Skip to content
Submodule
causalis.dgp.causaldata_instrumental.base

base

Submodule causalis.dgp.causaldata_instrumental.base with no child pages and 12 documented members.

Symbol indexAPI membersInstrumentalGeneratorinstrument_namefirst_stagebeta_z

Classes

Jump directly into the documented classes for this page.

1 items
InstrumentalGeneratorclass

Data

Jump directly into the documented data for this page.

1 items
IVCausalDatasetGeneratordata
class
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator

InstrumentalGenerator

Bases: causalis.dgp.causaldata.base.CausalDatasetGenerator

Generate synthetic datasets for binary instrumental-variable estimation.

The generated structural system is:

  • X is sampled with the same confounder machinery as :class:~causalis.dgp.causaldata.base.CausalDatasetGenerator.

  • Z is a binary instrument generated from P(Z=1|X).

  • D is a binary endogenous treatment generated from P(D=1|Z,X,U).

  • Y depends on D, X, and optionally the latent U, but has no direct dependence on Z.

Parameters inherited from CausalDatasetGenerator keep their usual meaning for the outcome equation and the non-instrument part of the treatment equation. In particular, beta_d, g_d, alpha_d, target_d_rate, and u_strength_d affect treatment assignment.

Parameters

instrument_namestr, default=”z”

Column name for the binary instrument.

first_stagefloat, default=1.25

Additive log-odds effect of Z on treatment assignment. Positive values make the instrument encourage treatment.

beta_zarray-like, optional

Linear coefficients of confounders in the instrument propensity.

g_zcallable, optional

Nonlinear instrument score g_z(X) -> shape (n,).

alpha_zfloat, default=0.0

Instrument propensity intercept. If target_z_rate is set, this is calibrated on each generated sample.

target_z_ratefloat, optional

Target marginal instrument rate. Defaults to 0.5.

instrument_sharpnessfloat, default=1.0

Multiplier on the X-driven instrument score.

include_oraclebool, default=True

Whether to include oracle columns for IV nuisance functions and treatment potential-outcome means.

Notes

With include_oracle=True, returned oracle columns include:

  • m: instrument propensity P(Z=1|X).

  • r_z0 and r_z1: first-stage nuisances P(D=1|Z=0,X) and P(D=1|Z=1,X).

  • g_z0 and g_z1: reduced-form nuisances E[Y|Z=0,X] and E[Y|Z=1,X).

  • iv_first_stage and iv_reduced_form: conditional differences in the first stage and reduced form.

  • late_x and late: conditional and sample-average Wald ratios.

  • g_d0, g_d1, and cate: treatment potential-outcome means and their natural-scale contrast.

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator

Sections

ParametersNotes
Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.instrument_name

instrument_name

Value: 'z'

‘z’

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.instrument_name

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.first_stage

first_stage

Value: 1.25

1.25

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.first_stage

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.beta_z

beta_z

Value: None

None

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.beta_z

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.g_z

g_z

Value: None

None

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.g_z

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.alpha_z

alpha_z

Value: 0.0

0.0

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.alpha_z

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.target_z_rate

target_z_rate

Value: 0.5

0.5

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.target_z_rate

Link to this symbol
attribute
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.instrument_sharpness

instrument_sharpness

Value: 1.0

1.0

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.instrument_sharpness

Link to this symbol
method
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.__post_init__

__post_init__

Initialize RNG and validate IV-specific configuration.

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.__post_init__

Link to this symbol
method
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.generate

generate

Draw a synthetic IV dataset of size n.

Parameters

nint

Number of samples to generate.

Unumpy.ndarray, optional

Latent confounder. If omitted, sampled from N(0, 1).

Returns

pandas.DataFrame

Generated dataset with outcome y, treatment d, instrument z (or instrument_name), confounders, and optional oracle columns.

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.generate

Sections

ParametersReturns
Link to this symbol
method
causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.to_iv_causal_data

to_iv_causal_data

Generate a dataset and convert it to :class:IVCausalData.

Oracle columns are intentionally not included as confounders when confounders is omitted.

Canonical target

causalis.dgp.causaldata_instrumental.base.InstrumentalGenerator.to_iv_causal_data

Link to this symbol
data
causalis.dgp.causaldata_instrumental.base.IVCausalDatasetGenerator

IVCausalDatasetGenerator

Value: None

None

Canonical target

causalis.dgp.causaldata_instrumental.base.IVCausalDatasetGenerator

Link to this symbol