From 3 years ago but it certainly still holds true. As mentioned in the comments, many PPC'ers use <a href="http://www.splittester.com" rel="nofollow">http://www.splittester.com</a> to help determine if there's enough data to determine a winner.<p>SEOBook recently opened another site focused primarily on PPC at PPCBlog.com and this was a recent discussion in the forums.
Pretty kludgey way of adding statistical significance.<p>I would expect anyone on HN would be capable of running the numbers and generating the actual stats.<p>If not, it would be a good learning exercise.
I hacked together a gtest calculator in ruby if anyone is interested. I keep meaning to clean it up, but I haven't had time.<p><a href="http://github.com/zachaysan/Split-Test-with-the-G-Test" rel="nofollow">http://github.com/zachaysan/Split-Test-with-the-G-Test</a>
Can't hurt to try this approach, as it takes approximately 10 seconds to set it up. Will give it a shot, and report back if the results are interesting...