Deterministic blockmodeling
Deterministic blockmodeling is approach in blockmodeling, that does not assume probabilistic model, and instead relies on the exact or approximate algorithms, which are used to find blockmodel(s). This approach minimizes some inconsistency, that can accure with the ideal block structure.[1] Such approach can be used only for analysis of nominal valued networks.[2]
Such analysis is focused on clustering (grouping) of the network (or adjacency matrix), that is obtained with minimizing an objective function, which measures discrepancy from the ideal block structure.[3]
This approach was popularized in 1970s, due to the presence of two computer packages (CONCOR and STRUCTURE), that were used to "find a permutation of the rows and columns in the adjacency matrix leading to an approximate block structure".[4]
Opposite approach to the deterministic blockmodeling is a stochastic blockmodeling approach.[5]
References
- ^ Brusco, Michael; Doreian, Patrick; Steinley, Douglas; Satornino, Cinthia B. (2013). "Multiobjective blockmodeling for social network analysis". Psychometrika. 78 (3): 498–525. doi:10.1007/S11336-012-9313-1.
- ^ Aleš Žiberna, Generalized blockmodeling of valued networks (pospološeno bločno modeliranje omrežij z vrednostmi na povezavah: doktorska disertacija. Ljubljana: Univerza v Ljubljani, Fakulteta za družbene vede, 2007, p. 22. URL: http://www2.arnes.si/~aziber4/blockmodeling/Dissertation-final-corrected.pdf.
- ^ Wyse, Jason; Friel, Nial; Latouche, Pierre (2015). "Inferring structure in bipartite networks using the latent blockmodel and exact ICL". Journal of Classification. 14: 75–100.
- ^ Snijders, Tom A. B.; Nowicki, Krzysztof (1997). "Estimation and Prediction for Stochastic Blockmodels for Graphs with Latent Block Structure". Journal of Classification. 14: 75–100.
- ^ Wyse, Jason; Friel, Nial; Latouche, Pierre (2015). "Inferring structure in bipartite networks using the latent blockmodel and exact ICL". Journal of Classification. 14: 75–100.