Spurious correlation #2,954 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Number of Grand Slam Finals played by Roger Federer and the second variable is The number of chefs and head cooks in Alaska. The chart goes from 2003 to 2015, 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 Number of Grand Slam Finals played by Roger Federer and the second variable is The number of chefs and head cooks in Alaska. The chart goes from 2003 to 2015, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Roger Federer sizzled on the court, more people in Alaska got fired up about cooking, leading to a rise in the number of chefs and head cooks. It seems like his backhand wasn’t the only thing heating up - he must have been serving some serious inspiration for culinary greatness!

^{Show image generation prompt} Model: dalle-3
Prompt: Style: [ a Polaroid photo ] Scene: A bustling kitchen in Alaska where chefs and head cooks are meticulously crafting their culinary masterpieces, with a large screen proudly displaying the number "31" to symbolize Roger Federer's 31 Grand Slam Finals. Enhanced prompt: Generate an image capturing a bustling kitchen in Alaska, blending the elegance of cooking with the precision of tennis. Imagine a group of chefs and head cooks immersed in their craft, each carefully perfecting their culinary creations. Amidst the organized chaos, a vintage Polaroid photo depicts the scene, evoking a sense of nostalgia and artistry. The kitchen exudes an atmosphere of passion and dedication, with the large screen in the corner proudly displaying the number "31," in homage to the 31 Grand Slam Finals played by Roger Federer. The chefs draw inspiration from Federer's legendary backhand, infusing their dishes with finesse and skill reminiscent of the tennis icon's graceful precision. 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: Number of Grand Slam Finals played by Roger Federer and The number of chefs and head cooks in Alaska. 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: Art nouveau An image that looks like it is a scene from 'Star Wars' Concept art a funny image you would see on reddit a Polaroid photo
ChatGPT: a Polaroid photo

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 Number of Grand Slam Finals played by Roger Federer and The number of chefs and head cooks in Alaska, in the following situation: Because as Roger Federer played in more Grand Slam Finals, more people became inspired by his elegance and precision, leading to an increase in Alaskan chefs who sought to create culinary masterpieces as exquisite as his backhand.. Keep the description simple.
ChatGPT: Imagine a bustling kitchen in Alaska, where a group of chefs and head cooks are gathered, each meticulously crafting their own culinary masterpieces. Amidst the busy scene, a large screen in the corner of the kitchen proudly displays the number "31," symbolizing the impressive 31 Grand Slam Finals that Roger Federer has played. The chefs, inspired by Federer's elegance and precision on the tennis court, are fervently honing their own skills to create dishes as refined and skillful as Federer's legendary backhand.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a Polaroid photo ] and depicting this scene: Imagine a bustling kitchen in Alaska, where a group of chefs and head cooks are gathered, each meticulously crafting their own culinary masterpieces. Amidst the busy scene, a large screen in the corner of the kitchen proudly displays the number "31," symbolizing the impressive 31 Grand Slam Finals that Roger Federer has played. The chefs, inspired by Federer's elegance and precision on the tennis court, are fervently honing their own skills to create dishes as refined and skillful as Federer's legendary backhand. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Style: [ a Polaroid photo ] Scene: A bustling kitchen in Alaska where chefs and head cooks are meticulously crafting their culinary masterpieces, with a large screen proudly displaying the number "31" to symbolize Roger Federer's 31 Grand Slam Finals. Enhanced prompt: Generate an image capturing a bustling kitchen in Alaska, blending the elegance of cooking with the precision of tennis. Imagine a group of chefs and head cooks immersed in their craft, each carefully perfecting their culinary creations. Amidst the organized chaos, a vintage Polaroid photo depicts the scene, evoking a sense of nostalgia and artistry. The kitchen exudes an atmosphere of passion and dedication, with the large screen in the corner proudly displaying the number "31," in homage to the 31 Grand Slam Finals played by Roger Federer. The chefs draw inspiration from Federer's legendary backhand, infusing their dishes with finesse and skill reminiscent of the tennis icon's graceful precision.

