The network boundary specification problem in the global and world city research: investigation of the reliability of empirical results from sampled networks

Despite the well-known dependence of vertex and network structural parameters on network boundary specification employed by researchers, there has so far been effectively no discussion of this methodological caveat in the global and world city literature. Given the reliance of empirical studies of urban networks on the sampling of underlying actors that form these networks by their interactions, we consider it of key importance to examine the dependence of network centralities of cities on network boundary specification. We consider three distinctive modelling approaches based on: (a) office networks, (b) ownership ties and (c) inter-organisational projects. Our results indicate that city network centralities obtained from sampled networks are highly consistent with those obtained from whole network analysis for samples featuring as little as 4% (office networks), 10% (ownership ties) and 25% (inter-organisational projects) of the underlying actors.