Spurious correlation #4,065 · View random
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 Saige and the second variable is Capital One Financial's stock price (COF). The chart goes from 2002 to 2022, 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 Popularity of the first name Saige and the second variable is Capital One Financial's stock price (COF). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

AI explanation

The name Saige became so trendy that all the cool kids wanted to open their first bank account, leading to a surge in new customers for Capital One. The demand for those coveted Capital One credit cards with quirky commercials featuring celebrities skyrocketed, causing the company's stock price to follow suit. It's a Saige sensation that even financial analysts can't fully explain!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a picturesque park filled with vibrant greenery and sunlight, where a group of children named Saige are joyfully playing. The children are shown laughing and holding hands, exuding happiness and innocence. In the background, a majestic financial building featuring the Capital One logo is prominently displayed. The building's electronic display showcases a rising stock price chart, symbolizing the growing investment in sustainable companies linked to the name Saige and the heightened environmental awareness it represents. The scene is filled with a sense of optimism and progress. 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: Popularity of the first name Saige and Capital One Financial's stock price (COF). 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: Realistic a Polaroid photo Cybernetic art Low poly Cybernetic art
ChatGPT: Cybernetic art

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 Popularity of the first name Saige and Capital One Financial's stock price (COF), in the following situation: Because the first name Saige became popular, more parents named their children after the color green. This increased environmental awareness, boosting investment in sustainable companies like Capital One, lifting their stock price.. Keep the description simple.
ChatGPT: A group of children named Saige are seen playing in a lush green park, laughing and smiling while holding hands. In the background, a large financial building with the Capital One logo prominently displays a rising stock price chart on its electronic display, reflecting the increased investment in sustainable companies due to the growing popularity of the name Saige and the resulting heightened environmental awareness.

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: [ Cybernetic art ] and depicting this scene: A group of children named Saige are seen playing in a lush green park, laughing and smiling while holding hands. In the background, a large financial building with the Capital One logo prominently displays a rising stock price chart on its electronic display, reflecting the increased investment in sustainable companies due to the growing popularity of the name Saige and the resulting heightened environmental awareness. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a picturesque park filled with vibrant greenery and sunlight, where a group of children named Saige are joyfully playing. The children are shown laughing and holding hands, exuding happiness and innocence. In the background, a majestic financial building featuring the Capital One logo is prominently displayed. The building's electronic display showcases a rising stock price chart, symbolizing the growing investment in sustainable companies linked to the name Saige and the heightened environmental awareness it represents. The scene is filled with a sense of optimism and progress.

*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 Popularity of the first name Saige caused Capital One Financial's stock price (COF) to increase.

AI academic paper

(Because p < 0.01)

From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game

The Journal of Financial Frolics and Fascinations

Jan 2024

^{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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Popularity of the first name Saige and Capital One Financial's stock price (COF). Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
"From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game"

[[ABSTRACT]]
The relationship between the popularity of the first name Saige and the stock price of Capital One Financial (COF) may seem like an odd pairing fit for a slapstick comedy, but our rigorous research suggests otherwise. Leveraging data from the US Social Security Administration and LSEG Analytics (Refinitiv), we embarked on a quest to uncover the perplexing correlation. Much to our delight, we discovered a correlation coefficient of 0.8572127 with a robust p-value of less than 0.01 for the period spanning 2002 to 2022. Join us in this whimsical journey through the land of statistical analyses and stock market tomfoolery as we unravel the unexpected intertwining of a name's popularity and financial capital.

[[LITERATURE REVIEW]]
The connection between a first name and a stock price may seem like a tale spun from the land of whimsy and wonder, but as we dive into the annals of research, we find that truth can be stranger than fiction. Smith et al. (2010) initially uncovered an unsuspecting link between unusual first names and financial market movements. However, as we peel back the layers of this peculiar phenomenon, we begin to realize that there's more to this story than meets the eye.
Doe (2015) presents a compelling argument for the psychological impact of names on decision-making and consumer behavior, shedding light on the potential influence of a person's name on their financial choices. Jones (2018) chimes in with a study suggesting that individuals with unique names may exhibit different risk-taking behaviors in the realm of investment, sparking our curiosity about the broader implications for corporations and stock prices.
Turning to non-fiction works, "Freakonomics" by Steven D. Levitt and Stephen J. Dubner offers a delightful exploration of unexpected correlations in the realms of economics and societal trends, demonstrating that the world of empirical research can often be as unpredictable as a game of musical chairs on a rollercoaster.
In the realm of fiction, the fantastical worlds of "The Magic of Thinking Big" by David J. Schwartz and "Rich Dad Poor Dad" by Robert T. Kiyosaki beckon us to consider the enchanting interplay between individual beliefs and financial success, casting a spell over our research pursuits.
Moreover, our foray into the digital domain has unearthed intriguing social media musings that hint at a cosmic connection between the popularity of the name Saige and the fluctuations of COF's stock price. In a thought-provoking tweet, @FinanceFanatic pondered, "Could Saige's rise to fame spell magic for COF's gains? #NameGame #StocksAndStars." While humorously cryptic, such online ruminations have fueled our curiosity and prompted us to delve into this bizarre correlation with renewed vigor and a dash of skepticism.
As we immerse ourselves in the eclectic tapestry of literature, both academic and anecdotal, we can't help but smirk at the zany journey that lies ahead. So, buckle up as we navigate the labyrinthine landscape of empirical inquiry and financial folly, where the unexpected reigns supreme, and statistical rigor dances with the whimsy of life's strange and delightful connections.

[[RESULTS]]
The analysis of the relationship between the popularity of the first name Saige and the stock price of Capital One Financial (COF) yielded some truly eye-opening results, much like stumbling upon a treasure chest in the midst of a statistical desert.
First and foremost, the correlation coefficient between the two variables was found to be a staggering 0.8572127. This remarkable value suggests a strong positive relationship that could make even the most seasoned statistician raise an eyebrow in surprise. It's as if the fates of the name Saige and COF's stock price were intertwined in a financial ballet that would put Swan Lake to shame.
Furthermore, the coefficient of determination (r-squared) clocked in at 0.7348136. This indicates that approximately 73.48% of the variability in COF's stock price can be explained by the popularity of the name Saige. That's no trivial amount of influence; it's as if the name Saige is the magician behind the stock price's mesmerizing performance, pulling financial rabbits out of a statistical hat.
As if these results weren't remarkable enough, the p-value for this correlation was found to be less than 0.01. In plain terms, this means the likelihood of observing such a strong relationship between Saige's popularity and COF's stock price by pure chance is about as probable as finding a four-leaf clover in a field of financial data.
To visually encapsulate the magnitude of this correlation, we have included a scatterplot (Fig. 1) that showcases the tight connection between the two variables. The plot resembles the perfect choreography between statistical data points and financial fluctuations, painting a picture so captivating it could rival a Renaissance masterpiece.
In sum, the results of our analysis reveal a compelling and statistically significant relationship between the popularity of the first name Saige and the stock price of Capital One Financial. It's a revelation that adds a touch of whimsy to the typically serious world of financial analysis, reminding us that in the realm of data, even the most unexpected connections can hold surprising insights.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

In the illustrious words of William Shakespeare, "What's in a name?" Well, it turns out, quite a bit, especially when it comes to the captivating correlation between the popularity of the first name Saige and Capital One Financial's (COF) stock price. Our findings not only support the existing research but also sprinkle a dash of statistical stardust onto the enchanting saga of names and numbers.

As we dust off the whimsical musings from our literature review, the study by Smith et al. (2010) takes on a newfound gravity as our results align with their discovery of unexpected linkages between unconventional names and financial market movements. It seems that the financial fates of COF are indeed intertwined with the ebb and flow of Saige's popularity, creating a riveting narrative that even J.K. Rowling would envy.

Furthermore, the psychological insights presented by Doe (2015) gain newfound weight as we observe the substantial influence of a name on financial choices, akin to a bard weaving stories of old. It appears that the name Saige wields a magical wand over the stock market, compelling investors to dance to a tune as enchanting as the Pied Piper's melody.

In a delightfully non-fiction turn of events, "Freakonomics" by Steven D. Levitt and Stephen J. Dubner proves prescient as we immerse ourselves in the unexpected correlation between a name and a financial entity. Our findings stand as a testament to the capricious nature of empirical research, where the line between mundane mundanity and magical realism blurs in a whirlwind of statistical significance.

Taking a cue from the world of Twitter, @FinanceFanatic's astute ponderings about Saige and COF now appear less whimsical and more prophetic. As our results align with these digitally whispered prophecies, it's as though the cosmos conspired to nudge us down this peculiar path of financial exploration, much like a celestial game of connect-the-dots played with stock tickers and baby names.

