However, we've seen time and time

[fomayof928@mowline]

When we run SEO split tests, this shows up in the data. As you can see in the graph below, it takes a week or two for the variant pages (in black) to outperform the prediction based on the control pages (in blue). A typical SEO split test – it often takes two weeks for improvements to show up. It's tempting to panic after a week or so that our test doesn't make a difference, and write it off as a neutral result.



S again that things often change after a week or two, so don't call it quits too soon! The other factor to keep in mind here is that the longer you leave it after this initial flat period, the more likely your results argentina number data will be significant, so you will be more confident in the result you will get. A note to anyone reading with a CRO background — I imagine you’re screaming at your screen that it’s not okay to leave the test too long to try and reach significance and that you need to set your end date in advance for the results to be accurate.



You would be correct for a CRO test measured using standard statistical models. In the case of SEO split tests, we measure significance using Bayesian statistical methods, meaning that it’s okay to continue the test until it reaches significance and you can trust your results at that point. 2. Testing groups of pages that don't have enough traffic (or are dominated by a small number of pages) The sites we've been able to run split tests on using Distilled ODN have very high traffic levels, as have the sections of the site we've tried to run split tests on.