Unfolding a symmetric matrix

作者: John C. Gower , Michael J. Greenacre

DOI: 10.1007/BF01202583

关键词:

摘要: Graphical displays which show inter-sample distances are important for the interpretation and presentation of multivariate data. Except when two-dimensional, however, they often difficult to visualize as a whole. A device, based on multidimensional unfolding, is described presenting some intrinsically high-dimensional in fewer, usually two, dimensions. This goal achieved by representing each sample pair points, say Ri ri, so that theoretical distance between i-th j-th samples represented twice, once rj Rj ri. Selfdistances andri need not be zero. The mathematical conditions unfolding exhibit symmetry established. Algorithms finding approximate fits, constrained symmetric, discussed examples given.

参考文章(13)
Phoebus J. Dhrymes, Applications of Multivariate Analysis Springer, New York, NY. pp. 42- 83 ,(1974) , 10.1007/978-1-4613-9383-2_2
Michael J. Greenacre, Michael W. Browne, An efficient alternating least-squares algorithm to perform multidimensional unfolding Psychometrika. ,vol. 51, pp. 241- 250 ,(1986) , 10.1007/BF02293982
Clyde Hamilton Coombs, A theory of data ,(1964)
Sandra G. Funk, Abraham D. Horowitz, Raanan Lipshitz, Forrest W. Young, The Perceived Structure of American Ethnic Groups: The Use of Multidimensional Scaling in Stereotype Research Personality and Social Psychology Bulletin. ,vol. 1, pp. 66- 68 ,(1974) , 10.1177/014616727400100122
Peter H. Scho̎nemann, ON METRIC MULTIDIMENSIONAL UNFOLDING Psychometrika. ,vol. 1969, pp. 349- 366 ,(1970) , 10.1002/J.2333-8504.1969.TB00773.X
Sandra G. Funk, Abraham D. Horowitz, Raanan Lipshitz, Forrest W. Young, The Perceived Structure of American Ethnic Groups: The Use of Multidimensional Scaling in Stereotype Research Sociometry. ,vol. 39, pp. 116- ,(1976) , 10.2307/2786212