← Back to the feed
Energy & materialsResearch findings

A Method to Measure Advertising Impact Using Naturally Occurring Interventions

Original published 2026.09.16 16:35 KSTAdded to Blackdeck 2026.10.19 06:47 KST

What has changed?

Treats naturally occurring marketing interventions as quasi-experiments to measure causal effects

Key points

  1. Treats naturally occurring marketing interventions as quasi-experiments to measure causal effects
  2. Precisely identifies intervention dates using Bayesian run-length inference
  3. Recovers effect within 6.2% of experimental estimate in one case and covers experimental value in the other

Connect it to your work

Detects and dates marketing interventions precisely using Bayesian inference and causal impact analysis

What remains unproven

The abstract reports simulation results; real-world performance is not established by this input.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivPseudo-Incrementality Testing: Measuring Advertising Lift from Naturally Occurring Interventions