Please find Part 1 of the analysis here https://nbviewer.org/urls/gitlab.wikimedia.org/conniecc1/we2.1.1-kr-2025/-/raw/main/central-notification-banner-PART1.ipynb

Summary
Impressions & Clicks
Scenario 1 (Banner A) had a total of 17,257,300 impressions and 8,150 clicks. Scenario 2 (Banner B&C) had 1,819,086 impressionsa and 2,616 clicks.

Account Creations
Scenario 1 (Banner A) had a total of 164 account creations. Scenario 2 (Banner B&C) had 69 account creations.

Growth Features Engagement
Scenario 1 (Banner A) had 81 users engaged with GrowthFeature homepage. Scenarios (Banner B&C) had 47 users engaged with GrowthFeatures homepage.

Growth Features Engagement Rate Comparison

• Overall, Scenario 1 (Banner A) had an engagement rate of 0.99%, and Scenario 2 (Banner B&C) had an engagement rate of 1.80%. And based on the test, the difference is statistically significant. Scenario 2 has a higher growth feature homepage engagement.
• High activity language & size wiki (pawiki & lbwiki): pawiki had an engagement rate of 0.93%, and lbwiki had an engagement rate of 0.77%. From the test result, the difference is not statistically significant. We cannot conclude that which Scenario has a higher growth feature homepage engagement than the other one for this group.
• Med activity language & size wiki (minwiki & astwiki): minwiki had an engagement rate of 0.36%, and astwiki had an engagement rate of 4.18%. From the test result, the difference is statistically significant. Scenario 2 has a higher growth feature homepage engagement than Scenario 1 for this group.
• Low activity language & size wiki (arywiki & zuwiki): arywiki had an engagement rate of 2.92%, and zuwiki had an engagement rate of 2.15%. From the test result, the difference is not statistically significant. We cannot conclude that which Scenario has a higher growth feature homepage engagement than the other one for this group.
• In conclusion, when comparing engagement rate, Scenario 2 (banner B&C) is the more effective. Its overall performance was statistically significant better than Scenario 1 (Banner A). However, this effect was not consistent across all wiki segments. for medium-Activity wikis, where Scenario 2 was more effective. For both the High-Activity and Low-Activity wikis, there was no significant difference in performance between the two scenarios. It's possible for a real effect to exist in high and low-activity groups, but the test may not be powerful enough to detect it.

Edits by Newly Registered Users
During the experiment period, we found the following number of edits from newly registered editors: