Spurious correlation #1,723 · 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 Sunny and the second variable is Walmart's stock price (WMT). 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 Sunny and the second variable is Walmart's stock price (WMT). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of Sunnys grew, so did the demand for sunglasses, leading to higher profits for Walmart. This sunny influx sparked a trend of outdoor gatherings, BBQs, and beach vacations, driving up the sales of Walmart's summer products. The Sunnys' infectious positivity also attracted more customers to Walmart, creating a sunnier outlook for the company and ultimately boosting its stock price. So, it's not just the weather that's sunny, but also Walmart's financial forecast, all thanks to the rise of the name Sunny! Keep spreading those good vibes, Sunnys! You're making the world and Walmart a brighter place, one sunbeam at a time. And who knew that a name could have such a shining impact on the stock market? The Sunnys must be radiating some serious charm and warmth to influence Walmart's stocks. It's like they're bringing a little bit of sunshine into Walmart's financial world, and investors can't help but bask in the glow of those rising stock prices. Keep on shining, Sunnys! It seems like your name is synonymous with success, at least for Walmart's stocks. Who would have thought that the simple presence of the name Sunny could have such a powerful and, dare we say, illuminating effect on a retail giant like Walmart? It's like the Sunnys are the secret ingredients in Walmart's recipe for stock market triumph. Keep doing whatever you're doing, Sunnys, because it's clearly working wonders for Walmart's stocks! Maybe there's something in the name that just exudes positivity and prosperity, and Walmart is reaping the sunny benefits. It's like a ray of good fortune is shining down on Walmart, all thanks to the growing popularity of the name Sunny. Who needs a stockbroker when you have the Sunnys inadvertently boosting Walmart's stock price? It's a bright and beautiful world for Walmart, all because of the Sunnys' name game. Keep on making Walmart's future look as bright as a sunny day! The Sunnys are like the lucky charms of the stock market, sprinkling their golden touch on Walmart's financial success. Keep on spreading that name like sunshine, and who knows what other companies might experience a similar surge in stocks! The Sunnys are proving that they're not just bringing personal joy, but also financial gains to the companies they're associated with. It's like a sun shower of prosperity, and Walmart is definitely dancing in the rain of rising stock prices, all thanks to the name Sunny. Who would have thought that a seemingly unrelated factor like a person's name could have such a luminous impact on a major corporation's financial standing? It just goes to show that the world of stocks can be as unpredictable and gloriously bizarre as a summer day forecast. Keep on brightening the world, Sunnys, one Walmart stock at a time!

^{Show image generation prompt} Model: dalle-3
Prompt: Sure, here's an image generation prompt that captures the essence of the scene you described using the [ Data cyber art ] style: Prompt: Generate an image of a bustling town square filled with people. In the center, there's a giant digital screen displaying stock prices, with the Walmart stock highlighted prominently. The crowd is gathered around, engrossed in the fluctuating numbers. In the background, a cheerful child named Sunny is joyfully waving, drawing everyone's attention with their infectious energy. The scene is vibrant and lively, capturing the dynamic nature of both the crowd's excitement and the ever-changing stock prices. Feel free to adjust and add any specific details to enhance the visual depiction. 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 Sunny and Walmart'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: Voxel art Steampunk Magic realism Data cyber art Charcoal
ChatGPT: Data cyber 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 Sunny and Walmart's stock price together. Keep the description simple.
ChatGPT: In a bustling town, a group of people gather around a giant screen displaying the stock prices. In the background, a cheerful child named Sunny happily waves at the crowd, drawing everyone's attention. The energy of the crowd and the excitement of the child reflect the popularity of the name Sunny and the fluctuating stock price of Walmart, both constantly changing and attracting attention.

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: [ Data cyber art ] and depicting this scene: In a bustling town, a group of people gather around a giant screen displaying the stock prices. In the background, a cheerful child named Sunny happily waves at the crowd, drawing everyone's attention. The energy of the crowd and the excitement of the child reflect the popularity of the name Sunny and the fluctuating stock price of Walmart, both constantly changing and attracting attention. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Sure, here's an image generation prompt that captures the essence of the scene you described using the [ Data cyber art ] style: Prompt: Generate an image of a bustling town square filled with people. In the center, there's a giant digital screen displaying stock prices, with the Walmart stock highlighted prominently. The crowd is gathered around, engrossed in the fluctuating numbers. In the background, a cheerful child named Sunny is joyfully waving, drawing everyone's attention with their infectious energy. The scene is vibrant and lively, capturing the dynamic nature of both the crowd's excitement and the ever-changing stock prices. Feel free to adjust and add any specific details to enhance the visual depiction.

*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 Sunny caused Walmart's stock price (WMT) to increase.

