Data glossaryConfounding Variable

Confounding Variable

Data scienceStatistics

A confounding variable is an outside influence that changes the effect of the dependent and independent variable, potentially leading to false conclusions.

A confounding variable is an outside influence that changes the effect of the cause-effect you are studying. Confounding variables can ruin an experiment and produce useless results, so it is generally important to identify potential confounding (also known as "lurking") variables to produce robust results in a scientific study.

In practice

An example is the correlation between murder rate and the sale of ice-cream. As the murder rate rises so does the sale of ice-cream. One suggestion for this could be that murderers cause people to buy ice-cream. This is highly unlikely. A second suggestion is that purchasing ice-cream causes people to commit murder, also highly unlikely. Then there is a third variable which includes a confounding variable. It is distinctly possible that the weather causes the correlation. While the weather is icy cold, fewer people are out interacting with others and less likely to purchase ice-cream. Conversely, when it is hot outside, there is more social interaction and more ice-cream being purchased.

Related terms

Data science

Anonymization

Data anonymization is a type of process to remove sensitive information to protect the identity of individuals in datasets.

Statistics

Correlation does not imply causation

An easy mistake to make (a 'logical fallacy') is to draw the conclusion that, because two variables are correlated, one causes the other.

Data science

Dataset

A dataset is a collection of related tables of data that may be accessed individually or in combination for analysis or reporting.