A joint count-continuous model of travel behavior with selection based on a multinomial probit residential density choice model

Abstract

This paper formulates a multidimensional choice model system that is capable of handling multiple nominal variables, multiple count dependent variables, and multiple continuous dependent variables.The system takes the form of a treatment-outcome selection system with multiple treatments and multiple outcome variables. The Maximum Approximate Composite Marginal Likelihood (MACML) approach is proposed in estimation, and a simulation experiment is undertaken to evaluate the ability of the MACML method to recover the model parameters in such integrated systems. These experiments show that our estimation approach recovers the underlying parameters very well and is efficient from an econometric perspective. The parametric model system proposed in the paper is applied to an analysis of household-level decisions on residential location, motorized vehicle ownership, the number of daily motorized tours, the number of daily non-motorized tours, and the average distance for the motorized tours. The empirical analysis uses the NHTS 2009 data from the San Francisco Bay area. Model estimation results show that the choice dimensions considered in this paper are inter-related, both through direct observed structural relationships and through correlations across unobserved factors (error terms) affecting multiple choice dimensions.The significant presence of self-selection effects (endogeneity) suggests that modeling the various choice processes in an independent sequence of models is not reflective of the true relationships that exist across these choice dimensions, as also reinforced through the computation of treatment effects in the paper.

Modeling car-sharing membership as a mobility tool: A multivariate Probit approach with latent variables

“…Both the multivariate Probit, e.g. [6,29,30], and the pro-bit with sample selection, e.g. [35,36,56], are well-established methodologies.…”

“…Also the bivariate probit with endogenious treatment is widely used in some 390 disciplines [57,58,59,60] and has recently been extended by Bhat and his colleagues to model mixed types of outcomes [61,6].…”

“…In this analysis, it is assumed that the choices on mobility tools are made simul- 10 taneously. As such multiple choices may share common underlying unobserved factors and one outcome might be an endogenous factor in another outcome, jointly modeling multiple outcomes accounts for interdependencies and provides deeper insights into the decision making process [4,5,6,7]. 15 For a long time, (motor-)bikes, private vehicles and public transportation subscriptions were the only relevant mobility tools.…”

“…Recent work by Bhat et al extended the multivariate Probit to accommo-date mixed types of outcomes, e.g. multinomial or ordered outcomes, in which common unobserved factors and endogeneity might be present [6]. The multivariate Probit also allows to accommodate truncated samples [35,36] as well as spatial and social interaction [7].…”

“…In addition, the distance to the closest 250 car-sharing station was calculated using the individual household coordinates and the station locations of the national car-sharing provider Mobility [44]. 6 The level of service was assigned based on the individual household coordinates from the micro census and a shape file with the level of service zones provided by [41]. The classification of the spatial structure was conducted based on the (available) workplace municipality code.…”