Measuring Spatiotemporal Association for Migration Flow Data

Keywords: spatial statistics, flow data, space-time, autocorrelation, LISA
Abstract Type: Paper Abstract

Abstract

Spatial flow data represent meaningful spatial interaction (SI) phenomena between geographic regions that are often highly dynamic. However, there is a lack of methods to measure spatiotemporal autocorrelation of flow data. To fill this gap, we proposed a new spatial statistical method called Space-Time Flow LISA. The method design is a combination of two existing method families, namely space-time LISA and Spatial Flow LISA. A critical component is the space-time weight matrix of flow data that blends pairwise spatial and temporal connectivity. We designed three versions of the weight matrix, namely contemporaneous, lagged, and hybrid, and compared their performance using a case study of the state-level U.S. migration from 2005 to 2017. Unlike Spatial Flow LISA that tends to detect short ‘HH’ flows and long ‘LL’ flows, Space-Time Flow LISA is less impeded by the distance between origin and destination, as it can pick up local patterns that are not spatially explicit but temporally dependent. In addition, it was able to detect time-sensitive patterns such as the outmigration from Louisiana forced by Hurricane Katrina. By integrating spatial, temporal, and attributive associations into a one-step analysis, the proposed Space-Time Flow LISA can well illustrate the spatiotemporal structure of flow phenomena, and reveal dynamic distribution changes over time.