| NEWS | R Documentation |
print() and summary() methods for pc(),
fci(), etc.
new as(*, "amat") methods to get the adjacency matrix
of a model, including a print() method for "amat"s.
?amatType documents the different kinds of adjacency matrices
in pcalg.
New functions ......
Deprecated LINGAM() in favor of new lingam().
Deprecated allDags() in favor of pdag2allDags().
Bug fix in simulate(<gies>).
Bug fix in LINGAM(., verbose=FALSE) (the default, now tested).
Fix plot(pc(..), zvalue.lwd=TRUE), and better document
that plot method.
Much faster gSquareDis() and gSquareBin() for
|S| in 1:4 or so.
More test coverage, notably for pcSelect() and mcor().
r.gauss.pardag() gets an optional argument labels.
Adapt to API change in igraph package.
More test coverage and first speed tweaks.
Function gac for testing if a set of nodes satisfies
the Generalized Adjustment Criterion (GAC). GAC is a sufficient and
necessary criterion for estimating causal effects via covariate
adjustment in DAGs, CPDAGs, MAGs and PAGs.
Function randDAG for generating random directed acyclic
graphs (DAGs) with fixed expected number of neighbours. Several
different methods are provided, each intentionally biased towards
certain properties. The methods are based on the analogue functions
in the igraph package.
Function unifDAG and unifDAG.approx for uniform
sampling of a labelled directed acyclic graph (DAG) with combinatorial
enumeration.
Function LINGAM for estimating the structure of Linear
non-Gaussian Additive Models
Function fciPlus for a fast (but accurate) version of
fci (note that the already existing function rfci is a
fast approximation of fci)
Functions gds, gies, ges for score based learning
Function backdoor for generalized backdoor criterion
Bugfix in function wgtMatrix; this affects functions
trueCov and
rmvDAG; to reproduce old version, use option 'back.compatible =
TRUE'
skeleton, pc, fci and rfci now
have 'alpha' as third argument,
then 'labels, p' where 'p' is optional; namely, derived from 'labels'
when these are specified.
The default for extending the skeleton to a CPDAG is now
udag2pdagRelaxed, which is completely deterministic (was
udag2pdag
before, which can use random orientations if sampling errors occur).