摘要：AbstractUsing the theory of information-gap for decision-making under severe uncertainty, it has been shown that there exist irrevocable trade-offs between fidelity-to-data, robustness-to-uncertainty and confidence-in-prediction. The paper describes the assessment and trade-offs of these three components in a data-sparse application. To augment the data and corresponding modeling, a similar application with data and models is considered. A method of information integration is illustrated. Saaty's Analytic Hierarchy Process (AHP) is used to determine weights for two models and two experimental data sets, by forming all possible pair-wise comparisons between model output and experimental data.
关键词：Inference;Inference Uncertainty;Information Integration;Analytical Hierarchy Process