*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 Number of Grand Slam Finals played by Roger Federer caused The number of chefs and head cooks in Alaska to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene

Journal of Sports Science and Gastronomy

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 Number of Grand Slam Finals played by Roger Federer and The number of chefs and head cooks in Alaska. 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]]
Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene

[[ABSTRACT]]
This study delves into the seemingly unrelated worlds of professional tennis and culinary arts to investigate the surprising correlation between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska. Utilizing data from Wikipedia and the Bureau of Labor Statistics, the research team explored this quirky relationship from 2003 to 2015. Our findings revealed a remarkably high correlation coefficient of 0.8976402, with a statistically significant p-value of less than 0.01.

The results suggest that as the number of Grand Slam finals played by Roger Federer increased, so did the employment of chefs and head cooks in Alaska. This unexpected correlation challenges conventional wisdom and prompts further investigation into the potential impact of tennis prowess on the culinary industry. In the words of a tennis-loving chef, "It appears that Federer's success on the court is a recipe for success in Alaska's kitchens as well!"

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The pursuit of knowledge often leads researchers down unexpected pathways, and the exploration of the relationship between the career achievements of a legendary tennis player and the culinary landscape of a northern state proves to be no exception. As the tennis aficionados and food enthusiasts alike may jest, “What does Roger Federer have to do with Alaskan chefs? It’s not a match made in heaven, but it's certainly an ace in the kitchen!”
In this paper, we examine the curious connection between the number of Grand Slam finals played by the Swiss tennis maestro, Roger Federer, and the employment trends of chefs and head cooks in the frosty terrain of Alaska. One might say, this investigation serves up a volley of surprises and perhaps a dash of culinary humor.
The serendipitous discovery of this correlation prompted the inquiry into whether there could be any plausible explanation or logical rationale for such a connection. It’s an unusual pairing, indeed, but as they say, “There’s no such thing as a free lunch, but perhaps there's a Grand Slam special!”

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation of the relationship between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska has elicited the interest of researchers across various disciplines. Smith (2010) examined the impact of professional tennis players' career achievements on unrelated industries, highlighting unforeseen correlations between individual sporting successes and non-sporting occupations.

In "Doe's Culinary Chronicles," the authors find that the culinary world is a melting pot of influences, where unexpected connections can simmer and stew until they reach a boiling point, much like a pot of chowder on a cold Alaskan evening.

Jones (2015) conducted a comprehensive review of employment trends in the state of Alaska, focusing on the culinary sector and its workforce dynamics. The study shed light on the intricate web of factors influencing the employment of chefs and head cooks in the region, paving the way for further investigations into potentially unforeseen determinants.

As the inquiry ventured beyond the conventional bounds of sports and culinary studies, it led to an unexpected intersection with non-fiction works such as "The Art of Professional Tennis: Strategies for Success" and "Alaska's Gastronomic Evolution." These diverse sources echoed the possibility of obscure links between seemingly disparate domains, hinting at the tantalizing prospects of unearthing hidden connections lurking in the depths of statistical databases and culinary archives.

Adding an element of whimsy to the scholarly discourse, fictional literature also manifested in the form of "The Tennis Chef's Cookbook: A Match Made in Culinary Heaven" and "The Alaskan Almanac of Odd Pairings." While these titles may seem fanciful, they serve as a whimsical reminder that the boundaries of exploration in interdisciplinary research are often far more elastic than initially presumed.

A social media post by a tennis enthusiast and amateur chef offered a lighthearted perspective on the matter, humorously quipping, "If Federer keeps serving aces on the court, maybe Alaskan chefs are getting inspired to serve up aces in the kitchen too! Don't let them double-fault your order, though."

Another tweet from an Alaskan culinary aficionado playfully underscored the potential influence of Grand Slam finals on the local gastronomic scene, stating, "Who would've thought that Federer's backhand could be the secret ingredient in Alaskan cuisine? It's a smashing revelation!"

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 Number of Grand Slam Finals played by Roger Federer and The number of chefs and head cooks in Alaska. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene

[[ABSTRACT]]
This study delves into the seemingly unrelated worlds of professional tennis and culinary arts to investigate the surprising correlation between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska. Utilizing data from Wikipedia and the Bureau of Labor Statistics, the research team explored this quirky relationship from 2003 to 2015. Our findings revealed a remarkably high correlation coefficient of 0.8976402, with a statistically significant p-value of less than 0.01.

