ERIC Number: ED116162
Record Type: Non-Journal
Publication Date: 1975-Oct
Reference Count: N/A
A General Statistical Framework for Assessing Categorical Clustering in Free Recall.
Hubert, Lawrence J.; Levin, Joel R.
A graph-theoretic paradigm is used to generalize the common measures of categorical clustering in free recall based on the number of observed repetitions. Two graphs are defined: a graph G that characterizes the a priori structure of the item set defined by a researcher, and a graph R that characterizes a subject's protocol. Two indices of clustering, denoted by gamma and omega, are obtained by evaluating the sum of the pairwise products of the weights on the corresponding edges of the two graphs. The gamma statistic is a direct generalization of the commonly used clustering indices and reduces to the number of repetitions whenever G represents a standard categorical decomposition of a stimulus list. The omega statistic, on the other hand, extracts more information from the protocol graph R than does gamma and incorporates a distance measured based on the number of intervening items in a subject's recall sequence. (Author)
Publication Type: Reports - Research
Education Level: N/A
Sponsor: National Inst. of Education (DHEW), Washington, DC.
Authoring Institution: Wisconsin Univ., Madison. Research and Development Center for Cognitive Learning.