multipleVLTransferEntropy: multipleVLTransferEntropy

In VLTimeCausality: Variable-Lag Time Series Causality Inference Framework

Description

multipleVLTransferEntropy is a function that infers Variable-lag Transfer Entropy of all pairwises of m time series TS[,1],...TS[,m].

Usage

multipleVLTransferEntropy(
  TS,
  maxLag,
  nboot = 0,
  lx = 1,
  ly = 1,
  VLflag = TRUE,
  autoLagflag = TRUE,
  alpha = 0.05
)

Arguments

TS	is a numerical time series of effect where TS[t,k] is an element at time t of kth time series.
maxLag	is a maximum possible time delay. The default is 0.2*length(Y).
nboot	is a number of times of bootstrapping for RTransferEntropy::transfer_entropy() function.
lx, ly	are lag parameters of RTransferEntropy::transfer_entropy().
VLflag	is a flag of Granger causality choice: either VLflag=TRUE for VL-Granger or VLflag=FALSE for Granger causality.
autoLagflag	is a flag for enabling the automatic lag inference function. The default is true. If it is set to be true, then maxLag is set automatically using cross-correlation. Otherwise, if it is set to be false, then the function takes the maxLag value to infer Granger causality.
alpha	is a significant-level threshold for TE bootstrapping by Dimpfl and Peter (2013).

Value

This function returns of a list of an adjacency matrix of causality where adjMat[i,j] is true if TS[,i] causes TS[,j].

Examples

## Generate simulation data
#out1<-SimpleSimulationVLtimeseries()
#TS<-cbind(out1$X,out1$Y)
## Run the function
#out2<-multipleVLTransferEntropy(TS,maxLag=1)

VLTimeCausality documentation built on Jan. 24, 2022, 5:07 p.m.