Spurious correlation #1,752 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Butter consumption and the second variable is Geothermal power generated in Germany. The chart goes from 2004 to 2021, 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 Butter consumption and the second variable is Geothermal power generated in Germany. The chart goes from 2004 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As butter consumption increased, people's manner of spreading it on toast created more friction. This led to a rise in toast-dropping incidents across Germany. The increased buttered-toast-dropping created a demand for new, innovative ways to harness this buttery energy. As a result, German engineers developed geothermal power technology that could be activated by the impact of falling toast, effectively turning buttered toast into a renewable energy source. Who knew that the path to a greener future was spread with butter?

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a quaint German town scene where a cozy café is surrounded by people enjoying buttery pastries. In the background, a modern geothermal power plant quietly hums, providing sustainable energy to the community. The style should be reminiscent of a painting, using delicate brushstrokes and soft colors to capture the charm of the town juxtaposed with the modern sustainability of the power plant. 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: Butter consumption and Geothermal power generated in Germany. 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: Symbolism Concept art 3D Pixar Style Parallax art Scalar art
ChatGPT: Scalar 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 Butter consumption and Geothermal power generated in Germany together. Keep the description simple.
ChatGPT: In a quaint German town, a group of people gather around a cozy café, enjoying delicious buttery pastries. In the background, a modern geothermal power plant hums quietly, providing sustainable energy to the community.

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: [ Scalar art ] and depicting this scene: In a quaint German town, a group of people gather around a cozy café, enjoying delicious buttery pastries. In the background, a modern geothermal power plant hums quietly, providing sustainable energy to the community. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a quaint German town scene where a cozy café is surrounded by people enjoying buttery pastries. In the background, a modern geothermal power plant quietly hums, providing sustainable energy to the community. The style should be reminiscent of a painting, using delicate brushstrokes and soft colors to capture the charm of the town juxtaposed with the modern sustainability of the power plant.

*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 Butter consumption caused Geothermal power generated in Germany to increase.

AI academic paper

(Because p < 0.01)

Butter Power: Unveiling the Margarine of Geothermal Energy

The Journal of Whimsical Energy 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 Butter consumption and Geothermal power generated in Germany. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Butter Power: Unveiling the Margarine of Geothermal Energy

[[ABSTRACT]]
This paper investigates the seemingly absurd yet surprisingly intriguing relationship between butter consumption and geothermal power generation in Germany. Utilizing data sourced from the USDA and the Energy Information Administration, we examined the correlation between these two seemingly unrelated factors from 2004 to 2021. The findings revealed a remarkably high correlation coefficient of 0.9278108, with a p-value of less than 0.01. This paper challenges conventional wisdom and delves into the buttery depths of geothermal power generation, offering a fresh perspective on renewable energy sources and dairy products.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between butter consumption and geothermal power generation in Germany may seem as bewildering as a cow doing calculus, but as the saying goes, "the proof of the pudding is in the eating." With data in hand and skepticism in mind, we set out to churn the creamy mysteries of this unlikely duo and shed some light on their potential interplay. While it may sound like a fondue of random variables, our statistical analysis has unearthed a correlation that is as strong as Gouda cheese.
The notion of butter and geothermal power being entwined might make one feel like they've stepped into a scientific version of Willy Wonka's chocolate factory – but instead of rivers of chocolate, we have streams of sizzling geothermal energy. This study aims to unveil the tangled web of factors at play and dig into the Earth's crust like a determined mole, all in the name of scientific exploration and perhaps a dash of whimsy.
As we embark on this research journey, it's essential to keep in mind that correlation does not imply causation – just as a spoonful of sugar does not cause the medicine to go down, despite the catchy tune. However, the strength of the correlation we have uncovered demands attention and ignites curiosity, much like a Eureka moment in the lab.
So, dear reader, prepare to be whisked away into the realms of dairy-driven energy and subterranean heat – it's a journey that promises to be as surprising as an unknown side effect in a clinical trial. Let's dive into the buttery depths and uncover the margarine of geothermal power – a blend of science, statistics, and a generous dollop of amusement.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Numerous studies have explored the intricacies of energy generation and consumption, shedding light on the complex factors at play. Smith et al. (2015) conducted a comprehensive analysis of renewable energy sources, including geothermal power, in Germany. Their findings emphasized the growing importance of sustainable energy production and the potential for further development in the geothermal sector. Similarly, Doe and Jones (2018) examined dietary patterns and food consumption trends in European countries, identifying Germany as a significant consumer of dairy products, including butter.

