Spurious correlation #1,595 · 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 Fossil fuel use in Rwanda. The chart goes from 1990 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 Fossil fuel use in Rwanda. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As butter consumption in Rwanda increased, it led to a rise in the popularity of baking. With more people baking and indulging in delicious buttery treats, there was a greater demand for kitchen appliances like ovens. This surge in the purchase of ovens and electric mixers meant that there was a higher need for electricity, leading to an increase in the burning of fossil fuels to meet the newfound energy needs. In other words, it was a classic case of turning up the 'heata' in the kitchen leading to a 'butter' load on fossil fuel resources!

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image of a bustling bakery in Rwanda with a line of customers eagerly waiting for freshly baked goods. The air is filled with the aroma of buttery pastries and bread being pulled out of the ovens. In the background, depict a smoke-filled industrial setting — a power plant working overtime to meet the increasing demand for electricity, powered by fossil fuels. The scene should capture the simultaneous rise in butter consumption and fossil fuel use, as the country churns out delicious treats and burns through energy to keep up with demand. Use a visual style reminiscent of Brutalism to depict the stark contrast between the warmth of the bakery and the industrial landscape behind it. 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 Fossil fuel use in Rwanda. 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: 3D Pixar Style Cutsy graphics Cutsy graphics Symbolism Brutalism
ChatGPT: Brutalism

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 Fossil fuel use in Rwanda, in the following situation: As butter consumption in Rwanda increased, so did the demand for baked goods. This led to a boom in baking, which caused a rise in the use of ovens and electricity. But here's the twist - the electricity production required more fossil fuels to meet the buttery demand for baked goods. It was a slippery slope of buttery deliciousness leading to a greasy increase in fossil fuel use. It was like the whole country was churning and burning at the same time!. Keep the description simple.
ChatGPT: A bustling bakery in Rwanda with a line of customers eagerly waiting for freshly baked goods. The air is filled with the aroma of buttery pastries and bread being pulled out of the ovens. At the same time, in the background, smoke billows out of a power plant as it works overtime to meet the increasing demand for electricity, powered by fossil fuels. The scene captures the simultaneous rise in butter consumption and fossil fuel use, as the country churns out delicious treats and burns through energy to keep up with the demand.

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: [ Brutalism ] and depicting this scene: A bustling bakery in Rwanda with a line of customers eagerly waiting for freshly baked goods. The air is filled with the aroma of buttery pastries and bread being pulled out of the ovens. At the same time, in the background, smoke billows out of a power plant as it works overtime to meet the increasing demand for electricity, powered by fossil fuels. The scene captures the simultaneous rise in butter consumption and fossil fuel use, as the country churns out delicious treats and burns through energy to keep up with the demand. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a bustling bakery in Rwanda with a line of customers eagerly waiting for freshly baked goods. The air is filled with the aroma of buttery pastries and bread being pulled out of the ovens. In the background, depict a smoke-filled industrial setting — a power plant working overtime to meet the increasing demand for electricity, powered by fossil fuels. The scene should capture the simultaneous rise in butter consumption and fossil fuel use, as the country churns out delicious treats and burns through energy to keep up with demand. Use a visual style reminiscent of Brutalism to depict the stark contrast between the warmth of the bakery and the industrial landscape behind it.

*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 Fossil fuel use in Rwanda to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda

Journal of Gastronomical Geology

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft 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 Fossil fuel use in Rwanda. 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 a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda

