Research:VisualEditor/Anonymous

VisualEditor analytics	Impact on new users	Anonymous edits	Real-time dashboards
Project home Blog Open data	A/B test docs A/B test results draft	Descriptive stats draft	Hourly edits by user type, as % of all edits: en • de • es • fr • he • it • nl • pl • ru • sv Hourly edits by user type, as % of all edits by user type: en • de • es • fr • he • it • nl • pl • ru • sv Hourly edits as % of all edits by user type: en • de • es • fr • he • it • nl • pl • ru • sv Hourly edits, absolute number: en • de • es • fr • he • it • nl • pl • ru • sv Hourly edits, absolute number by user type: en • de • es • fr • he • it • nl • pl • ru • sv Daily unique editors by user type: en • de • es • fr • he • it • nl • pl • ru • sv Hourly reverted revisions by revert type: en • de • es • fr • he • it • nl • pl • ru • sv All graphs: en • de • es • fr • he • it • nl • pl • ru • sv Ganglia stats

We compared all main-namespace anonymous edits since the VisualEditor rollout to all anonymous editors on the English Wikipedia. We found a 13.5%, significant difference in the proportion of edits with a non-empty edit summary saved via VE compared to the proportion of the same edits saved via wikitext.

Anonymous main-namespace edits with a non-empty edit summary.

X-squared = 3020.731, df = 1, p-value < 2.2e-16
alternative hypothesis: two.sided 
95 percent confidence interval:
 0.1304051 0.1400960 
sample estimates:
   prop 1    prop 2 
0.5493696 0.4141190