In "The Butter Battle Book" by Dr. Seuss, the authors find a whimsical portrayal of a rivalry between two groups, reminiscent of the unforeseen connection between butter consumption and geothermal power generation in Germany that we are investigating. The book offers a lighthearted perspective on conflict resolution, much like the unexpected unity we have uncovered between dairy products and renewable energy sources. On the non-fiction front, "The Omnivore's Dilemma" by Michael Pollan challenges readers to contemplate the complexities of food production and consumption, intertwining with our examination of the enigmatic relationship between butter and geothermal power.

Moving further into the realm of fiction, "A Tale of Two Cities" by Charles Dickens presents a narrative of two seemingly unrelated elements converging, echoing the surprising connection we have unearthed between butter and geothermal power. Additionally, J.K. Rowling's "Harry Potter and the Goblet of Fire" introduces the Triwizard Tournament, a competition where unexpected alliances and challenges arise, mirroring the unconventional correlations we have identified in our study.

On a lighter note, movies such as "Groundhog Day" and "The Grand Budapest Hotel" provide an intriguing lens through which to view our research topic. While these films may not directly explore butter consumption or geothermal power generation, their themes of repetition and unexpected occurrences resonate with the unpredictability of our findings. The interconnectedness of seemingly disparate elements is a central theme in these films, much like the curious relationship we have unveiled between butter and geothermal energy.

As we delve into the body of literature surrounding our research topic, it is evident that while the initial investigation may raise an eyebrow or two, the unexpected connections that emerge offer a delightful blend of scientific inquiry and whimsy.

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 Butter consumption and Geothermal power generated in Germany. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Butter Power: Unveiling the Margarine of Geothermal Energy

[[ABSTRACT]]
This paper investigates the seemingly absurd yet surprisingly intriguing relationship between butter consumption and geothermal power generation in Germany. Utilizing data sourced from the USDA and the Energy Information Administration, we examined the correlation between these two seemingly unrelated factors from 2004 to 2021. The findings revealed a remarkably high correlation coefficient of 0.9278108, with a p-value of less than 0.01. This paper challenges conventional wisdom and delves into the buttery depths of geothermal power generation, offering a fresh perspective on renewable energy sources and dairy products.

[[LITERATURE REVIEW]]
Numerous studies have explored the intricacies of energy generation and consumption, shedding light on the complex factors at play. Smith et al. (2015) conducted a comprehensive analysis of renewable energy sources, including geothermal power, in Germany. Their findings emphasized the growing importance of sustainable energy production and the potential for further development in the geothermal sector. Similarly, Doe and Jones (2018) examined dietary patterns and food consumption trends in European countries, identifying Germany as a significant consumer of dairy products, including butter.
In "The Butter Battle Book" by Dr. Seuss, the authors find a whimsical portrayal of a rivalry between two groups, reminiscent of the unforeseen connection between butter consumption and geothermal power generation in Germany that we are investigating. The book offers a lighthearted perspective on conflict resolution, much like the unexpected unity we have uncovered between dairy products and renewable energy sources. On the non-fiction front, "The Omnivore's Dilemma" by Michael Pollan challenges readers to contemplate the complexities of food production and consumption, intertwining with our examination of the enigmatic relationship between butter and geothermal power.
Moving further into the realm of fiction, "A Tale of Two Cities" by Charles Dickens presents a narrative of two seemingly unrelated elements converging, echoing the surprising connection we have unearthed between butter and geothermal power. Additionally, J.K. Rowling's "Harry Potter and the Goblet of Fire" introduces the Triwizard Tournament, a competition where unexpected alliances and challenges arise, mirroring the unconventional correlations we have identified in our study.
On a lighter note, movies such as "Groundhog Day" and "The Grand Budapest Hotel" provide an intriguing lens through which to view our research topic. While these films may not directly explore butter consumption or geothermal power generation, their themes of repetition and unexpected occurrences resonate with the unpredictability of our findings. The interconnectedness of seemingly disparate elements is a central theme in these films, much like the curious relationship we have unveiled between butter and geothermal energy.
As we delve into the body of literature surrounding our research topic, it is evident that while the initial investigation may raise an eyebrow or two, the unexpected connections that emerge offer a delightful blend of scientific inquiry and whimsy.

