It's not that I don't care, I just don't care very much: confounding between attribute non-attendance and taste heterogeneity

摘要

With the growing interest in the topic of attribute non-attendance, there is now widespread useof latent class (LC) structures aimed at capturing such behaviour. Specically, these studies rely ona conrmatory LC model, using two separate values for each coefficient, one of which is xed to zerowhile the other is estimated, and then use the obtained class probabilities as an indication of thedegree of attribute non-attendance. In the present paper, we argue that this approach is in fact mis-guided, and that the results are likely to be affiected by confounding with regular taste heterogeneity.We contrast the conrmatory model with an exploratory LC structure in which the values in bothclasses are estimated. We also put forward a combined latent class mixed logit model (LC-MMNL)which allows jointly for attribute non-attendance and for continuous taste heterogeneity. Across twocase studies, the exploratory LC model clearly rejects the conrmatory LC approach and suggeststhat rates of non-attendance may be much lower than what is suggested by the standard model, oreven zero. The combined LC-MMNL model similarly produces signicant improvements in modelt, along with substantial reductions in the implied rate of attribute non-attendance, in some caseseven eliminating the phenomena across the sample population. Our results thus call for a reappraisalof the large body of recent work that has implied high rates of attribute non-attendance for someattributes. Finally, we also highlight a number of general issues with attribute non-attendance, inparticular relating to the computation of willingness to pay measures.