Information Technology Reference
In-Depth Information
cabipl(X = as.matrix(SACrime08.data), constant = 0.055,
dim.biplot = 1, n.int = rep(5,14), offset = c(0, 2, 0, 0.5),
ort.lty = 2, plot.col.points = FALSE, predictions.sample = 9,
propshift = -0.24)
leaving all other arguments at their defaults.
A screenshot of a three-dimensional biplot constructed from the first three columns
of
U
1
/
2
is given in Figure 7.2. This biplot is an example of the output of
our R function
cabipl
with argument
dim.bipl = 3
. The full call to
cabipl
is:
1
/
2
and
V
cabipl(X = as.matrix(SACrime08.data), dim.biplot = 3,
samples.plot = TRUE, size.points.3d = 0.025, ID.labs = TRUE,
adjust.3d = c(1.5, 0.5),
ID.3d = rownames(SACrime08.data))
RAC
0
Rape
0.01
0
PubV
0
0.002
0.004
0.006
0.008
Mrd
0
0.005
InAs
0
0.005
0.01
0.015
0.02
DrgR
0
0.05
0.1
0.15
0.2
CmRb
0.02
0.01
0
CmAs
0
CrJk
0
BRs
0
BNRs
0
0.0002
0.0004
AtMr
0
AGBH
0.02
0
Arsn
0.005
0
Gaut
Mpml
FrSt
NWst
NCpe
KZN
WCpe
Limp
ECpe
Figure 7.1
One-dimensional CA biplot for the 2007/08 crime contingency table.
Proportional to Pearson residuals in deviation form
R
−
1
/
2
C
−
1
/
2
; constructed from
(
X
−
E
)
1
/
2
1
/
2
.
U
and
V