over the last few decades, numerous improvements have been made that aim to better unravel the underlying process leading up to observed choice outcomes, while also better predicting the outcomes of choice behavior. These methods are integrated in Hybrid Choice Models (HCMs) and attempt to more realistically explain individual choice behavior and in doing so a substantial part of the population heterogeneity (Ben-Akiva et al., 2002). The Integrated Choice and Latent Variable (ICLV) model within the HCM conceptual framework permits the inclusion of attitudes, opinions and perceptions as psychometric latent variables in such a way that consumer behavior is better understood (Ashok et al. 2002; Bolduc et al., 2005;). Although the number of applications of ICLV models has been on the rise in the last decade (see, for example Johansson et al., 2006; Temme et al., 2008; Abou-Zeid et al., 2011; Daly et al., 2012; Alvarez-Daziano and Bolduc, 2013; Polydoropolou et al., 2013), Bhat and Dubey (2014) indicate that the conceptual value of ICLV models has not been adequately translated to benefits in practice because of the difficulties in model convergence and estimation, and the very lengthy estimation times of these models even when convergence is achieved. These issues are particularly the case when more than one or two latent variables are considered within the traditional logit kernel-based ICLV models, since the number of latent variables has a direct impact on the dimensionality of the integral that needs to be estimated in the log-likelihood function. The consequence has been that most ICLV models in the literature have gravitated toward the use of a very limited number of latent constructs, rather than exploring a fuller set of possible latent variables. The aim of this paper is to empirically apply and test the new MNP kernel-based ICLV formulation of Bhat and Dubey (2014) in the context of an analysis of teenagers’ mode choice to school. In doing so, an ICLV mode choice model (with five alternatives: Car, Motorcycle, Bus, Walk, Bicycle) that incorporates three latent psychological factors is developed. For the model estimation, we use SP data drawn from the first wave of a 2012 transport survey undertaken in Cyprus and targeted toward high school students (11 to 18 years old). 2,124 teenagers participated in the survey, and each of them was presented with two SP choice instances for mode choice to school. The choice scenarios presented were based on an experimental design procedure to extract as much information as possible regarding the effects of each explanatory variable considered (i.e. travel time, travel cost, walking time to bus station, cycle lanes availability, sidewalks characteristics and weather conditions). In the analysis, we include three latent psychological factors (or constructs) to explain school mode choice: Safety Consciousness , Green Lifestyle and Physical Activity Propensity . The indicators for these constructs were collected in the survey on a 7-point Likert ordinal scale. This new approach offers significant advantages, as the dimensionality of integration in the log-likelihood function is independent of the number of latent variables allowing us to incorporate three latent variables with a large data sample, with 10 ordinal indicators of the latent variables, and estimate the ICLV model without any convergence problems. The estimation results are also used to compute aggregate-level elasticity effects to characterize the magnitude of the impact of the variables used in the model. The results of this paper are encouraging for the use of Bhat and Dubey’s (2014) formulation of ICLV models, and it is hoped that it will promote the use of ICLV models in practice to formulate richer and more realistic behavioral representations of underlying decision processes. In addition the results are useful to researchers and authorities that deal with school transportation issues, as the model application provides important information regarding the value of investing in bicycling and walking infrastructure. It also suggests the need to improve bus and walking safety, and communicate such improvements to the public. References Abou-Zeid, M., M. Ben-Akiva, M. Bierlaire, C.F. Choudhury and S. Hess (2011). Attitudes and Value of Time Heterogeneity. Paper presented at the 90th Annual Meeting of the Transportation Research Board , Washington, D.C., January 2011. Alvarez-Daziano, R., and D. Bolduc (2013). Incorporating Pro-environmental Preferences towards Green Automobile Technologies through a Bayesian Hybrid Choice Model. Transportmetrica A: Transport Science 9(1), 74-106. Ashok, K., W.R. Dillon, S. Yuan (2002). Extending discrete choice models to incorporate attitudinal and other latent variables. Journal of Marketing Research , pp. 31–46. Bhat, C.R., and S.K. Dubey (2014). A New Estimation Approach to Integrate Latent Psychological Constructs in Choice Modeling. Transportation Research Part B: Methodological , Vol. 67, pp. 68-85. Ben-Akiva, M., J. Walker, A. T. Bernardino, D. A. Gopinath, T. Morikawa, and A. Polydoropoulou (2002). Integration of Choice and Latent Variable Models. In Perpetual Motion: Travel Behaviour Research Opportunities and Application Challenges (H. S. Mahmassani, ed.). Elsevier, Amsterdam, pp. 431–470. Bolduc, D., M. Ben-Akiva, J. Walker, A. Michaud (2005). Hybrid Choice Models with Logit Kernel: Applicability to Large Scale Models. In: Lee-Gosselin, M., Doherty, S. (eds.) Integrated Land-Use and Transportation Models: Behavioural Foundations , Elsevier, Oxford, pp. 275-302. Daly, A., S. Hess, B. Patruni, D. Potoglou, and C. Rohr (2012). Using Ordered Attitudinal Indicators in a Latent Variable Choice Model: a study of the impact of security on rail travel behavior.” Transportation, 39(2), pp. 267-297. Johansson, M. V., T. Heldt and P. Johansson (2006). The Effects of Attitudes and Personality Traits on Mode Choice. Transportation Research Part A, Vol. 40 (6), pp. 507–525. Polydoropoulou, A., M. Kamargianni, and A. Tsirimpa (2013). Car Use Addiction vs. Ecological Consciousness: Which one Prevails on Mode
 Choice Behavior?  In book:  Travel Behaviour Research , Editors: Roorda, M., and E. Miller.  0 0 1 965 5501 UCSB 45 12 6454 14.0 Normal 0 false false false EN-US JA X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin:0cm; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:12.0pt; font-family:Cambria; mso-ascii-font-family:Cambria; mso-ascii-theme-font:minor-latin; mso-hansi-font-family:Cambria; mso-hansi-theme-font:minor-latin;} Temme, D., M. Paulssen, and T. Dannewald (2008). Incorporating Latent Variables Into Discrete Choice Models - A Simultaneous Estimation Approach Using SEM Software. BuR-Business Research, Vol. 1(2), pp. 220-237.