about · email me · subscribe
Spurious correlation #3,368 · 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 Nuclear power generation in China.  The chart goes from 1992 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As butter consumption increased, it led to slippery fingers. This inadvertently caused a surge in the pressing of buttons and flipping of switches at the nuclear power plants, ultimately boosting nuclear power generation in China. After all, it's udderly hard to resist the power of butter!

Model: dalle-3
Prompt: Generate an idyllic scene of a bright, pastel-colored, cartoon-style depiction of a lush green pasture in China. Within it, include adorable cows grazing contently on rich, green grass, with smiley faces and gentle expressions as they enjoy their meal. Above them, fluffy, cute white clouds float in a bright blue sky, adding to the cheerful atmosphere. In the distance, integrate sleek, modern wind turbines spinning gracefully in the breeze, capturing the positive, eco-friendly depiction of energy production. 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 Nuclear power generation in China. 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 Steampunk Cubism Low poly Cute cartoon
ChatGPT: Cute cartoon

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 Nuclear power generation in China, in the following situation: Because butter consumption increased, causing cows to produce more methane, which was used to power generators in China, leading to an increase in nuclear power generation.. Keep the description simple.
ChatGPT: A lush green pasture in China is dotted with grazing cows, each munching contently on rich, green grass. Above them, fluffy white clouds float in the bright blue sky. In the distance, a cluster of sleek, modern wind turbines spin gracefully in the breeze, harnessing the power of the cows' increased methane production to generate clean energy for China's nuclear power plants.

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: [ Cute cartoon ] and depicting this scene: A lush green pasture in China is dotted with grazing cows, each munching contently on rich, green grass. Above them, fluffy white clouds float in the bright blue sky. In the distance, a cluster of sleek, modern wind turbines spin gracefully in the breeze, harnessing the power of the cows' increased methane production to generate clean energy for China's nuclear power plants. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an idyllic scene of a bright, pastel-colored, cartoon-style depiction of a lush green pasture in China. Within it, include adorable cows grazing contently on rich, green grass, with smiley faces and gentle expressions as they enjoy their meal. Above them, fluffy, cute white clouds float in a bright blue sky, adding to the cheerful atmosphere. In the distance, integrate sleek, modern wind turbines spinning gracefully in the breeze, capturing the positive, eco-friendly depiction of energy production.

*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.

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 Nuclear power generation in China to increase.

AI academic paper

(Because p < 0.01)
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

Journal of Unconventional Correlations

Jan 2024

Reminder: This paper is AI-generated. Not real!
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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.You write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Butter consumption and Nuclear power generation in China. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from USDA and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9393633 and p < 0.01 for 1992 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the introduction 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 introduction section of an academic research paper presenting the findings of the connection between Butter consumption and Nuclear power generation in China. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the annals of statistical research, it is not uncommon for unlikely pairs to find themselves in the embrace of correlation coefficients. These amorous entanglements often leave researchers scratching their heads, wondering whether causation exists or if it's all just a statistical fling. Our current study is no exception, as we delve into the curious combination of butter consumption and nuclear power generation in the vast and enigmatic land of China.

The idea that butter and nuclear power could have anything in common may seem like a spread too thin. However, as we embark on this scientific journey, we aim to unravel the creamy mysteries that lay hidden within the confines of seemingly unrelated variables. After all, when life gives you correlations, make correlation-ade, right?

Before we delve into the rich and flavorful depths of butter and the electrifying world of nuclear power, it's crucial to acknowledge the element of surprise that often accompanies statistical research. Just when you think you've seen it all, a statistician's world will be flipped on its axis by a correlation so unexpected, it's as if a black swan flew into the lab and started doing the cha-cha with the null hypothesis.

We begin with butter, the golden elixir of palatables. Butter, that creamy and delectable companion to toast, pastries, and life's other simple pleasures, has long been the stuff of dreams for both chefs and dairy enthusiasts alike. Despite its charm, this dairy delight has found itself dragged into the realm of statistical analysis. It seems that butter's allure knows no bounds, even extending to the cold, unyielding world of numbers and data.

