FCIAlgorithm<T>
Models & Types · AiDotNet.CausalDiscovery.ConstraintBased
FCI (Fast Causal Inference) — constraint-based discovery with latent confounders.
Inheritance: CausalDiscoveryBase<T> → ConstraintBasedBase<T> → FCIAlgorithm<T>
For Beginners
Sometimes two variables appear related not because one causes the other, but because a hidden third variable causes both. FCI can detect this pattern.
How It Works
FCI extends the PC algorithm to handle latent (unmeasured) variables. It outputs a Partial Ancestral Graph (PAG) which uses different edge marks (→, ←→, o→) to indicate whether edges are definitely directed, bidirected (due to a latent common cause), or uncertain.
Reference: Spirtes, Glymour, and Scheines (2000), “Causation, Prediction, and Search”.
Constructors
| Constructor | Summary |
|---|---|
FCIAlgorithm(CausalDiscoveryOptions options) |
Properties
| Property | Summary |
|---|---|
bool SupportsLatentConfounders { get; } |
|
bool SupportsNonlinear { get; } |
|
string Name { get; } |