
434 Data Analysis and Statistics for Geography, Environmental Science, and Engineering
where N is a scale factor (e.g., 1,000 or 10,000 depending on the units of population) and x
i
and P
i
are the number of events and population in region i.
13.4.3 Geary’s c
The Geary statistic c is a measure of dissimilarity, because it uses squared differences between
values of the variable instead of the product and is divided by 2.
c
wz z
w
z
ij
j
n
i
n
ij
j
n
i
n
i
i
n
=
−
∑∑
∑
2
2
2
(13.10)
This can be rewritten in the more common form
c
zz
ij
j
n
i
n
ij
j
n
i
n
i
i
n
=
∑
()
1
2
2
2
(13.11)
Note that for binary weights (1 or 0) this expression reduces to
c
zz
wz
ij