Disentangling Use and Non-Use Values: A structurally consistent approach using revealed and stated preference choice data

In this paper we develop a random utility model designed to distinguish and estimate, within a single, coherent framework, the use and non-use value of an array of environmental goods. The motivating example is the valuation of improvements in the ecological status of rivers. In a departure from the extreme reduced-form of the standard linear mixed logit specification, our model is developed from our understanding of the underlying structure of preferences. To identify the parameters of that model we pursue an estimation strategy based on combining revealed preference data with stated preference data from a choice experiment. We explore the properties of the model in a Monte Carlo experiment and then apply it to a dataset collected in a large scale survey carried out across Northern England. This implementation reveals intuitively plausible estimates of the use and non-use parameters of the model and provides interesting insights into the distance decay in those two different forms of value.