TBF_FCI.__init__

TBF_FCI.__init__(target, *, target_edge_rule='any', bf_thresh=1.0, forbidden_edges=None, max_lag=2, allow_contemporaneous=True)

Create a new temporal TBF-PC causal discovery model.

Parameters:

target

Target variable name at time t that the algorithm orients toward.

target_edge_rule

Rule used to retain lagged → target edges. Choose from "any", "conservative", or "fullS".

bf_thresh

Positive Bayes factor threshold applied during conditional independence testing.

forbidden_edges

Optional sequence of node pairs that must be excluded from the final graph.

max_lag

Maximum lag (inclusive) to consider when constructing temporal drivers.

allow_contemporaneous

Whether contemporaneous edges at time t are permitted.