Skip to content
AP Statistics · Regression Analysis

Spurious correlation

Spurious correlation appears in 7 reviewed AP Statistics questions and sits in Regression Analysis. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Spurious correlation is tested

Example 1Easier
A researcher finds a strong positive correlation (r = 0.85) between ice cream sales and the number of sunburns reported per week. She suspects that outdoor temperature is a lurking variable. Which of the following best describes the role of temperature?
  1. ATemperature is a confounding variable linked to both ice cream sales and sunburns, making the correlation spuriousCorrect
  2. BTemperature has no role because the correlation is already strong
  3. CTemperature is an effect modifier that reverses the direction of the correlation between ice cream sales and sunburns
  4. DTemperature is a response variable that is predicted by both weekly ice cream sales and the weekly number of sunburns

Why A is right

Temperature is a lurking/confounding variable that drives both ice cream sales (people buy more ice cream when it is hot) and sunburns (people spend more time outdoors and are more exposed to UV radiation when it is hot). The correlation between ice cream and sunburns is spurious — it exists because both variables are associated with temperature, not because one causes the other.
Why the other 3 choices miss
B
Incorrect. A strong correlation does not rule out confounding. In fact, confounding variables can create strong but meaningless correlations. Temperature is clearly relevant despite the strong r value.
C
Incorrect. An effect modifier changes the strength or direction of an association within subgroups. Temperature does not reverse the ice cream-sunburn relationship; it creates it.
D
Incorrect. Temperature is an explanatory (lurking) variable that affects both ice cream sales and sunburns. It is not predicted by them; it drives them.

Studied alongside

Other concepts from Regression Analysis.