12.07.2015 Views

Jolliffe I. Principal Component Analysis (2ed., Springer, 2002)(518s)

Jolliffe I. Principal Component Analysis (2ed., Springer, 2002)(518s)

Jolliffe I. Principal Component Analysis (2ed., Springer, 2002)(518s)

SHOW MORE
SHOW LESS
  • No tags were found...

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

5.2. <strong>Principal</strong> Coordinate <strong>Analysis</strong> 85Figure 5.2. Artistic qualities of painters: plot of 54 painters with respect to theirfirst two PCs. The symbol × denotes member of the ‘Venetian’ school.is looking for major directions of variation between means rather thanmajor directions of variation in a common distribution (de Falguerolles,personal communication). This view is in line with the fixed effect modelof Section 3.9, and is discussed further in Section 5.3.A variation of the simple plot of PC scores for the first two PCs isproposed by Tarpey (2000). Lines are added to the plot, correspondingto the directions of the first PC for two subsets of the data, derived bydividing the full data set according to the sign of the first PC for the wholedata set. The idea is to indicate possible non-linearity in the data (seeSection 14.1.3).5.2 <strong>Principal</strong> Coordinate <strong>Analysis</strong><strong>Principal</strong> coordinate analysis is a scaling or ordination method, sometimesknown as classical scaling. It was popularized by Gower (1966). Torgerson(1952, 1958) discussed similar ideas, but did not point out the links be-

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!