Multivariate classification of constrained data: problems and alternatives

被引:6
作者
Aruga, R [1 ]
机构
[1] Univ Turin, Dept Analyt Chem, I-10125 Turin, Italy
关键词
closed data; compositional data; multivariate classification; principal component analysis; radial data;
D O I
10.1016/j.aca.2004.07.068
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The problems relating to multivariate classifications carried out on matrices of constrained data are examined with reference both to row-sum constraints (closed, or compositional data) and to constraints concerning the ratio between variables (radial, or V-shaped data). As regards the use of principal component analysis (PCA) with closed data, the two opposite drawbacks observed previously with raw data and after a log row centering (or Aitchison's transform) are confirmed. It is demonstrated, in particular, that classifications based on raw closed data give too much weight to major variables, while those based on log row centered data to minor and trace variables. In consideration of this, a 'unified' procedure is proposed, which simultaneously processes with principal component analysis the two kinds of data above. Such a procedure seems to obviate the cited drawbacks and to give correct classifications. These results have been obtained using both simulated and real data, the latter referring to a set of archaeological glass finds. The problem of the influence of responses below the detection limit on the classifications is also examined, together with some aspects relating to the classification of radial data. (C) 2004 Elsevier B.V. All rights reserved.
引用
收藏
页码:45 / 51
页数:7
相关论文
共 26 条
[1]  
AITCHISON J, 1982, J ROY STAT SOC B, V44, P139
[2]   A NEW APPROACH TO NULL CORRELATIONS OF PROPORTIONS [J].
AITCHISON, J .
JOURNAL OF THE INTERNATIONAL ASSOCIATION FOR MATHEMATICAL GEOLOGY, 1981, 13 (02) :175-189
[3]   Logratios and natural laws in compositional data analysis [J].
Aitchison, J .
MATHEMATICAL GEOLOGY, 1999, 31 (05) :563-580
[4]  
AITCHISON J, 1983, BIOMETRIKA, V70, P57
[5]  
Aitchison J., 1986, The Statistical Analysis of Compositional Data, DOI DOI 10.1007/978-94-009-4109-0
[6]   The problem of responses less than the reporting limit in unsupervised pattern recognition [J].
Aruga, R .
TALANTA, 2004, 62 (05) :871-878
[7]   The problem of multivariate classification of samples with radial (or V-shaped) chemical data [J].
Aruga, R .
TALANTA, 2003, 60 (05) :937-944
[8]   Closure of analytical chemical data and multivariate classification [J].
Aruga, R .
TALANTA, 1998, 47 (04) :1053-1061
[9]   Treatment of responses below the detection limit: some current techniques compared by factor analysis on environmental data [J].
Aruga, R .
ANALYTICA CHIMICA ACTA, 1997, 354 (1-3) :255-262
[10]   MULTIVARIATE-ANALYSIS OF DATA ON GLASS COMPOSITIONS - A METHODOLOGICAL NOTE [J].
BAXTER, MJ .
ARCHAEOMETRY, 1989, 31 :45-53