Spurious correlation #5,714 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'cat memes' and the second variable is Air quality in Green Bay, Wisconsin. The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'cat memes' and the second variable is Air quality in Green Bay, Wisconsin. The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As cat memes surged, so did the demand for indoor plants. More people in Green Bay started filling their homes with air-purifying plants to create the perfect backdrop for photographing their feline friends. The collective increase in plant ownership led to an unexpected uptick in indoor air quality, proving that when it comes to cleaner air, the internet really is the cat's meow.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a cozy living room with abundant greenery and indoor plants. Cats are nestled among the foliage, playfully pawing at fluffy cat toys or looking out of the window at the thriving plant life. The room exudes a tranquil atmosphere, with the clean air and vibrant greenery creating a peaceful and inviting space for both humans and their feline friends. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Google searches for 'cat memes' and Air quality in Green Bay, Wisconsin. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Woodblock painting A Discovery magazine cover image a funny image you would see on reddit Parallax art Oragami
ChatGPT: a funny image you would see on reddit

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Google searches for 'cat memes' and Air quality in Green Bay, Wisconsin, in the following situation: As cat memes surged, so did the demand for indoor plants. More people in Green Bay started filling their homes with air-purifying plants to create the perfect backdrop for photographing their feline friends. The collective increase in plant ownership led to an unexpected uptick in indoor air quality, proving that when it comes to cleaner air, the internet really is the cat's meow.. Keep the description simple.
ChatGPT: In Green Bay, Wisconsin, as people were searching for "cat memes" on Google, indoor plant sales surged. The scene shows indoor spaces filled with lush greenery, creating the perfect setting for snapping adorable photos of cats. Meanwhile, the air quality improved with the increase in air-purifying plants, providing a fresh and clean environment for both the humans and their furry companions.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a funny image you would see on reddit ] and depicting this scene: In Green Bay, Wisconsin, as people were searching for "cat memes" on Google, indoor plant sales surged. The scene shows indoor spaces filled with lush greenery, creating the perfect setting for snapping adorable photos of cats. Meanwhile, the air quality improved with the increase in air-purifying plants, providing a fresh and clean environment for both the humans and their furry companions. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a cozy living room with abundant greenery and indoor plants. Cats are nestled among the foliage, playfully pawing at fluffy cat toys or looking out of the window at the thriving plant life. The room exudes a tranquil atmosphere, with the clean air and vibrant greenery creating a peaceful and inviting space for both humans and their feline friends.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in cat memes (Google searches for 'cat memes') caused Air quality in Green Bay, Wisconsin to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin

Journal of Feline Phenomena

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Google searches for 'cat memes' and Air quality in Green Bay, Wisconsin. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin

[[ABSTRACT]]
This paper investigates the surprisingly strong association between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. The study utilized data from Google Trends and the Environmental Protection Agency to explore this delightful yet unexpected connection. Our analysis revealed a correlation coefficient of 0.8471866, with a p-value lower than a cat's curiosity, at p < 0.01, covering the years 2004 to 2023.

The findings suggest that as Google searches for 'cat memes' increased, air quality in Green Bay, Wisconsin improved. This unexpected correlation left our research team feline quite amused, but we can't help but paws and wonder if there's more to this mysterious link. Perhaps it's time for environmental researchers to take a closer look at the impact of adorable feline images on local air quality.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The pursuit of scientific inquiry often leads us to unexpected findings, and this study is no exception. As researchers, we are accustomed to investigating logical, linear relationships between variables, but every meow and then, we come across a connection that leaves us a-mews-ed and scratching our heads.
Our research delves into the intriguing correlation between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. It may sound like the purr-fect example of an odd couple, but the statistical analysis reveals a startling relationship that begs further exploration.
It's not every day that one gets to delve into the world of feline internet humor and environmental metrics, but this study gives us the opportunity to do just that. As we paws to consider this unusual correlation, we can't help but wonder what underlying factors may be at play. Are the residents of Green Bay using cat memes as a coping mechanism for poor air quality, or could there be a more intricate and meow-tivating explanation? This is a purr-plexing mystery that promises to captivate both the scientific community and casual observers alike.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The present investigation presented a unique opportunity to explore the unexpected correlation between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. Previous research by Smith (2015) and Doe (2018) had primarily focused on conventional measures of air quality and their impact on public health and well-being. However, the intriguing dynamics of online phenomena and their potential ecological implications were often overlooked in these studies, leaving this area of inquiry uncharted.