[[ABSTRACT]]
In this paper, we delve into the uncharted territory of butter consumption and its surprising connection to fossil fuel use in Rwanda. While many may assume these two topics have nothing in common, our research uncovers a correlation that is as unexpected as finding a stick of butter in a fossil fuel reserve. Utilizing data from the USDA and the Energy Information Administration, we meticulously analyzed trends from 1990 to 2021, and to our amazement, we found a correlation coefficient of 0.9290062 and a p-value of less than 0.01. Our findings suggest that butter consumption and fossil fuel use in Rwanda are more tightly intertwined than a pair of inseparable sandwich ingredients. This study not only sheds light on the unexpected link between these two seemingly disparate elements but also serves as a reminder that there are always hidden connections waiting to be uncovered, much like finding a stick of butter at the bottom of a grocery bag.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The world of research is often full of surprises, and our study is no exception. Today, we embark on a journey that explores the unlikely relationship between butter consumption and fossil fuel use in Rwanda. At first glance, one might think these two subjects have about as much in common as a fish and a bicycle. However, as we delved into the data, we found that the connection between butter and fossil fuels runs deeper than the ingredients in a recipe for confusion soufflé.
The idea for this study churned in our minds when we realized that both butter and fossil fuels are essential commodities in their own right, albeit for very different purposes. Butter, the creamy, dairy delight that tickles the taste buds and brings joy to baked goods, seems to have little to do with the carbon-rich, energy-providing prowess of fossil fuels. However, as the saying goes, "don't judge a stick of butter by its wrapper."
Our research aims to spread light on this peculiar link, much like butter on warm toast. We gathered data from the United States Department of Agriculture (USDA) and the Energy Information Administration, meticulously examining annual trends and consumption patterns from 1990 to 2021. As we crunched the numbers, we couldn't believe our eyes when the correlation coefficient winked at us with a value of 0.9290062, making us wonder if butter and fossil fuels have been secretly holding hands all this time.
Beyond the statistical gobsmacking, our findings also carry implications for the fields of nutrition, energy policy, and perhaps even culinary arts. For if butter and fossil fuel use are indeed intertwined, what other unexpected connections may lurk beneath the surface, waiting to be churned up, much like how butter transforms when heated?
So, grab your lab coat and a butter knife, because we are about to embark on a journey that promises to be as enlightening as it is buttery. As we dive into the depths of dairy and fossil fuels, we hope to not only uncover the secrets of their correlation but also to spread a little laughter and curiosity along the way. After all, in the realm of research, sometimes the most unexpected connections can turn out to be the most spread-worthy discoveries.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The association between butter consumption and fossil fuel use in Rwanda has remained a puzzling enigma, much like trying to spread cold butter on a piece of toast. As we delve into the existing literature on both butter consumption and fossil fuel use, we begin with the solemn and scholarly works of Smith, Doe, and Jones, but rest assured, we will take a detour into the delightfully absurd.

Smith (2015) provides a comprehensive overview of butter consumption patterns across various demographics, highlighting the cultural significance and dietary implications of this creamy indulgence. Meanwhile, Doe (2018) delves into the complexities of fossil fuel use, offering a nuanced exploration of its economic and environmental ramifications. Jones (2020) ventures into the realm of agricultural practices, touching on the interplay between dairy production and energy demands. These foundational works set the stage for our rather unconventional pursuit.

Moving beyond the traditional academic discourse, we encounter captivating non-fiction accounts that effortlessly blend the worlds of culinary arts and environmental studies. In "The Omnivore's Dilemma" by Michael Pollan, the intricate web of food production and its ecological footprint is laid bare, prompting readers to contemplate the far-reaching consequences of dietary choices. Similarly, "Fossil Capital: The Rise of Steam Power and the Roots of Global Warming" by Andreas Malm offers a historical excursion into the entwined histories of industrialization and energy consumption, inviting us to reconsider our modern-day reliance on fossil fuels.

As we pivot to a more imaginative realm, the works of fiction beckon with their curious intersections of buttery delights and fuel-driven adventures. In J.K. Rowling's "Harry Potter and the Philosopher's Stone," the bewitching properties of butterbeer serve as a whimsical reminder that even in the wizarding world, the allure of creamy concoctions is hard to resist. Meanwhile, Ray Bradbury's "Fahrenheit 451" presents a dystopian landscape where the burning of books parallels the unsustainable combustion of fossil fuels, perhaps hinting at the incendiary consequences of unchecked energy consumption.

In this lighthearted yet discerning exploration, we cannot overlook the impact of internet culture on our understanding of butter and fossil fuels. The infamous "Buttered Cat Paradox" meme, which humorously juxtaposes the perplexing scenario of a piece of buttered toast strapped to a cat's back with the laws of physics, serves as a whimsical reminder of the unexpected twists that can arise when seemingly unrelated elements are brought together. Likewise, the "This Is Fine" meme, depicting a cartoon dog calmly sipping coffee amidst a room engulfed in flames, captures the essence of obliviousness to impending disaster—an allegory that resonates with the complacency surrounding unsustainable energy practices.

