Given observational data from two disparate product campaigns, how would you mathematically structure a quasi-experiment or A/B test if we observe a 3% baseline increase for one product?

Interview question asked to Data Scientists interviewing at Mapbox, Coupang, New Relic and other companies. Original question asked: Given observational data from two disparate product campaigns, how would you mathematically structure a quasi-experiment or A/B test if we observe a 3% baseline increase for one product?.