Hacker News Reader

Trying to do exactly that at http://visualwebsiteoptimizer.com/ab-split-test-duration/ and http://visualwebsiteoptimizer.com/ab-split-significance-calc... but yeah, we need a better way to present this.

View on HN

Have you considered adding a "recommend days" field to your product? Given the number of people per experiment and the number of conversions, you could potentially calculate a minimum time to run the experiment and simply explain that sometimes you are more likely to get false positives prior to the minimum time?

Also, it makes me very happy to know that you're aware of this problem and are trying to tackle it. It makes me more likely to recommend it to clients.

Reply on news.ycombinator.com