Interface: MediationDmlRequest

@kortexya/reasoninglayer

---

@kortexya/reasoninglayer / Causal / MediationDmlRequest

Interface: MediationDmlRequest

Defined in: src/types/causal.ts:981

Request to estimate the mediation decomposition for continuous covariates via cross-fitted Double Machine Learning.

Properties

basisDegree?

optional basisDegree: number | null

Defined in: src/types/causal.ts:983

Polynomial basis degree for the linear nuisances (default 1).

---

folds?

optional folds: number | null

Defined in: src/types/causal.ts:985

Number of cross-fitting folds (default 5).

---

forestMaxDepth?

optional forestMaxDepth: number | null

Defined in: src/types/causal.ts:987

Maximum tree depth when learner is "forest" (default 8).

---

forestTrees?

optional forestTrees: number | null

Defined in: src/types/causal.ts:989

Number of trees when learner is "forest" (default 100).

---

identification?

optional identification: IdentificationRefDto | null

Defined in: src/types/causal.ts:994

Gate this estimation on a persisted identification certificate. Absent means legacy behavior, honestly labeled caller_asserted.

---

learner?

optional learner: string | null

Defined in: src/types/causal.ts:996

Nuisance learner: "linear" (default) or "forest".

---

observations

observations: ContinuousMediationObservationDto[]

Defined in: src/types/causal.ts:998

The observed sample with feature-vector covariates.