The flexibility of models of recognition memory: The case of confidence ratings
The flexibility of models of recognition memory: The case of confidence ratings
复制标题
DOI：
10.1016/j.jmp.2015.05.002
复制
发表时间：
2015-08-01
影响因子：
1.8
通讯作者：
Kellen, David
中科院分区：
文献类型：
--
作者：
Klauer, Karl Christoph;Kellen, David
归一化最大似然（NML）指数是从最小描述长度原则导出的模型选择指数。与传统的模型选择指数相比，它还量化了与其功能形式相关的模型之间的灵活性差异。我们提出了一种计算参数化多项式或乘积多项式分布的分类数据模型的 NML 指数的新方法，并将其应用于比较基于置信度的接收者操作特征 (ROC) 数据的主要识别记忆模型的灵活性。针对典型大小的数据集将 NML 惩罚制成表格，并拟合插值函数，允许对大小在列表数据之间的数据集进行插值 NML 惩罚。恢复研究表明，NML 指数在 ROC 数据的模型选择方面比传统的模型选择指数表现更好。在对 850 个 ROC 数据集进行的基于 NML 的荟萃分析中，双过程信号检测模型的版本获得了最多的支持，其次是有限混合信号检测模型和两高阈值模型的约束版本。 (C) 2015 Elsevier Inc. 保留所有权利。
The normalized maximum likelihood (NML) index is a model-selection index derived from the minimum-description length principle. In contrast to traditional model-selection indices, it also quantifies differences in flexibility between models related to their functional form. We present a new method for computing the NML index for models of categorical data that parameterize multinomial or product-multinomial distributions and apply it to comparing the flexibility of major models of recognition memory for confidence-rating based receiver-operating-characteristic (ROC) data. NML penalties are tabulated for datasets of typical sizes and interpolation functions are fitted that allow one to interpolate NML penalties for datasets with sizes between the tabulated ones. Recovery studies suggest that the NML index performs better than traditional model-selection indices in model selection from ROC data. In an NML-based meta-analysis of 850 ROC datasets, versions of the dual-process signal detection models received most support followed by the finite mixture signal detection model and constrained versions of two-high threshold models. (C) 2015 Elsevier Inc. All rights reserved.