next up previous
Next: References

Ripley's K function

Andy Long

This summary of Ripley's K function is taken from Bailey and Gatrell[1].

The definition of the K function is as follows:

displaymath113

where tex2html_wrap_inline127 is the intensity, or mean number of events per unit area. If R is the area of region tex2html_wrap_inline131 , then the expected number of events in tex2html_wrap_inline131 is tex2html_wrap_inline135 .

Let tex2html_wrap_inline137 be the distance between the tex2html_wrap_inline139 and tex2html_wrap_inline141 events in tex2html_wrap_inline131 , and tex2html_wrap_inline145 be the indicator function which is 1 if tex2html_wrap_inline147 and 0 otherwise. Then an estimate of K is given by

displaymath114

This estimate does not account for the fact that there may be pairs for which one partner point is outside the region, and hence unobservable. Thus an edge-corrected estimate of K is given by

displaymath115

where tex2html_wrap_inline153 is the conditional probability that an event is observed in region tex2html_wrap_inline131 , given that it is a distance tex2html_wrap_inline137 from the event i. (To understand how to calculate tex2html_wrap_inline153 , draw a circle around the tex2html_wrap_inline139 point; if the circle intersects the boundary of tex2html_wrap_inline131 , calculate the ratio of the area inside the boundary to the whole area.)

The ordinary estimate of tex2html_wrap_inline127 is N/R. Thus the computational formula for tex2html_wrap_inline171 becomes

displaymath116

Note that we are always interested in values of h small compared to the scale of region tex2html_wrap_inline131 : ``it is not realistic to attempt to explore second order effects which operate on the same physical scale as the dimensions of [ tex2html_wrap_inline131 ].''

As an exploratory tool, we need to consider what manner of comparison we can make to help us interpret K. For a homogeneous Poisson process, the number of events within a chosen distance h of an event would be just tex2html_wrap_inline183 . This suggests a plot of

displaymath117

against a plot of f(h)=h.

``Under regularity K(h) would be less than tex2html_wrap_inline183 , whereas under clustering K(h) would be greater than tex2html_wrap_inline183 .'' Hence, where L(h) is above the identity function line, we imagine that there is clustering at that scale; where it is below, there is greater regularity than we would expect in the face of a Poisson process.




next up previous
Next: References

Andrew E Long
Thu Oct 14 13:22:58 EDT 1999