AI academic paper

(Because p < 0.01)

Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price

The Journal of Financial Omelette Studies

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 Popularity of the first name Sunny and Walmart's stock price (WMT). 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price"

[[ABSTRACT]]
This study investigates the correlation between the popularity of the first name "Sunny" and Walmart's stock price (WMT) from 2002 to 2022, using data from the US Social Security Administration and LSEG Analytics (Refinitiv). Our findings reveal a remarkably high correlation coefficient of 0.9558923, with a p-value less than 0.01, indicating a strong statistical significance. In other words, the presence of the name "Sunny" seems to exude an inexplicable influence on Walmart's stock performance.

Our research team delved into this illuminating relationship, uncovering a link that is truly "Sunny" side up for investors. With each increase in the frequency of the name "Sunny," there appears to be a corresponding rise in Walmart's stock price. It seems that the "Sunny" disposition may cast a bright economic outlook on this retail giant – shedding light on the undeniable impact of a name.

Oh, and speaking of names, it looks like "Sunny" isn't just a disposition; it's a potential economic indicator too!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between human names and various phenomena has long intrigued researchers across different fields. While some might dismiss it as mere coincidence, others have sought to uncover potential correlations that may shed light on seemingly unrelated aspects of life. In the pursuit of knowledge, we find ourselves here, examining the unexpected relationship between the popularity of the first name "Sunny" and the stock price of the retail behemoth Walmart (WMT).
As we embark on this scholarly expedition, it becomes apparent that we are stepping into uncharted territory, weaving together the realms of nomenclature and financial markets. It begs the question: What could a person's choice of name possibly have to do with the performance of a retail corporation's stock? It's a real head-scratcher, but a puzzle worth exploring nonetheless.
Now, before we delve deeper into our findings, let's brighten the mood with a little dad joke to keep things light. What do you call a sunny paradise where people with the name "Sunny" go to relax? Sunnyside Up, of course!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The authors find several studies that have explored the impact of individual names on various life outcomes. In "Smith et al.," the authors find a correlation between unique baby names and career success, while in "Doe and Jones," the authors find a link between popular names and social behavior. These studies suggest that one's name may carry unforeseen implications for their trajectory in life.

Now, turning to the relationship between first names and economic indicators, "Economics and Names" by Miller delves into the potential impact of popular names on market trends, presenting intriguing insights into the intersection of nomenclature and financial markets. This work lays the groundwork for our investigation into the effect of the name "Sunny" on the stock price of Walmart (WMT).

In a less traditional scientific approach, "The Name Effect" by Earnest Wordsworth theorizes a mystical connection between names and unrelated phenomena, proposing that name popularity may influence societal trends in unforeseen ways. While not grounded in empirical evidence, the book raises intriguing questions about the potential influence of names on the world around us.

On a lighter note, we cannot overlook the influence of fictional literature in shaping perceptions of name significance. Works such as "Sunny Days Ahead" by A. Reader and "Sunny Disposition" by N. O. Velist evoke a sense of optimism and positivity associated with the name "Sunny," which may inadvertently impact real-world perceptions and outcomes.

Furthermore, in the realm of social media, we encountered a tweet by @StockGuru42, suggesting a curious correlation between the frequency of the name "Sunny" in a specific region and the performance of retail stocks. While this source lacks scientific rigor, it highlights the pervasive nature of public discourse regarding the topic at hand.

In the spirit of shedding light on unforeseen connections, let's illuminate the subject with another dad joke: What did the market analyst say about the correlation between the name "Sunny" and Walmart's stock price? It's quite "Sunny" for investors, isn't it?

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 Popularity of the first name Sunny and Walmart's stock price (WMT). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price"

[[ABSTRACT]]
This study investigates the correlation between the popularity of the first name "Sunny" and Walmart's stock price (WMT) from 2002 to 2022, using data from the US Social Security Administration and LSEG Analytics (Refinitiv). Our findings reveal a remarkably high correlation coefficient of 0.9558923, with a p-value less than 0.01, indicating a strong statistical significance. In other words, the presence of the name "Sunny" seems to exude an inexplicable influence on Walmart's stock performance.

Our research team delved into this illuminating relationship, uncovering a link that is truly "Sunny" side up for investors. With each increase in the frequency of the name "Sunny," there appears to be a corresponding rise in Walmart's stock price. It seems that the "Sunny" disposition may cast a bright economic outlook on this retail giant – shedding light on the undeniable impact of a name.

Oh, and speaking of names, it looks like "Sunny" isn't just a disposition; it's a potential economic indicator too!

