If we work with small distribution (the size is less or equal to 30) and the distribution approximates the normal, we will use t-statistics.

**How to calculate confidence interval?**

```python
st.t.interval(alpha = 0.95, df = len(data)-1, loc = data.mean(), scale = st.sem(data))
```
- From `scipy.stats` we use the `t.interval()` function for the Student's T distribution.
- As it was before, `alpha` means the confidence level.
- `df` is the number of **degrees of freedom**.
- `loc` is the **mean**.
- `sem` is the **standard error** of the sample.

**Degrees of freedom**

The degree of freedom is the number of independent information elements that go into estimating a parameter. 

The formula is  `N - 1`, where `N` is the **sample size**.

Try to change the `alpha` parameter and observe the changes.

import scipy.stats as st
import numpy as np

data = [104, 106, 106, 107, 107, 107, 108, 108, 108, 108, 108, 109, 109, 109, 110, 110, 111, 111, 112]
# Calculate the confidence interval
confidence = st.t.interval(alpha = 0.95,
                           df = len(data)-1,
                           loc = np.mean(data),
                           scale = st.sem(data))

print(confidence)

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.