Premium
Validity in World City Network Measurements
Author(s) -
Neal Zachary
Publication year - 2014
Publication title -
tijdschrift voor economische en sociale geografie
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.766
H-Index - 55
eISSN - 1467-9663
pISSN - 0040-747X
DOI - 10.1111/tesg.12094
Subject(s) - measure (data warehouse) , construct (python library) , linkage (software) , computer science , bipartite graph , projection (relational algebra) , architecture , global network , regional science , real world data , data science , artificial intelligence , geography , data mining , theoretical computer science , telecommunications , algorithm , graph , biochemistry , chemistry , archaeology , gene , programming language
In the literature on world city networks, there has been a proliferation of both theories and measurement methodologies, but relatively little attention to the linkage between theory and measurement. In this paper, I review the interlocking world city network model ( IWCNM ) and three additional bipartite projection‐based measures of the world city network, considering which theoretical conception of the ‘world city network’ construct each can validly measure. I introduce a new Stata command, onemode , to compute these four measures, and use them to produce world city networks from three publicly available datasets on advanced producer services, international organisations, and engineering and architecture firms. The results suggest that each projection‐based measure is potentially valid, but only for a corresponding understanding of the world city network. Researchers are encouraged to clearly define what they mean when invoking the phrase ‘the world city network,’ and only then selecting a measurement that is valid.