Interface: DmlAteRequest
@kortexya/reasoninglayer / Causal / DmlAteRequest
Interface: DmlAteRequest
Defined in: src/types/causal.ts:765
Request to estimate the ATE (or ATT) for continuous covariates via Double Machine Learning (cross-fitted AIPW).
Properties
basisDegree?
optionalbasisDegree:number|null
Defined in: src/types/causal.ts:771
Polynomial basis degree for the nuisance models (default 1 = linear; 2 or
more captures non-linear confounding). Ignored when learner is
"forest" (trees use the raw features).
folds?
optionalfolds:number|null
Defined in: src/types/causal.ts:773
Number of cross-fitting folds (default 5).
forestMaxDepth?
optionalforestMaxDepth:number|null
Defined in: src/types/causal.ts:775
Maximum tree depth when learner is "forest" (default 8).
forestTrees?
optionalforestTrees:number|null
Defined in: src/types/causal.ts:777
Number of trees when learner is "forest" (default 100).
identification?
optionalidentification:IdentificationRefDto|null
Defined in: src/types/causal.ts:782
Gate this estimation on a persisted identification certificate. Absent
means legacy behavior, honestly labeled caller_asserted.
learner?
optionallearner:string|null
Defined in: src/types/causal.ts:788
Nuisance learner: "linear" (default — logistic + ridge over the
polynomial basis) or "forest" (a random forest on the raw features,
flexible under high-dimensional / non-smooth confounding).
observations
observations:
ContinuousObservationDto[]
Defined in: src/types/causal.ts:790
The observed sample with feature-vector covariates.
repetitions?
optionalrepetitions:number|null
Defined in: src/types/causal.ts:797
Number of repeated cross-fitting partitions S (default 1 = a single
partition). With S >= 2 the estimate is the median over S seeded,
treatment-stratified partitions and its variance carries the
across-partition dispersion correction.
seed?
optionalseed:number|null
Defined in: src/types/causal.ts:802
Seed for the repeated-cross-fitting partitions (default 0); results are
deterministic per (seed, repetitions).