What is A/B Testing?
What is A/B Testing
A/B testing also known as split testing, is a randomized experiment with two different variants – A and B and a matric that define success. A/B testing is a way to compare two versions of a single variable, typically by testing a subject’s response to variant A against the subject response to variant B and hence which variant is better.
In the end, it measures which version was more successful and therefore selecting that version for real -world use.
Condition to Apply A/B Testing
A/B testing is a way of testing features in your application for various reasons like usability, popularity, noticeability, etc and how those factors influence the end user. It’s usually associated with the User Experience (UI) of the application but of course the backend services need to be available to do this.
An A/B test is simply a way for companies to test how much a particular variable affects their audience’s reaction.
Example – A/B testing on a
website. By randomly serving visitors two versions of a website that differ
only in the design, color and Place of button etc. Buttons in an email
newsletter from red to green, Place of button from left to right and design
rectangle to square shape. So after each test, the company will do the changes
that performed well and test it against the other colors, design and place that
did well until the best response for the changes.
Note – Preferences change overtime as complacency sets in, so our hypothetical testing may repeat this test on an annual basis to make sure it is sending out the most effective changes it can.
- In A/B testing certain elements are usually tested: –
- The call to action’s (i.e. the button’s) wording, size, color and placement.
- Headline or product description.
- Form’s length and types of fields.
- Layout and style of website.
- Product pricing and promotional offers.
- Images on landing and product pages.
- Amount of text on the page (short vs. long).
A/B testing tips:
- Test one change at a time – Testing multiple changes in a single A/B test makes it impossible to identify how each action has affected the results.
- Scientific/Logical approach – To change which design and content throughout the application. Every one change should affect the A/B testing result.
- Never stray from your usual practices – A/B test variants are always delivered to real customers in a live production environment. So try something radical in terms of design changes or re-ordering of content but make sure never stray from your brand guidelines and established practices. A/B testing is all about finding the small changes that make a big impact.
- Keep an eye on your experiments – it’s always worth monitoring your A/B tests throughout their duration. If it becomes apparent before the test has ended that a new variant is performing very poorly, it may be worth your while to stop the test then and there, to avoid causing further harm to your overall conversion rate.
- Do not test version A first and then start testing version B. Always test both version A and B simultaneously and split traffic between two versions.
- Don’t surprise regular or old visitors by doing major changes.
- Give the A/B test enough time to produce useful result.
- A/B test should beconsistent across the whole website. If testing a sign-up button that appears in multiple locations, then a visitor should see the same variation everywhere.
- A/B test can have only three outcomes: no result, a negative result or a positive result. The key to optimizing conversion rates is to do a ton of A/B tests, so that all positive results add up to a huge boost to sales and achieved goals.
Tools Used in A/B Testing: One of the commonly tool used Is “Google Analytics”.
First what is Google Analytics: Google Analytics is a premium web analytics service offered by Google that tracks and reports website traffic, currently as a platform inside the Google Marketing Platform brand. Google Analytics also provides an SDK that allows gathering usage data from iOS and Android Apps, known as Google Analytics for Mobile Apps.
How Google Analytics works with A/B testing: A/B testing can be integrated with Google Analytics and below are the steps to setup tool with the website.
a. Create Experiments: – In Google Analytics from the reporting sidebar. Select Behaviour, then Experiments. ?This is how get to experiments after setup. Select Create
Experiments only require a Name and the Goal (Objective) for evaluating success of A/B Testing.
b. Original URL and Hypothesis Variation URLs: – Add all of Original and hypotheses Url’s to the experiment.
c. Insert the experiment Testing Code: Once hypotheses URLs are setup, then next step is to select “Manually insert the code” and install the experiment code snippet just inside the <head> tag of your Original Page.
After you have saved the template, click Next Step and GA will verify that your experiment code is properly in place.
Author – Puja Singh