Violin Plot [Simply explained]

A violin plot is a method of plotting numeric data and can be understood as a combination of a box plot and a kernel density plot. It provides a visualization of data distribution.

But how do we interpret a violin plot?

Kernel Density Estimation:
This is the outer layer of the violin plot and displays the density of the data at different values. The width of the plot at different values indicates the density of the data: a wider section suggests a higher density (more data points), whereas a narrower section indicates lower density (fewer data points). The violin plot is typically symmetrical, meaning it mirrors the density estimation on either side of its axis.

Central Box Plot which is Optional:
Inside the violin, there is often a miniature box plot which provides additional details about the data's distribution. The central line in this box plot represents the median of the data, while the edges of the box represent the interquartile range, giving insights into the data's spread.

Whiskers which are Optional:
Like in a box plot, whiskers might extend from the box, indicating variability outside the upper and lower quartiles. They can provide a visual cue for identifying outliers.

► Make a Violin Plot online

► E-BOOK

[harjeet]

The most amazing explanation about violin plot, I have found on youtube. Thanks for putting the effort in making this amazing video.

[sqfiswi]

THANK YOU!! this video is simple and very helpful

[Vladimir-Marin]

This is so helpful, thank you so much, I really appreciate it 😍

[DrNithinKRaju_Anatomist]

Please make a video on "split violin plot" also

[seanhunter]

Violin plots are a really terrible way to visualise data. Either you care about the distribution, in which case the best visualization is to just plot the distribution in the normal way- horizontally, not pivoted 90 degrees and mirrored, or you want to emphasise the quartiles, median etc in which case a boxplot is better. A violin plot makes it harder to see the box plot and is way worse than seeing the full distribution in the normal way. In most papers where I see violin plots they go ahead and just plot the distribution in the normal way anyway.

Secondly, the kernel smoothing used in the kde to create the violin is often so extreme you think you know much more about the distribution than is really supported by your data.

[siddharthakar]

why do i have a feeling that you are from germany and berlin may be haha

[yacinebenm]

The most useless plot ever, why not just a box plot and a histogram lol

But you do you