Latent Order Logistic Graph Models
Convert to either an UndirectedNet or DirectedNet object
Convert to either an UndirectedNet or DirectedNet object
Convert a DirectedNet to a network object
Convert a UndirectedNet to a network object
Network conversion
BinaryNet
Calculate network statistics from a formula
Internal Symbols
Extracts estimated model coefficients.
Creates a model
Creates a probability model for a latent ordered network model
indexing
Goodness of Fit Diagnostics for a LOLOG fit
Conduct goodness of fit diagnostics
An lolog plug-in for easy C++ prototyping and access
LatentOrderLikelihood
LOLOG Model Terms
Fits a LOLOG model via Monte Carlo Generalized Method of Moments
Models
Create a skeleton for a package extending lolog
Fits a latent ordered network model using Monte Carlo variational infe...
Plots a gofit object
Conduct Monte Carlo diagnostics on a lolog model fit
plot an DirectedNet object
Plot an UndirectedNet object
prints a gofit object
Print a lolog object
Print of a lologVariationalFit object
Register Statistics
Generates BinaryNetworks from a fit lolog object
Summary of a lolog object
Estimation of Latent Order Logistic (LOLOG) Models for Networks. LOLOGs are a flexible and fully general class of statistical graph models. This package provides functions for performing MOM, GMM and variational inference. Visual diagnostics and goodness of fit metrics are provided. See Fellows (2018) <arXiv:1804.04583> for a detailed description of the methods.