Google

Spurious correlation is when two variables appear to be directly influencing each other when in reality they are not. Usually this misconception is caused by a confounding variable. DAGs (directed acyclic graphs) can help visualize which variables may influence each other and indicate if there is a possibility for a spurious correlation.  

Spurious Correlation

A DAG is a way of describing qualitative causal relationships among variables. In these graphics, arrows are used to indicate when a variable is assumed to directly influence another variable. 

Directed Acyclic Graph (DAG)

An amusing illustration of a spurious correlation is a 2012 study finding a strong positive correlation ($$r = 0.79$$) between a nation's per capita chocolate consumption and its number of Nobel laureates. Although the statistical relationship is robust, eating chocolate does not cause people to win Nobel prizes. Instead, this correlation is driven by third variables, such as a country's geographic location and wealth; European nations with higher per capita income tend to both consume more chocolate and invest more heavily in education and technology.

Example of a Spurious Correlation: Chocolate and Nobel Prizes

What term describes a situation where two variables appear to be directly influencing each other, but in reality, their relationship is an illusion usually caused by a confounding variable?

A researcher discovers a strong positive correlation between the number of hours students spend on social media and their reported levels of anxiety. However, further analysis reveals that a third variable—academic workload—independently increases both social media use (as a coping mechanism) and anxiety levels. In this scenario, the original correlation between social media use and anxiety is best described as a spurious correlation.

Learn Before

Related