Neighbor relationships

Neighbor relationships underlie BoundarySeer's statistical methods. Data values are compared between neighboring points, polygons, and raster pixels for all boundary detection methods.

BoundarySeer determines relationships from the data files themselves.

Point data

BoundarySeer automatically finds nearest neighbors for points using a Delaunay triangulation (shown in the point data icon). You may edit neighbor relationships using the spatial network editor.

Polygon data

BoundarySeer defines adjacent polygons to be any two polygons that share an edge. Polygons without neighbors do not work for boundary detection. If you are wombling, difference boundaries cannot be detected around isolated polygons, and, if you are doing constrained classification, the isolated polygon will always be in its own class.

Polygons that overlap may not share a common edge, and may not appear to neighbor each other. Also, overlapping polygons may cause problems in analyses like location uncertainty, for which points must be contained in only one polygon.

Raster data

Raster pixels by definition share edges with each other, as shown in the icon itself.

See also:

• Introduction to importing data

• Data formats

• Editing spatial networks