Measure causal impact of YouTube ads
Company: Google
Role: Data Scientist
Category: Analytics & Experimentation
Difficulty: medium
Interview Round: Onsite
Overview: Estimate the incremental sales effect of a 6-week YouTube campaign, explain why regressing weekly sales on ad spend is biased, and design and size a geo-level experiment. Cover carryover after the campaign ends, a backup quasi-experiment, spillover between regions, and how many geos are needed.