Spurious correlation #2,276 · 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 Simon Property Group's stock price (SPG). 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 Simon Property Group's stock price (SPG). The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the nation collectively laughed at silly feline antics, the demand for retail therapy skyrocketed. Simon Property Group, being a major player in the shopping mall industry, saw a surge in foot traffic as people sought out purrfectly quirky cat-themed merchandise and impulsively decided to treat themselves. This unexpected economic paw-sitivity led to investors feeling bullish about SPG’s prospects, causing the stock price to climb higher than a cat scaling a curtain. Remember, when cat memes are on the rise, so are the profits – it’s a clawsome connection!

^{Show image generation prompt} Model: dalle-3
Prompt: Generating prompt for DALL-E-3: Let's create a cheerful and lighthearted image with a cute cartoon style. Picture a person with a big smile on their face, thoroughly enjoying the content on their phone. They're happily scrolling through a 'cat memes' search result on Google. In the background, have a stock market ticker displaying Simon Property Group's stock price rising, adding an element of unexpected joy and humor. 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 Simon Property Group's stock price. 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: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s inspired by bauhaus Cute cartoon Brutalism Steampunk
ChatGPT: Cute cartoon

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 Simon Property Group's stock price together. Keep the description simple.
ChatGPT: A person scrolling through their phone with a big smile on their face while looking at a 'cat memes' search result on Google, with a stock market ticker in the background showing Simon Property Group's stock price rising.

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: [ Cute cartoon ] and depicting this scene: A person scrolling through their phone with a big smile on their face while looking at a 'cat memes' search result on Google, with a stock market ticker in the background showing Simon Property Group's stock price rising. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generating prompt for DALL-E-3: Let's create a cheerful and lighthearted image with a cute cartoon style. Picture a person with a big smile on their face, thoroughly enjoying the content on their phone. They're happily scrolling through a 'cat memes' search result on Google. In the background, have a stock market ticker displaying Simon Property Group's stock price rising, adding an element of unexpected joy and humor.

*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 Simon Property Group's stock price (SPG) to increase.

AI academic paper

(Because p < 0.01)

Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity

The Journal of Humor and Applied Economics

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 Simon Property Group's stock price (SPG). Make lots of jokes, goofy observations, and puns.

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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity

[[ABSTRACT]]
This research delves into the intriguing world of internet memes and stock market dynamics by analyzing the connection between Google searches for "cat memes" and the stock price of Simon Property Group (SPG). Leveraging data from Google Trends and LSEG Analytics (Refinitiv) spanning the period of 2004 to 2023, a remarkable correlation coefficient of 0.8979141 and p < 0.01 were unearthed. The findings astoundingly suggest a strong relationship between the indulgence in feline humor and the performance of SPG shares. This unexpected juxtaposition of internet culture and financial markets prompts playful pondering and opens a window into the capricious whims of market behavior. The study concludes with a call for further exploration into the playful side of stock market analysis, encouraging researchers to embrace the quirks and quips of internet culture in understanding market dynamics.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The allure of internet memes has captivated the denizens of the digital realm, permeating the virtual landscape with an irrepressible and often inexplicable charm. This inexplicable charm has inspired a myriad of research endeavors, some serious and some purely whimsical. In this study, we take the proverbial plunge into the world of internet memes, focusing specifically on the felicitous phenomenon of "cat memes." Concurrently, we embark on a financial escapade into the realm of stock market sensitivity, with our gaze firmly fixated on the notable Simon Property Group (SPG) stock. The juxtaposition of these seemingly disparate domains leads to an intriguing endeavor to uncover any potential connections between the indulgence in feline humor and the performance of SPG shares.
What prompts this juxtaposition, you ask? Only the inscrutable vagaries of human behavior could lead one to ponder the connection between the endearing antics of our feline friends on the internet and the fiscal fortunes of a cornerstone of the real estate investment trust sector. Yet, as we delve into the annals of internet culture and financial markets, we are confronted with a conundrum that demands our attention, if not our amusement.
As our investigation unfolds, we are compelled to acknowledge the intriguing and at times bewildering nature of human cognition and the proclivity for amusing distractions even in the most austere of arenas. Thus, we endeavor to shed light on the latent correlations between the frivolity of internet memes and the gravity of stock market dynamics. Our findings will surely prompt playful pondering and perhaps a few raised eyebrows.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their study, Smith et al. (2018) explore the cognitive impact of internet memes on human behavior and decision-making processes. They assert that the viewing of humorous memes, particularly those featuring feline subjects, can induce a state of cognitive relaxation, potentially influencing individuals' perceptions and actions. Similarly, Doe and Jones (2015) delve into the realm of consumer behavior and its susceptibility to external stimuli, positing that seemingly innocuous stimuli, such as cat memes, can subtly influence consumer preferences and choices.

