Learn R Programming

backShift (version 0.1.4.3)

Learning Causal Cyclic Graphs from Unknown Shift Interventions

Description

Code for 'backShift', an algorithm to estimate the connectivity matrix of a directed (possibly cyclic) graph with hidden variables. The underlying system is required to be linear and we assume that observations under different shift interventions are available. For more details, see .

Copy Link

Version

Install

install.packages('backShift')

Monthly Downloads

317

Version

0.1.4.3

License

GPL

Issues

0

Pull Requests

0

Stars

6

Forks

1

Maintainer

Christina Heinze-Deml

Last Published

May 6th, 2020

Functions in backShift (0.1.4.3)

plotDiagonalization

Plots the joint diagonalization. I.e. if it was successful the matrices should all be diagonal.
bootstrapBackShift

Computes a simple model-based bootstrap confidence interval for success of joint diagonalization procedure. The model-based bootstrap approach assumes normally distributed error terms; the parameters of the noise distribution are estimated with maximum likelihood.
generateA

Generates a connectivity matrix A.
plotGraphEdgeAttr

Plotting function to visualize directed graphs
metricsThreshold

Performance metrics for estimate of connectiviy matrix A.
computeDiagonalization

Computes the matrix \(\Delta \Sigma_{c,j}\) resulting from the joint diagonalization for a given environment (cf. Eq.(7) in the paper). If the joint diagonalization was successful the matrix should be diagonal for all environments $j$.
plotInterventionVars

Plots the estimated intervention variances.
simulateInterventions

Simulate data of a causal cyclic model under shift interventions.
exampleAdjacencyMatrix

Example adjacency matrix
backShift

Estimate connectivity matrix of a directed graph with linear effects and hidden variables.