## Violin and Swarm Plots

About **violin plots**

Let's talk about sample **variances**. The measure of scattering is well visualized by the **violin plot**.

It is similar in use to **boxplot**. Consider an example from life. Let's compare the data on annual incomes in the USA and Canada in 2020:

The graph tells us that they are quite close.

The white dot in the center of the graph indicates the **median** of the **distribution**.

The bolder part of the line means the first quantile (bottom) and the third quantile (top). Anything outside the horizontal line is an outlier. Now let's compare the data on annual incomes in the USA and Brazil in 2020:

The graph tells us that they are quite close. In this graph, the **distributions** are clearly different. The **violin plot** for income in Brazil is below.
Let's build a **violin plot** of the `'Impression'`

columns for the test and control groups:

About **swarm plots**

The **swarm plot** goes well with the **violin plot**. Let's look at their combination:

Now we have a visual representation of data scatter. But are these variances equal? Alas, we cannot draw such a conclusion by looking only at the graphs. As you might have guessed, statistics have a tool to check. But first, practice time!

Everything was clear?

Course Content

# The Art of A/B Testing

1. What is A/B testing?

The Art of A/B Testing

## Violin and Swarm Plots

About **violin plots**

Let's talk about sample **variances**. The measure of scattering is well visualized by the **violin plot**.

It is similar in use to **boxplot**. Consider an example from life. Let's compare the data on annual incomes in the USA and Canada in 2020:

The graph tells us that they are quite close.

The white dot in the center of the graph indicates the **median** of the **distribution**.

The bolder part of the line means the first quantile (bottom) and the third quantile (top). Anything outside the horizontal line is an outlier. Now let's compare the data on annual incomes in the USA and Brazil in 2020:

The graph tells us that they are quite close. In this graph, the **distributions** are clearly different. The **violin plot** for income in Brazil is below.
Let's build a **violin plot** of the `'Impression'`

columns for the test and control groups:

About **swarm plots**

The **swarm plot** goes well with the **violin plot**. Let's look at their combination:

Now we have a visual representation of data scatter. But are these variances equal? Alas, we cannot draw such a conclusion by looking only at the graphs. As you might have guessed, statistics have a tool to check. But first, practice time!

Everything was clear?