Compositional Canonical Correlation Analysis

The study of the relationships between two compositions by means of canonical correlation analysis is addressed A coimnositional version of canonical correlation analysis is developed. and called CODA-CCO. We consider two approaches, using the centred log-ratio transformation and the calculation of all possible pairwise log-ratios within sets. The relationships between both approaches are pointed out, and their merits are discussed. The related covariance matrices are structurally singular, and this is efficiently dealt with by using generalized inverses. We develop compositional canonical biplots and detail their properties. The canonical biplots are shown to be powerful tools for discovering the most salient relationships between two compositions. Some guidelines for compositional canonical biplots construction are discussed. A geological data set with X-ray fluorescence spectrometry measurements on major oxides and trace elements is used to illustrate the proposed method. The relationships between an analysis based on centred log-ratios and on isometric log-ratios are also shown.

[1]  V. Pawlowsky-Glahn,et al.  Modeling and Analysis of Compositional Data , 2015 .

[2]  V. Pawlowsky-Glahn,et al.  Modelling and Analysis of Compositional Data: Pawlowsky-Glahn/Modelling and Analysis of Compositional Data , 2015 .

[3]  K. Gerald van den Boogaart,et al.  Analyzing Compositional Data with R , 2013 .

[4]  V. Pawlowsky-Glahn,et al.  Compositional data analysis : theory and applications , 2011 .

[5]  Roberto Cesareo,et al.  X-Ray fluorescence spectrometry , 2002 .

[6]  Abel M. Rodrigues.  Matrix Algebra Useful for Statistics , 2007 .

[7]  Charles E. Heckler,et al.  Applied Multivariate Statistical Analysis , 2005, Technometrics.

[8]  Jan Graffelman,et al.  Enriched biplots for canonical correlation analysis , 2005 .

[9]  Jan Graffelman,et al.  Optimal Representation of Supplementary Variables in Biplots from Principal Component Analysis and Correspondence Analysis , 2003 .

[10]  G. Mateu-Figueras,et al.  Isometric Logratio Transformations for Compositional Data Analysis , 2003 .

[11]  J. Aitchison,et al.  Biplots of Compositional Data , 2002 .

[12]  C. Braak,et al.  Interpreting canonical correlation analysis through biplots of structure correlations and weights , 1990 .

[13]  B. Manly.  Multivariate Statistical Methods : A Primer , 1986 .

[14]  C. Braak.  Canonical Correspondence Analysis: A New Eigenvector Technique for Multivariate Direct Gradient Analysis , 1986 .

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

[16]  R. Cranley,et al.  Multivariate Analysis—Methods and Applications , 1985 .

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

[18]  J. Aitchison.  Principal component analysis of compositional data , 1983 .

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

[20]  D. Stewart,et al.  A general canonical correlation index. , 1968, Psychological bulletin.

[21]  T. W. Anderson,et al.  An Introduction to Multivariate Statistical Analysis , 1959 .

[22]  H. Hotelling.  Relations Between Two Sets of Variates , 1936 .

[23]  Pierre Legendre,et al.  Canonical Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[24]  Anja Vogler,et al.  An Introduction to Multivariate Statistical Analysis , 2004 .

[25]  Ter Braak,et al.  Canoco reference manual and CanoDraw for Windows user''s guide: software for canonical community ord , 2002 .

[26]  C.J.F. ter Braak,et al.  Biplots in Reduced-Rank Regression , 1994 .

[27]  Hisashi Kobayashi,et al.  Modeling and analysis , 1978 .

[28]  B. Chappell,et al.  X-ray fluorescence spectrometry , 1977 .

[29]  H. Hotelling.  The most predictable criterion. , 1935 .