I have a rather complex network (air travel in the US) with more than 500 nodes, and small-world, scale-free proprieties, spanning over 10 years, and with quarterly information.

As I'm trying to characterise the network, I've pulled a couple of statistics, such as degree centrality, density, average path length, closeness, etc... However, I know what it means to have a low density for example, but I don't know how to validate its variation. Meaning that if I get for one year density = 0.021, and the year after density = 0.018, is that variation a lot or not? The same obviously applies to all other statistics I can get from this network.

What I want is to understand if the network characteristics being used by researchers, are adequate or not, when looking at this particular dataset, as if they vary too much, working with one year only might not make that much sense.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.