We all know that A/B and multivariate testing is important for successful landing pages, but did you know that these testing methods started back in the 1700’s with the answer for scurvy?

It’s time for a history lesson to explore how other types of testing have influenced the landing page testing methods we use and love today.

The History of A/B and Multivariate Testing

It was 1747 and scurvy was a major problem for that time. A British Royal Navy ship surgeon, Mr. James Lind, started what would be the beginning of A/B and multivariate testing. By giving specific crew members different solutions, then testing the results of those variations over time, he came to the conclusion that citrus fruits were the cure to scurvy.

Although many didn’t believe him at first, he went on to prove this and pioneer what we know in our testing methods, today.  When we use modern multivariate testing and A/B testing for landing pages, we should thank Mr. James Lind for our conversion rate increases.

Hypothesis Testing

If you’ve taken an introductory statistics course, this term may ring a bell for you. It’s statistical hypothesis testing, and it also is a forefounder to the A/B testing and multivariate testing methods we use for landing pages.

Hypothesis testing is basically the product of three statisticians: Ronald Fisher, an agricultural statistician, and the mathematician/statistician team of Jerzy Neyman and Egon Pearson. Two differing methods created by these men in the early 20th century have actually combined into a hybrid to become modern hypothesis testing.

According to Wikipedia, this testing method is:

A method of making decisions using data, whether from a controlled experiment or an observational study (not controlled). In statistics, a result is called statistically significant if it is unlikely to have occurred by chance alone, according to a pre-determined threshold probability, the significance level.

Just as in multivariate testing, this type of testing uses data gathered from a control and an uncontrolled subject. Depending on elements introduced, different results will occur. Again, for us this relates to how we can add elements, including change in headline, colors, CTA and others to improve our landing page conversion rates.

Likelihood Ratio Testing

Another creation of the Neyman/Pearson is likelihood ratio testing. The comparison of two models, “null” (control) and alternative, are the basis of this type of testing. A better description is quoted here, from Wikipedia:

In statistics, a likelihood ratio test is a statistical test used to compare the fit of two models, one of which (the null model) is a special case of the other (the alternative model). The test is based on the likelihood ratio, which expresses how many times more likely the data are under one model than the other. This likelihood ratio…can then be used to compute a p-value, or compared to a critical value to decide whether to reject the null model in favour of the alternative model.

Again, another method directly related to A/B testing and multivariate testing. Whether it’s multi or singular elements, we can learn how this method influences our own online marketing testing.

A/B and Multivariate Testing Today

Going through this little history lesson about the roots of multivariate testing and A/B testing can better help us understand the importance and methods to improve our online marketing efforts. Whether you’re curing scurvy, a poorly performing conversion rate or really any type of  complex problem solving, use these testing methods to your advantage.

If you’re looking for help with A/B and multivariate testing, contact our landing page experts.