tim and mo compete on your behalf to answer tough questions proposed by mat gershof of conductri. The quiz is sponsored by conductrs, who help build industry leading experimentation software for aby testing, adaptive optimization and predictive targeting. Find out more at conducti dot com. Tim: What's the main reason we bother using random selection in our experiments? Mo: To minimize type one error or e, to estimate posterior distributions? And band wagoning is allowed here!
We try not to navel gaze too much on this show, but our 200th episode felt like just enough of a milestone that we could do a mid-year "look back, look forward" show with a 7-year range. And we tracked down our original Commonwealth representative to join us for that discussion. Did we (first) party (cookie) like it was 1999? Maybe not, but that's the sort of reference you get with Jim Cain, the founder of Napkyn Analytics, and a co-founder of this very podcast! For complete show notes, including links to items mentioned in this episode and a transcript of the show, visit the show page.