Conducting experiments

The Yandex Advertising Network gives you tools to analyze statistics that help increase the effectiveness of your ad units and revenue from your site. You can also experiment with ad units yourself.

Experimentation is a controllable method for researching some kind of phenomenon.

Experimental results serve as confirmation or refutation of a hypothesis.

You can use experiments to find ways to improve your site. For example, you can find out the following:

The optimal number of ads in a single ad unit.
How to place ad units on the page so that ads are noticeable but don't get in users' way.
What designs and formats blend seamlessly into the content of your site.

You can conduct experiments on ads placed on your site using Varioqub. This tool allows you to create an experiment with multiple options, changing the elements and layout of the site and comparing different ad units and their settings. As a result of your experiment, you get statistics for indicators that help determine the most effective option in terms of monetization and user metrics. For more information, see Varioqub experiments in the Help section.

Experimentation guidelines

One experiment — one hypothesis

: When conducting one experiment, test no more than one hypothesis at a time. For example, test only a new unit configuration or a different unit position if you want to see how your revenue is affected.

Avoid times when significant changes are made to your site

: Choose a period of time when there are no other changes being made to your site (such as changes to the design or layout).

Choose similar periods to compare metrics

: Compare impression dynamics for the same periods. For example, compare viewable impressions in January of the current year with January of the previous year. To learn more, see Seasonal statistical fluctuations.