Kernel estimation is a popular approach to estimation of the pair correlation function function which is a fundamental spatial point process characteristic. Least squares cross validation was suggested by Guan (2007a) as a data-driven approach to select the kernel bandwidth. The method can, however, be computationally demanding for large point pattern data sets. We suggest a modified least squares cross validation approach that is asymptotically equivalent to the one proposed by Guan (2007a) but is computationally much faster.
Keywords: bandwidth, kernel estimator, pair correlation function, spatial point process