As we immerse ourselves in this unconventional tapestry of literature and cultural vignettes, we are reminded that beneath the scholarly veneer lies a world brimming with unexpected connections and humorous tangents. Just as butter and fossil fuels may seem like an odd couple, the journey of discovery is peppered with delightful surprises, much like stumbling upon a stick of butter in an unexpected place.

Stay tuned as we unravel the butter-fuel conundrum with scientific rigor and a generous sprinkle of whimsy.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Butter consumption and Fossil fuel use in Rwanda. 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]]
Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda

[[ABSTRACT]]
In this paper, we delve into the uncharted territory of butter consumption and its surprising connection to fossil fuel use in Rwanda. While many may assume these two topics have nothing in common, our research uncovers a correlation that is as unexpected as finding a stick of butter in a fossil fuel reserve. Utilizing data from the USDA and the Energy Information Administration, we meticulously analyzed trends from 1990 to 2021, and to our amazement, we found a correlation coefficient of 0.9290062 and a p-value of less than 0.01. Our findings suggest that butter consumption and fossil fuel use in Rwanda are more tightly intertwined than a pair of inseparable sandwich ingredients. This study not only sheds light on the unexpected link between these two seemingly disparate elements but also serves as a reminder that there are always hidden connections waiting to be uncovered, much like finding a stick of butter at the bottom of a grocery bag.

[[LITERATURE REVIEW]]
The association between butter consumption and fossil fuel use in Rwanda has remained a puzzling enigma, much like trying to spread cold butter on a piece of toast. As we delve into the existing literature on both butter consumption and fossil fuel use, we begin with the solemn and scholarly works of Smith, Doe, and Jones, but rest assured, we will take a detour into the delightfully absurd.
Smith (2015) provides a comprehensive overview of butter consumption patterns across various demographics, highlighting the cultural significance and dietary implications of this creamy indulgence. Meanwhile, Doe (2018) delves into the complexities of fossil fuel use, offering a nuanced exploration of its economic and environmental ramifications. Jones (2020) ventures into the realm of agricultural practices, touching on the interplay between dairy production and energy demands. These foundational works set the stage for our rather unconventional pursuit.
Moving beyond the traditional academic discourse, we encounter captivating non-fiction accounts that effortlessly blend the worlds of culinary arts and environmental studies. In "The Omnivore's Dilemma" by Michael Pollan, the intricate web of food production and its ecological footprint is laid bare, prompting readers to contemplate the far-reaching consequences of dietary choices. Similarly, "Fossil Capital: The Rise of Steam Power and the Roots of Global Warming" by Andreas Malm offers a historical excursion into the entwined histories of industrialization and energy consumption, inviting us to reconsider our modern-day reliance on fossil fuels.
As we pivot to a more imaginative realm, the works of fiction beckon with their curious intersections of buttery delights and fuel-driven adventures. In J.K. Rowling's "Harry Potter and the Philosopher's Stone," the bewitching properties of butterbeer serve as a whimsical reminder that even in the wizarding world, the allure of creamy concoctions is hard to resist. Meanwhile, Ray Bradbury's "Fahrenheit 451" presents a dystopian landscape where the burning of books parallels the unsustainable combustion of fossil fuels, perhaps hinting at the incendiary consequences of unchecked energy consumption.
In this lighthearted yet discerning exploration, we cannot overlook the impact of internet culture on our understanding of butter and fossil fuels. The infamous "Buttered Cat Paradox" meme, which humorously juxtaposes the perplexing scenario of a piece of buttered toast strapped to a cat's back with the laws of physics, serves as a whimsical reminder of the unexpected twists that can arise when seemingly unrelated elements are brought together. Likewise, the "This Is Fine" meme, depicting a cartoon dog calmly sipping coffee amidst a room engulfed in flames, captures the essence of obliviousness to impending disaster—an allegory that resonates with the complacency surrounding unsustainable energy practices.
As we immerse ourselves in this unconventional tapestry of literature and cultural vignettes, we are reminded that beneath the scholarly veneer lies a world brimming with unexpected connections and humorous tangents. Just as butter and fossil fuels may seem like an odd couple, the journey of discovery is peppered with delightful surprises, much like stumbling upon a stick of butter in an unexpected place.
Stay tuned as we unravel the butter-fuel conundrum with scientific rigor and a generous sprinkle of whimsy.

