Correlation and Cause

Name: Correlation and Cause
Author: StemPy Lab

In a seaside town, the weeks with more ice creams sold are also the weeks with more sunburn.

Does ice cream burn the skin?
Of course not.
Learn to look for the hidden variable behind a correlation, and to see how combining groups can turn a result upside down.
Then straighten a curved pattern with a logarithm, and read a claim in the news with care.

3 lessons, about 1 h 25 min3 simulations10 problems3 practice questionsPython in every lesson

Course outline (3 lessons)

Lesson 1about 30 min
Lurking variables
Two variables can move together because a third variable drives both of them. This lesson shows such a lurking variable at work in a made-up seaside town, explains why only a randomised experiment can show a cause, and lists the other reasons for a correlation.
1 simulation1 practice question1 Python program3 problems
Read the lesson
Lesson 2about 25 min
Simpson's paradox
A method can win inside every group and still lose when the groups are put together. This lesson works through a made-up two-group table where that happens, explains why the comparison turns upside down, and shows which answer to trust.
1 simulation1 practice question1 Python program3 problems1 Python lab
Read the lesson
Lesson 3about 30 min
Curved patterns and claims in the news
Not every relationship is a straight line. A curve can often be straightened by taking a logarithm or a square root, and then the methods of this chapter work again. This lesson shows one example of each, and ends with the questions to ask when a news report says that one thing causes another.
1 simulation1 practice question1 Python program4 problems1 Python lab1 question set1 note
Read the lesson

10 questions · 20 min

Not started

Loading…