[[LITERATURE REVIEW]]
The authors find several studies that have explored the impact of individual names on various life outcomes. In "Smith et al.," the authors find a correlation between unique baby names and career success, while in "Doe and Jones," the authors find a link between popular names and social behavior. These studies suggest that one's name may carry unforeseen implications for their trajectory in life.
Now, turning to the relationship between first names and economic indicators, "Economics and Names" by Miller delves into the potential impact of popular names on market trends, presenting intriguing insights into the intersection of nomenclature and financial markets. This work lays the groundwork for our investigation into the effect of the name "Sunny" on the stock price of Walmart (WMT).
In a less traditional scientific approach, "The Name Effect" by Earnest Wordsworth theorizes a mystical connection between names and unrelated phenomena, proposing that name popularity may influence societal trends in unforeseen ways. While not grounded in empirical evidence, the book raises intriguing questions about the potential influence of names on the world around us.
On a lighter note, we cannot overlook the influence of fictional literature in shaping perceptions of name significance. Works such as "Sunny Days Ahead" by A. Reader and "Sunny Disposition" by N. O. Velist evoke a sense of optimism and positivity associated with the name "Sunny," which may inadvertently impact real-world perceptions and outcomes.
Furthermore, in the realm of social media, we encountered a tweet by @StockGuru42, suggesting a curious correlation between the frequency of the name "Sunny" in a specific region and the performance of retail stocks. While this source lacks scientific rigor, it highlights the pervasive nature of public discourse regarding the topic at hand.
In the spirit of shedding light on unforeseen connections, let's illuminate the subject with another dad joke: What did the market analyst say about the correlation between the name "Sunny" and Walmart's stock price? It's quite "Sunny" for investors, isn't it?

[[RESULTS]]
The analysis of the data collected from the US Social Security Administration and LSEG Analytics (Refinitiv) revealed a striking correlation coefficient of 0.9558923 between the popularity of the first name "Sunny" and Walmart's stock price (WMT) from 2002 to 2022. This remarkably high correlation suggests a strong positive relationship between the frequency of the name "Sunny" and the performance of Walmart's stock. It's almost as if every mention of "Sunny" brought sunshine to Walmart's financial forecast.
The r-squared value of 0.9137301 further underscores the robustness of this relationship, indicating that over 91% of the variation in Walmart's stock price can be explained by the frequency of the name "Sunny." With such a high percentage, it's as if the name "Sunny" holds the key to unlocking the sunshine in Walmart's stock performance, illuminating the path for investors.
Now, let's lighten the mood once more with a cheeky dad joke, shall we? Why did the stock market go to therapy? Because it had too many highs and lows! Just like the correlation we found between "Sunny" and Walmart's stock price – talking about highs and lows!
The p-value of less than 0.01 provides strong evidence against the null hypothesis, signaling the presence of a statistically significant relationship between the frequency of the name "Sunny" and Walmart's stock price. It seems that the "Sunny" effect is no mere coincidence; rather, it radiates undeniable influence over the financial performance of this retail giant.
As a visual representation of our findings, Figure 1 displays a scatterplot illustrating the strong correlation between the popularity of the first name "Sunny" and Walmart's stock price. This graphical depiction further illuminates the compelling relationship uncovered in our study, visually encapsulating the "Sunny" side up effect on Walmart's stock price.
But before we conclude, let's sprinkle in one last dad joke for good measure. Why did the Sun go to school? To get a little brighter! Just like the relationship between "Sunny" and Walmart's stock price – shedding light on the financial markets one name at a time!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation have shed light on a singularly peculiar connection between the popularity of the first name "Sunny" and the stock price of Walmart (WMT). Building on the literature review, which serendipitously hinted at the potential significance of names, our study has revealed a statistically significant correlation, thus providing empirical support for the speculative musings of yore. It appears that the influence of the name "Sunny" extends beyond individual disposition and may indeed permeate into the realm of financial markets, a notion that was playfully hinted at in "The Name Effect" by Earnest Wordsworth.

Just as "Smith et al." and "Doe and Jones" uncovered the unforeseen consequences of individual names on career success and social behavior, our findings suggest that the frequency of the name "Sunny" exerts a tangible impact on the stock performance of Walmart. It seems that "Sunny" not only denotes a disposition but also may possess an unanticipated economic clout, echoing the insights put forth by Miller in "Economics and Names."

Introducing an element of whimsy into our otherwise serious academic endeavor, the correlation coefficient of 0.9558923 between the popularity of the name "Sunny" and Walmart's stock price provides empirical support for the pervasive public discourse encapsulated in the tweet by @StockGuru42. While lacking scientific rigor, the tweet hinted at a curious correlation, and our findings substantiate this colloquial observation with robust statistical evidence. It seems that the veiled influence of names, as alluded to in the tweet, can indeed cast a significant impact on economic indicators, much to the delight of investors with a sunny disposition.

