At the third Action Seminar, Jon Correll, who normally only works with the largest companies, tells how to run split tests so you get the best possible information as to how a page converts.
The biggest trap I see in CRO (conversion rate optimization). Have you ever done a split test, you put something forward and you feel like it’s Christmas. You just opened up your presents and Santa gave you exactly what you wanted. And then the next day the initial results come back and you feel like you just got crapped on the head. Right?
It happens all the time! But, it’s important not to get emotional about it. It’s important to try and test and learn. So, don’t do it unless you’re committed to statistical relevance. And I’ve seen people just say, “Well, this was up by blah, blah, blah”. Maybe 50% but they only had about 20 conversions go through. That doesn’t work, trust me.
So, you have to be able to have…the reason is that there are a lot of different things that are happening. This was really a pretty smooth client, with different pages that they run and different traffic segmentations. And you can see from day to day that each of those traffic segments are up and down. One of your tests my cross…just like this. And one might work better on one day and another. It may not mean anything. It may just be noise in the results. So you want to be able to commit to that, and it may look like this, where one’s down, one’s up, and if you’re watching this every hour, every day, you’re just going to want to commit hary cary…you would just want it to be over, because it’s going to feel painful. Like “I’m losing money…oh, my gosh!” Don’t do that. Commit to it.
Here are a couple of simple rules:
Never start a test on a Friday. Why? Because we’ve, over many years, realized that Friday to Monday are weird days. People are getting drunk or doing other things, at the beach…there are just different people on the weekends. OK?
Commit to running a test at least a full 7 + 1 days. If you have a site with less traffic it should be 14 + 1 days. 14 + 1 or 7 + 1 just means if you start on a Monday it should end on a Tuesday. That way I have a full 7 days. Full 14 days is the same thing.
And then have at least a 95% confidence level.
And there are various other statistical things, but just make sure that it is real. Otherwise, these stats, if you don’t have real stats they will lie to you all the time and you think you won on something and long term it will not impact your bottom line if you’re not careful.
For more information about the Action Seminar, go to http://www.actionseminar.com/
If you like this lesson (and are not already a member of the Marketing Rebel Insider's Club), you will be glad to know that there is a vast library of small business marketing lessons and training programs just like this...
...plus a private Facebook-like chat stream where you can get answers to all of your
questions about marketing tools and techniques, small business growth, and life as an entrepreneur...
...which is only available to members of the Marketing Rebel Insider's Club.
You can access all of this immediately for less than $1/day.
You will see for yourself why our members love this online club so much...
... and why they don't invest in marketing tools or strategies without first checking in with The Club.
Click Here to start your membership today.
We'll see you on the inside...
Stan Dahl & The Marketing Rebel Team