Incorporating Variance and Covariance Heterogeneity in the Generalized Nested Logit Model: An Application to Modeling Long Distance Travel Choice Behavior

This study combines the most flexible isolated closed-form extensions of the multinomial logit (MNL) and nested logit (NL) models in an integrated model structure to yield a behaviorally rich, yet computationally tractable choice model. Specifically, the authors combine the generalized NL model that allows for non-independent errors, the heteroscedastic MNL which allows non-constant errors across observations, and the covariance heterogeneous NL model which allows for non-constant correlation structure across observations. The resulting model, called the heterogeneous generalized NL (HGNL) model extends the ability to represent the complex behavioral processes involved in choice decision-making. The value and need for the additional modeling complexity of the HGNL model is tested in the empirical context of mode and rail service class choice behavior for long distance intercity travel. An incremental modeling approach is adopted, i.e., the authors start from the simple MNL model and sequentially relax some of its restrictive assumptions to estimate progressively more flexible model structures. The statistical fit and behavioral appeal of the estimated models improve substantially with each additional relaxation, strongly supporting the concept of integrating isolated generalizations. The HGNL model allows for heterogeneity in error variance and covariance structure, thereby explicitly accounting for the role of error variance/covariance in the choice decision process.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01001440
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jun 30 2005 10:35AM