Premium
Distance in Spatial Analysis: Measurement, Bias, and Alternatives
Author(s) -
Mu Wangshu,
Tong Daoqin
Publication year - 2020
Publication title -
geographical analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.773
H-Index - 65
eISSN - 1538-4632
pISSN - 0016-7363
DOI - 10.1111/gean.12254
Subject(s) - polygon (computer graphics) , metric (unit) , point (geometry) , distance measures , computer science , algorithm , mathematics , mathematical optimization , artificial intelligence , geometry , telecommunications , operations management , frame (networking) , economics
Distance is an important and basic concept in geography. Many theories, methods, and applications involve distance explicitly or implicitly. While measuring the distance between two locations is a straightforward task, many geographical processes involve areal units, where the distance measurement can be complicated. This research investigates distance measurement between a location (point) and an area (polygon). We find that traditional polygon‐to‐point distance measurements, which involve abstracting a polygon into a central or representative point, could be problematic and may lead to biased estimates in regression analysis. To solve this issue, we propose a new polygon‐to‐point distance metric along with two algorithms to compute the new distance metric. Simulation analysis shows the effectiveness of the new distance metric in providing unbiased estimates in linear regression.