Events and Meetings of Italian Statistical Society, Statistics and Demography: the Legacy of Corrado Gini

Font Size: 
The effect of location errors on distance-based measures of spatial concentration
Diego Giuliani, Simonetta Cozzi, Maria Michela Dickson, Giuseppe Espa

Last modified: 2015-09-04


It is probably fair to say that Ripley’s K-function is currently the most popular distance-based measure to summarize the cumulative characteristics of a spatial distribution of events in the context of micro-geographic data. It has indeed proved a very versatile tool to test for the presence of spatial concentration within a point pattern. As a consequence, the K-function has been largely applied in various fields such as geography, ecology, epidemiology and economics.

The K-function is based on the assumption that spatial information is completely accurate. In many practical circumstances, however, such information is inevitably affected by location errors. For various technical reasons, and especially in the context of socio-economic data, the geocoding processes cannot be exact. Typically, for a share of units, that in some cases is not negligible, it is not possible to identify the exact spatial coordinates. This results in point patterns with missing spatial values or coarsened locations.

By means of Monte Carlo experiments we aim at assessing the effect of this specific kind of non-sampling errors on the estimation of the K-function and we evaluate the consequences for inference.

Full Text: Untitled