GENERAL STATISTICAL FRAMEWORK FOR ASSESSING CATEGORICAL CLUSTERING IN FREE-RECALL
GENERAL STATISTICAL FRAMEWORK FOR ASSESSING CATEGORICAL CLUSTERING IN FREE-RECALL
复制标题
DOI：
10.1037/0033-2909.83.6.1072
复制
发表时间：
1976-01-01
影响因子：
22.4
通讯作者：
LEVIN, JR
中科院分区：
文献类型：
--
作者：
HUBERT, LJ;LEVIN, JR
图理论范式用于根据观察到的重复次数的数量来概括自由召回中分类聚类的常见度量。定义了两个图：图G图，其表征了由研究人员定义的项目集的先验结构；和图R，它是[人类]主体的协议的特征。两个指标的聚类指数，用.gamma表示。和.omega。通过评估2个图的相应边缘上的重量产物的配对产物的总和获得。 .gamma。统计量是对常用聚类指数的直接概括，并且每当G代表刺激列表的标准分类分解时，重复的数量就减少了。 .omega。统计量比.gamma从协议图R中提取更多信息。并根据受试者的召回顺序中的中间项目数量合并距离度量。
A graph-theoretic paradigm was used to generalize the common measures of categorical clustering in free recall based on the number of observed repetitions. Two graphs were defined: graph G, which characterized the a priori structure of the item set defined by a researcher; and graph R, which characterized a [human] subject''s protocol. Two indices of clustering, denoted by .GAMMA. and .OMEGA. were obtained by evaluating the sum of the pair-wise products of the weights on the corresponding edges of the 2 graphs. The .GAMMA. statistic were a direct generalization of the commonly used clustering indices and reduced to the number of repetitions whenever G represented a standard categorical decomposition of a stimulus list. The .OMEGA. statistic extracted more information from the protocol graph, R, than did .GAMMA. and incorporated a distance measure based on the number of intervening items in a subject''s recall sequence.