Tangri, D. and Wright, R. V S. (1993). Multivariate analysis of compositional data: applied comparisons favour standard principal components analysis over Aitchison's loglinear contrast method. Archaeometry 35 (1). Vol 35(1), pp. 103-115.
Title The title of the publication or report |
Multivariate analysis of compositional data: applied comparisons favour standard principal components analysis over Aitchison's loglinear contrast method | |
---|---|---|
Issue The name of the volume or issue |
Archaeometry 35 (1) | |
Series The series the publication or report is included in |
Archaeometry | |
Volume Volume number and part |
35 (1) | |
Page Start/End The start and end page numbers. |
103 - 115 | |
Biblio Note This is a Bibliographic record only. |
Please note that this is a bibliographic record only, as originally entered into the BIAB database. The ADS have no files for download, and unfortunately cannot advise further on where to access hard copy or digital versions. | |
Publication Type The type of publication - report, monograph, journal article or chapter from a book |
Journal | |
Abstract The abstract describing the content of the publication or report |
There has been debate about whether standard principal components analysis is appropriate for the multivariate analysis of compositional data (eg oxide composition of glass). Loglinear transformation has been recommended by Aitchison as a prerequisite. This paper argues that previous comparisons of methodological merits have tended to circularity of argument by making assumptions about the form of a good multivariate result. To break the circularity of argument the authors have introduced randomised variables into five data sets. A good result must recognise these randomised variables as noise and place them near the centroid of the principal components scattergram of variable loadings. Standard principal components analysis is found to perform better than loglinear transformation in its ability to recognise the randomised variables. It is concluded that loglinear transformation tends to introduce spurious structure into a table of compositional data. There is a comment from M J Baxter (112--15) who is not wholly convinced by their reasoning. | |
Year of Publication The year the book, article or report was published |
1993 | |
Locations Any locations covered by the publication or report. This is not the place the book or report was published. |
|
|
Source Where the record has come from or which dataset it was orginally included in. |
BIAB
(The British Archaeological Bibliography (BAB))
|
|
Created Date The date the record of the pubication was first entered |
20 Jan 2002 |