something like this is done comparing monthly sums from a previous year with the current, to qualify the impact a campaign had in numbers. doing the difference you get the tendency for this year, and check if the actual result diverges from the tendency after the event.
Links to GitHub page (<a href="http://google.github.io/CausalImpact/" rel="nofollow">http://google.github.io/CausalImpact/</a>) and the code itself (<a href="https://github.com/google/CausalImpact" rel="nofollow">https://github.com/google/CausalImpact</a>).