What is it about?
We introduce a flow-based cluster algorithm, flowbca, written in Stata's development language Mata. Examples of applications are provided from the research fields of economic geography, industrial input-output analysis and social network analysis. All kinds of flow data - think of commuting flows from residence to workplace, job-to-job flows, migration flows, trade flows, friendship ties, social media data flows, etc. - could be used to define self-contained clusters. Examples of clusters include regional clusters such as local labor markets or global trade clusters, and communities of people.
Featured Image
Photo by Martin Sanchez on Unsplash
Why is it important?
So far, the flow-based cluster algorithms available in Stata focus on visualizing social networks. A limitation of these algorithms is that they are not able to flexibly aggregate units based on relational data of flows. Other agglomerative hierarchical clustering algorithms that are available in Stata are distance-based instead of flow-based. The flowbca command might be very useful for researchers in various research disciplines, as in many disciplines the availability of relational data of flows has been increasing over the last years.
Perspectives
The main purpose to write flowbca was to define local labor markets based on relational data of commuting flows from place of home to place of work. The algorithm allows researchers to operationalize local labor markets (i) for different subgroups of workers, and (ii) at a continuous level of regional aggregation. This provides a choice of how to operationalize clusters in research and allows a researcher to compare the results and conclusions based on alternative sets of clusters.
Dr Jordy Meekes
Universiteit Leiden
Read the Original
This page is a summary of: Flowbca: A Flow-Based Cluster Algorithm in Stata, September 2018, SAGE Publications,
DOI: 10.1177/1536867x1801800305.
You can read the full text:
Resources
Contributors
The following have contributed to this page