In essence, our results not only affirm the existing literature but also sprinkle a generous helping of delightfully unexpected insights into the enchanting nexus of names and stock prices. It's as if financial analysis donned a cloak of merriment, inviting us to pirouette through the historically serious corridors of economic inquiry with all the grace of a ballerina in a bull market.

In the words of Coco Chanel, "The most courageous act is still to think for yourself. Aloud," and with our findings, we have indeed dared to think aloud, unraveling a tale that stands as a testament to the delightful and sometimes confounding intricacies of the nexus between names and financial performances.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
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 short conclusion of an academic research paper presenting the findings of the connection between Popularity of the first name Saige and Capital One Financial's stock price (COF). Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game"

[[ABSTRACT]]
The relationship between the popularity of the first name Saige and the stock price of Capital One Financial (COF) may seem like an odd pairing fit for a slapstick comedy, but our rigorous research suggests otherwise. Leveraging data from the US Social Security Administration and LSEG Analytics (Refinitiv), we embarked on a quest to uncover the perplexing correlation. Much to our delight, we discovered a correlation coefficient of 0.8572127 with a robust p-value of less than 0.01 for the period spanning 2002 to 2022. Join us in this whimsical journey through the land of statistical analyses and stock market tomfoolery as we unravel the unexpected intertwining of a name's popularity and financial capital.

[[INTRDUCTION]]
INTRODUCTION
In the world of academic research, one often stumbles upon correlations that are about as likely as finding a unicorn prancing through Wall Street. And yet, here we are, delving into the perplexing association between the popularity of the first name Saige and the stock price of Capital One Financial (COF). It's a pairing that's as unexpected as finding a penguin chilling in the Sahara desert.
As researchers, we often tiptoe through the tulips of data, hoping to unearth meaningful connections. Little did we know that our journey would take us on a raucous adventure filled with statistical acrobatics and financial frolics. But fear not, for we are armed with the tools of econometric analysis and an unwavering sense of humor, ready to navigate the wild terrain of name popularity and stock prices.
While some might dub our pursuit as a whimsical escapade, we take our research seriously (well, most of the time). With the aid of data from the US Social Security Administration and LSEG Analytics (Refinitiv), we ventured into uncharted territory to unravel the unique relationship between a name and financial capital.
So, fasten your seatbelts as we embark on this merry journey through the labyrinth of correlation coefficients, p-values, and perhaps a sprinkle of financial enchantment. It's time to unravel the surprising saga of COF's price with a dash of name game, where statistical rigor meets the delightful absurdity of life's quirky connections.

[[RESULTS]]
The analysis of the relationship between the popularity of the first name Saige and the stock price of Capital One Financial (COF) yielded some truly eye-opening results, much like stumbling upon a treasure chest in the midst of a statistical desert.
First and foremost, the correlation coefficient between the two variables was found to be a staggering 0.8572127. This remarkable value suggests a strong positive relationship that could make even the most seasoned statistician raise an eyebrow in surprise. It's as if the fates of the name Saige and COF's stock price were intertwined in a financial ballet that would put Swan Lake to shame.
Furthermore, the coefficient of determination (r-squared) clocked in at 0.7348136. This indicates that approximately 73.48% of the variability in COF's stock price can be explained by the popularity of the name Saige. That's no trivial amount of influence; it's as if the name Saige is the magician behind the stock price's mesmerizing performance, pulling financial rabbits out of a statistical hat.
As if these results weren't remarkable enough, the p-value for this correlation was found to be less than 0.01. In plain terms, this means the likelihood of observing such a strong relationship between Saige's popularity and COF's stock price by pure chance is about as probable as finding a four-leaf clover in a field of financial data.
To visually encapsulate the magnitude of this correlation, we have included a scatterplot (Fig. 1) that showcases the tight connection between the two variables. The plot resembles the perfect choreography between statistical data points and financial fluctuations, painting a picture so captivating it could rival a Renaissance masterpiece.
In sum, the results of our analysis reveal a compelling and statistically significant relationship between the popularity of the first name Saige and the stock price of Capital One Financial. It's a revelation that adds a touch of whimsy to the typically serious world of financial analysis, reminding us that in the realm of data, even the most unexpected connections can hold surprising insights.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our findings have unveiled a correlation between the popularity of the first name Saige and the stock price of Capital One Financial (COF) that's as strong as the lure of a freshly brewed cup of coffee on a Monday morning. The striking correlation coefficient of 0.8572127 and the robust p-value of less than 0.01 stand as empirical evidence of the unexpected tango between a name and financial capital.

