Efficient Estimation of the Value of Information in Monte Carlo Models
This work addresses a bottleneck in decision modeling for fields like crisis transportation planning by enabling efficient EVI estimation in large-scale Monte Carlo simulations.
The authors tackled the computational intractability of estimating the expected value of information (EVI) in large Monte Carlo models by introducing an approximate method based on pre-posterior analysis, linear approximations, and multiple linear regression, making it efficient and practical for extremely large models.
The expected value of information (EVI) is the most powerful measure of sensitivity to uncertainty in a decision model: it measures the potential of information to improve the decision, and hence measures the expected value of outcome. Standard methods for computing EVI use discrete variables and are computationally intractable for models that contain more than a few variables. Monte Carlo simulation provides the basis for more tractable evaluation of large predictive models with continuous and discrete variables, but so far computation of EVI in a Monte Carlo setting also has appeared impractical. We introduce an approximate approach based on pre-posterior analysis for estimating EVI in Monte Carlo models. Our method uses a linear approximation to the value function and multiple linear regression to estimate the linear model from the samples. The approach is efficient and practical for extremely large models. It allows easy estimation of EVI for perfect or partial information on individual variables or on combinations of variables. We illustrate its implementation within Demos (a decision modeling system), and its application to a large model for crisis transportation planning.