Content
Get updates on tests we run to improve conversion...
Argument for multivariate testing over AB testing
30/07/2010
Multivariate testing can provide more of an insight for website owners, according to a marketing expert.
A marketing expert has explained why multivariate testing may be more useful than A/B testing in some cases.
In an article for BusinessWeek, Kim Ann King explains how, if trying to work out the effectiveness of single elements, A/B testing may be the right choice.
However, she points out that multivariate testing can be much more incisive, especially when website owners are trying to see how a number of elements impact upon a page.
She adds: "What's important to understand about multivariate testing is that it not only shows you which combination of elements generate more sales or pull more leads, but it also reveals which individual elements influence visitor behaviour vs those that do not.
"Evaluating the impact of combinations of factors and variations often reveals significant interaction effects that can have a dramatic impact on your conversion goals."
Many experts prefer A/B testing over multivariate testing as the latter requires a higher number of visitors to pass through a site in order to achieve statistical significance.
Posted by Elspeth Williams
In an article for BusinessWeek, Kim Ann King explains how, if trying to work out the effectiveness of single elements, A/B testing may be the right choice.
However, she points out that multivariate testing can be much more incisive, especially when website owners are trying to see how a number of elements impact upon a page.
She adds: "What's important to understand about multivariate testing is that it not only shows you which combination of elements generate more sales or pull more leads, but it also reveals which individual elements influence visitor behaviour vs those that do not.
"Evaluating the impact of combinations of factors and variations often reveals significant interaction effects that can have a dramatic impact on your conversion goals."
Many experts prefer A/B testing over multivariate testing as the latter requires a higher number of visitors to pass through a site in order to achieve statistical significance.
Posted by Elspeth Williams