On the other hand, nuclear power — the enigmatic source of energy that holds both the promise of endless electricity and the eerie specter of atomic annihilation. It's the ultimate power couple of protons and neutrons, mingling in a high-stakes game of energy production. The marriage of nuclear power and its potential hazards has kept researchers busy for decades, and now, it finds itself intertwined with the world of butter consumption. What a peculiar duet!

In this paper, we strive not just to churn out numbers, but to bypass the superficial and dive deep into the undercurrents of statistical intrigue. With a pat of butter in one hand and a Geiger counter in the other, we march forth into the land of correlation, armed with both curiosity and skepticism. The statistical stage is set, the variables are waiting, and the puns are ripe for the picking. It's time to spread the connection between butter consumption and nuclear power generation in China like nobody's business.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Nuclear power generation in China. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the annals of statistical research, it is not uncommon for unlikely pairs to find themselves in the embrace of correlation coefficients. These amorous entanglements often leave researchers scratching their heads, wondering whether causation exists or if it's all just a statistical fling. Our current study is no exception, as we delve into the curious combination of butter consumption and nuclear power generation in the vast and enigmatic land of China.
The idea that butter and nuclear power could have anything in common may seem like a spread too thin. However, as we embark on this scientific journey, we aim to unravel the creamy mysteries that lay hidden within the confines of seemingly unrelated variables. After all, when life gives you correlations, make correlation-ade, right?
Before we delve into the rich and flavorful depths of butter and the electrifying world of nuclear power, it's crucial to acknowledge the element of surprise that often accompanies statistical research. Just when you think you've seen it all, a statistician's world will be flipped on its axis by a correlation so unexpected, it's as if a black swan flew into the lab and started doing the cha-cha with the null hypothesis.
We begin with butter, the golden elixir of palatables. Butter, that creamy and delectable companion to toast, pastries, and life's other simple pleasures, has long been the stuff of dreams for both chefs and dairy enthusiasts alike. Despite its charm, this dairy delight has found itself dragged into the realm of statistical analysis. It seems that butter's allure knows no bounds, even extending to the cold, unyielding world of numbers and data.
On the other hand, nuclear power — the enigmatic source of energy that holds both the promise of endless electricity and the eerie specter of atomic annihilation. It's the ultimate power couple of protons and neutrons, mingling in a high-stakes game of energy production. The marriage of nuclear power and its potential hazards has kept researchers busy for decades, and now, it finds itself intertwined with the world of butter consumption. What a peculiar duet!
In this paper, we strive not just to churn out numbers, but to bypass the superficial and dive deep into the undercurrents of statistical intrigue. With a pat of butter in one hand and a Geiger counter in the other, we march forth into the land of correlation, armed with both curiosity and skepticism. The statistical stage is set, the variables are waiting, and the puns are ripe for the picking. It's time to spread the connection between butter consumption and nuclear power generation in China like nobody's business.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find that butter consumption has been a staple of the Western diet for centuries, with its rich, creamy texture and versatile culinary applications. Meanwhile, Doe and Jones analyze the complex landscape of nuclear power generation, highlighting its role in the global energy sector and its potential impact on climate change mitigation.

Turning to non-fiction sources, the works of "The China Study" by T. Colin Campbell and "Nuclear Power: A Very Short Introduction" by Maxwell Irvine provide valuable insights into the dietary and energy dynamics of China. These texts offer a serious examination of nutritional habits and power generation, setting the stage for our exploration of the unforeseen intersection between butter consumption and nuclear power generation.

In the realm of fiction, Michael Crichton's "Prey" and Dan Brown's "Digital Fortress" present compelling narratives that involve technological and scientific elements, albeit in fictional contexts. While not directly related to our study, these literary works underscore the captivating allure of technological phenomena, lending an air of intrigue to our discussion.

In a departure from conventional scholarly sources, the researchers also conducted a thorough review of unconventional texts. This included perusing the backs of shampoo bottles, hoping to stumble upon hidden revelations of the butter-nuclear power nexus. Alas, the results were lathered in disappointment, as the bottles remained silent on the matter, offering nothing but promises of silky-smooth hair.

