Open source platform for stress free deployments, measured impact, and smarter decisions.

GrowthBook Users

`Bayesian Evaluation of AB Test`
Hey Folks,
Is there any documentation I can deep dive into about how Growthbook evaluates the AB tests using the Bayesian Approach (defining prior, likelihood, etc.)?

We have some documentation on our stats engine (includes a link to our Whitepaper) - <https://docs.growthbook.io/statistics/overview>

<@U01TCPDB58C> would you have by any chance a numerical example of the bayesian approach? I read the docs you sent but some parts were a bit confusing for me. For example, how does D1 and D2 are generated.

Our stats engine is fully open source if you wanted to look at the python code and see what's happening under the hood - <https://github.com/growthbook/growthbook/tree/main/packages/stats/gbstats/bayesian>

Ahh cool! Thanks a lot <@U01TCPDB58C> for sharing :slightly_smiling_face: