비대칭 다차원척도법의 시각화 = Visualizations of Asymmetric Multidimensional Scaling

다국어 초록 (Multilingual Abstract)

Distances or dissimilarities among units are assumed to be symmetric in most cases of multidimensional scaling(MDS); consequently, it is not an easy task to deal with asymmetric distances. Current asymmetric MDS still face difficulties in the interpretation of results. This study proposes a simpler asymmetric MDS that utilizes the order statistic of an asymmetric matrix. The proposed Web method demonstrates that some influences among objects are visualized by direction, size and shape of arrow to ease the interpretability of users.

참고문헌 (Reference)

1 Choi, Y. S., "Walk in Multidimensional Scaling -SAS/MDS, SAS/IML and R-" Free Academy 2014

2 Shepard, R. N., "The analysis of prosimities: Multidimensional scaling with an unknown distance function. I and II" 27 : 125-140, 1962

3 Ramsay, J. O., "Some statistical approaches to multidimensional scaling data" 145 : 285-312, 1982

4 Torgerson, W. S., "Multidimesional scaling: I. Theory and Method" 17 : 401-419, 1952

5 Kruskal, J. B., "Multidimensional scaling by optimizing goodness-of-fit to a nonmetric hypothesis" 29 : 1-27, 1964

6 Cox, T. F., "Multidimensional Scaling, Second Edition" Chapman & Hall/CRC 2001

7 허명회, "Multidimensional Scaling of Asymmetric Distance Matrices" 한국통계학회 25 (25): 613-620, 2012

8 Haiyan, L., "Data visualization of asymmetric data using sammon mapping and applications of selforganizing maps" University of Maryland 2005

9 Oh, M. S., "Bayesian multidimensional scaling and choice of dimension" 96 : 1031-1044, 2001

10 Everitt, B. S., "Applied Multivariate Data Analysis" Edward Arnold 1991