Modelling heterogeneity in response behaviour towards a sequence of discrete choice questions: a probabilistic decision process model

There is a growing body of evidence in the non-market valuation literaturesuggesting that responses to a sequence of discrete choice questions tend to violate theassumptions typically made by analysts regarding independence of responses andstability of preferences. Decision processes (or heuristics) such as value learning andstrategic misrepresentation have been offered as explanations for these results. Whilea few studies have tested these heuristics as competing hypotheses, none hasinvestigated the possibility that each explains the response behaviour of a subgroup ofthe population. In this paper, we make a contribution towards addressing this researchgap by presenting a probabilistic decision process model designed to estimate theproportion of respondents employing defined heuristics. We demonstrate the modelon binary and multinomial choice data sources and find three distinct types ofresponse behaviour. The results suggest that accounting for heterogeneity in responsebehaviour may be a better way forward than attempting to identify a single heuristicto explain the behaviour of all respondents.