Incrementality

class pymc_marketing.mmm.incrementality.Incrementality(model, idata=None, data=None)

Incrementality and counterfactual analysis for MMM models.

Computes incremental channel contributions by comparing predictions with actual spend vs. counterfactual (perturbed) spend, accounting for adstock carryover effects. See the module docstring for the full mathematical formulation and design rationale.

Parameters:

modelMMM

Fitted MMM model instance. Its frozen_deterministics property decides which deterministics are held at their posterior values during counterfactual evaluation.

idataxr.DataTree, optional

DataTree containing posterior samples and fit data. Exactly one of idata and data must be provided.

dataMMMIDataWrapper, optional

Existing data wrapper to reuse instead of building one from idata.

Attributes:

modelMMM

The fitted model whose graph the counterfactuals are evaluated on.

idataxr.DataTree

Posterior samples and fit data.

dataMMMIDataWrapper

Data wrapper for accessing model data.

Raises:

ValueError

If both idata and data are provided, or neither is; or if the idata coordinates do not match the fitted model’s.

Examples

>>> incr = mmm.incrementality
>>> roas = incr.contribution_over_spend(frequency="quarterly")
>>> cac = incr.spend_over_contribution(frequency="monthly")

Methods

Incrementality.__init__(model[, idata, data])
Incrementality.compute_incremental_contribution(...)	Compute incremental channel contributions using counterfactual analysis.
Incrementality.compute_joint_incremental_contribution(...)	Compute the incremental contribution of all channels together.
Incrementality.contribution_over_spend(frequency)	Compute incremental contribution per unit of spend.
Incrementality.marginal_contribution_over_spend(...)	Compute marginal contribution per additional unit of spend.
Incrementality.spend_over_contribution(frequency)	Compute spend per unit of incremental contribution.