A function that encapsulates the general structure of our algorithms for
testing generic identifiability. Allows for various identification algorithms
to be used in concert, in particular it will use the identifier functions
in the list idStepFunctions sequentially until it can find no more
identifications. The step functions that are currently available for use
in idStepFunctions are
htcIdentifyStep,
ancestralIdentifyStep,
edgewiseIdentifyStep,
trekSeparationIdentifyStep.
generalGenericID(mixedGraph, idStepFunctions, tianDecompose = T)returns an object of class 'GenericIDResult,' this
object is just a list with 9 components:
solvedParentsa list whose ith element contains a vector containing the subsets of parents of node i for which the edge j->i could be shown to be generically identifiable.
unsolvedParentsas for solvedParents but for the
unsolved parents.
solvedSiblingsas for solvedParents but for the
siblings of node i (i.e. the bidirected neighbors of i).
unsolvedSiblingsas for solvedSilbings but for the
unsolved siblings of node i (i.e. the bidirected neighbors of i).
identifiera function that takes a (generic) covariance
matrix corresponding to the graph and identifies the edges parameters
from solvedParents and solvedSiblings. See htcIdentifyStep
for a more in-depth discussion of identifier functions.
mixedGrapha mixed graph object of the graph.
idStepFunctionsa list of functions used to generically
identify parameters. For instance, htcID uses the function
htcIdentifyStep to identify edges.
tianDecomposethe argument tianDecompose.
callthe call made to this function.
a MixedGraph object representing the L-SEM.
a list of identification step functions
TRUE or FALSE determining whether or not the Tian decomposition should be used before running the current generic identification algorithm. In general letting this be TRUE will make the algorithm faster and more powerful.