Biplots of Compositional Data

Summary. The singular value decomposition and its interpretation as a linear biplot have proved to be a powerful tool for analysing many forms of multivariate data. Here we adapt biplot methodology to the specific case of compositional data consisting of positive vectors each of which is constrained to have unit sum. These relative variation biplots have properties relating to the special features of compositional data: the study of ratios, subcompositions and models of compositional relationships. The methodology is applied to a data set consisting of six-part colour compositions in 22 abstract paintings, showing how the singular value decomposition can achieve an accurate biplot of the colour ratios and how possible models interrelating the colours can be diagnosed.

[1]  M. Greenacre.  Singular value decomposition of matched matrices , 2003 .

[2]  M. Greenacre,et al.  Measuring Asymmetries in Brand Associations Using Correspondence Analysis , 2003 .

[3]  Juan M. C. Larrosa.  A Compositional Statistical Analysis of Capital per Worker , 2003 .

[4]  M. Greenacre.  Ratio maps and correspondence analysis , 2002 .

[5]  Analysis of Matched Matrices , 2001 .

[6]  Michael Greenacre,et al.  Tying Up the Loose Ends in Simple Correspondence Analysis , 2001 .

[7]  J. Aitchison.  Logratios and Natural Laws in Compositional Data Analysis , 1999 .

[8]  Michael Greenacre,et al.  Biplots in correspondence analysis , 1993 .

[9]  J. Aitchison.  On criteria for measures of compositional difference , 1992 .

[10]  K R Gabriel,et al.  Biplots in biomedical research. , 1990, Statistics in medicine.

[11]  R. Clarke,et al.  Theory and Applications of Correspondence Analysis , 1985 .

[12]  John Aitchison,et al.  The Statistical Analysis of Compositional Data , 1986 .

[13]  M. Greenacre,et al.  Topics in Applied Multivariate Analysis: SCALING A DATA MATRIX IN A LOW-DIMENSIONAL EUCLIDEAN SPACE , 1982 .

[14]  K Ruben Gabriel,et al.  Biplot Display of Multivariate Matrices for Inspection of Data and Diagnosis. , 1980 .

[15]  K. Ruben Gabriel,et al.  The Biplot as a Diagnostic Tool for Models of Two-Way Tables , 1978 .

[16]  J. Cheminée,et al.  Application of correspondence factor analysis to the study of major and trace elements in the Erta Ale Chain (Afar, Ethiopia) , 1975 .

[17]  R. W. May.  Progresses in R- and Q-Mode Analysis: Correspondence Analysis and its Application to the Study of Geological Processes: Discussion , 1974 .

[18]  Richard Darling,et al.  Progresses in R- and Q-Mode Analysis: Correspondence Analysis and its Application to the Study of Geological Processes , 1974 .

[19]  K. Ruben Gabriel,et al.  Analysis of Meteorological Data by Means of Canonical Decomposition and Biplots. , 1972 .

[20]  K. Gabriel,et al.  The biplot graphic display of matrices with application to principal component analysis , 1971 .

[21]  Konrad B. Krauskopf,et al.  Introduction to geochemistry , 1967 .

[22]  A. T. Miesch,et al.  Multivariate Analysis of Geochemical Data on Tektites , 1966, The Journal of Geology.

[23]  C. Eckart,et al.  The approximation of one matrix by another of lower rank , 1936 .

[24]  G. Hardy.  MENDELIAN PROPORTIONS IN A MIXED POPULATION. , 1908 .

[25]  James Clerk Maxwell,et al.  On the theory of compound colours, and the relations of the colours of the spectrum , 1860, Proceedings of the Royal Society of London.