# {py:mod}`causalis.scenarios.unconfoundedness.model`

```{py:module} causalis.scenarios.unconfoundedness.model
```

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model
:allowtitles:
```

## Module Contents

### Classes

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`IRM <causalis.scenarios.unconfoundedness.model.IRM>`
  - ```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM
    :summary:
    ```
````

### API

`````{py:class} IRM(data: typing.Optional[causalis.dgp.causaldata.CausalData] = None, ml_g: typing.Any = None, ml_m: typing.Any = None, *, n_folds: int = 5, n_rep: int = 1, normalize_ipw: bool = False, trimming_rule: str = 'truncate', trimming_threshold: float = 0.01, weights: typing.Optional[numpy.ndarray | typing.Dict[str, typing.Any]] = None, relative_baseline_min: float = 1e-08, random_state: typing.Optional[int] = None, n_jobs: int = 1, store_diagnostics: bool = True)
:canonical: causalis.scenarios.unconfoundedness.model.IRM

Bases: {py:obj}`sklearn.base.BaseEstimator`

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM
```

```{rubric} Initialization
```

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.__init__
```

````{py:method} fit(data: typing.Optional[causalis.dgp.causaldata.CausalData] = None, *, store_diagnostics: typing.Optional[bool] = None) -> causalis.scenarios.unconfoundedness.model.IRM
:canonical: causalis.scenarios.unconfoundedness.model.IRM.fit

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.fit
```

````

````{py:method} estimate(score: str = 'ATE', alpha: float = 0.05, groups: typing.Optional[pandas.DataFrame | pandas.Series] = None, cov_type: str = 'HC3', cov_kwds: typing.Optional[typing.Dict[str, typing.Any]] = None) -> causalis.data_contracts.causal_estimate.CausalEstimate | causalis.data_contracts.gate_estimate.GateEstimate
:canonical: causalis.scenarios.unconfoundedness.model.IRM.estimate

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.estimate
```

````

````{py:property} diagnostics_
:canonical: causalis.scenarios.unconfoundedness.model.IRM.diagnostics_
:type: typing.Dict[str, typing.Any]

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.diagnostics_
```

````

````{py:property} coef
:canonical: causalis.scenarios.unconfoundedness.model.IRM.coef
:type: numpy.ndarray

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.coef
```

````

````{py:property} se
:canonical: causalis.scenarios.unconfoundedness.model.IRM.se
:type: numpy.ndarray

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.se
```

````

````{py:property} pvalues
:canonical: causalis.scenarios.unconfoundedness.model.IRM.pvalues
:type: numpy.ndarray

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.pvalues
```

````

````{py:property} summary
:canonical: causalis.scenarios.unconfoundedness.model.IRM.summary
:type: pandas.DataFrame

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.summary
```

````

````{py:property} orth_signal
:canonical: causalis.scenarios.unconfoundedness.model.IRM.orth_signal
:type: numpy.ndarray

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.orth_signal
```

````

````{py:method} gate(groups: pandas.DataFrame | pandas.Series, alpha: float = 0.05, cov_type: str = 'HC3', cov_kwds: typing.Optional[typing.Dict[str, typing.Any]] = None) -> causalis.data_contracts.gate_estimate.GateEstimate
:canonical: causalis.scenarios.unconfoundedness.model.IRM.gate

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.gate
```

````

````{py:method} gatet(groups: pandas.DataFrame | pandas.Series, alpha: float = 0.05, cov_type: str = 'HC3', cov_kwds: typing.Optional[typing.Dict[str, typing.Any]] = None) -> causalis.data_contracts.gate_estimate.GateEstimate
:canonical: causalis.scenarios.unconfoundedness.model.IRM.gatet

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.gatet
```

````

````{py:method} sensitivity_analysis(r2_y: float, r2_d: float, rho: float = 1.0, H0: float = 0.0, alpha: float = 0.05) -> causalis.scenarios.unconfoundedness.model.IRM
:canonical: causalis.scenarios.unconfoundedness.model.IRM.sensitivity_analysis

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.sensitivity_analysis
```

````

````{py:method} confint(alpha: float = 0.05) -> pandas.DataFrame
:canonical: causalis.scenarios.unconfoundedness.model.IRM.confint

```{autodoc2-docstring} causalis.scenarios.unconfoundedness.model.IRM.confint
```

````

`````
