liveBook · Manning

Probability of enablement

As explained in Causal AI

The probability of enablement is the conditional probability that an outcome would occur if a binary cause were present, conditioned only on the outcome having been absent.

Probability of enablement (PE) answers a counterfactual question: among cases where the outcome was absent, how likely is that outcome under the intervention or presence of a binary cause? It explains whether introducing X could enable Y, rather than merely predicting whether X and Y are associated. section 8.3.1

For binary cause X and outcome Y, PE considers the outcome that would occur if X were present, conditioned on observing Y absent. The conditioning isolates cases needing explanation; the counterfactual intervention supplies the causal question. section 8.3.1

PE supports practical causal workflows that ask why an outcome occurred or failed to occur:

  • Attribute customer churn or retention to a promotion. section 8.3.1
  • Assign credit in reinforcement learning and investigate engineering root causes. section 8.3.1
  • Support personalized-medicine questions involving binary treatments and outcomes. section 8.3.1

How Causal AI covers it

How deep it goes
Defines the binary counterfactual query and contrasts it with association, without developing identification assumptions or estimation procedures.
Examples
Uses a subscription-churn scenario in which a promotion is offered to prevent subscribers from leaving.
What it assumes
Assumes binary causes and outcomes while introducing counterfactual reasoning through plain-language causal questions.
What you can do after
Evaluate whether introducing a binary cause could enable an absent outcome in a counterfactual analysis.
How it connects
Connects counterfactuals with causal inference, marketing attribution, reinforcement learning, root cause analysis, and personalized medicine.
Cover of Causal AI
liveBookmanning.com
Read Causal AI on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Causal AI. The section links point to the parts of the book it draws on.