Abstract
A widely applicable edge correction method for estimating summary statistics of a spatial point pattern is proposed. We reconstruct point patterns in a larger region containing the sampling window by matching sampled and simulated kth nearest neighbour distance distributions of the given pattern and then apply plus sampling. Simulation studies show that this approach, called quasi-plus sampling, gives estimates with smaller root mean squared errors than estimates obtained by using other popular edge corrections. We apply the proposed approach to real data and yield an estimate of a summary statistic that is more plausible than that obtained by a popular edge correction.
Original language | English |
---|---|
Pages (from-to) | 5287-5295 |
Number of pages | 9 |
Journal | Computational Statistics and Data Analysis |
Volume | 52 |
Issue number | 12 |
Early online date | 22 May 2008 |
DOIs | |
Publication status | Published - Aug 2008 |