In the previous segment, you learnt how to handle missing values in a time series data. In this segment, you will learn how to detect and handle outliers in a time series data. Let’s understand that from Chiranjoy.

**Method of detecting outliers:**

**Extreme value analysis:**Remove the smallest and largest values in the dataset

**Box Plot:**The points lying on either side of the whiskers are considered to be outliers as shown in the image. The length of these whiskers is subjective and can be defined by you according to the problem.**Histogram:**Simply plotting a histogram can also reveal the outliers – basically the extreme values with low frequencies visible in the plot.

Now that you have learnt how to detect and handle outliers, let’s now apply that learning to detect outliers on the air passenger traffic dataset.

After exploring the dataset we understood that there are no outliers in the dataset.