A simplified method for value of information using constructed scales

Decision Analysis
By: , and 

Links

Abstract

The value of information is a central concept in decision analysis, used to quantify how much the expected outcome of a decision would be improved if epistemic uncertainty could be resolved prior to committing to a course of action. One of the challenges, however, in quantitative analysis of the value of information is that the calculations are demanding, especially in requiring predictions of outcomes as a function of alternative actions and sources of uncertainty. However, the concept of value of information is important in early framing of some decisions, before such predictions are available. We propose a novel measure of the value of information based on constructed scales (CVOI), grounded in the algebra of the expected value of perfect information (EVPI), but requiring less of experts and analysts. The CVOI calculation decomposes EVPI into a contribution representing the relevance of the uncertainty to the decision and a contribution representing the magnitude of uncertainty; constructed ratio scales are then proposed for each contribution. We demonstrate the use of CVOI to identify research priorities related to migratory bird management in the face of climate change.

Publication type Article
Publication Subtype Journal Article
Title A simplified method for value of information using constructed scales
Series title Decision Analysis
DOI 10.1287/deca.2023.0474
Volume 20
Issue 3
Year Published 2023
Language English
Publisher INFORMS
Contributing office(s) National Climate Change and Wildlife Science Center, Patuxent Wildlife Research Center, Eastern Ecological Science Center
Description 11 p.
First page 220
Last page 230
Google Analytic Metrics Metrics page
Additional publication details