The most promising of these tools is kernel density estimation (Chainey and
Ratcliffe, 2005; Sabel, 2006). There are many advantages of kernel
density estimation (KDE) as opposed to statistical hotspot and
clustering techniques such as K-means. The main advantage for this
method lies in determining the spread of risk of an accident. The
spread of risk can be defined as the area around a defined cluster in
which there is an increased likelihood for an accident to occur based
on spatial dependency. Secondly by using this density method, an
arbitrary spatial unit of analysis can be defined and be homo genous
for the whole area which makes comparison and ultimately a
taxonomy possible.