[[RESULTS]]
The results of our analysis revealed a striking correlation between butter consumption and geothermal power generation in Germany over the period of 2004 to 2021. The correlation coefficient of 0.9278108 suggests a relationship as strong as the gravitational pull between the Earth and the moon – but in this case, it's the attraction between dairy delicacies and underground heat.
We harnessed the power of statistics to uncover this unexpected connection, and the r-squared value of 0.8608329 indicates that a sizable portion of the variability in geothermal power generation can be explained by fluctuations in butter consumption. It's as if we stumbled upon a secret recipe for renewable energy that involves a pinch of butter and a dash of geological heat.
The p-value of less than 0.01 provides further support for the significance of this finding, rendering it as statistically robust as a titanium-coated hypothesis. This result is not one to be margarined – it's a bona fide revelation that tickles the scientific taste buds and challenges conventional notions of causality.
As promised, Figure 1 showcases the visual representation of this covariation between butter consumption and geothermal power generation. Behold the scatterplot that captures the dance of butter and geothermal power, an unlikely duet with all the charm of an unexpected harmony.
The strength of this correlation raises questions that are as intriguing as they are perplexing – much like a perplexing equation that somehow yields a delightful solution. It begs us to ponder: is there an undiscovered synergy between butter and geothermal energy, or are these findings the result of some statistical fluke that leaves us feeling as bewildered as a cat with a complex calculus problem?
In any case, the robustness of the correlation demands further investigation and contemplation, inviting researchers to immerse themselves in the creamy conundrum of butter power and its influence on geothermal energy. These results serve as a delicious catalyst for future inquiry, stirring the pot of scientific curiosity with a generous helping of wonder and whimsy.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study undoubtedly raise eyebrows, delight the scientific taste buds, and challenge conventional notions of causality. The robust correlation coefficient of 0.9278108, akin to a mesmerizing chemical reaction, provides compelling evidence for the unexpected link between butter consumption and geothermal power generation in Germany. Our results not only support the prior research on sustainable energy production and dietary patterns but also add a creamy layer of intrigue to the scientific landscape.

The whimsical literature review, which playfully explored the unexpected connections between butter and geothermal power in various fictional and non-fictional works, takes on a newfound seriousness in light of our empirical findings. The seemingly absurd crossover of buttery indulgence and subterranean heat emerges as a bona fide area of scientific inquiry, prompting further exploration into the tantalizing synergy between dairy products and renewable energy sources.

Much like a mishmash of ingredients coming together to form a delectable dish, the statistical robustness of our results beckons researchers to dig deeper into the mechanistic underpinnings of this captivating correlation. As beguiling as a magician's sleight of hand, the r-squared value of 0.8608329 underscores the substantial influence of butter consumption on geothermal power generation, tantalizing the scientific community with the promise of uncovering a hitherto unexplored pathway for sustainable energy production.

The p-value of less than 0.01, akin to a resounding applause for a groundbreaking discovery, solidifies the credibility of our findings and underscores the significance of this unexpected relationship. This enigmatic butter-power connection, much like a culinary mystery waiting to be unraveled, invites further scrutiny and speculation, urging scholars to engage in a delightful fusion of scientific rigor and intellectual whimsy.

In conclusion, the unanticipated unity between butter consumption and geothermal power generation in Germany stands as a savory testament to the serendipitous nature of scientific inquiry. As we ponder the implications of this dairy-infused revelation, we are reminded of the potential for unexpected discoveries to transmute the ordinary into the extraordinary – much like the transformative alchemy of a culinary conundrum yielding a novel recipe for renewable energy.

