This discussion paper resulted in a publication in Land Economics (2014). Volume 90(4), pages 717-745.
This paper contrasts the discovered preference hypothesis against the theory of coherent arbitrariness in a split-sample stated choice experiment on flood risk exposure in the Netherlands. A semi-parametric local multinomial logit model (L-MNL) is developed as an alternative to the Swait and Louviere (1993) procedure to control for preference dynamics within and between samples. The L-MNL model finds empirical support for the discovered preference hypothesis in the form of a declining starting point bias induced by the first choice task. These results differ from the Swait and Louviere procedure which, due to its limited flexibility, accepts the standard assumption underlying microeconomic theory of stable preference parameters throughout the choice sequence. The observed preference dynamics puts the use of choice experiments at risk of generating biased welfare estimates if not controlled for.