Soft Triangles for Expert Aggregation
This work addresses expert aggregation in risk control, offering a new approach for handling uncertain probabilities, but it appears incremental as it modifies existing statistical methods without demonstrating broad impact.
The paper tackles the problem of eliciting expert assessments for uncertain parameters in risk control, particularly focusing on probabilities that involve 'uncertainty about uncertainty', and proposes a novel formulation using range and median instead of variance and mean, with precise formulas provided for these distributions.
We consider the problem of eliciting expert assessments of an uncertain parameter. The context is risk control, where there are, in fact, three uncertain parameters to be estimates. Two of these are probabilities, requiring the that the experts be guided in the concept of "uncertainty about uncertainty." We propose a novel formulation for expert estimates, which relies on the range and the median, rather than the variance and the mean. We discuss the process of elicitation, and provide precise formulas for these new distributions.