A/B testing is the process of testing two versions of a page to see which one performs better in reaching your business objectives.

1. Define what to test
The main goal is increasing your ROI. Figure out the best page(s) to test. Here are a few examples of good testing variables:

Call-to-action’s (i.e. button’s) wording, size, color and placement,

Headline or product description,

Form’s length and types of fields,

Product pricing and promotional offers,

Images on landing and product pages,

Amount of text on the page (short vs. long).

2. Create the page variation

3. Configure a Google Analytics account
This is necessary in order to record the statistics of your test.

4. Create your campaign in Google Analytics
Simply follow the wizard by creating a new experiment in the Behavior > Experiments menu of Google Analytics. To learn more, take a look at their online help.

Good practices	Bad practices
Know how long to run a test before giving up Don't give up too early! Wait for your test results to be significant. Take a look at the statistical confidence in Google Analytics; It should be at least 95%. Don't give up too late neither because poorly performing variations could cost you revenues.	Don't test versions at different time periods If you test one version one week and the second the next one, your results won't be accurate, or worse, wrong!
Do many A/B tests Don't despair if your first A/B test turns out to be a lemon. The key in optimizing conversion rates is to do a ton of A/B in order to put together all the most effective configurations.	Don’t surprise regular visitors If you are testing a core part of your website, include only new visitors in the test. You want to avoid shocking regular visitors, especially because the variations may not ultimately be implemented.
Test only one variable Try only one variable at a time, otherwise you won't be able to clearly interpret the results of your modifications.

Good practices

Bad practices

Know how long to run a test before giving up
Don't give up too early! Wait for your test results to be significant. Take a look at the statistical confidence in Google Analytics; It should be at least 95%.
Don't give up too late neither because poorly performing variations could cost you revenues.

Don't test versions at different time periods
If you test one version one week and the second the next one, your results won't be accurate, or worse, wrong!

Do many A/B tests
Don't despair if your first A/B test turns out to be a lemon. The key in optimizing conversion rates is to do a ton of A/B in order to put together all the most effective configurations.

Don’t surprise regular visitors
If you are testing a core part of your website, include only new visitors in the test. You want to avoid shocking regular visitors, especially because the variations may not ultimately be implemented.

Test only one variable
Try only one variable at a time, otherwise you won't be able to clearly interpret the results of your modifications.

Here is a basic guide for your first A/B testing:

Good practices

Bad practices