Section 1.1 — Introduction to data

Section 1.1 — Introduction to data#

This notebook contains all the code from Section 1.1 Introduction to data of the No Bullshit Guide to Statistics.

Random selection#

import random
samplingframe = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
random.sample(samplingframe, 3)

[10, 8, 2]

Random assignment#

def flip_coin():
    r = random.random()
    if r < 0.5:
        print("intervention")
    else:
        print("control")

flip_coin()

control

Discussion#

Random sampling alternatives#

import random
random.seed(22)

# select sample of 20 from 100 individuals
pop1 = range(1,101)
print(sorted(random.sample(pop1, 20)))

[4, 7, 11, 16, 18, 23, 24, 30, 32, 35, 41, 45, 58, 71, 77, 79, 84, 88, 90, 95]

# 5 strata of 20 individuals
strata = [range(1,21) for s in range(5)]
for statum in strata:
    print(sorted(random.sample(statum, 4)))

[1, 2, 9, 14]
[6, 7, 10, 14]
[2, 4, 17, 19]
[6, 9, 11, 20]
[5, 10, 13, 17]

# choose 2 clusters out of 10
clusters = range(1,11)
print(sorted(random.sample(clusters, 2)))

[5, 10]
Contents