In an A/B test, a way to describe that half of traffic – or 50% of visitors – saw one version (control), often called Version A, while the other half of traffic was directed to the variant (typically called Version B).
Dividing traffic equally, usually as a 50/50 split, is the fastest, most accurate, and most reliable way to conduct an A/B test.
However, it is possible to split traffic other ways, for example 80/20 or 70/30.
But unequal traffic allocation it is not recommended. When traffic is not equally allocated, the results tend to be more uncertain and may take longer to reach a significant conclusion.
Therefore, equal allocation, or a 50/50 split is the optimal traffic set-up.« Back to Glossary Index