Enum CausalEffectVerdict 

pub enum CausalEffectVerdict {
    Identified {
        adjustment_set: Vec<String>,
        back_door_paths_considered: usize,
    },
    IdentifiedByFrontDoor {
        mediator_set: Vec<String>,
    },
    NoCausalPath {
        reason: String,
    },
    Underidentified {
        unblocked_back_door_paths: Vec<Vec<String>>,
        candidates_tried: usize,
    },
    UnknownNode {
        which: String,
    },
}

v0.44: verdict on whether the causal effect of source on target is identifiable from observational data over the frontier’s link graph. The lift of v0.40’s Identifiability to graph-aware reasoning.

Variants

Identified

All back-door paths from source to target are blocked by the adjustment set under the back-door criterion.

Fields

adjustment_set: Vec<String>

The adjustment set Z that blocks all back-door paths. Empty means no adjustment is needed (no open back-door path exists).

back_door_paths_considered: usize

Number of back-door paths the search considered.

IdentifiedByFrontDoor

v0.44.2: identified via Pearl’s front-door criterion (1995 §3.3). Used when confounders may be unobserved but a mediator set M satisfies all three front-door conditions:

1. M intercepts every directed path from source to target.
2. There is no back-door path from source to any element of M.
3. All back-door paths from M to target are blocked by source. The effect is then identifiable via the front-door formula P(Y | do(X)) = Σ_m P(M = m | X) Σ_{x’} P(Y | M = m, X = x’) P(X = x’).

Fields

mediator_set: Vec<String>

The mediator set M that the source’s effect on the target flows through. For v0.44.2 the search is restricted to singletons.

NoCausalPath

Source and target are not connected, or source has no directed path to target — the effect question is ill-posed at the graph level.

Fields

reason: String

Underidentified

At least one open back-door path remains under every adjustment set the search examined, AND no front-door mediator was found. The effect is not identifiable from observational data alone — an intervention is required.

Fields

unblocked_back_door_paths: Vec<Vec<String>>

candidates_tried: usize

UnknownNode

Either source or target is missing from the frontier.

Fields

which: String

Implementations

impl CausalEffectVerdict

pub fn as_str(&self) -> &'static str

Trait Implementations

impl Clone for CausalEffectVerdict

fn clone(&self) -> CausalEffectVerdict

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CausalEffectVerdict

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CausalEffectVerdict

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CausalEffectVerdict

fn eq(&self, other: &CausalEffectVerdict) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for CausalEffectVerdict

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for CausalEffectVerdict

impl StructuralPartialEq for CausalEffectVerdict