In "The Air We Breathe: Understanding Air Quality and Its Impacts," the authors elucidate the detrimental effects of poor air quality on respiratory health and overall quality of life. Nevertheless, the lighthearted realm of cat memes and their potential influence on environmental variables was conspicuously absent from the scholarly discourse. It's almost as if the researchers were suffering from a deficiency in "Pawsitive Approaches to Environmental Studies," as the feline influence had not yet graced their academic radar.

Expanding beyond the realm of non-fiction literature, we immerse ourselves in fiction works that, while not directly addressing the topic at hand, offer valuable insights into the whimsical world of internet culture and environmental intrigue. In "Whiskers and Wisdom: Tales of Feline Fortunes," the authors transport readers into a realm where cats reign supreme, offering a symbolic exploration of the coexistence of human society and the natural world. Similarly, in "Purr-fectly Perplexing: A Tale of Environmental Enigmas," the authors weave a narrative that blends the enigmatic forces of nature with the endearing charm of feline companions.

In undertaking this unconventional investigation, the authors embraced a multi-disciplinary approach, which included familiarizing themselves with popular television content that may shed light on the interplay between online behavior and environmental circumstances. Shows such as "The Great Catsby" and "Paws and Recreation" provided a window into the world of feline fascination and its potential impact on individual well-being. While tangentially related to the subject at hand, these cultural touchstones offered a playful exploration of the ways in which humanity interacts with its environmental context, broadening the scope of inquiry beyond traditional academic paradigms.

This review aims to contextualize the current study within the existing literature while injecting a playful twist into the scholarly discourse, much like a well-timed cat meme in a serious conversation.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Google searches for 'cat memes' and Air quality in Green Bay, Wisconsin. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

Here are the title, abstract, literature review, and results sections. Please harken back to 1-2 of the goofy items in the literature review, but pretend to take them completely seriously. Discuss how your results supported the prior research.

Do not write a conclusion. I will add a conclusion after this.

[[TITLE]]
Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin

[[ABSTRACT]]
This paper investigates the surprisingly strong association between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. The study utilized data from Google Trends and the Environmental Protection Agency to explore this delightful yet unexpected connection. Our analysis revealed a correlation coefficient of 0.8471866, with a p-value lower than a cat's curiosity, at p < 0.01, covering the years 2004 to 2023.

The findings suggest that as Google searches for 'cat memes' increased, air quality in Green Bay, Wisconsin improved. This unexpected correlation left our research team feline quite amused, but we can't help but paws and wonder if there's more to this mysterious link. Perhaps it's time for environmental researchers to take a closer look at the impact of adorable feline images on local air quality.

[[LITERATURE REVIEW]]
The present investigation presented a unique opportunity to explore the unexpected correlation between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. Previous research by Smith (2015) and Doe (2018) had primarily focused on conventional measures of air quality and their impact on public health and well-being. However, the intriguing dynamics of online phenomena and their potential ecological implications were often overlooked in these studies, leaving this area of inquiry uncharted.
In "The Air We Breathe: Understanding Air Quality and Its Impacts," the authors elucidate the detrimental effects of poor air quality on respiratory health and overall quality of life. Nevertheless, the lighthearted realm of cat memes and their potential influence on environmental variables was conspicuously absent from the scholarly discourse. It's almost as if the researchers were suffering from a deficiency in "Pawsitive Approaches to Environmental Studies," as the feline influence had not yet graced their academic radar.
Expanding beyond the realm of non-fiction literature, we immerse ourselves in fiction works that, while not directly addressing the topic at hand, offer valuable insights into the whimsical world of internet culture and environmental intrigue. In "Whiskers and Wisdom: Tales of Feline Fortunes," the authors transport readers into a realm where cats reign supreme, offering a symbolic exploration of the coexistence of human society and the natural world. Similarly, in "Purr-fectly Perplexing: A Tale of Environmental Enigmas," the authors weave a narrative that blends the enigmatic forces of nature with the endearing charm of feline companions.
In undertaking this unconventional investigation, the authors embraced a multi-disciplinary approach, which included familiarizing themselves with popular television content that may shed light on the interplay between online behavior and environmental circumstances. Shows such as "The Great Catsby" and "Paws and Recreation" provided a window into the world of feline fascination and its potential impact on individual well-being. While tangentially related to the subject at hand, these cultural touchstones offered a playful exploration of the ways in which humanity interacts with its environmental context, broadening the scope of inquiry beyond traditional academic paradigms.
This review aims to contextualize the current study within the existing literature while injecting a playful twist into the scholarly discourse, much like a well-timed cat meme in a serious conversation.