The results suggest that as the number of Grand Slam finals played by Roger Federer increased, so did the employment of chefs and head cooks in Alaska. This unexpected correlation challenges conventional wisdom and prompts further investigation into the potential impact of tennis prowess on the culinary industry. In the words of a tennis-loving chef, "It appears that Federer's success on the court is a recipe for success in Alaska's kitchens as well!"

[[LITERATURE REVIEW]]
The investigation of the relationship between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska has elicited the interest of researchers across various disciplines. Smith (2010) examined the impact of professional tennis players' career achievements on unrelated industries, highlighting unforeseen correlations between individual sporting successes and non-sporting occupations.
In "Doe's Culinary Chronicles," the authors find that the culinary world is a melting pot of influences, where unexpected connections can simmer and stew until they reach a boiling point, much like a pot of chowder on a cold Alaskan evening.
Jones (2015) conducted a comprehensive review of employment trends in the state of Alaska, focusing on the culinary sector and its workforce dynamics. The study shed light on the intricate web of factors influencing the employment of chefs and head cooks in the region, paving the way for further investigations into potentially unforeseen determinants.
As the inquiry ventured beyond the conventional bounds of sports and culinary studies, it led to an unexpected intersection with non-fiction works such as "The Art of Professional Tennis: Strategies for Success" and "Alaska's Gastronomic Evolution." These diverse sources echoed the possibility of obscure links between seemingly disparate domains, hinting at the tantalizing prospects of unearthing hidden connections lurking in the depths of statistical databases and culinary archives.
Adding an element of whimsy to the scholarly discourse, fictional literature also manifested in the form of "The Tennis Chef's Cookbook: A Match Made in Culinary Heaven" and "The Alaskan Almanac of Odd Pairings." While these titles may seem fanciful, they serve as a whimsical reminder that the boundaries of exploration in interdisciplinary research are often far more elastic than initially presumed.
A social media post by a tennis enthusiast and amateur chef offered a lighthearted perspective on the matter, humorously quipping, "If Federer keeps serving aces on the court, maybe Alaskan chefs are getting inspired to serve up aces in the kitchen too! Don't let them double-fault your order, though."
Another tweet from an Alaskan culinary aficionado playfully underscored the potential influence of Grand Slam finals on the local gastronomic scene, stating, "Who would've thought that Federer's backhand could be the secret ingredient in Alaskan cuisine? It's a smashing revelation!"

[[RESULTS]]
The analysis of the data from 2003 to 2015 revealed a strong positive correlation between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska, with a correlation coefficient of 0.8976402. This indicates a remarkably robust relationship between these seemingly unrelated variables, suggesting that as the number of Grand Slam finals played by Roger Federer increased, so did the employment of chefs and head cooks in Alaska.
The r-squared value of 0.8057580 indicates that approximately 80.6% of the variability in the employment of chefs and head cooks in Alaska can be explained by the number of Grand Slam finals played by Roger Federer. A noteworthy result, prompting one to ponder: "Are Roger's forehands and backhands secretly influencing the presentation of Alaskan cuisine?"
The p-value of less than 0.01 reflects a statistically significant relationship between these variables, further accentuating the unexpected nature of this correlation. It presents a conundrum worthy of a culinary mystery novel - "The Case of the Grand Slam Gourmand: Roger Federer and the Alaskan Culinary Conundrum."
The impact of these findings extends beyond the purely statistical realm, as they challenge conventional assumptions and inspire further investigation into the influence of elite athletic performance on the culinary industry. Perhaps we are witnessing the emergence of a new performance-enhancing cuisine!

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study have unveiled a robust and statistically significant correlation between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska. Our findings support and extend previous research that hinted at unexpected linkages between individual sporting achievements and seemingly unrelated occupational sectors.

Our study's strong correlation coefficient of 0.8976402 aligns with the work of Smith (2010), who identified unforeseen relationships between professional sporting accomplishments and non-sporting professions. This suggests that Federer's success on the tennis court indeed bears a peculiar and influential connection to the culinary domain in Alaska. Pardon the pun, but it seems that Federer's "serve" extends beyond the tennis court and influences the "serving" in Alaskan kitchens as well.

In addition, the literature review highlighted the diverse influences on the culinary world, as described in "Doe's Culinary Chronicles." This unforeseen correlation may be emblematic of the myriad influences simmering within the culinary industry, waiting to be uncovered by keen research. Indeed, our study's findings underscore the need for further exploration of the intricate web of influences shaping the employment of chefs and head cooks in Alaska.

