Changelog updates for Destinations, Passkeys, React Native SDK, and Mixpanel Agent - #121
Conversation
- Updated changelogs.mdx Mintlify-Source: dashboard-editor
Confidence Score: 5/5Documentation-only changelog additions; no code or configuration changes. All 8 new entries are well-formed MDX, placed in correct reverse-chronological order, and internally consistent. The cross-reference between the Bonferroni and Benjamini-Hochberg entries was already raised in a prior review thread. Files Needing Attention: No files require special attention.
|
| Filename | Overview |
|---|---|
| changelogs.mdx | Adds 8 changelog entries: React Native SDK feature flags (2026-07-10), two Experiments entries for Breakdowns and Benjamini-Hochberg (both 2026-06-18), and five Experiments statistical method entries (2026-04-05). Entries are correctly ordered chronologically and well-structured MDX. |
Reviews (2): Last reviewed commit: "Merge branch 'main' into dillon-mp" | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
|
|
||
| - **Control family-wise error:** Bonferroni divides your confidence threshold by the number of comparisons (metrics × non-control variants), reducing false positives across the whole experiment. | ||
| - **Trust multi-metric readouts:** When you track many metrics at once, Bonferroni makes sure a single flashy result isn't just noise. | ||
| - **Pair with the right method:** For segmented results, Mixpanel automatically switches to Benjamini-Hochberg, which preserves more power at scale. |
There was a problem hiding this comment.
The Bonferroni Correction entry is dated 2026-04-05, but it mentions that Mixpanel "automatically switches to Benjamini-Hochberg" for segmented results — a capability whose dedicated changelog entry is dated two months later (2026-06-18). A reader finding the April entry would encounter a claim about behaviour that the product doesn't surface until June. Can you confirm both corrections shipped together in April, or should the BH cross-reference be dropped from the April entry?
1 participant
More backlog catchup.
React Native SDK
BHC
Breakdowns in Experiments
CUPED
Winsorization
Pre-experiment Bias
SRM
Bonferroni Correction
Mintlify
0 threads from 0 users in Mintlify