# How Optimizely Web Experimentation and Optimizely Feature Experimentation handle outliers

• Updated

Relevant products:

• Optimizely Web Experimentation
• Optimizely Feature Experimentation

This topic describes how to:
• Learn about outliers in experimentation data
• Discover how Optimizely Web Experimentation and Optimizely Feature Experimentation smooths outliers from your experimental results
• Enable outlier smoothing in the Metrics Builder interface

The feature is currently available for all Optimizely Web Experimentation and Optimizely Feature Experimentation plan types.

In statistics, an outlier is an observation that has an abnormally higher or lower value than other observations in a data set. Outliers can severely skew the accuracy of any analysis conducted on a data set and can lead to potentially incorrect conclusions.

Outliers can occur during your experiment, usually resulting from unusual or unexpected behavior by a customer.

For example, suppose you are running an experiment that aims to improve the average order value for your e-commerce site. Your visitors usually submit orders with an average total value of \$200. Imagine a small number of visitors who submitted orders with 100 or even 1000 times higher value than the average. If the result calculations included these extreme orders, they could introduce bias into your A/B comparison and lead you to draw the wrong conclusions from your experiment.

For this reason, Optimizely Web Experimentation and Optimizely Feature Experimentation give you the option to use outlier smoothing on your experiment results. This feature is currently available for revenue metrics in A/B experiments.

## How outlier smoothing works

When outlier smoothing is enabled, Optimizely Web Experimentation and Optimizely Feature Experimentation first identifies any values that exceed the daily exclusion threshold, which is three standard deviations higher than the arithmetic mean of your metric.

`arithmetic mean + (3 * standard deviation)`

These extreme values are designated as outliers. It is important to note that there may be no values that fall outside the custom threshold for that day, so in other words, no outliers for that day.

Next, Optimizely Web Experimentation and Optimizely Feature Experimentation replaces these outliers with the metric's harmonic mean value. This process is known as outlier smoothing.

Optimizely Web Experimentation and Optimizely Feature Experimentation recalculates the daily exclusion threshold each day, using a moving average of the arithmetic mean and standard deviation of your metric over the previous seven (7) days. This process repeats for each day of the experiment.

During the first seven (7) days of the experiment, Optimizely Web Experimentation and Optimizely Feature Experimentation calculates the daily exclusion threshold using all the available experiment data up to that point. For this reason, changes to the threshold may be more noticeable during an experiment's first week

## Smooth outliers for revenue metrics

If your account has access to the feature, you will see an option to enable outlier smoothing in the Metrics Builder interface. Selecting the option ensures that outliers for the revenue metrics in that experiment will be automatically detected, and the harmonic mean of the metric will replace their values.

<% if (previousArticle || nextArticle) { %>
<% if (previousArticle) { %>
<% if (previousTitle) { %>

#### <%= previousTitle %>

<% } %> <%= previousArticle.title %>
<% } %> <% if (nextArticle) { %>
<% if (nextTitle) { %>

#### <%= nextTitle %>

<% } %> <%= nextArticle.title %>
<% } %>
<% } %>
<% if (allItems.length > 1) { %>