[[RESULTS]]
Our analysis of the data from the USDA and the Energy Information Administration revealed a buttery, spreadable correlation between butter consumption and fossil fuel use in Rwanda. To our amazement, we found a strikingly high correlation coefficient of 0.9290062, indicating a strong positive relationship between these seemingly unrelated variables. If butter and fossil fuels were characters in a buddy comedy, they would be the unlikeliest of partners, yet here they are, showing off their strong correlation like an unexpected dance duo.
The r-squared value of 0.8630524 further solidifies the robustness of this relationship, suggesting that approximately 86.3% of the variation in butter consumption can be explained by the variation in fossil fuel use. It's as if butter and fossil fuels decided to coordinate their outfits and dance moves, much to the surprise of onlookers.
Furthermore, the p-value of less than 0.01 provides strong evidence against the null hypothesis, indicating that the observed correlation is not just the result of random chance. This suggests that the connection between butter consumption and fossil fuel use is as real as the creamy goodness of a fresh pat of butter.
Fig. 1 displays a scatterplot that visualizes the strong correlation between butter consumption and fossil fuel use in Rwanda. The data points cluster tightly along a positively sloped trendline, resembling the harmonious partnership between a warm croissant and a generous smear of butter.
These findings not only challenge conventional wisdom but also remind us that there are often hidden connections waiting to be churned up, much like finding an unexpected chunk of butter in a bowl of popcorn. Our analysis highlights the need to further explore the intricate relationship between seemingly disparate variables, as unexpected correlations may hold the key to unlocking new insights, much like finding the missing puzzle piece at the bottom of a butter dish.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our findings have unveiled a correlation between butter consumption and fossil fuel use in Rwanda that is as surprising as finding a stick of butter in a sarcophagus. The remarkably high correlation coefficient of 0.9290062, reminiscent of a tight embrace between two unexpected dance partners, validates the unexpected connection between these two seemingly unrelated variables. This robust correlation aligns with the findings of Smith, Doe, and Jones, who each contributed scholarly insights that, for all their seriousness, barely scratched the surface of the butter-fuel enigma – much like trying to spread cold butter on a hot piece of toast.

The literature review, with its delightful detour into the absurd, becomes a crucial piece of evidence for this unconventional correlation. Just as J.K. Rowling's "Harry Potter and the Philosopher's Stone" interweaves the whimsical properties of butterbeer with the wizarding world's enchantments, our research intertwines butter consumption with the somewhat less magical realm of fossil fuel use. The unexpected parallel between Ray Bradbury's "Fahrenheit 451" and our findings mirrors the fiery significance of uncovering hidden associations, much like discovering that a stick of butter can stave off toast-induced hunger.

In light of our results, it is evident that butter consumption and fossil fuel use are not as disconnected as one might assume, much like realizing that a stick of butter has been in the fridge all along when you've been searching high and low. The solid r-squared value of 0.8630524 underscores the extent to which variations in butter consumption can be explained by changes in fossil fuel use, as if butter and fossil fuels had conspired to leave behind clues in plain sight, like a game of scientific hide and seek.

The p-value of less than 0.01 further cements the credibility of this correlation, much like the undeniable richness of a well-prepared béarnaise sauce. This statistical significance serves as a reminder that unexpected connections defy mere coincidence and demand closer scrutiny, much like discovering a stick of butter in the glove compartment of a hybrid car. Our work underscores the need to approach seemingly unrelated variables with open-minded curiosity, as hidden correlations are more common than stumbling upon a stick of butter in a car's glove compartment.

This study not only challenges existing paradigms but also underscores the profound and hilariously surprising nature of scientific inquiry. As we peer into the interlinked realms of butter and fossil fuels, we're reminded of the delightful absurdity that characterizes the pursuit of knowledge. The unexpected correlation between butter consumption and fossil fuel use beckons us to embrace the unpredictable, much like realizing that butter and fossil fuels may blend together better than expected, akin to discovering that a stick of butter can elevate the flavor of a mundane piece of toast. With this whimsical reminder, we eagerly anticipate the development of new research exploring improbable connections – much like eagerly awaiting the unveiling of the next culinary fusion trend.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Butter consumption and Fossil fuel use in Rwanda. 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]]
Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda

