getParentsStable {CompareCausalNetworks}  R Documentation 
Estimate the connectivity matrix of a causal graph using stability selection.
Description
Estimates the connectivity matrix of a directed causal graph, using various possible methods. Supported methods at the moment are ARGES, backShift, bivariateANM, bivariateCAM, CAM, FCI, FCI+, GES, GIES, hiddenICP, ICP, LINGAM, MMHC, rankARGES, rankFci, rankGES, rankGIES, rankPC, regression, RFCI and PC. Uses stability selection to select an appropriate sparseness.
Usage
getParentsStable(
X,
environment,
interventions = NULL,
EV = 1,
nodewise = TRUE,
threshold = 0.75,
nsim = 100,
sampleSettings = 1/sqrt(2),
sampleObservations = 1/sqrt(2),
parentsOf = 1:ncol(X),
method = c("ICP", "hiddenICP", "backShift", "pc", "LINGAM", "ges", "gies", "CAM",
"fci", "rfci", "regression", "bivariateANM", "bivariateCAM")[1],
alpha = 0.1,
mode = c("raw", "parental", "ancestral")[1],
variableSelMat = NULL,
excludeTargetInterventions = TRUE,
onlyObservationalData = FALSE,
indexObservationalData = NULL,
setOptions = list(),
verbose = FALSE
)
Arguments
X 
A (nxp)data matrix with n observations of p variables. 
environment 
A vector of length n, where the entry for
observation i is an index for the environment in which observation i took
place (simplest case entries 
interventions 
A optional list of length n. The entry for observation
i is a numeric vector that specifies the variables on which interventions
happened for observation i (a scalar if an intervention happened on just
one variable and 
EV 
A bound on the expected number of falsely selected edges. 
nodewise 
If 
threshold 
The empirical selection frequency in (0.5,1) under subsampling that needs to be surpassed for an edge to be selected. 
nsim 
The number of resamples for stability selection. 
sampleSettings 
The fraction of different environments to resample in each resampling (at least two different environments will be selected so the argument is without effect if there are just two different environments in total). 
sampleObservations 
The fraction of samples to resample in each environment. 
parentsOf 
The variables for which we would like to estimate the parents. Default are all variables. 
method 
A string that specfies the method to use. The methods

alpha 
The level at which tests are done. This leads to confidence
intervals for 
mode 
Output type  can be "raw", "parental" or "ancestral". If "raw" output is the output of the underlying method, without modifications. If "parental" output described parental relations; if "ancestral" output is casted to ancestral relations. #TODO explain further 
variableSelMat 
An optional logical matrix of dimension (pxp). An
entry 
excludeTargetInterventions 
When looking for parents of variable k
in 1,...,p, set to 
onlyObservationalData 
If set to 
indexObservationalData 
Index in 
setOptions 
A list that can take methodspecific options; see the individual documentations of the methods for more options and their possible values. 
verbose 
If 
Value
A sparse matrix, where a 0 entry in (j,k) corresponds to an estimate
of 'no edge' j
> parentsOf[k]
. Entries between 0 and 100
give the selection percentage of this edge over all resamples (set to 0 if
below critical threshold) and all nonzero values are considered as selected
edges.
Author(s)
Nicolai Meinshausen meinshausen@stat.math.ethz.ch, Christina HeinzeDeml heinzedeml@stat.math.ethz.ch
References
Stability selection (2010): N. Meinshausen and P. Buhlmann, Journal of the Royal Statistical Society: Series B, 72, 417473
See Also
getParents
for the underlying pointestimate of
the causal graph.