A policy model has (at least) four different interpretations: (a) intention: the intention/interpretation of the simulation designer/programmer, (b) validation: the meaning established by the validation of the model in terms of the mapping(s) to sets of evidence, (c) use: the meaning established as a result of the use of a model in a policy making/advice context and (d) interpretation: the narrative interpretation of the policy maker/advisor when justifying decisions made where this refers to a policy model.
These four different interpretations are loosely connected via social processes. The relation between intention and validation is relatively well discussed in the context of “scientific” model specification and development. The relation between use and interpretation has been discussed in a number of specific contexts. However when and how a relationship between the scientific world of intention/validation and the policy world of use/interpretation are established in practice is an area with little active research.
Both personal experience and philosophical considerations suggest that these two worlds are very different in terms of both purpose and method. However this does not mean that there cannot be any well-founded connection between them. The key question is understanding the social processes of how this can happen, what are the conditions that facilitate it happening and what is the nature of the relationship between the four views when it does happen.
Interestingly these issues have been faced and extensively discussed in the field of Artificial Intelligence, which has confronted the distinction between meaning of internal models (loosely, the beliefs of an agent about its environment) in these four ways. The field of AI has not come up with a final solution to these problems, and is itself divided into those that inhabit separate approaches that adopt a subset of these approaches to model meaning. However it is suggestive of some ways forward, namely:
• a recognition of the problem that there are these different ways of attributing meaning to a policy model (and hence avoid some common errors derived from conflating these four views);
• symbol grounding in the sense of learning meanings through repeated use and adjustment (either in response to validation or interpretation views or both);
• and the observation of scientific-policy interaction as it actually occurs (e.g. an ethnographic study of scientist/policy advisor interaction).
Some developments in the area of participatory policy modelling can be seen as forays into this arena, albeit without structured assessment.