The correlation revealed is a delightful revelation that tickles the fancy of financial analysts and name enthusiasts alike. It's as if the name Saige whispers secret financial wisdom to the stock market, prompting COF's price to pirouette in rhythm to its popularity. While some may view this correlation as a statistical oddity, it serves as a reminder that in the world of data, even the quirkiest connections can hold meaningful insights.

This research sheds light on the whimsical aspects of statistical analysis, where data paints a canvas of unexpected surprises, much like stumbling upon a hidden treasure in a field of numerical values. Our findings not only emphasize the robustness of statistical analyses but also add a touch of enchantment to the typically serious landscape of stock market research.

In light of these revelatory findings, it's safe to say that the saga of COF's price intertwined with the name game of Saige has enchanted us all. It's a tale that leaves us with a sense of wonder and a reminder that in the quest for knowledge, one must always be open to the delightful absurdity of life's unexpected connections.

Given the compelling nature of our results, we boldly assert that further research into the captivating correlation between the popularity of the first name Saige and the stock price of COF is not only unnecessary but dare we say, it's like carrying an umbrella on a day with no rain - utterly redundant. With that said, let us bid ado to this whimsical research journey and embrace the delightful mysteries that await in the realms of statistical analysis.

No further research needed in this name-game-stock-price saga.

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 From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Financial Frolics and Fascinations

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 From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Gnomish Economic Research and 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 From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game with an abstract of The relationship between the popularity of the first name Saige and the stock price of Capital One Financial (COF) may seem like an odd pairing fit for a slapstick comedy, but our rigorous research suggests otherwise. Leveraging data from the US Social Security Administration and LSEG Analytics (Refinitiv), we embarked on a quest to uncover the perplexing correlation. Much to our delight, we discovered a correlation coefficient of 0.8572127 with a robust p-value of less than 0.01 for the period spanning 2002 to 2022. Join us in this whimsical journey through the land of statistical analyses and stock market tomfoolery as we unravel the unexpected intertwining of a name's popularity and financial capital.

ChatGPT:

Saige, stock price, Capital One Financial, COF, correlation, popularity, first name, Social Security Administration, LSEG Analytics, Refinitiv, correlation coefficient, statistical analysis, stock market, name popularity, financial capital, 2002-2022

*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

Popularity of the first name Saige
Detailed data title: Babies of all sexes born in the US named Saige
Source: US Social Security Administration
See what else correlates with Popularity of the first name Saige

Capital One Financial's stock price (COF)
Detailed data title: Opening price of Capital One Financial (COF) 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 Capital One Financial's stock price (COF)

Correlation r = 0.8572127 (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 = 0.7348136 (Coefficient of determination)
This means 73.5% of the change in the one variable (i.e., Capital One Financial's stock price (COF)) is predictable based on the change in the other (i.e., Popularity of the first name Saige) over the 21 years from 2002 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.9E-7.^Show 0.0000006923165410831364000000
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 0.86 in 6.9E-5% of random cases. Said differently, if you correlated 1,444,426 random variables^Note You don't actually need 1 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 20 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 20 because we have two variables measured over a period of 21 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.

[ 0.68, 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.

	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Popularity of the first name Saige (Babies born)	274	279	383	393	375	374	374	363	325	290	288	465	501	418	518	510	497	481	528	672	848
Capital One Financial's stock price (COF) (Stock price)	54.15	30.2	61.33	84.05	86.4	77.07	47.76	31.8	38.66	43.01	43.39	59.53	76.61	82.79	70.77	88.55	100.08	74.49	103.41	99.73	146.08

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([274,279,383,393,375,374,374,363,325,290,288,465,501,418,518,510,497,481,528,672,848,])
array_2 = np.array([54.15,30.2,61.33,84.05,86.4,77.07,47.76,31.8,38.66,43.01,43.39,59.53,76.61,82.79,70.77,88.55,100.08,74.49,103.41,99.73,146.08,])
array_1_name = "Popularity of the first name Saige"
array_2_name = "Capital One Financial's stock price (COF)"

# 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 Popularity of the first name Saige
Line chart for only Capital One Financial's stock price (COF)
AI-generated correlation image
The spurious research paper: From Saige to Stocks: The Surprising Saga of COF's Price with a Dash of Name Game

View another random correlation

How fun was this correlation?

Your rating is much appreciated!

Correlation ID: 4065 · Black Variable ID: 4073 · Red Variable ID: 1785


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