Pseudo-Incrementality Testing: Measuring Advertising Lift from Naturally Occurring Interventions
Abstract
We develop a method for measuring the incremental effect of advertising when randomized exper- iments are unavailable. Firms generate abrupt interventions in their own marketing as a byproduct of operations: budgets are cut, channels launch, programs pause. We propose a two-stage proce- dure that treats these events as quasi-experiments. The first stage discovers and dates interventions by exact Bayesian run-length inference on marketing activity series. The second stage runs a causal impact analysis against a variance-constrained structural time series counterfactual, with simulation-based inference, five qualification conditions, and a closed-form power bound. We validate the procedure on the two experimental benchmarks that Meta released with its GeoLift framework. The method identifies the day of intervention exactly in both cases. On the experiment where advertising was removed, it recovers the effect within 6.2 percent of the experimental esti- mate (implied return of 1.50 versus 1.60). On the experiment where advertising was added, its 90 percent interval covers the experimental estimate and excludes zero. Of six estimators evaluated on the same released data, ours is the only one that requires no geographic panel and produces intervals that are both correct on both experiments and narrow enough to act on.
Related
- Measuring Gift Card Program Incrementality via Causal Data Fusion
- The complementary-competitive interplay of consumer information search and experience sharing: Implications for targeted advertising and firm performance
- Cyclic Riemannian nilmanifolds are naturally reductive
- Finite bases for Brandt semirings and naturally semilattice-ordered inverse semigroups
- Asymptotic analysis of a Fredholm determinant occurring in the description of the dynamical correlation functions of the Lieb--Liniger Bose gas
BibTeX
@misc{filippou2026pseudoincrementality,
title = {{Pseudo-Incrementality Testing: Measuring Advertising Lift from Naturally Occurring Interventions}},
author = {Georgios Filippou and Boi Mai Quach and Ashish Kumar Jha},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.18257},
eprint = {2609.18257},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.18257},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Pseudo-Incrementality Testing: Measuring Advertising Lift from Naturally Occurring Interventions
AU - Georgios Filippou
AU - Boi Mai Quach
AU - Ashish Kumar Jha
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.18257
UR - https://arxiv.org/abs/2609.18257
AB - We develop a method for measuring the incremental effect of advertising when randomized exper- iments are unavailable. Firms generate abrupt interventions in their own marketing as a byproduct of operations: budgets are cut, channels launch, programs pause. We propose a two-stage proce- dure that treats these events as quasi-experiments. The first stage discovers and dates interventions by exact Bayesian run-length inference on marketing activity series. The second stage runs a causal impact analysis against a variance-constrained structural time series counterfactual, with simulation-based inference, five qualification conditions, and a closed-form power bound. We validate the procedure on the two experimental benchmarks that Meta released with its GeoLift framework. The method identifies the day of intervention exactly in both cases. On the experiment where advertising was removed, it recovers the effect within 6.2 percent of the experimental esti- mate (implied return of 1.50 versus 1.60). On the experiment where advertising was added, its 90 percent interval covers the experimental estimate and excludes zero. Of six estimators evaluated on the same released data, ours is the only one that requires no geographic panel and produces intervals that are both correct on both experiments and narrow enough to act on.
ER -