Quantifying inhomogeneity of spatial point patterns

This article compares measures for quantifying the level of inhomogeneity of a given spatial point pattern. Comparisons are based on two main metrics: first, we evaluate the performance of the measures on both certain stochastic point processes and on very specific point patterns designed to expose potential weaknesses of the inhomogeneity measures. Second, we evaluate the computational complexity of the measures. Results show that choosing a measure is a tradeoff between accurate assessment of inhomogeneity and computational complexity. The only exception is the proposed extended wrap-around measure, which is performing well in terms of both metrics.