| rfci | R Documentation |
Run the Really Fast Causal Inference algorithm for causal discovery using one of several engines.
rfci(engine = c("tetrad", "pcalg"), test, alpha = 0.05, ...)
engine |
Character; which engine to use. Must be one of:
|
test |
Character; name of the conditionalâindependence test. |
alpha |
Numeric; significance level for the CI tests. |
... |
Additional arguments passed to the chosen engine (e.g. test or algorithm parameters). |
For specific details on the supported tests and parameters for each engine, see:
TetradSearch for Tetrad,
PcalgSearch for pcalg.
While it is possible to call the function returned directly with a data frame,
we recommend using disco(). This provides a consistent interface and handles knowledge
integration.
A function that takes a single argument data (a data frame). When called,
this function returns a list containing:
knowledge A Knowledge object with the background knowledge
used in the causal discovery algorithm. See knowledge() for how to construct it.
caugi A caugi::caugi object representing the learned causal graph.
This graph is an RFCI-PAG (RFCI Partial Ancestral Graph), but since RFCI-PAGs are not yet
natively supported in caugi, it is currently stored with class UNKNOWN.
Please see the definition 3.2 of the paper referenced for definition of an RFCI-PAG, and it's differences from a standard PAG.
Colombo, D., Maathuis, M. H., Kalisch, M., & Richardson, T. S. (2012). Learning high-dimensional directed acyclic graphs with latent and selection variables. The Annals of Statistics, 294-321.
Other causal discovery algorithms:
boss(),
boss_fci(),
fci(),
ges(),
gfci(),
grasp(),
grasp_fci(),
gs(),
iamb-family,
pc(),
sp_fci(),
tfci(),
tges(),
tpc()
data(tpc_example)
# Recommended path using disco()
rfci_pcalg <- rfci(engine = "pcalg", test = "fisher_z", alpha = 0.05)
disco(tpc_example, rfci_pcalg)
# or using rfci_pcalg directly
rfci_pcalg(tpc_example)
# With all algorithm arguments specified
rfci_pcalg <- rfci(
engine = "pcalg",
test = "fisher_z",
alpha = 0.05,
skel.method = "original",
fixedGaps = NULL,
fixedEdges = NULL,
NAdelete = FALSE,
m.max = 10,
rules = c(rep(TRUE, 9), FALSE),
conservative = TRUE,
maj.rule = FALSE,
numCores = 1,
verbose = FALSE
)
disco(tpc_example, rfci_pcalg)
#### Using tetrad engine with tier knowledge ####
# Requires Tetrad to be installed
if (verify_tetrad()$installed && verify_tetrad()$java_ok) {
kn <- knowledge(
tpc_example,
tier(
child ~ tidyselect::starts_with("child"),
youth ~ tidyselect::starts_with("youth"),
oldage ~ tidyselect::starts_with("oldage")
)
)
# Recommended path using disco()
rfci_tetrad <- rfci(engine = "tetrad", test = "fisher_z", alpha = 0.05)
disco(tpc_example, rfci_tetrad, knowledge = kn)
# or using rfci_tetrad directly
rfci_tetrad <- rfci_tetrad |> set_knowledge(kn)
rfci_tetrad(tpc_example)
}
# With all algorithm arguments specified
if (verify_tetrad()$installed && verify_tetrad()$java_ok) {
rfci_tetrad <- rfci(
engine = "tetrad",
test = "fisher_z",
alpha = 0.05,
depth = 10,
max_disc_path_length = 2,
exclude_selection_bias = FALSE,
fdr_q = 0.05
)
disco(tpc_example, rfci_tetrad)
}
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.