Data Mining for the Social Sciences: An Introduction by Paul Attewell & David Monaghan

Author:Paul Attewell & David Monaghan
Language: eng
Format: mobi
ISBN: 9780520280977
Publisher: University of California Press
Published: 2015-04-29T14:00:00+00:00

FIGURE 8.1

A three-dimensional scatterplot produced by JMP Pro.

When we perform a PCA of our three variables using JMP, we can visually inspect the relations between the data, the variables, and the principal components by producing three biplots. These are simply scatterplots with the principal components forming the axes (figure 8.2).

Both the top and middle plots have component 1, the first principal component, as the x axis. The fact that the data cloud is spread out horizontally clearly demonstrates that most of the variance in the data occurs along this dimension—79.3% of it, to be exact (table 8.2). We can also see that the vertical variance is slightly more pronounced in the top-left plot. This is because the vertical dimension here is the second principal component, which describes more of the variance, intrinsically, than does the third.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.