Exponential-Family Models for Signed Networks
Dyadwise shared enemies
Dyadwise shared friends
ergm.sign: A Package for Exponential Random Graph Models for Signed Ne...
Edgewise shared enemies
Edgewise shared friends
Logical layer constraint
Conduct Goodness-of-Fit Diagnostics for a Signed ERGM
Geometrically weighted dyadwise shared enemies distribution
Geometrically weighted dyadwise shared friends distribution
Geometrically weighted edgewise shared enemy distribution
Geometrically weighted edgewise shared friend distribution
Geometrically weighted non-edgewise shared enemey distribution
Geometrically weighted non-edgewise shared friend distribution
Delayed edgewise shared enemies
Delayed edgewise shared friends
Delayed node matching on attribute (lag-1)
Delayed reciprocity
Geometrically weighted delayed edgewise shared enemies
Geometrically weighted delayed edgewise shared friends
Evaluation of negative edges
Evaluation of positive edges
Fit an ERGM with MPLE using a logistic regression model
Create Signed Network Object
Combine Signed Networks into a Multi- or Dynamic-Network Object
Non-edgewise shared enemies
Non-edgewise shared friends
Visualization for Dynamic Signed Networks
Visualization for Signed Networks
Propose a randomly selected dyad to toggle, respecting the layer const...
Statnet Control
Summary formula method for dynamic signed networks
Network Attributes for Signed Networks
Default MH algorithm respecting the layer constraint
Multilayer network to single layer network.
Extends the 'ergm.multi' packages from the Statnet suite to fit (temporal) exponential-family random graph models for signed networks. The framework models positive and negative ties as interdependent, which allows estimation and testing of structural balance theory. The package also includes options for descriptive summaries, visualization, and simulation of signed networks. See Krivitsky, Koehly, and Marcum (2020) <doi:10.1007/s11336-020-09720-7> and Fritz, C., Mehrl, M., Thurner, P. W., & Kauermann, G. (2025) <doi:10.1017/pan.2024.21>.