Descriptive statistics

The term descriptive statistics refers to methods that allow summarizing collections of data. To demonstrate the most important methods, we start by defining a dataset first.

measurements = [5, 2, 6, 4, 8, 6, 2, 5, 1, 3, 3, 6]

Measurements of central tendency

We can measure the location of our measurement in space using numpy’s statistics functions and Python’s statistics module.

import numpy as np
import statistics as st

np.mean(measurements)

4.25

np.median(measurements)

4.5

st.mode(measurements)

6

Measurements of spread

Numpy also allows measuring the spread of measurements.

np.std(measurements)

2.0052015692526606

np.var(measurements)

4.020833333333333

np.min(measurements), np.max(measurements)

(1, 8)

np.percentile(measurements, [25, 50, 75])

array([2.75, 4.5 , 6.  ])

Exercise

Find out if the median of a sample dataset is always a number within the sample. Use these three examples to elaborate on this:

example1 = [3, 4, 5]

example2 = [3, 4, 4, 5]

example3 = [3, 4, 5, 6]