Comparison of Decisions under Unknown Experiments
研究计量经济学家在只知道两种实验的决策结果时，如何比较哪个实验的期望效用更高，给出了一个充要条件来判断一组决策对应的所有实验的信息价值是否都高于另一组。
We take the perspective of an econometrician who wants to determine which of two experiments provides higher expected utility but only knows the decisions under each experiment. To compare these decisions, the econometrician must make inferences about what the experiment might have been for each set of decisions. We provide a necessary and sufficient condition that identifies when every experiment consistent with one set of decisions has a higher value of information than every experiment consistent with the other set of decisions.