Bayesian A/B Testing
Data Skeptic
00:00
Aby Testing
When we look at aby testing from a statistical point of view, there's this underlying assumption that we have this independent and identically distributed sample. But i actualy think that's not really true, because like the casinos, if they're trying to maximize the amount people play, they never know when ika really high rolleris going to walk in the door. Are those challenges that get dealt with in abe testing? Yet that's altly tod question. You have to think an ab test is actill an approximation to if you are to divide the universe in two, this is crazy, but this is the best we can do.
Transcript
Play full episode
