MétaCan
Menu
Back to cohort

On the persistent mischaracterization of Google and Facebook A/B tests: How to conduct and report online platform studies

2025· article· en· W4405995310 on OpenAlexafffund
Johannes Boegershausen, Yann Cornil, Shangwen Yi, David J. Hardisty

Bibliographic record

VenueInternational Journal of Research in Marketing · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicSocial Media in Health Education
Canadian institutionsUniversity of British Columbia
FundersSocial Sciences and Humanities Research CouncilÉcole Supérieure des Sciences Economiques et CommercialesSocial Sciences and Humanities Research Council of CanadaUniversiteit van Amsterdam
KeywordsInternet privacyAdvertisingBusinessSocial mediaWorld Wide WebComputer science

Abstract

fetched live from OpenAlex

Marketing research has increasingly relied on online platform studies , which are studies conducted in a naturalistic online environment and which leverage the A/B testing tool provided by platforms such as Facebook or Google Ads. These studies allow researchers to compare the effectiveness of different ads and the way they are delivered, and to study “real” consumer behavior, such as clicking on ads. However, they lack true random assignment of ads to consumers, preventing causal inference. In this manuscript, we present a comprehensive review of 133 published online platform studies revealing how researchers have, so far, utilized and characterized these studies; we find that most of these studies are mistakenly presented as (randomized) experiments and most of their findings are erroneously described as causal. Our review suggests limited awareness of the inherent confoundedness of online platform studies (i.e., the inability to attribute user responses to ad creatives versus the platform’s targeting algorithms). Importantly, the prevalence of these undesirable practices has remained relatively constant over time. Against this backdrop, we offer clear guidance on how to position, conduct, and report online platform studies for researchers interested in this method and for reviewers invited to evaluate it.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.012
metaresearch head score (Gemma)0.075
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.294
Threshold uncertainty score0.932

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0120.075
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.408
GPT teacher head0.563
Teacher spread0.155 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations22
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueInternational Journal of Research in MarketingSame topicSocial Media in Health EducationFrench-language works237,207