Who is missing from the merchant survey?
Study design
Draw a stratified sample of storefronts by ward and opening hours. Retain a contact-attempt log for every sampled merchant.
Instrument and data fields
Ask whether the owner has paid for a comparable service, who approves purchases and what would prevent a paid trial.
Simulated evidence
Day shops: 24 yes, 16 no and 10 no response. Evening shops: 8 yes, 12 no and 30 no response.
Check before drawing a conclusion
Write down the comparison you would make and the unit each row represents. Identify one explanation the study design cannot rule out, then describe how it would affect the decision.
Reveal the worked analysis
Among respondents the rates are 60% and 40%. Across all sampled shops, support ranges from 32% if all missing owners say no to 72% if all say yes. Offer a small paid trial before committing.
Recontact at different hours and keep refusals separate from unreachable shops. The wide bounds show why the phone result alone cannot justify expansion.