Attending to the reasons for attribute non-attendance in Choice Experiments

This paper focuses on behavioural reasons underlying stated attribute non-attendance. In order to identify and incorporate procedures for dealing with heterogeneous attribute processing strategies, we ask respondents follow-up questions regarding their reasons for ignoring attributes. Based on these statements, we conclude that the standard way of assigning a zero impact of ignored attributes on the likelihood is inappropriate. We find that some respondents act in accordance with the passive bounded rationality assumption since they ignore an attribute simply because it does not affect their utility. Excluding these genuine zero preferences, as the standard approach essentially does, might bias results. Other respondents claim to have ignored attributes to simplify choices. However, we find that these respondents have actually not completely ignored attributes. We argue along the rationally adaptive behavioural model that preferences are indeed elicited in these cases, and we show how using a scaling approach can appropriately weight these observations in the econometric model. Finally, we find that some respondents ignore attributes for protest-like reasons which essentially convey no information about preferences. We suggest that using the standard approach combined with weighting procedures and recoding of non-attendance statements conditional on the specific reasons for non-attendance could be more appropriate than the current standard way of taking stated non-attendance into account.choice experiment, attribute non-attendance, passive bounded rationality, rationally adaptive behaviour, error component logit model