A Comparison of Approaches to Advertising Measurement: Evidence from Big Field Experiments at Facebook

Gordon, Brett R.; Zettelmeyer, Florian; Bhargava, Neha; chapsky, Dan

doi:10.2139/ssrn.3033144

Cited by 102 publications

(80 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cross-sectional estimates for the probability of transaction lift are an order of magnitude larger than the experimental estimates. Collectively, this adds to evidence from experimental studies that naive observational estimates exhibit biases (Gordon et al, 2015;Hoban and Bucklin, 2015;Lewis et al, 2011;Lewis and Reiley, 2014).…”

Section: A24 Difference-in-differences and Observational Estimatesmentioning

confidence: 55%

See 1 more Smart Citation

When Less Is More: Data and Power in Advertising Experiments

Johnson

Lewis²,

Reiley³

2017

Marketing Science

View full text Add to dashboard Cite

Yahoo! Research partnered with a nationwide retailer to study the effects of online display advertising on both online and in-store purchases. We use a randomized field experiment on 3 million Yahoo! users who are also past customers of the retailer. We find statistically significant evidence that the retailer ads increase sales 3.6% relative to the control group. We show that control ads boost measurement precision by identifying and removing the half of in-campaign sales data that is unaffected by the ads. Less data gives us 31% more precision in our estimates-equivalent to increasing our sample to 5.3 million users. By contrast, we only improve precision by 5% when we include additional covariate data to reduce the residual variance in our experimental regression. The covariate-adjustment strategy disappoints despite exceptional consumer-level data including demographics, ad exposure levels, and two years' worth of past purchase history.

show abstract

Section: A24 Difference-in-differences and Observational Estimatesmentioning

confidence: 55%

“…We look forward to future research including studies that leverage either ghost-ad and intent-to-treat (see e.g. Gordon et al 2015) experimentation platforms and illuminates how advertising influences consumer choice.…”

Section: Resultsmentioning

confidence: 99%

When Less Is More: Data and Power in Advertising Experiments

Johnson

Lewis²,

Reiley³

2017

Marketing Science

View full text Add to dashboard Cite

show abstract

“…However, as argued by Peukert (2019), the repercussions of the ad-based business model on the provision of cultural goods are not well explored yet. Generally, there is a lot of uncertainty about the actual returns to online advertising (Lewis and Rao 2015;Gordon et al 2019). Moreover, the use of ad blocking tools can undermine generated revenues (Shiller et al 2018).…”

Section: Discussionmentioning

confidence: 99%

Crowdfunding a monthly income: an analysis of the membership platform Patreon

Regner¹

2020

J Cult Econ

View full text Add to dashboard Cite

Membership platforms allow creators to crowdfund a monthly income, while campaigns on conventional reward crowdfunding portals aim to reach a specified funding target within a preset period. We study transaction-level data from Patreon, the biggest membership platform, to gain insights about behavioral patterns at this emerging type of crowdfunding. Our analysis shows that hundreds of creators crowdfund a sizable income (more than $2500 monthly). We also find that measures of communication quality are determinants of project success, in line with the related literature. Funding dynamics-pledges as well as deletions-are heterogeneous across campaigns. Our analysis suggests that the option to delete the monthly pledge to a creator at any time serves as a feedback mechanism. We conclude that crowdfunding a monthly income offers the creative class a viable alternative to advertising-based business models.

show abstract

“…While much better than prior ways to measure advertising effectiveness, there are still substantial challenges. Correlational research, even with detailed data, typically yields inaccurate measures of advertising effects because the signal-to-noise ratio for advertising's effect on sales is low (Lewis, Rao, and Reiley 2015;Gordon et al 2016). Furthermore, even with experiments, advertising effects are subtle relative to the variance in purchase behavior, and so studies need to be highly powered .…”

Section: Why Has There Been a Shift In Academic Emphasis From Personamentioning

confidence: 99%

Digital Economics

Goldfarb

Tucker

2019

Journal of Economic Literature

1,363

417

View full text Add to dashboard Cite

Digital technology is the representation of information in bits. This technology has reduced the cost of storage, computation, and transmission of data. Research on digital economics examines whether and how digital technology changes economic activity. In this review, we emphasize the reduction in five distinct economic costs associated with digital economic activity: search costs, replication costs, transportation costs, tracking costs, and verification costs. (JEL D24, D83, L86, O33, R41)

show abstract

A Comparison of Approaches to Advertising Measurement: Evidence from Big Field Experiments at Facebook

Cited by 102 publications

References 45 publications

When Less Is More: Data and Power in Advertising Experiments

When Less Is More: Data and Power in Advertising Experiments

Crowdfunding a monthly income: an analysis of the membership platform Patreon

Digital Economics

Contact Info

Product

Resources

About