spurious correlations

correlation is not causation

discover · random · spurious scholar
← previous page · next page →

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Annual US household spending on used cars and the second variable is Solar power generated in Grenada. The chart goes from 2007 to 2021, and the two variables track closely in value over that time.

View details about correlation #5,900

^{Show scatterplot}

What else correlates?
Annual US household spending on used cars · all weird & wacky
Solar power generated in Grenada · all energy

View details about correlation #2,395

^{Show scatterplot}

What else correlates?
Bachelor's degrees awarded in social services · all education
The number of phlebotomists in Florida · all cccupations

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Christopher and the second variable is Burglaries in Oklahoma. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

View details about correlation #2,487

^{Show scatterplot}

What else correlates?
Popularity of the first name Christopher · all first names
Burglaries in Oklahoma · all random state specific

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the 'first world problems' meme and the second variable is Google searches for 'vihart'. The chart goes from 2006 to 2023, and the two variables track closely in value over that time.

View details about correlation #5,130

^{Show scatterplot}

What else correlates?
Popularity of the 'first world problems' meme · all memes
Google searches for 'vihart' · all google searches

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Sales of LP/Vinyl Albums and the second variable is Costco Wholesale's stock price (COST). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

View details about correlation #1,636

^{Show scatterplot}

What else correlates?
Sales of LP/Vinyl Albums · all weird & wacky
Costco Wholesale's stock price (COST) · all stocks

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Bachelor's degrees awarded in Education and the second variable is The number of proofreaders in Kansas. The chart goes from 2012 to 2020, and the two variables track closely in value over that time.

View details about correlation #3,361

^{Show scatterplot}

What else correlates?
Bachelor's degrees awarded in Education · all education
The number of proofreaders in Kansas · all cccupations

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Lamont and the second variable is Burglary rates in the US. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

View details about correlation #5,950

^{Show scatterplot}

What else correlates?
Popularity of the first name Lamont · all first names
Burglary rates in the US · all random state specific

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Democratic Senators in Indiana and the second variable is Google searches for 'why isnt 11 pronounced onety one'. The chart goes from 2004 to 2018, and the two variables track closely in value over that time.

View details about correlation #5,215

^{Show scatterplot}

What else correlates?
Votes for Democratic Senators in Indiana · all elections
Google searches for 'why isnt 11 pronounced onety one' · all google searches

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the 'one does not simply' meme and the second variable is Total comments on Numberphile YouTube videos. The chart goes from 2011 to 2023, and the two variables track closely in value over that time.

View details about correlation #4,995

^{Show scatterplot}

What else correlates?
Popularity of the 'one does not simply' meme · all memes
Total comments on Numberphile YouTube videos · all YouTube

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of judges in Indiana and the second variable is Viewership of The Big Bang Theory. The chart goes from 2008 to 2019, and the two variables track closely in value over that time.

View details about correlation #1,859

^{Show scatterplot}

What else correlates?
The number of judges in Indiana · all cccupations
Viewership of "The Big Bang Theory" · all films & actors

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Sunny and the second variable is Solar power generated in Egypt. The chart goes from 1983 to 2021, and the two variables track closely in value over that time.

View details about correlation #1,902

^{Show scatterplot}

What else correlates?
Popularity of the first name Sunny · all first names
Solar power generated in Egypt · all energy

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Frozen yogurt consumption and the second variable is Violent crime rates. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

View details about correlation #5,905

^{Show scatterplot}

What else correlates?
Frozen yogurt consumption · all food
Violent crime rates · all random state specific

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is London Gold Prices and the second variable is Customer satisfaction with Whole Foods . The chart goes from 2007 to 2012, and the two variables track closely in value over that time.

View details about correlation #5,942

^{Show scatterplot}

What else correlates?
London Gold Prices · all weird & wacky
Customer satisfaction with Whole Foods · all weird & wacky

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of movies Mila Kunis appeared in and the second variable is POSCO Holdings' stock price (PKX). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

View details about correlation #5,882

^{Show scatterplot}

What else correlates?
The number of movies Mila Kunis appeared in · all films & actors
POSCO Holdings' stock price (PKX) · all stocks

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is How 'hip and with it' Matt Parker's YouTube video titles are and the second variable is The number of zoologists in Nevada. The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

View details about correlation #4,878

^{Show scatterplot}

What else correlates?
How 'hip and with it' Matt Parker's YouTube video titles are · all YouTube
The number of zoologists in Nevada · all cccupations

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Associates degrees awarded in Parks & Recreation and the second variable is Google searches for 'tummy ache'. The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

View details about correlation #1,472

^{Show scatterplot}

What else correlates?
Associates degrees awarded in Parks & Recreation · all education
Google searches for 'tummy ache' · all google searches

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Popularity of the first name Kendrick and the second variable is Popularity of the 'doge' meme. The chart goes from 2006 to 2022, and the two variables track closely in value over that time.

View details about correlation #5,107

^{Show scatterplot}

What else correlates?
Popularity of the first name Kendrick · all first names
Popularity of the 'doge' meme · all memes

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Butter consumption and the second variable is Wind power generated in United States. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

View details about correlation #2,205

^{Show scatterplot}

What else correlates?
Butter consumption · all food
Wind power generated in United States · all energy

← Previous page
Discover a new correlation
View random correlation
View all correlations
View all research papers
Get permission to re-use these charts

Why this works

Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.”^Note Fun fact: the chart used on the wikipedia page to demonstrate data dredging is also from me. I've been being naughty with data since 2014.
Instead of starting with a hypothesis and testing it, I instead tossed a bunch of data in a blender to see what correlations would shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably no direct connection between these variables, despite what the AI says above.^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. You will often see trend-lines form. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A naive p-value calculation does not take this into account.^Note You will calculate a lower chance of "randomly" achieving the result than represents reality.

To be more specific: p-value tests are probability values, where you are calculating the probability of achieving a result at least as extreme as you found completely by chance. When calculating a p-value, you need to assert how many "degrees of freedom" your variable has. I count each year (minus one) as a "degree of freedom," but this is misleading for continuous variables.

This kind of thing can creep up on you pretty easily when using p-values, which is why it's best to take it as "one of many" inputs that help you assess the results of your analysis.
Y-axes doesn't start at zero: I truncated the Y-axes of the graphs above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. If you click on any of the charts that abuse this, you can scroll down to see a version that starts at zero.
Confounding variable: Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
Outliers: Some datasets here have outliers which drag up the correlation.^Note In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

Because this page is automatically generated, I don't know whether any of the charts displayed on it have outliers. I'm just a footnote. ¯\_(ツ)_/¯
I intentionally mishandeled outliers, which makes the correlation look extra strong.
Low n: There are not many data points included in some of these charts.^Note You can do analyses with low ns! But you shouldn't data dredge with a low n.
Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.

Pro-tip: click on any correlation to see:

Detailed data sources
Prompts for the AI-generated content
Explanations of each of the calculations (correlation, p-value)
Python code to calculate it yourself

Project by Tyler Vigen
emailme@tylervigen.com · about · subscribe

CC BY 4.0