[[RESULTS]]
The analysis of the data revealed a remarkably strong correlation coefficient of 0.8471866 between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. This finding suggests a potential relationship between the frivolous pursuit of feline amusement and the substantial improvement in air quality, which is nothing to sneeze at.
The coefficient of determination, also known as r-squared, was calculated to be 0.7177252, indicating that approximately 71.77% of the variability in air quality can be explained by the variability in Google searches for 'cat memes'. This highlights a rather impressive level of association, making it clear that there is more to this curious correlation than mere coincidence.
Moreover, the p-value obtained (p < 0.01) is not to be overlooked, being lower than the probability of a cat knocking over a delicate experiment - it provides strong evidence against the null hypothesis and supports the significant relationship between the two variables. This statistical analysis embodies the strength of the correlation, making it quite the 'purr-suasive' argument for further investigation.
Subsequently, the scatterplot (Fig. 1) visually depicts the robust positive relationship between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. The points on the plot form a discernible pattern that resembles a litter of well-behaved data points, further emphasizing the validity of the correlation.
These findings prompt us to reflect on the potential implications of such a correlation. Is there a 'paws-itive' influence of cat memes on environmental well-being, or does this correlation merely scratch the surface of a more complex and nuanced connection? The unexpected nature of this relationship evokes both curiosity and amusement, leaving us with a 'tail' of scientific discovery that is as captivating as a cat video on the internet.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of the present study provide compelling evidence of a strong and significant association between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. This unexpected correlation, which left our research team feline quite amused, is supported by previous research (Smith, 2015; Doe, 2018), albeit in less conventional contexts. The extent to which the pursuit of feline amusement impacts environmental variables has been a topic of increasing interest in the scholarly community, and our findings contribute to this emerging field of inquiry.

The robust positive relationship between Google searches for 'cat memes' and air quality, as evidenced by the high correlation coefficient and the low p-value, suggests that the impact of cat memes on local air quality is nothing to sneeze at – pun intended. The r-squared value of 0.7177252 indicates that approximately 71.77% of the variability in air quality can be explained by the variability in Google searches for 'cat memes', implying a substantial influence of feline amusement on environmental conditions.

The literature review, which playfully intertwined serious environmental discourse with whimsical feline fascination, set the stage for the unexpected yet statistically supported correlation between cat memes and air quality. Integrating seemingly unrelated cultural touchstones, such as "The Great Catsby" and "Paws and Recreation," allowed us to explore the intersection of internet culture and environmental circumstances, shedding light on the potential impact of online behavior on ecological variables. Thus, the present study expands the scope of inquiry, demonstrating the relevance of seemingly nontraditional sources of insight – like a cat leaping out of the most unexpected places.

In this light, the findings of this study offer a 'purr-suasive' argument for further exploration of the influence of cat memes on environmental well-being. The implications of this correlation spark a sense of curiosity and amusement akin to a captivating cat video on the internet, urging the scientific community to delve deeper into the intertwined world of online phenomena and ecological dynamics. These unexpected research discoveries remind us that sometimes, the most delightful and 'pawsitively' engaging insights emerge from the unlikeliest places, much like stumbling upon a hidden gem in a sea of seemingly mundane data.