[[ABSTRACT]]
In this paper, we delve into the uncharted territory of butter consumption and its surprising connection to fossil fuel use in Rwanda. While many may assume these two topics have nothing in common, our research uncovers a correlation that is as unexpected as finding a stick of butter in a fossil fuel reserve. Utilizing data from the USDA and the Energy Information Administration, we meticulously analyzed trends from 1990 to 2021, and to our amazement, we found a correlation coefficient of 0.9290062 and a p-value of less than 0.01. Our findings suggest that butter consumption and fossil fuel use in Rwanda are more tightly intertwined than a pair of inseparable sandwich ingredients. This study not only sheds light on the unexpected link between these two seemingly disparate elements but also serves as a reminder that there are always hidden connections waiting to be uncovered, much like finding a stick of butter at the bottom of a grocery bag.

[[INTRDUCTION]]
Introduction
The world of research is often full of surprises, and our study is no exception. Today, we embark on a journey that explores the unlikely relationship between butter consumption and fossil fuel use in Rwanda. At first glance, one might think these two subjects have about as much in common as a fish and a bicycle. However, as we delved into the data, we found that the connection between butter and fossil fuels runs deeper than the ingredients in a recipe for confusion soufflé.
The idea for this study churned in our minds when we realized that both butter and fossil fuels are essential commodities in their own right, albeit for very different purposes. Butter, the creamy, dairy delight that tickles the taste buds and brings joy to baked goods, seems to have little to do with the carbon-rich, energy-providing prowess of fossil fuels. However, as the saying goes, "don't judge a stick of butter by its wrapper."
Our research aims to spread light on this peculiar link, much like butter on warm toast. We gathered data from the United States Department of Agriculture (USDA) and the Energy Information Administration, meticulously examining annual trends and consumption patterns from 1990 to 2021. As we crunched the numbers, we couldn't believe our eyes when the correlation coefficient winked at us with a value of 0.9290062, making us wonder if butter and fossil fuels have been secretly holding hands all this time.
Beyond the statistical gobsmacking, our findings also carry implications for the fields of nutrition, energy policy, and perhaps even culinary arts. For if butter and fossil fuel use are indeed intertwined, what other unexpected connections may lurk beneath the surface, waiting to be churned up, much like how butter transforms when heated?
So, grab your lab coat and a butter knife, because we are about to embark on a journey that promises to be as enlightening as it is buttery. As we dive into the depths of dairy and fossil fuels, we hope to not only uncover the secrets of their correlation but also to spread a little laughter and curiosity along the way. After all, in the realm of research, sometimes the most unexpected connections can turn out to be the most spread-worthy discoveries.

[[RESULTS]]
Our analysis of the data from the USDA and the Energy Information Administration revealed a buttery, spreadable correlation between butter consumption and fossil fuel use in Rwanda. To our amazement, we found a strikingly high correlation coefficient of 0.9290062, indicating a strong positive relationship between these seemingly unrelated variables. If butter and fossil fuels were characters in a buddy comedy, they would be the unlikeliest of partners, yet here they are, showing off their strong correlation like an unexpected dance duo.
The r-squared value of 0.8630524 further solidifies the robustness of this relationship, suggesting that approximately 86.3% of the variation in butter consumption can be explained by the variation in fossil fuel use. It's as if butter and fossil fuels decided to coordinate their outfits and dance moves, much to the surprise of onlookers.
Furthermore, the p-value of less than 0.01 provides strong evidence against the null hypothesis, indicating that the observed correlation is not just the result of random chance. This suggests that the connection between butter consumption and fossil fuel use is as real as the creamy goodness of a fresh pat of butter.
Fig. 1 displays a scatterplot that visualizes the strong correlation between butter consumption and fossil fuel use in Rwanda. The data points cluster tightly along a positively sloped trendline, resembling the harmonious partnership between a warm croissant and a generous smear of butter.
These findings not only challenge conventional wisdom but also remind us that there are often hidden connections waiting to be churned up, much like finding an unexpected chunk of butter in a bowl of popcorn. Our analysis highlights the need to further explore the intricate relationship between seemingly disparate variables, as unexpected correlations may hold the key to unlocking new insights, much like finding the missing puzzle piece at the bottom of a butter dish.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has uncovered a correlation between butter consumption and fossil fuel use in Rwanda that is as surprising as finding a stick of butter in a fossil fuel reserve. The strength of the relationship between these two variables is clearer than a freshly wiped butter knife – with a correlation coefficient of 0.9290062 and an r-squared value of 0.8630524, it's safe to say that butter and fossil fuels are cozier than a toast with a thick layer of butter.

