Review on Determining the Number of Communities in Network Data
By: Zhengyuan Du, Jason Cui
Potential Business Impact:
Finds hidden groups in connected data.
This paper reviews statistical methods for hypothesis testing and clustering in network models. We analyze the method by Bickel et al. (2016) for deriving the asymptotic null distribution of the largest eigenvalue, noting its slow convergence and the need for bootstrap corrections. The SCORE method by Jin et al. (2015) and the NCV method by Chen et al. (2018) are evaluated for their efficacy in clustering within Degree-Corrected Block Models, with NCV facing challenges due to its time-intensive nature. We suggest exploring eigenvector entry distributions as a potential efficiency improvement.
Similar Papers
Joint estimation of asymmetric community numbers in directed networks
Methodology
Finds hidden groups in connected information.
A Goodness-of-Fit Test for Sparse Networks
Methodology
Tests if network patterns fit a model.
Goodness-of-fit test for multi-layer stochastic block models
Methodology
Finds hidden groups in connected data.