Turning to the world of finance, Book (2017) provides a comprehensive analysis of the intricate relationship between non-traditional data sources and stock market performance, emphasizing the increasing relevance of unconventional indicators in predicting market movements. Ipsium (2020) further elucidates the impact of internet culture on financial markets, underlining the role of social media trends and online phenomena in shaping investor sentiment and market dynamics.

The intersection of internet culture and finance ignites a playful yet thought-provoking discourse, with Book's "The Internet Made Me Do It" and Smith's "The Psychology of Memes" offering insightful perspectives on the cognitive implications of internet phenomena on human decision-making and behavior. On a more imaginative note, works of fiction such as "The Cat in the Hat" by Dr. Seuss and "The Chronicles of Narnia: The Lion, the Witch, and the Meme Lord" by C.S. Lewis, although not directly related to financial markets, exemplify the enduring portrayal of feline figures in literature and popular culture.

A departure from traditional research approaches, the authors also draw inspiration from children's cartoons and shows, including "The Aristocats" and "Tom and Jerry," to explore the endearing and enigmatic allure of feline characters. This whimsical exploration serves to highlight the multifaceted influence of feline symbolism in human cognition and popular culture.

In a surprising twist, the authors also found themselves lost in a rabbit hole of feline-themed amusement, ultimately leading to an impromptu office cat meme contest and a rousing debate on the investment potential of internet-famous felines. This unexpected detour, although ostensibly unrelated to the subject at hand, underscores the irresistibly magnetic pull of cat memes and their place in the peculiar tapestry of human behavior and market dynamics.

In summary, the literature surveyed presents a captivating interplay between internet memes, feline motifs, and financial markets, inviting readers to embark on a delightful expedition through the delightful, if not confounding, interconnections between online culture and stock market sensitivity.

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 Simon Property Group's stock price (SPG). Make lots of jokes, goofy observations, and puns.

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]]
Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity

[[ABSTRACT]]
This research delves into the intriguing world of internet memes and stock market dynamics by analyzing the connection between Google searches for "cat memes" and the stock price of Simon Property Group (SPG). Leveraging data from Google Trends and LSEG Analytics (Refinitiv) spanning the period of 2004 to 2023, a remarkable correlation coefficient of 0.8979141 and p < 0.01 were unearthed. The findings astoundingly suggest a strong relationship between the indulgence in feline humor and the performance of SPG shares. This unexpected juxtaposition of internet culture and financial markets prompts playful pondering and opens a window into the capricious whims of market behavior. The study concludes with a call for further exploration into the playful side of stock market analysis, encouraging researchers to embrace the quirks and quips of internet culture in understanding market dynamics.

