Abstract
Principal component analysis (PCA) of an objects × variables data matrix is used for obtaining a low-dimensional biplot configuration, where data are approximated by the inner products of the vectors corresponding to objects and variables. Borg and Groenen (Modern multidimensional scaling. Springer, New York, 1997) have suggested another biplot procedure which uses a technique for approximating data by projections of object vectors on variable vectors. This technique is formulated as constraining the variable vectors in PCA to be of unit length and can be called unit-length vector analysis (UVA). However, an algorithm for UVA has not yet been developed. In this paper, we present such an algorithm, discuss the properties of UVA solutions, and demonstrate the advantage of UVA in biplots for standardized data with homogeneous variances among variables. The advantage of UVA-based biplots is that the projections of object vectors onto variable vectors express the approximation of data in an easy way, while in PCA-based biplots we must consider not only the projections, but also the lengths of variable vectors in order to visualize approximations.
Similar content being viewed by others
References
Bechel GG, Tucker LR, Chang W (1971) A scalar product model for the multidimensional scaling of choice. Psychometrika 36: 369–388
Borg I, Groenen P (1997) Modern multidimensional scaling. Springer, New York
Browne MW (1967) On oblique Procrustes rotation. Psychometrika 32: 125–132
Cox TF, Cox MAA (2001) Multidimensional scaling, 2nd edn. CRC Press, Boca Raton
Cramer EM (1974) On Browne’s solution for oblique Procrustes rotation. Psychometrika 39: 159–163
Flury B (1988) Common component analysis and related multivariate models. Wiley, New York
Gabriel KR (1971) The biplot graphical display of matrices with application to principal component analysis. Biometrika 58: 453–467
Gower JC, Hand DJ (1996) Biplots. Chapman and Hall, London
Gower JC, Dijksterhuis GB (2004) Procrustes problems. Oxford University Press, Oxford
Gower JC, Groenen P, Van de Velden M (2010) Area biplots. J Comput Graph Stat 19: 46–61
Jennrich RI (2002) A simple general method for oblique rotation. Psychometrika 67: 7–20
Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, New York
Pietersz R, Groenen PFJ (2004) Rank reduction of correlation matrices by majorization. Quant Finance 4: 649–662
Roskam EE (1968) Metric analysis of ordinal data in psychology. Drukkerij/Uitgeverij VAM, Voorschoten
Takane Y, Shibayama T (1991) Principal component analysis with external information of both subjects and variables. Psychometrika 56: 97–120
ten Berge JMF, Kiers HAL (1996) Optimality criteria for principal component analysis and generalizations. Br J Math Stat Psychol 49: 335–345
ten Berge JMF, Nevels K (1977) A general solution of Mosier’s oblique Procrustes problem. Psychometrika 42: 593–600
Tucker LR (1960) Intra-individual and inter-individual multidimensionality. In: Gulliksen H, Messick S (eds) Psychological scaling: theory and applications. Wiley, New York, pp 155–167
Yanai H, Shigemasu K, Mayekawa S, Ichikawa M (1990) Factor analysis: theory and applications. Asakura Publishing Company, Tokyo (in Japanese)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Adachi, K. Constrained principal component analysis of standardized data for biplots with unit-length variable vectors. Adv Data Anal Classif 5, 23–36 (2011). https://doi.org/10.1007/s11634-010-0081-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11634-010-0081-4