The statistical significance of our results, as denoted by the p-value of less than 0.01, reinforces the validity of the observed correlation. This unexpected nexus between the prowess of a tennis champion and the employment trends in the culinary sector challenges preconceived notions and calls for wider contemplation. It seems we have stumbled upon a "deuce" of a discovery – the serve and the simmer, so to speak.

Our findings open new avenues for interdisciplinary research, motivating future inquiries into the potential impact of elite athletic achievement on gastronomic trends. This unexpected correlation adds a layer of complexity to the dynamics of employment in the culinary field and prompts further investigation into the subtle yet substantial influences at play. As one might jest, it appears that Federer's on-court finesse may have a "marinating" effect on the culinary landscape of Alaska.

In conclusion, our study not only reaffirms the unanticipated relationship between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska but also encourages scholars to delve into the captivating web of connections that intertwine disparate domains. This research undoubtedly prompts a reevaluation of the conventional boundaries and inspirations that underpin occupational dynamics, leaving us to ponder the remarkable synergy between a Swiss tennis virtuoso and Alaskan culinary artistry.

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 Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Sports Science and Gastronomy

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 Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Culinary and Sports Synergy

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 Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene with an abstract of This study delves into the seemingly unrelated worlds of professional tennis and culinary arts to investigate the surprising correlation between the number of Grand Slam finals played by Roger Federer and the employment of chefs and head cooks in Alaska. Utilizing data from Wikipedia and the Bureau of Labor Statistics, the research team explored this quirky relationship from 2003 to 2015. Our findings revealed a remarkably high correlation coefficient of 0.8976402, with a statistically significant p-value of less than 0.01.
The results suggest that as the number of Grand Slam finals played by Roger Federer increased, so did the employment of chefs and head cooks in Alaska. This unexpected correlation challenges conventional wisdom and prompts further investigation into the potential impact of tennis prowess on the culinary industry. In the words of a tennis-loving chef, "It appears that Federer's success on the court is a recipe for success in Alaska's kitchens as well!

ChatGPT:

Roger Federer, Alaska, culinary arts, professional tennis, Grand Slam finals, employment, chefs, head cooks, correlation coefficient, statistical significance, Bureau of Labor Statistics, Wikipedia, tennis impact on culinary industry

*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

Number of Grand Slam Finals played by Roger Federer
Source: Wikipedia
See what else correlates with Number of Grand Slam Finals played by Roger Federer

The number of chefs and head cooks in Alaska
Detailed data title: BLS estimate of chefs and head cooks in Alaska
Source: Bureau of Larbor Statistics
See what else correlates with The number of chefs and head cooks in Alaska

Correlation r = 0.8976402 (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 = 0.8057580 (Coefficient of determination)
This means 80.6% of the change in the one variable (i.e., The number of chefs and head cooks in Alaska) is predictable based on the change in the other (i.e., Number of Grand Slam Finals played by Roger Federer) over the 13 years from 2003 through 2015.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.1E-5.^Show 0.0000313626562918372800000000
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 0.0031% of random cases. Said differently, if you correlated 31,885 random variables^Note You don't actually need 31 thousand variables to find a correlation like this one. 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.

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 12 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 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.

[ 0.69, 0.97 ] 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.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015
Number of Grand Slam Finals played by Roger Federer (Finals)	1	3	2	4	4	3	4	1	1	1	0	1	2
The number of chefs and head cooks in Alaska (Chefs And Head Cooks)	340	520	450	520	590	610	600	360	300	180	260	350	470

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([1,3,2,4,4,3,4,1,1,1,0,1,2,])
array_2 = np.array([340,520,450,520,590,610,600,360,300,180,260,350,470,])
array_1_name = "Number of Grand Slam Finals played by Roger Federer"
array_2_name = "The number of chefs and head cooks in Alaska"

# 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 Number of Grand Slam Finals played by Roger Federer
Line chart for only The number of chefs and head cooks in Alaska
AI-generated correlation image
The spurious research paper: Serving Up the Stats: A Grand Slam Connection Between Roger Federer and Alaska's Culinary Scene

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 2954 · Black Variable ID: 136 · Red Variable ID: 4766


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