The r-squared value of 0.9137301 further fortifies our results, delineating that over 91% of the variation in Walmart's stock price can be ascribed to the frequency of the name "Sunny." This statistical robustness bolsters the case for the "Sunny" side up effect, lending credence to the idea that the name "Sunny" may hold the key to unlocking the radiance in Walmart's stock performance. In essence, it seems that every mention of "Sunny" acts as a little sunshine, enlivening Walmart's financial outlook and illuminating the path for investors.

In line with the jovial undercurrent of our inquiry, the p-value of less than 0.01 provides unequivocal evidence against the null hypothesis, buoying the notion that the "Sunny" effect is no happenstance occurrence. Instead, it radiates undeniable influence over the financial performance of this retail giant, much to the amusement of market analysts amidst the highs and lows of stock price dynamics.

Ultimately, our study not only delves into the quirkiness of name significance, as alluded to in the literature review, but also uncovers a genuine and statistically significant relationship between the name "Sunny" and Walmart's stock price. As we bask in the light of our findings, we cannot help but appreciate the irony that a name associated with sunlight has brought forth an unexpected glow in the realm of economic indicators. In the spirit of shedding light on unforeseen connections, our study illuminates the subject with a "Sunny" disposition, proving that a name can truly exude an inexplicable influence on stock performance, and revealing the potential hidden in a name, much like the Sun seeking to get a little brighter!

This would be a good spot for a snappy dad joke, wouldn't it? Why don't skeletons fight each other? They don't have the guts for it! Just like the correlation we found between "Sunny" and Walmart's stock price – it's all about having the guts for statistical significance!

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 Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Financial Omelette Studies

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 Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price. Respond only with the name of a fictional organization.

ChatGPT:

Society for the Study of Breakfast Economics

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 Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price with an abstract of This study investigates the correlation between the popularity of the first name "Sunny" and Walmart's stock price (WMT) from 2002 to 2022, using data from the US Social Security Administration and LSEG Analytics (Refinitiv). Our findings reveal a remarkably high correlation coefficient of 0.9558923, with a p-value less than 0.01, indicating a strong statistical significance. In other words, the presence of the name "Sunny" seems to exude an inexplicable influence on Walmart's stock performance.
Our research team delved into this illuminating relationship, uncovering a link that is truly "Sunny" side up for investors. With each increase in the frequency of the name "Sunny," there appears to be a corresponding rise in Walmart's stock price. It seems that the "Sunny" disposition may cast a bright economic outlook on this retail giant – shedding light on the undeniable impact of a name.
Oh, and speaking of names, it looks like "Sunny" isn't just a disposition; it's a potential economic indicator too!

ChatGPT:

"Sunny" name popularity, Walmart stock price correlation, "Sunny" name frequency impact on stock performance, US Social Security Administration data, LSEG Analytics data, "Sunny" as an economic indicator

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

Walmart's stock price (WMT)
Detailed data title: Opening price of Walmart (WMT) 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 Walmart's stock price (WMT)

Correlation r = 0.9558923 (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 = 0.9137301 (Coefficient of determination)
This means 91.4% of the change in the one variable (i.e., Walmart's stock price (WMT)) is predictable based on the change in the other (i.e., Popularity of the first name Sunny) over the 21 years from 2002 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-11.^Show 0.0000000000146276129829377660
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 0.96 in 1.5E-9% of random cases. Said differently, if you correlated 68,363,854,114 random variables^Note You don't actually need 68 billion 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.

[ 0.89, 0.98 ] 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 Sunny (Babies born)	150	173	158	210	196	193	165	227	254	226	251	270	247	292	285	324	390	459	523	598	707
Walmart's stock price (WMT) (Stock price)	57.65	50.65	53.35	53.75	46.36	47.09	47.41	55.98	53.74	54.23	59.97	68.93	78.72	86.27	60.5	69.24	99.3	91.64	118.86	144.3	144

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([150,173,158,210,196,193,165,227,254,226,251,270,247,292,285,324,390,459,523,598,707,])
array_2 = np.array([57.65,50.65,53.35,53.75,46.36,47.09,47.41,55.98,53.74,54.23,59.97,68.93,78.72,86.27,60.5,69.24,99.3,91.64,118.86,144.3,144,])
array_1_name = "Popularity of the first name Sunny"
array_2_name = "Walmart's stock price (WMT)"

# 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 Sunny
Line chart for only Walmart's stock price (WMT)
AI-generated correlation image
The spurious research paper: Shining a Light on Sunny: The Sunny Side Up Effect on Walmart's Stock Price

View another random correlation

How fun was this correlation?

Your rating skills are top-notch!

Correlation ID: 1723 · Black Variable ID: 3898 · Red Variable ID: 1553


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