$2\mathrm{.}106$ A$/$B testing allows businesses to test a new design or format for a web page to determine if the new web page is more effective than the current one. Web designers decide to create a new call$-$to$-$action button for a web page. Every visitor to the web page was randomly shown either the original call$-$to$-$action button $($the control$)$ or the new variation. The metric used to measure success was the download rate: the number of people who downloaded the file divided by the number of people who saw that particular call$-$to$-$action button.

Results of the experiment yielded the following:

Variations Downloads Visitors

Original call$-$to$-$action button $3513,642$

New call$-$to$-$action button $4853,556$