Discrete distributions

Introduzione alla statistica in Python

Maggie Matsui

Content Developer, DataCamp

Rolling the dice

Six-sided die

Rolling the dice

Each side of a die has 1/6 probability

Choosing salespeople

Names in a box, each with 25% probability

Probability distribution

Describes the probability of each possible outcome in a scenario

Each side of a die has 1/6 probability

Expected value: mean of a probability distribution

Expected value of a fair die roll = $(1 \times \frac{1}{6}) + (2 \times \frac{1}{6}) +(3 \times \frac{1}{6}) +(4 \times \frac{1}{6}) +(5 \times \frac{1}{6}) +(6 \times \frac{1}{6}) = 3.5$

Visualizing a probability distribution

Bar plot with a bar for each number 1 through six, with height 1/6.

Probability = area

$$P(\text{die roll}) \le 2 = ~?$$

Bars for 1 and 2 highlighted

Probability = area

$$P(\text{die roll}) \le 2 = 1/3$$

1/6 + 1/6 = 1/3

Uneven die

six-sided die with two sides with 3 dots

Expected value of uneven die roll = $(1 \times \frac{1}{6}) +(2 \times 0) +(3 \times \frac{1}{3}) +(4 \times \frac{1}{6}) +(5 \times \frac{1}{6}) +(6 \times \frac{1}{6}) = 3.67$

Visualizing uneven probabilities

Probability distribution of uneven die. Bars for 1, 4, 5, 6 are height 1/6, bar for 2 is height 0, bar for 3 is height 1/3

Adding areas

$$P(\text{uneven die roll}) \le 2 = ~?$$

1/6 + 0

Adding areas

$$P(\text{uneven die roll}) \le 2 = 1/6$$

1/6 + 0

Discrete probability distributions

Describe probabilities for discrete outcomes

Fair die

Fair die plot

Discrete uniform distribution

Uneven die

Uneven die plot

Sampling from discrete distributions

print(die)

  number      prob
0      1  0.166667
1      2  0.166667
2      3  0.166667
3      4  0.166667
4      5  0.166667
5      6  0.166667

np.mean(die['number'])

3.5

rolls_10 = die.sample(10, replace = True)
rolls_10

  number      prob
0      1  0.166667
0      1  0.166667
4      5  0.166667
1      2  0.166667
0      1  0.166667
0      1  0.166667
5      6  0.166667
5      6  0.166667
...

Visualizing a sample

rolls_10['number'].hist(bins=np.linspace(1,7,7)) 
plt.show()

histogram of 10 rolls

Sample distribution vs. theoretical distribution

Sample of 10 rolls

histogram of 10 rolls

np.mean(rolls_10['number']) = 3.0

Theoretical probability distribution

probability distribution of fair die

mean(die['number']) = 3.5

A bigger sample

Sample of 100 rolls

histogram of 100 rolls

np.mean(rolls_100['number']) = 3.4

Theoretical probability distribution

probability distribution of fair die

mean(die['number']) = 3.5

An even bigger sample

Sample of 1000 rolls

histogram of 1000 rolls

np.mean(rolls_1000['number']) = 3.48

Theoretical probability distribution

probability distribution of fair die

mean(die['number']) = 3.5

Law of large numbers

As the size of your sample increases, the sample mean will approach the expected value.

Sample size	Mean
10	3.00
100	3.40
1000	3.48

Let's practice!

Introduzione alla statistica in Python