Unfazed by this setback, our investigation persisted, venturing into the uncharted territory of conspiracy theories and urban legends. This peculiar exploration yielded wild tales of clandestine butter-powered reactors and covert dairy initiatives, painting a picture of a world where creamy substances and atomic energy coalesce in clandestine collaborations.

As we wade through these peculiar and diverse sources, it becomes evident that the connection between butter consumption and nuclear power generation in China is not merely a matter of statistics and data analysis. It transcends traditional academic boundaries, inviting us to ponder the delightful absurdity of life's juxtapositions and to embrace the whimsical dance of correlation that defies conventional logic.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the methodology 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 methodology section of an academic research paper presenting the findings of the connection between Butter consumption and Nuclear power generation in China. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from USDA and Energy Information Administration . You used data from 1992 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

[[INTRODUCTION]]
In the annals of statistical research, it is not uncommon for unlikely pairs to find themselves in the embrace of correlation coefficients. These amorous entanglements often leave researchers scratching their heads, wondering whether causation exists or if it's all just a statistical fling. Our current study is no exception, as we delve into the curious combination of butter consumption and nuclear power generation in the vast and enigmatic land of China.
The idea that butter and nuclear power could have anything in common may seem like a spread too thin. However, as we embark on this scientific journey, we aim to unravel the creamy mysteries that lay hidden within the confines of seemingly unrelated variables. After all, when life gives you correlations, make correlation-ade, right?
Before we delve into the rich and flavorful depths of butter and the electrifying world of nuclear power, it's crucial to acknowledge the element of surprise that often accompanies statistical research. Just when you think you've seen it all, a statistician's world will be flipped on its axis by a correlation so unexpected, it's as if a black swan flew into the lab and started doing the cha-cha with the null hypothesis.
We begin with butter, the golden elixir of palatables. Butter, that creamy and delectable companion to toast, pastries, and life's other simple pleasures, has long been the stuff of dreams for both chefs and dairy enthusiasts alike. Despite its charm, this dairy delight has found itself dragged into the realm of statistical analysis. It seems that butter's allure knows no bounds, even extending to the cold, unyielding world of numbers and data.
On the other hand, nuclear power — the enigmatic source of energy that holds both the promise of endless electricity and the eerie specter of atomic annihilation. It's the ultimate power couple of protons and neutrons, mingling in a high-stakes game of energy production. The marriage of nuclear power and its potential hazards has kept researchers busy for decades, and now, it finds itself intertwined with the world of butter consumption. What a peculiar duet!
In this paper, we strive not just to churn out numbers, but to bypass the superficial and dive deep into the undercurrents of statistical intrigue. With a pat of butter in one hand and a Geiger counter in the other, we march forth into the land of correlation, armed with both curiosity and skepticism. The statistical stage is set, the variables are waiting, and the puns are ripe for the picking. It's time to spread the connection between butter consumption and nuclear power generation in China like nobody's business.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the savory relationship between butter consumption and nuclear power generation in China, we embarked on a data-gathering odyssey that would make Odysseus himself jealous. Our research team scoured the depths of the internet, navigating through a sea of websites and databases like intrepid explorers on a statistical treasure hunt. The primary sources of our data were the United States Department of Agriculture (USDA) for butter consumption and the Energy Information Administration for nuclear power generation. We collected data spanning from 1992 to 2021, a period rife with both societal changes and technological advancements.

Our data collection process was as meticulous as a pastry chef measuring ingredients for the perfect croissant. We gathered information on butter consumption in pounds per capita, capturing the ebb and flow of this creamy delight in the tumultuous sea of dietary trends. As for nuclear power generation, we obtained data on electricity production from nuclear sources in gigawatt-hours, measuring the electrifying pulse of atomic energy coursing through the nation’s power grid.

With our smorgasbord of data meticulously assembled, it was time to unleash the might of statistical analysis in unraveling the enigmatic connection between these seemingly divergent variables.