[[LITERATURE REVIEW]]
In their study, Smith et al. (2018) explore the cognitive impact of internet memes on human behavior and decision-making processes. They assert that the viewing of humorous memes, particularly those featuring feline subjects, can induce a state of cognitive relaxation, potentially influencing individuals' perceptions and actions. Similarly, Doe and Jones (2015) delve into the realm of consumer behavior and its susceptibility to external stimuli, positing that seemingly innocuous stimuli, such as cat memes, can subtly influence consumer preferences and choices.
Turning to the world of finance, Book (2017) provides a comprehensive analysis of the intricate relationship between non-traditional data sources and stock market performance, emphasizing the increasing relevance of unconventional indicators in predicting market movements. Ipsium (2020) further elucidates the impact of internet culture on financial markets, underlining the role of social media trends and online phenomena in shaping investor sentiment and market dynamics.
The intersection of internet culture and finance ignites a playful yet thought-provoking discourse, with Book's "The Internet Made Me Do It" and Smith's "The Psychology of Memes" offering insightful perspectives on the cognitive implications of internet phenomena on human decision-making and behavior. On a more imaginative note, works of fiction such as "The Cat in the Hat" by Dr. Seuss and "The Chronicles of Narnia: The Lion, the Witch, and the Meme Lord" by C.S. Lewis, although not directly related to financial markets, exemplify the enduring portrayal of feline figures in literature and popular culture.
A departure from traditional research approaches, the authors also draw inspiration from children's cartoons and shows, including "The Aristocats" and "Tom and Jerry," to explore the endearing and enigmatic allure of feline characters. This whimsical exploration serves to highlight the multifaceted influence of feline symbolism in human cognition and popular culture.
In a surprising twist, the authors also found themselves lost in a rabbit hole of feline-themed amusement, ultimately leading to an impromptu office cat meme contest and a rousing debate on the investment potential of internet-famous felines. This unexpected detour, although ostensibly unrelated to the subject at hand, underscores the irresistibly magnetic pull of cat memes and their place in the peculiar tapestry of human behavior and market dynamics.
In summary, the literature surveyed presents a captivating interplay between internet memes, feline motifs, and financial markets, inviting readers to embark on a delightful expedition through the delightful, if not confounding, interconnections between online culture and stock market sensitivity.

[[RESULTS]]
Upon delving into the data, the research team uncovered a remarkable correlation coefficient of 0.8979141 and an r-squared of 0.8062497 when examining the relationship between Google searches for "cat memes" and the stock price of Simon Property Group (SPG) from 2004 to 2023. The p-value of less than 0.01 serves to further underscore the robustness of this connection, indicating an extremely low probability of observing such a strong correlation by random chance alone.
The scatterplot (Fig. 1) visually depicts the pronounced positive relationship between these seemingly incongruous variables, showcasing the undeniable bond between internet feline humor and the fluctuations in SPG stock price. It is worth noting that this correlation does not imply causation; however, the strength of the association cannot be denied.
Perhaps it is purr-haps not surprising that the whimsical world of cat memes, with its endearing and often amusing feline subjects, would exhibit a substantial link to the fiscal fortunes of a real estate investment trust such as SPG. The truly astonishing nature of this correlation prompts contemplation on the capricious whims of market behavior and the unexpected sources of influence that may sway investor sentiment.
The findings of this study elevate the discourse on stock market analysis by infusing it with an element of levity and whimsy, urging researchers to acknowledge and explore the unforeseen connections that may influence market dynamics. This unexpected juxtaposition of internet culture and financial markets invites playful pondering and challenges traditional notions of the factors at play in market sensitivity.
In conclusion, the results of this research endeavor underscore the potent influence of internet memes, particularly those of the feline variety, on the financial realm, and advocate for further exploration into the interplay between internet culture and market dynamics.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study provide compelling evidence supporting the prior research into the cognitive impact of internet memes and their influence on human behavior and decision-making processes. Building upon the work of Smith et al. (2018) and Doe and Jones (2015), who proposed that exposure to humorous memes, particularly those featuring feline subjects, can have an effect on cognitive relaxation and consumer preferences, our findings reveal a strong association between Google searches for "cat memes" and the stock price of Simon Property Group (SPG). This fortuitous connection not only enriches our understanding of the whimsical world of internet culture but also highlights the unforeseen influence of seemingly lighthearted online phenomena on market dynamics.

The striking correlation coefficient of 0.8979141 and an r-squared of 0.8062497 point to a robust relationship between the indulgence in feline humor and the performance of SPG shares. The p-value of less than 0.01 further solidifies the significance of this connection, indicating a notably low probability of observing such a strong correlation by random chance alone. These statistical findings align with the proposition put forth by Book (2017) regarding the relevance of unconventional indicators in predicting market movements. The pursuit of "purr-fect" investment decisions may indeed lead financial analysts to unexpected sources of insight.

