randomGVARmodel {graphicalVAR}R Documentation

Simulate a graphical VAR model

Description

Simulates an contemporaneous and temporal network using the method described by Yin and Li (2001)

Usage

randomGVARmodel(Nvar, probKappaEdge = 0.1, probKappaPositive = 0.5, probBetaEdge = 0.1, 
      probBetaPositive = 0.5, maxtry = 10, kappaConstant = 1.1)

Arguments

Nvar

Number of variables

probKappaEdge

Probability of an edge in contemporaneous network

probKappaPositive

Proportion of positive edges in contemporaneous network

probBetaEdge

Probability of an edge in temporal network

probBetaPositive

Propotion of positive edges in temporal network

maxtry

Maximum number of attempts to create a stationairy VAR model

kappaConstant

The constant used in making kappa positive definite. See Yin and Li (2001)

Details

The resulting simulated networks can be plotted using the plot method.

Value

A list containing:

kappa

True kappa structure (residual inverse variance-covariance matrix)

beta

True beta structure

PCC

True partial contemporaneous correlations

PDC

True partial temporal correlations

Author(s)

Sacha Epskamp

References

Yin, J., & Li, H. (2011). A sparse conditional gaussian graphical model for analysis of genetical genomics data. The annals of applied statistics, 5(4), 2630-2650.


[Package graphicalVAR version 0.3.4 Index]