Biology Reference
In-Depth Information
TABLE 6.1
Eigenvalues From PCA of Squirrel Jaws
PC
Eigenvalues
% of Total Variance
10
2
3
1
1.13
3
51.56
10
2
4
2
2.15
3
9.83
10
2
4
3
1.64
3
7.49
10
2
4
4
1.36
3
6.22
10
2
4
5
1.16
3
5.32
10
2
5
6
9.52
4.36
3
10
2
5
7
7.18
3.28
3
10
2
5
8
5.45
2.49
3
10
2
5
9
4.49
2.05
3
10
2
5
10
3.58
1.64
3
10
2
5
11
3.25
1.49
3
10
2
5
12
2.36
1.08
3
10
2
5
13
1.79
0.82
3
10
2
5
14
1.37
0.63
3
10
2
6
15
9.83
0.45
3
10
2
6
16
9.31
0.43
3
10
2
6
17
6.87
3
0.31
10
2
6
18
3.72
3
0.17
10
2
6
19
3.06
3
0.14
10
2
6
20
2.17
3
0.10
10
2
6
21
1.66
3
0.08
10
2
7
22
7.04
3
0.03
10
2
7
23
5.37
0.02
3
10
2
7
24
3.62
0.02
3
10
2
7
25
1.15
0.01
3
10
2
8
26
5.02
0.01
3
,
difficulty with applying this rule is that scree plots often do not have inflection points that
are as obvious as the one in
Figure 6.7
.
Fortunately, there is a more rigorous approach to testing whether two successive PCs
have distinct variances. This is an application of a test developed by
Anderson (1958)
and
discussed in
Morrison (1990)
. The null hypothesis is that some sets of
R
consecutive