BaseExperiment#

class causalpy.experiments.base.BaseExperiment[source]#

Base class for quasi experimental designs.

Subclasses should set _default_model_class to a PyMC model class (e.g. LinearRegression) so that model=None instantiates a sensible Bayesian default. To use an OLS/sklearn model — or, for experiments that declare supports_pymc_forecast, a PyMCForecastModel — pass one explicitly.

Parameters:: model (PyMCModel | RegressorMixin | PyMCForecastModel | None) – Model instance to use. If None and _default_model_class is set, an instance of that default class is constructed.

Notes

Optional maketables integration is exposed through __maketables_* hooks. Users can control the HDI interval level used by ETable(result) via set_maketables_options(), for example: result.set_maketables_options(hdi_prob=0.95).

Methods

`BaseExperiment.build`()	Construct the model graph without sampling anything.
`BaseExperiment.effect_summary`(*[, group])	Generate a decision-ready summary of causal effects.
`BaseExperiment.fit`(**kwargs)	Run the posterior phase and populate `result`.
`BaseExperiment.generate_report`(*[, ...])	Generate a self-contained HTML report for this experiment.
`BaseExperiment.print_coefficients`([round_to])	Ask the model to print its posterior coefficients.
`BaseExperiment.sample_prior_predictive`(**kwargs)	Run the optional prior phase and populate `prior_result`.
`BaseExperiment.set_maketables_options`(*[, ...])	Set optional maketables rendering options for this experiment.

Attributes

`has_prior_predictive`	Whether the prior phase has run (draws, and bundle where kept).
`idata`	Return fitted DataTree when the model backend supports it.
`is_built`	Whether the model graph / fit design exists (no draws implied).
`is_configured`	design matrices are ready.
`is_fitted`	Whether posterior draws and the posterior result bundle exist.
`model`	The underlying model instance.
`prior_result`	Prior-group result bundle; raises before prior sampling.
`result`	Posterior-group result bundle; raises before `fit()`.
`supports_pymc_forecast`
`labels`
`data`
`supports_bayes`
`supports_ols`

__init__(model=None)[source]#

Parameters:: model (PyMCModel | RegressorMixin | PyMCForecastModel | None)
Return type:: None

classmethod __new__(*args, **kwargs)#