Kurtosis refers to the degree of presence of outliers (extreme values) in the distribution.

Kurtosis is a statistical measure, whether the data is heavy-tailed or light-tailed in a normal distribution.

Table of Contents

## Types of excess kurtosis

### Excess Kurtosis

The excess kurtosis is used in statistics and probability theory to compare the kurtosis coefficient with that normal distribution. Excess kurtosis can be positive (Leptokurtic distribution), negative (Platykurtic distribution), or near to zero (Mesokurtic distribution).

Since normal distributions have a kurtosis of 3, excess kurtosis is calculating by subtracting kurtosis by 3.

Excess kurtosis = Kurt – 3

**Mesokurtic**(kurtosis same as the normal distribution).**Leptokurtic**or heavy-tailed distribution (kurtosis more than normal distribution).**Platykurtic**or short-tailed distribution (kurtosis less than normal distribution).

### 1. Mesokurtic (kurtosis = 3)

Mesokurtic is the same as the normal distribution, which means kurtosis is near to 0. In Mesokurtic, distributions are moderate in breadth, and curves are a medium peaked height.

Excess kurtosisinMesokurtic = 3-3 = 0

### 2. Leptokurtic (kurtosis > 3)

Leptokurtic is having very long and skinny tails, which means there are more chances of outliers. Positive values of kurtosis indicate that distribution is peaked and possesses thick tails. An extreme positive kurtosis indicates a distribution where more of the numbers are located in the tails of the distribution instead of around the mean.

### 3. Platykurtic (kurtosis < 3)

Platykurtic having a lower tail and stretched around center tails means most of the data points are present in high proximity with mean. A platykurtic distribution is flatter (less peaked) when compared with the normal distribution.

**Summary Table**

Kurtosis | Excess Kurtosis | |

Mesokurtic | =3 | =0 |

Leptokurtic | >3 | >0 |

Platykurtic | <3 | <0 |

## Video

In Hindi: Kurtosis Video

## Code (Python)

```
# if scipy library is not installed
pip install scipy
x = [55, 78, 65, 98, 97, 60, 67, 65, 83, 65]
from scipy.stats import kurtosis
print(kurtosis(x, fisher=False))
```

OUTPUT2.0453729382893178

**Note:** We set the **fisher=False** in the above code, so it calculate Pearson’s definition of kurtosis where the kurtosis value for normal distribution = 3.

The output of kurtosis is around **2.05 **which is less than 3 and the value of excess kurtosis is around **-0.95**. So we can conclude the distribution is Platykurtic, i.e. a distribution with thicker tails and flatter than the normal distribution.

You messed the tails… Leptokurtic -> more mass in the center, less mass around stdev and more mass in the tails (fat tails).

buenas noches, glorious blog on unctuous loss. such a thing helped.