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 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 Butter consumption and Geothermal power generated in Germany. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
Butter Power: Unveiling the Margarine of Geothermal Energy

[[ABSTRACT]]
This paper investigates the seemingly absurd yet surprisingly intriguing relationship between butter consumption and geothermal power generation in Germany. Utilizing data sourced from the USDA and the Energy Information Administration, we examined the correlation between these two seemingly unrelated factors from 2004 to 2021. The findings revealed a remarkably high correlation coefficient of 0.9278108, with a p-value of less than 0.01. This paper challenges conventional wisdom and delves into the buttery depths of geothermal power generation, offering a fresh perspective on renewable energy sources and dairy products.

[[INTRDUCTION]]
The connection between butter consumption and geothermal power generation in Germany may seem as bewildering as a cow doing calculus, but as the saying goes, "the proof of the pudding is in the eating." With data in hand and skepticism in mind, we set out to churn the creamy mysteries of this unlikely duo and shed some light on their potential interplay. While it may sound like a fondue of random variables, our statistical analysis has unearthed a correlation that is as strong as Gouda cheese.
The notion of butter and geothermal power being entwined might make one feel like they've stepped into a scientific version of Willy Wonka's chocolate factory – but instead of rivers of chocolate, we have streams of sizzling geothermal energy. This study aims to unveil the tangled web of factors at play and dig into the Earth's crust like a determined mole, all in the name of scientific exploration and perhaps a dash of whimsy.
As we embark on this research journey, it's essential to keep in mind that correlation does not imply causation – just as a spoonful of sugar does not cause the medicine to go down, despite the catchy tune. However, the strength of the correlation we have uncovered demands attention and ignites curiosity, much like a Eureka moment in the lab.
So, dear reader, prepare to be whisked away into the realms of dairy-driven energy and subterranean heat – it's a journey that promises to be as surprising as an unknown side effect in a clinical trial. Let's dive into the buttery depths and uncover the margarine of geothermal power – a blend of science, statistics, and a generous dollop of amusement.

[[RESULTS]]
The results of our analysis revealed a striking correlation between butter consumption and geothermal power generation in Germany over the period of 2004 to 2021. The correlation coefficient of 0.9278108 suggests a relationship as strong as the gravitational pull between the Earth and the moon – but in this case, it's the attraction between dairy delicacies and underground heat.
We harnessed the power of statistics to uncover this unexpected connection, and the r-squared value of 0.8608329 indicates that a sizable portion of the variability in geothermal power generation can be explained by fluctuations in butter consumption. It's as if we stumbled upon a secret recipe for renewable energy that involves a pinch of butter and a dash of geological heat.
The p-value of less than 0.01 provides further support for the significance of this finding, rendering it as statistically robust as a titanium-coated hypothesis. This result is not one to be margarined – it's a bona fide revelation that tickles the scientific taste buds and challenges conventional notions of causality.
As promised, Figure 1 showcases the visual representation of this covariation between butter consumption and geothermal power generation. Behold the scatterplot that captures the dance of butter and geothermal power, an unlikely duet with all the charm of an unexpected harmony.
The strength of this correlation raises questions that are as intriguing as they are perplexing – much like a perplexing equation that somehow yields a delightful solution. It begs us to ponder: is there an undiscovered synergy between butter and geothermal energy, or are these findings the result of some statistical fluke that leaves us feeling as bewildered as a cat with a complex calculus problem?
In any case, the robustness of the correlation demands further investigation and contemplation, inviting researchers to immerse themselves in the creamy conundrum of butter power and its influence on geothermal energy. These results serve as a delicious catalyst for future inquiry, stirring the pot of scientific curiosity with a generous helping of wonder and whimsy.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has churned out some udderly fascinating findings regarding the curious connection between butter consumption and geothermal power generation in Germany. It seems that the creamy delight of butter and the sizzling allure of geothermal energy have more in common than meets the eye – a pairing as unexpected as a cow moonlighting as a volcanologist.

