Estimation on Stated - Preference Experiments Constructed from Revealed - Preference Choices ∗ by Kenneth Train and Wesley W

Transportation researchers have recently introduced a stated-preference (sp) method in which the attributes of the sp alternatives are based on the choice that the respondent made in a real-world setting. This practice can enhance the realism of the sp task and the efficacy of preference revelation. However, the practice creates dependence between the sp attributes and unobserved factors, contrary to the independence assumption that is maintained for standard estimation procedures. We describe a general estimation method that accounts for this nonindependence and give specific examples based on standard and mixed logit specifications of utility. We show conditions under which standard estimation methods are consistent despite the non-independence. We illustrate the general methodology through an application to shippers’ choice of route and mode along the Columbia/Snake River system. ∗We benefited greatly from comments and suggestions by Eric Bradlow, Paul Burke, David Hensher, Jordan Louviere, Daniel McFadden, and John Rose. We are grateful for generous support from the Navigation Economic Technologies (NETS) program of the U.S. Army Corps of Engineers’ Institute for Water Resources, under the direction of Keith Hofseth.