The captivating interplay between internet memes, feline motifs, and financial markets, as highlighted in the literature review, finds its empirical validation in this study's results. The undeniable bond between the whimsical world of cat memes and the fluctuations in SPG stock price poses intriguing questions about the diverse pathways through which market sentiment may be influenced. While the correlation observed does not imply causation, the pronounced positive relationship visually depicted in the scatterplot underscores the potent influence of internet feline humor on the fiscal fortunes of SPG. This unexpected revelation may encourage future research endeavors to explore the multifaceted interconnections between online culture and stock market sensitivity, embracing the playful and enigmatic aspects of internet phenomena.

In summary, the findings of this study uphold the literature's proposition of a compelling relationship between internet memes, particularly those featuring feline subjects, and market dynamics. It is evident that the allure of cat memes extends beyond mere amusement, permeating the complex fabric of human cognition and market behavior. This research journey encourages scholars to recognize the intricate and often unexpected sources of influence that may shape investor sentiment and market movements, prompting a deeper examination of the interplay between internet culture and financial markets. The whimsical yet impactful connection uncovered in this study invites playful pondering and challenges traditional notions of the factors at play in market sensitivity, heralding a delightful expedition through the delightful, if not confounding, interconnections between online culture and stock market dynamics.

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 Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Humor and Applied Economics

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 Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity. Respond only with the name of a fictional organization.

ChatGPT:

Society for Feline Behavior and Economic Analysis

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 Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity with an abstract of This research delves into the intriguing world of internet memes and stock market dynamics by analyzing the connection between Google searches for "cat memes" and the stock price of Simon Property Group (SPG). Leveraging data from Google Trends and LSEG Analytics (Refinitiv) spanning the period of 2004 to 2023, a remarkable correlation coefficient of 0.8979141 and p < 0.01 were unearthed. The findings astoundingly suggest a strong relationship between the indulgence in feline humor and the performance of SPG shares. This unexpected juxtaposition of internet culture and financial markets prompts playful pondering and opens a window into the capricious whims of market behavior. The study concludes with a call for further exploration into the playful side of stock market analysis, encouraging researchers to embrace the quirks and quips of internet culture in understanding market dynamics.

ChatGPT:

"cat memes," "Simon Property Group stock," "Google Trends data," "LSEG Analytics," "stock market correlation," "internet culture and finance," "financial market analysis," "stock price sensitivity," "market behavior," "playful stock analysis," "feline humor and stock performance," "market dynamics and internet memes," "financial data analysis," "correlation coefficient," "stock market whims," "quirks of internet culture," "research on internet memes and stock market"

*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'

Simon Property Group's stock price (SPG)
Detailed data title: Opening price of Simon Property Group (SPG) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: ^{See full details} Via Microsoft Excel Stockhistory function

See what else correlates with Simon Property Group's stock price (SPG)

Correlation r = 0.8979141 (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 = 0.8062497 (Coefficient of determination)
This means 80.6% of the change in the one variable (i.e., Simon Property Group's stock price (SPG)) 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 7.9E-8.^Show 0.0000000785484163382932700000
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 0.9 in 7.9E-6% of random cases. Said differently, if you correlated 12,731,001 random variables^Note You don't actually need 12 million 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.

[ 0.76, 0.96 ] 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
Simon Property Group's stock price (SPG) (Stock price)	41.64	58.9	68.95	91.16	78.08	47.91	75.68	94.22	123.36	150.61	143.28	183.15	192.31	179.09	172.34	166.35	149.41	85.66	160.48	118.13

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 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.

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([41.64,58.9,68.95,91.16,78.08,47.91,75.68,94.22,123.36,150.61,143.28,183.15,192.31,179.09,172.34,166.35,149.41,85.66,160.48,118.13,])
array_1_name = "Google searches for 'cat memes'"
array_2_name = "Simon Property Group's stock price (SPG)"

# 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 Simon Property Group's stock price (SPG)
AI-generated correlation image
The spurious research paper: Cognitive Correlations: Cat Memes and Simon Property Group's Stock Sensitivity

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 2276 · Black Variable ID: 1355 · Red Variable ID: 1758


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