This paper discusses a number of issues relating to the pre-analysis and cleaning of stated preference data, where the paper will look specifically at the problems caused by non-trading, lexicographic and inconsistent response patterns. The paper will argue that this process is in fact considerably more complex and challenging than many in the field have hitherto acknowledged, with the standard practice being the use of rather ad-hoc procedures for the identification of the above listed phenomena. A detailed analysis on four different SP datasets highlights the potential impacts of these methods on model estimation results.
Abstract