Documentation

This is the documentation index. In this documentation we will explain the usage of PhpAb. We will describe design of the library and all the components it exists of.

Before you go into depth it's important to realize what A/B testing is and how it works.

Understanding A/B testing

A/B testing, sometimes also called bucket tests or split-run testing, is a way to run an experiment with two variants, A and B. A and B are also called the control and the variation.

The goal is two run an experiment and analyze with variation has an outcome that meets the requirements most. Requirements can variate a lot and totally depend on the business case. One could use A/B testing for user experience for example. But one could also apply A/B testing to technical problems to see which version of an application performs better for example.

Multivariate testing

Multivariate testing is very similar to A/B testing with a difference that one runs multiple variants in an experiment. This library also supports multivariate testing.

References

For more information on A/B testing, Google is your best friend. We've made a selection of some useful websites that you can visit.

• https://en.wikipedia.org/wiki/A/B_testing
• https://en.wikipedia.org/wiki/Multivariate_statistics
• https://vwo.com/ab-testing/
• https://blog.kissmetrics.com/ab-testing-introduction/
• http://conversionxl.com/how-to-build-a-strong-ab-testing-plan-that-gets-results/
• http://blog.hubspot.com/blog/tabid/6307/bid/30556/The-Critical-Difference-Between-A-B-and-Multivariate-Tests.aspx

License

PhpAb is released under the MIT license.