Bipartite Partial Configuration Model - Documentation¶
The Bipartite Partial Configuration Model (BiPCM) is a statistical null model for binary bipartite networks. It offers an unbiased method of analyzing node similarities and obtaining statistically validated monopartite projections [Saracco2016].
The BiPCM is related to the Bipartite Configuration Model (BiCM) [Saracco2015], but imposes only constraints on the degrees of one bipartite node layer. It belongs to a series of entropy-based null model for binary biparite networks, see also
Please consult the original articles for details about the underlying methods and applications to user-movie and international trade databases [Saracco2016], [Straka2016].
An example case is illustrated in the Tutorial.
How to cite¶
If you use the bipcm module, please cite its location on Github and the original article [Saracco2016].
References¶
| [Saracco2015] | F. Saracco, R. Di Clemente, A. Gabrielli, T. Squartini, Randomizing bipartite networks: the case of the World Trade Web, Scientific Reports 5, 10595 (2015) |
| [Straka2016] | M. J. Straka, F. Saracco, G. Caldarelli, Product Similarities in International Trade from Entropy-based Null Models, Complex Networks 2016, 130-132 (11 2016), ISBN 978-2-9557050-1-8 |