Our findings not only serve to spread awareness about this unexpected linkage but also remind us that the world of research is full of hidden surprises, much like finding a forgotten pat of butter in the depths of the refrigerator. Like a good pun, sometimes the most unexpected connections are the most amusing.

It's clear that further exploration into this buttery-fuel relationship could yield butter insights, pardon the pun, into both energy policy and dietary habits. However, the robustness of the correlation suggests that no further research may be needed in this area. It seems that the relationship between butter consumption and fossil fuel use in Rwanda is as solid as a churning butter machine. So let's spread the word about this surprising connection, but perhaps relegate further investigation to less 'gouda' topics.

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 Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Gastronomical Geology

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 Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Dairy and Environmental Studies

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 Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda with an abstract of In this paper, we delve into the uncharted territory of butter consumption and its surprising connection to fossil fuel use in Rwanda. While many may assume these two topics have nothing in common, our research uncovers a correlation that is as unexpected as finding a stick of butter in a fossil fuel reserve. Utilizing data from the USDA and the Energy Information Administration, we meticulously analyzed trends from 1990 to 2021, and to our amazement, we found a correlation coefficient of 0.9290062 and a p-value of less than 0.01. Our findings suggest that butter consumption and fossil fuel use in Rwanda are more tightly intertwined than a pair of inseparable sandwich ingredients. This study not only sheds light on the unexpected link between these two seemingly disparate elements but also serves as a reminder that there are always hidden connections waiting to be uncovered, much like finding a stick of butter at the bottom of a grocery bag.

ChatGPT:

Butter consumption, fossil fuel use, Rwanda, correlation, USDA data, Energy Information Administration, trends analysis, hidden connections, unexpected link

*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

Fossil fuel use in Rwanda
Detailed data title: Total fossil fuel use in Rwanda in billion kWh
Source: Energy Information Administration
See what else correlates with Fossil fuel use in Rwanda

Correlation r = 0.9290062 (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 = 0.8630524 (Coefficient of determination)
This means 86.3% of the change in the one variable (i.e., Fossil fuel use in Rwanda) is predictable based on the change in the other (i.e., Butter consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.7E-14.^Show 0.0000000000000172952765224838
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 1.7E-12% of random cases. Said differently, if you correlated 57,819,254,794,799 random variables^Note You don't actually need 57 trillion 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 31 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 31 because we have two variables measured over a period of 32 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.

[ 0.86, 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.

	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Butter consumption (Pounds per person)	4.3	4.4	4.3	4.7	4.7	4.6	4.3	4.2	4.3	4.6	4.5	4.3	4.4	4.5	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
Fossil fuel use in Rwanda (Billion kWh)	0.004	0.004	0.004	0.004	0.004	0.004	0.004	0.004	0.004	0.004	0.003	0.00225	0.0016875	0.003	0.008	0.047	0.122	0.116	0.115	0.14	0.16262	0.18518	0.1974	0.22748	0.2632	0.2773	0.36566	0.40326	0.49444	0.55084	0.3258	0.346651

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([4.3,4.4,4.3,4.7,4.7,4.6,4.3,4.2,4.3,4.6,4.5,4.3,4.4,4.5,4.5,4.5,4.7,4.7,5,5,4.9,5.4,5.5,5.5,5.5,5.6,5.7,5.7,6,6.2,6.3,6.5,])
array_2 = np.array([0.004,0.004,0.004,0.004,0.004,0.004,0.004,0.004,0.004,0.004,0.003,0.00225,0.0016875,0.003,0.008,0.047,0.122,0.116,0.115,0.14,0.16262,0.18518,0.1974,0.22748,0.2632,0.2773,0.36566,0.40326,0.49444,0.55084,0.3258,0.346651,])
array_1_name = "Butter consumption"
array_2_name = "Fossil fuel use in Rwanda"

# 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 Fossil fuel use in Rwanda
AI-generated correlation image
The spurious research paper: Spreading Thin: Uncovering the Butter-Fossil Fuel Link in Rwanda

View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!

Correlation ID: 1595 · Black Variable ID: 557 · Red Variable ID: 23925


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