👋 Hi GB team! Quick question about the API docs: specifically, for
- am I right in assuming that each variation's metrics are relative to the control variation? I didn't see this in the docs, so just wanted to be sure. Thanks!
10/31/2023, 4:56 PM
@blue-sundown-32899 has marked the issue as closed. Reopen Issue button
10/31/2023, 4:57 PM
10/31/2023, 5:07 PM
Hi Angela, I'll double check this and follow up shortly.
(Every question in this channel is turned into a support request within our internal tool 🙂 )
10/31/2023, 6:24 PM
Hi Angela, yes, I confirmed that the A/B test metrics are relative to the control variation.
`expected`, `ciLow`, `ciHigh`, `pValue`, `risk`, `chanceToBeatControl` will all be relative to the control variation and have to do with the Uplift (i.e. the Relative Change).
The `mean` and `stddev` are the mean and standard deviation of the metric within that variation, and are not relative to any other variations.