priors: Set of possible priors for the number of changepoints (CPs)...

In ARTIVA: Time-Varying DBN Inference with the ARTIVA (Auto Regressive TIme VArying) Model

Description

Set of possible priors used in the ARTIVAsubnet function for the number of changepoints (resp. incoming edges) according to a given number of maximum changepoints maxCP (resp. incoming Edges maxPred) when parameters (alphaCP, betaCP for the CPs or alphaEdges, betaEdges for the edges) in function ARTIVAsubnet are set to default (alpha=1, beta=0.5). In the ARTIVAsubnet procedure, the number of CPs (respectively the number of incoming edges) is sampled from a truncated Poisson with mean lambda, where lambda is drawn from an Inverse Gamma distribution (alpha, beta), see Lebre et al. (2010) for more details.

Usage

data(priors)

Format

A matrix of 96 rows by 44 columns (kmax, alpha, beta and the probability for k=0 to 40 according to the chosen values of kmax, alpha and beta).

References

Statistical inference of the time-varying structure of gene-regulation networks S. Lebre, J. Becq, F. Devaux, M. P. H. Stumpf, G. Lelandais, BMC Systems Biology, 2010, 4:130.

See Also

choosePriors,ARTIVAsubnet, ARTIVAnet

Examples

# See some prior probability density when the maximal number of
# CPs/parents is equal to 5
data(priors)
choosePriors(kmax=5,priors)

ARTIVA documentation built on May 1, 2019, 6:31 p.m.