Statistical Features
In this lesson, various statistical features are discussed.
We'll cover the following
Introduction to statistical features
Features that provide numerical information about the given data are known as statistical features. They help to extensively explore the nature and properties of data. The following are some features that will be discussed here:

Mean/Median

Standard deviation (STD)

Quantiles

Skewness
The above properties of data provide information that helps in the examination, inference, and prediction. These properties can only be applied to quantitative parts of the data.
Mean/Median

Mean: This is the average of the dataset computed by dividing the sum of numbers with their quantity.

Median: This is the exact middle value of a dataset. The data needs to be sorted first to get this measure.
In statistics, the median value is preferred to be used over the mean value because sometimes the mean value can get affected by exceptionally small or large outliers which might bend the mean in the wrong direction. Therefore, the median value is considered as it provides a correct approximation of the middle value of the dataset.
Standard deviation (STD)
STD stands for standard deviation. This measure informs us how far the values of a dataset are dispersed from their mean value.
A low std value means that data points of the dataset are close to their mean value, and a high std value means that data points are widely spread and are far from the mean value. The square of std returns the variance of data.
Quantiles
Quantile is a statistical measure that divides the data into equal parts. The main type of quantile is called quartile, which divides data into four or less equal parts.
Three lines are dropped on data for this division. Each of these lines falls on specific values in the dataset which are explained below.

The value that the first line hit is called the 1st quartile and is denoted with Q1. This point of data indicates that 25% of the data is below this point, and 75% of the data is above this point. The data point that this line hits is the middle value between the smallest value of the dataset, and the median value of the dataset.

The value that the second line hit is called the 2nd quartile and is denoted with Q2. This point of data indicates that 50% of the data is below this point, and 50% of the data is above this point. The data point that this line hits is the median value of the dataset.

The value that the third line hit is called the 3rd quartile and is denoted with Q3. This point of data indicates that 75% of the data is below this point, and 25% of the data is above this point. The data point that this line hits is the middle value between the median value of the dataset and the largest value of the dataset.
The following table summarizes this information:
Symbol  Names  Definition 

Q1  First Quartile  Splits off the lowest 25% of data from the highest 75% 
Q2  Second Quartile  Splits dataset in half 
Q3  Third Quartile  Splits off the highest 25% of data from the lowest 75% 
Get handson with 1000+ tech skills courses.
Learn to code, grow your skills, and succeed in your tech interview