The robust correlation coefficient and p-value we uncovered are as strong as the aroma of sizzling butter in a hot pan, leaving little room to spread doubt about the statistical significance of this relationship. It's a revelation that's as surprising as finding a cheeseburger growing on a tree!

While our findings are quite the melting pot of intrigue, it's essential to remember that correlation does not imply causation, much like finding a statistically significant connection between the number of Nicolas Cage movies watched and the price of bananas. However, the strength of this correlation demands attention and raises questions as captivating as a physics problem that keeps a scientist up at night.

As we wrap up this study, we can confidently say that our results provide food for thought and spark a curiosity that's as infectious as a laughter in a crowded room. It's as clear as a Petri dish in a sterilized lab – the relationship between butter consumption and geothermal power generation warrants further investigation and contemplation.

Thus, we boldly proclaim that no more research is needed in this specific area. Let us butter wait and see what other deliciously puzzling correlations await our scientific palates. This study will go down in history as a creamy testament to the intriguing, albeit unlikely, interplay between dairy delights and subterranean heat.

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 Butter Power: Unveiling the Margarine of Geothermal Energy. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Whimsical Energy 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 Butter Power: Unveiling the Margarine of Geothermal Energy. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Alternative Energy Innovation and Exploration

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 Butter Power: Unveiling the Margarine of Geothermal Energy with an abstract of This paper investigates the seemingly absurd yet surprisingly intriguing relationship between butter consumption and geothermal power generation in Germany. Utilizing data sourced from the USDA and the Energy Information Administration, we examined the correlation between these two seemingly unrelated factors from 2004 to 2021. The findings revealed a remarkably high correlation coefficient of 0.9278108, with a p-value of less than 0.01. This paper challenges conventional wisdom and delves into the buttery depths of geothermal power generation, offering a fresh perspective on renewable energy sources and dairy products.

ChatGPT:

butter consumption, geothermal power generation, Germany, USDA data, Energy Information Administration, correlation coefficient, p-value, renewable energy sources, dairy products

*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

Butter consumption
Detailed data title: Per capita consumption of Butter in the US
Source: USDA
See what else correlates with Butter consumption

Geothermal power generated in Germany
Detailed data title: Total geothermal power generated in Germany in billion kWh
Source: Energy Information Administration
See what else correlates with Geothermal power generated in Germany

Correlation r = 0.9278108 (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 = 0.8608329 (Coefficient of determination)
This means 86.1% of the change in the one variable (i.e., Geothermal power generated in Germany) is predictable based on the change in the other (i.e., Butter consumption) over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.0E-8.^Show 0.0000000295193533573949220000
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 0.93 in 3.0E-6% of random cases. Said differently, if you correlated 33,876,081 random variables^Note You don't actually need 33 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 17 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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.

[ 0.81, 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Butter consumption (Pounds per person)	4.5	4.5	4.7	4.7	5	5	4.9	5.4	5.5	5.5	5.5	5.6	5.7	5.7	6	6.2	6.3	6.5
Geothermal power generated in Germany (Billion kWh)	0.0002	0.0002	0.0004	0.0004	0.018	0.019	0.02	0.018998	0.024999	0.069001	0.098	0.133	0.175	0.163	0.178	0.197	0.231	0.249

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([4.5,4.5,4.7,4.7,5,5,4.9,5.4,5.5,5.5,5.5,5.6,5.7,5.7,6,6.2,6.3,6.5,])
array_2 = np.array([0.0002,0.0002,0.0004,0.0004,0.018,0.019,0.02,0.018998,0.024999,0.069001,0.098,0.133,0.175,0.163,0.178,0.197,0.231,0.249,])
array_1_name = "Butter consumption"
array_2_name = "Geothermal power generated in Germany"

# 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 Butter consumption
Line chart for only Geothermal power generated in Germany
AI-generated correlation image
The spurious research paper: Butter Power: Unveiling the Margarine of Geothermal Energy

View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!

Correlation ID: 1752 · Black Variable ID: 557 · Red Variable ID: 23686


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