The findings of this study not only contribute to the scientific understanding of environmental variables but also underscore the importance of considering unconventional influences on ecological dynamics, reminding us that in the world of research, as in life, it's important to remain open to unexpected connections and, much like a curious cat, explore uncharted territories.

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Feline Phenomena

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin. Respond only with the name of a fictional organization.

ChatGPT:

Society for Feline Well-being and Environmental Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin with an abstract of This paper investigates the surprisingly strong association between Google searches for 'cat memes' and air quality in Green Bay, Wisconsin. The study utilized data from Google Trends and the Environmental Protection Agency to explore this delightful yet unexpected connection. Our analysis revealed a correlation coefficient of 0.8471866, with a p-value lower than a cat's curiosity, at p < 0.01, covering the years 2004 to 2023.
The findings suggest that as Google searches for 'cat memes' increased, air quality in Green Bay, Wisconsin improved. This unexpected correlation left our research team feline quite amused, but we can't help but paws and wonder if there's more to this mysterious link. Perhaps it's time for environmental researchers to take a closer look at the impact of adorable feline images on local air quality.

ChatGPT:

'cat memes', air quality, Green Bay, Wisconsin, Google searches, correlation coefficient, Environmental Protection Agency, Google Trends, environmental research, feline images, impact on air quality

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Google searches for 'cat memes'
Detailed data title: Relative volume of Google searches for 'cat memes' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'cat memes'

Air quality in Green Bay, Wisconsin
Detailed data title: Percentage of days with good air quality in Green Bay, WI
Source: Environmental Protection Agency
See what else correlates with Air quality in Green Bay, Wisconsin

Correlation r = 0.8471866 (Pearson correlation coefficient)
Correlation is a measure of how much the variables move together. If it is 0.99, when one goes up the other goes up. If it is 0.02, the connection is very weak or non-existent. If it is -0.99, then when one goes up the other goes down. If it is 1.00, you probably messed up your correlation function.

r² = 0.7177252 (Coefficient of determination)
This means 71.8% of the change in the one variable (i.e., Air quality in Green Bay, Wisconsin) is predictable based on the change in the other (i.e., Google searches for 'cat memes') over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.4E-6.^Show 0.0000024442870122726520000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.85 in 0.00024% of random cases. Said differently, if you correlated 409,117 random variables^Note You don't actually need 409 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.65, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Google searches for 'cat memes' (Rel. search volume)	0.166667	0.25	0.181818	1	0.25	0.333333	0.5	1.6	9.25	19.25	19.5	29.75	36.6667	40.5	35.75	45.3333	30.1667	21	23.75	20.9
Air quality in Green Bay, Wisconsin (Good air quality)	73.3333	58.7302	66.8016	60.9551	58.8068	63.9889	67.1348	51.9231	71.3115	72.6027	71.5069	78.453	83.3333	86.1111	78.6111	85.0415	84.153	73.4247	83.2869	64.0884

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.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations 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^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.
no direct connection between these variables, despite what the AI says above. 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. 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 simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph 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. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.166667,0.25,0.181818,1,0.25,0.333333,0.5,1.6,9.25,19.25,19.5,29.75,36.6667,40.5,35.75,45.3333,30.1667,21,23.75,20.9,])
array_2 = np.array([73.3333,58.7302,66.8016,60.9551,58.8068,63.9889,67.1348,51.9231,71.3115,72.6027,71.5069,78.453,83.3333,86.1111,78.6111,85.0415,84.153,73.4247,83.2869,64.0884,])
array_1_name = "Google searches for 'cat memes'"
array_2_name = "Air quality in Green Bay, Wisconsin"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Google searches for 'cat memes'
Line chart for only Air quality in Green Bay, Wisconsin
AI-generated correlation image
The spurious research paper: Pawsitively Purrfect: An Intriguing Correlation Between Google Searches for 'Cat Memes' and Air Quality in Green Bay, Wisconsin

View another random correlation

How fun was this correlation?

Your correlation rating is out of this world!

Correlation ID: 5714 · Black Variable ID: 1355 · Red Variable ID: 20687


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: