Public Health Decision Making
Managing Structural Uncertainty in Health Economic Decision Models
It was George Box who famously wrote 'Essentially, all models are wrong, but some are useful'. Given our limited understanding of the highly complex world in which we live this statement seems entirely reasonable. Why then, in the context of health economic decision modelling, do we often act as if our models are right even if we believe that they are wrong?
Imagine we build a model, perhaps along with some variants based on alternative assumptions. We very carefully quantify parameter uncertainty, and we may even quantify the value of obtaining more information. We then present our results to the 'decision maker'. If we believe George Box then we must accept that our model output point estimates, our uncertainty analysis distributions, and our estimates of the value of information are all 'wrong' because they are generated by a model that does not perfectly represent reality. The challenge is to quantify how wrong.
Our current approach to quantifying structural uncertainty in health economic decision models is to build on the discrepancy modelling research that was initiated by the Managing Uncertainty in Complex Models (MUCM) project. Mark Strong (working with Jeremy Oakley and Jim Chilcott) is exploring this as part of his MRC Fellowship in Health Services/Public Health Research