Browse > Article
http://dx.doi.org/10.5351/KJAS.2005.18.1.129

A Method of Expressing Multivariate Representative Observations Based on the Self-Consistency of Principal Components  

Kim KeeYoung (Department of Statistics, Korea University)
Park YongJu (Dept. of Consumer Credit Risk Management, Koram Bank)
Publication Information
The Korean Journal of Applied Statistics / v.18, no.1, 2005 , pp. 129-135 More about this Journal
Abstract
Representative observations are useful to express explicitly the distributional variation of the data by a few selected observations corresponding to the quantiles in the univariate situation. Jones and Rice(1992) extended it to the multidimensional case by the principal component based method. This study introduces a modified version of Jones and Rice exploiting the self-consistency of principal components in expressing the chosen observation vectors. Compared to that of Jones and Rice, the suggested method tends to provide with less susceptible representative observations to the sampling variation of the data and the resulted vectors benefits from the self-consistency.
Keywords
Principal component analysis; Self-consistency; Representative observation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Jones, M. C. and Rice, J. A. (1992). Displaying the important feature of large collections of similar curves, The American Statistician, 46, 140-145   DOI   ScienceOn
2 Hastie, T. and Stuetzle, W. (1989). Principal curves, Journal of the American Statistical Association, 84, 502-516   DOI   ScienceOn
3 Tarpey, T. and Flury, B. (1996). Self-consistency: a fundamental concept in statistics, Statistical Science, 11, 229-243   DOI   ScienceOn
4 Flury, B. (1990). Principal points, Biometrika, 77, 33-41   DOI   ScienceOn
5 Tarpey, T. (1995). Principal points and self-consistent points of symmetric multivariate distributions, Journal of Multivariate Analysis, 53, 39-51   DOI   ScienceOn
6 Tarpey, T. (1999). Self-consistency and principal component analysis, Journal of the American Statistical Association, 94, 456-467   DOI   ScienceOn