Finding useful questions: On Bayesian diagnosticity, probability, impact, and information gain
Finding useful questions: On Bayesian diagnosticity, probability, impact, and information gain
复制标题
DOI：
10.1037/0033-295x.112.4.979
复制
发表时间：
2005-10-01
影响因子：
5.4
通讯作者：
Nelson, JD
中科院分区：
文献类型：
--
作者：
Nelson, JD
人们应该如何评估一个问题的有用性已经提出了几个规范，特别是贝叶斯诊断性，信息增益（互信息），Kullback-Liebler距离，概率增益（错误最小化）和影响（绝对变化）。分类，协变评估，医疗诊断和选择任务的几个概率模型的先前的实验中，不区分这些规范作为人类直觉和行为的描述性模型。计算优化发现的情况下，信息增益，概率增益和影响强烈矛盾贝叶斯诊断。在这些情况下，诊断性的主张在规范上是低等的。一项新实验的结果与贝叶斯诊断的预测强烈矛盾。规范性的理论关注也反对使用诊断性。它的结论是贝叶斯诊断是规范上有缺陷的，经验上不合理的。
Several norms for how people should assess a question's usefulness have been proposed, notably Bayesian diagnosticity, information gain (mutual information), Kullback-Liebler distance, probability gain (error minimization), and impact (absolute change). Several probabilistic models of previous experiments on categorization, covariation assessment, medical diagnosis, and the selection task are shown to not discriminate among these norms as descriptive models of human intuitions and behavior. Computational optimization found situations in which information gain, probability gain, and impact strongly contradict Bayesian diagnosticity. In these situations, diagnosticity's claims are normatively inferior. Results of a new experiment strongly contradict the predictions of Bayesian diagnosticity. Normative theoretical concerns also argue against use of diagnosticity. It is concluded that Bayesian diagnosticity is normatively flawed and empirically unjustified.