Generalized extreme value (GEV)-based error structures for multiple discrete-continuous choice models

摘要: This paper formally derives the class of multiple discrete-continuous generalized extreme value (MDCGEV) models, a general choice models based on (GEV) error specifications. Specifically, proves existence of, and form closed-form consumption probability expressions for with GEV-based structures. In addition to deriving form, compact readily usable that can be used estimate cross-nested The version MDCGEV model is applied analyze household annual expenditure patterns in various transportation-related expenses using data from Consumer Expenditure Survey United States. Model estimation results predictive log-likelihood validation tests indicate superiority over mutually exclusively nested non-nested Further, was amenable accommodation socio-demographic heterogeneity inter-alternative covariance across decision-makers through parameterization allocation parameters.