The Washington PostDemocracy Dies in Darkness

7 charts: Why you shouldn’t confuse correlation with causation

One of the problems with research of any kind, including and especially in education, is the problem of confusing correlation with causation. This sounds technical, but it really goes to the heart of the problem with research that confuses the first for the second. For example, a study may report that test scores rose after implementation of a specific academic program, and the conclusion could be made that the program helped. But the test scores could have risen for any other number of reasons, including kids eating better breakfasts or being tutored outside of school.

A post on has some charts showing why correlation does not, in fact, mean causation. The charts came from This is a a Web site dedicated to showing “spurious” correlations that are hilarious. Here are seven of the charts, and you can find the rest here:

Divorce rate in Maine correlates with per capita consumption of margarine in U.S.

Per capita consumption of cheese correlates with number of people who died by becoming tangled in their bedsheets

Worldwide non-commercial space launches correlates with sociology doctorates awarded in U.S.

U.S. spending on science, space, and technology correlates with suicides by hanging, strangulation and suffocation

Money spent on pets in U.S. correlates with number of lawyers in California

Letters in Winning Word of Scripps National Spelling Bee correlates with number of people killed by venomous spiders

Precipitation in Multnomah County, OR inversely correlates with number of lawyers in American Samoa