CausalGraphModel

class pymc_marketing.mmm.causal.CausalGraphModel(causal_model, treatment, outcome)

Represent a causal model based on a Directed Acyclic Graph (DAG).

Provides methods to analyze causal relationships and determine the minimal adjustment set for backdoor adjustment between treatment and outcome variables.

Parameters:

causal_modelCausalModel

An instance of dowhy’s CausalModel, representing the causal graph and its relationships.

treatmentlist[str]

A list of treatment variable names.

outcomestr

The outcome variable name.

References

[1]

microsoft/dowhy

Methods

CausalGraphModel.__init__(causal_model, ...)
CausalGraphModel.build_graphical_model(...)	Create a CausalGraphModel from a string representation of a graph.
CausalGraphModel.compute_adjustment_sets(...)	Compute minimal adjustment sets and handle warnings.
CausalGraphModel.get_backdoor_paths()	Find all backdoor paths between the combined treatment and outcome variables.
CausalGraphModel.get_unique_adjustment_nodes()	Compute the minimal adjustment set required for backdoor adjustment across all treatments.