sampleParms: Sample initial parameters for the MCMC simulation.

In EDISON: Network Reconstruction and Changepoint Detection

Description

This function samples the initial hyperparameters and parameters that are needed for the MCMC simulation.

Usage

sampleParms(X, GLOBvar, HYPERvar, s_init = NULL, options)

Arguments

X	Input data.
GLOBvar	Global variables of the MCMC simulation.
HYPERvar	Hyperparameter variables.
s_init	Initial number of changepoints.
options	MCMC options, as given by e.g. defaultOptions.

Value

Returns a list with elements:

E	The initial changepoint vector.
S	The intial networks structure.
B	The initial regression parameters.
Sig2	The inital sigma squared variances.
betas	The intial hyperparameters for the exponential information sharing prior.
hyper_params	The initial hyperparameters for the binomial information sharing prior.

Author(s)

Sophie Lebre

Frank Dondelinger

References

For more information about the parameters and hyperparameters, see:

Dondelinger et al. (2012), "Non-homogeneous dynamic Bayesian networks with Bayesian regularization for inferring gene regulatory networks with gradually time-varying structure", Machine Learning.

See Also

init

EDISON documentation built on May 2, 2019, 2:39 a.m.