Exploratory Spatial Data Analysis for Flow Data: Exploring The Error Term of Spatial Interaction Models

Abstrak

In a number of problem domains there is an increasing interest in exploring flow data, which is defined as data that captures movement between places on a given network, including most branch of engineering, transportation, telecommunication, social system, and economic geography;.. However, the current state of the art in exploratory spatial data analysis (ESDA,); which is largely dominated by geo-statistical and lattice data analysis, lack techniques and methodologies for the exploration of flow data. Although the general underlying concepts are largely the same, flow data requires a different set of specific methods for data exploration. In this paper I extend the methods of spatial stat is tic for identifying spatial clusters and outliers to work with flow data, and demonstrate the methods to detect spatial error dependence and heteroskedasticity  in the error term of spatial interaction models.