The next term is **standard deviation**; this value is similar to the variance because **standard deviation** is a square root of the variance; hence the formulas will vary for the population and sample.

**Definition**

**Standard deviation** is a measure of how data spread out in relation to the mean. 

**68–95–99.7 rule**

In statistics, one standard deviation or sigma plotted above and below the mean value corresponds to 68% of data; two sigmas include 95% and three 99.7. 

**Example**
Let's figure it out with the sample of kittens' weights in grams.

Look at the picture; in this case, we deal with such values:
- Mean value = 100 grams.
- Standard deviation (sigma - the sign you can see on the picture) = 20 grams.

So, as we said, the one sigma above and below the mean corresponds to 68% of values. In this case, 68% are the values from **mean - standard deviation = 100 - 20 = 80** to **mean + standard deviation = 100 + 20 = 120**.

This section will help us deal with the first real statistical case: finding confidence intervals. It requires knowledge of NumPy, pandas, Matplotlib, and Seaborn library to calculate math formulas and build visualization! To encourage you to pass this section, I want to point out that you will run across a small amount of theory but a significant amount of practice!

An inseparable part of a data analyst's life is conducting hypothesis testing. After completing this section, you will understand the idea behind testing in statistics and will be able to conduct a t-test using Python.

You have the data distribution with the mean value of 1500 standard deviation of 100. Match the percent of data with the numerical interval.