Hacker News new | past | comments | ask | show | jobs | submit login

> Sure, you're never going to know exactly how many people you advertised to would have organically, eventually found your product and bought it.

This is typically an order of magnitude less than the attribution figures stated by digital marketing experts. A/B test is the right method to use, but the crucial thing is you need an earmarked population to see zero adds over your attribution window, since what you care about is impact on incremental sales, rather than incremental click likelihood.

There is a long econometrics literature on this and it is not a fussy technicality, the figures typically differ by 10x +.




Instagram definitely does this. I'm part of the magic cohort who never see any ads :)




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: