spurious correlations

correlation is not causation

random · discover · next page →

don't miss spurious scholar,
where each of these is an academic paper

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of mechanical drafters in Colorado and the second variable is Season wins for the Denver Broncos. The chart goes from 2003 to 2022, and the two variables track closely in value over that time.

View details about correlation #1,914

^{Show scatterplot}

What else correlates?
The number of mechanical drafters in Colorado · all cccupations
Season wins for the Denver Broncos · all sports

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 Killian and the second variable is Automotive recalls for issues with the Air Bags. The chart goes from 1990 to 2022, and the two variables track closely in value over that time.

View details about correlation #2,599

^{Show scatterplot}

What else correlates?
Popularity of the first name Killian · all first names
Automotive recalls for issues with the Air Bags · all weird & wacky

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 The number of epidemiologists in Colorado. The chart goes from 2005 to 2020, and the two variables track closely in value over that time.

View details about correlation #2,246

^{Show scatterplot}

What else correlates?
Butter consumption · all food
The number of epidemiologists in Colorado · all cccupations

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 eggs and the second variable is Emerson Electric Co.'s stock price (EMR). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

View details about correlation #2,009

^{Show scatterplot}

What else correlates?
Annual US household spending on eggs · all weird & wacky
Emerson Electric Co.'s stock price (EMR) · all stocks

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 Tyler and the second variable is Gasoline pumped in Italy. The chart goes from 1980 to 2022, and the two variables track closely in value over that time.

View details about correlation #1,080

^{Show scatterplot}

What else correlates?
Popularity of the first name Tyler · all first names
Gasoline pumped in Italy · all energy

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The distance between Venus and Mercury and the second variable is The number of nursing assistants in Indiana. The chart goes from 2012 to 2022, and the two variables track closely in value over that time.

View details about correlation #2,732

^{Show scatterplot}

What else correlates?
The distance between Venus and Mercury · all planets
The number of nursing assistants in Indiana · 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 Science technologies and the second variable is Google searches for 'avocado toast'. The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

View details about correlation #2,965

^{Show scatterplot}

What else correlates?
Associates degrees awarded in Science technologies · all education
Google searches for 'avocado toast' · 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 Blanca and the second variable is Robberies in Texas. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

View details about correlation #2,498

^{Show scatterplot}

What else correlates?
Popularity of the first name Blanca · all first names
Robberies in Texas · 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 The number of movies Amy Poehler appeared in and the second variable is Popularity of the 'whip nae nae' meme. The chart goes from 2015 to 2023, and the two variables track closely in value over that time.

View details about correlation #5,865

^{Show scatterplot}

What else correlates?
The number of movies Amy Poehler appeared in · all films & actors
Popularity of the 'whip nae nae' meme · all memes

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'Taylor Swift' and the second variable is Fossil fuel use in British Virgin Islands. The chart goes from 2006 to 2021, and the two variables track closely in value over that time.

View details about correlation #5,825

^{Show scatterplot}

What else correlates?
Google searches for 'Taylor Swift' · all google searches
Fossil fuel use in British Virgin Islands · all energy

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Number of public school students in 9th grade and the second variable is Bank of America's stock price (BAC). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

View details about correlation #1,828

^{Show scatterplot}

What else correlates?
Number of public school students in 9th grade · all education
Bank of America's stock price (BAC) · all stocks

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Searches for 'never gonna give you up' and the second variable is Google searches for 'who is elon musk'. The chart goes from 2006 to 2023, and the two variables track closely in value over that time.

View details about correlation #4,986

^{Show scatterplot}

What else correlates?
Searches for 'never gonna give you up' · all memes
Google searches for 'who is elon musk' · all google searches

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of physicists in California and the second variable is Michael Schumacher's Formula One Ranking. The chart goes from 2003 to 2012, and the two variables track closely in value over that time.

View details about correlation #3,705

^{Show scatterplot}

What else correlates?
The number of physicists in California · all cccupations
Michael Schumacher's Formula One Ranking · 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 distance between Uranus and the moon and the second variable is Electricity generation in Japan. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

View details about correlation #2,730

^{Show scatterplot}

What else correlates?
The distance between Uranus and the moon · all planets
Electricity generation in Japan · all energy

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 History and the second variable is Centene's stock price (CNC). The chart goes from 2011 to 2021, and the two variables track closely in value over that time.

View details about correlation #2,709

^{Show scatterplot}

What else correlates?
Associates degrees awarded in History · all education
Centene's stock price (CNC) · all stocks

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Per capita consumption of margarine and the second variable is The divorce rate in Maine. The chart goes from 2000 to 2009, and the two variables track closely in value over that time.

View details about correlation #5,920

^{Show scatterplot}

What else correlates?
Per capita consumption of margarine · all food
The divorce rate in Maine · all random state specific

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