To begin with, we conducted a preliminary exploration of the data, scrutinizing trends, outliers, and patterns with the keen eye of a seasoned detective piecing together clues. We examined the time series data for both butter consumption and nuclear power generation, unveiling the rhythmic dance of fluctuations and the potential syncopation of their movements.

Next, we unleashed the formidable power of correlation analysis, aiming to quantify the degree of association between butter consumption and nuclear power generation. Like matchmakers with a penchant for peculiar pairings, we calculated the Pearson correlation coefficient, seeking to measure the strength and direction of the relationship between these two unlikely companions. To ensure the robustness of our findings, we also computed the Spearman rank correlation coefficient, accounting for any nonlinear relationships that may have lurked beneath the surface.

But we didn’t stop there. Determined to unravel the deeper layers of this intriguing liaison, we employed multiple regression analysis to disentangle the web of interdependent factors. Like unraveling a statistical puzzle where butter and nuclear power were the unlikely protagonists, we crafted regression models to tease out the individual and combined effects of various covariates. Our models featured covariates such as economic indicators, demographic variables, and other potential confounding factors, delving into the complexity of the Chinese socio-economic landscape like fearless explorers charting uncharted territories of statistical intrigue.

In the realm of statistical methods, our approach was as rigorous as a speed-dating event for variables, ensuring that no potential relationship went unnoticed or unexplored. With our data captured, analyzed, and prodded from every angle, we stood ready to unveil the unexpected insights that lay hidden within the intriguing intersection of butter consumption and nuclear power generation in China.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
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 results section of an academic research paper presenting the findings of the connection between Butter consumption and Nuclear power generation in China. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from USDA and Energy Information Administration .

For the time period 1992 to 2021, you found a correlation 0.9393633, r-squared of 0.8824033, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
Spreading the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the annals of statistical research, it is not uncommon for unlikely pairs to find themselves in the embrace of correlation coefficients. These amorous entanglements often leave researchers scratching their heads, wondering whether causation exists or if it's all just a statistical fling. Our current study is no exception, as we delve into the curious combination of butter consumption and nuclear power generation in the vast and enigmatic land of China.
The idea that butter and nuclear power could have anything in common may seem like a spread too thin. However, as we embark on this scientific journey, we aim to unravel the creamy mysteries that lay hidden within the confines of seemingly unrelated variables. After all, when life gives you correlations, make correlation-ade, right?
Before we delve into the rich and flavorful depths of butter and the electrifying world of nuclear power, it's crucial to acknowledge the element of surprise that often accompanies statistical research. Just when you think you've seen it all, a statistician's world will be flipped on its axis by a correlation so unexpected, it's as if a black swan flew into the lab and started doing the cha-cha with the null hypothesis.
We begin with butter, the golden elixir of palatables. Butter, that creamy and delectable companion to toast, pastries, and life's other simple pleasures, has long been the stuff of dreams for both chefs and dairy enthusiasts alike. Despite its charm, this dairy delight has found itself dragged into the realm of statistical analysis. It seems that butter's allure knows no bounds, even extending to the cold, unyielding world of numbers and data.
On the other hand, nuclear power — the enigmatic source of energy that holds both the promise of endless electricity and the eerie specter of atomic annihilation. It's the ultimate power couple of protons and neutrons, mingling in a high-stakes game of energy production. The marriage of nuclear power and its potential hazards has kept researchers busy for decades, and now, it finds itself intertwined with the world of butter consumption. What a peculiar duet!
In this paper, we strive not just to churn out numbers, but to bypass the superficial and dive deep into the undercurrents of statistical intrigue. With a pat of butter in one hand and a Geiger counter in the other, we march forth into the land of correlation, armed with both curiosity and skepticism. The statistical stage is set, the variables are waiting, and the puns are ripe for the picking. It's time to spread the connection between butter consumption and nuclear power generation in China like nobody's business.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the relationship between butter consumption and nuclear power generation in China revealed a rather unexpected and buttery smooth correlation. The correlation coefficient between these seemingly unrelated variables was found to be 0.9393633, with an r-squared value of 0.8824033 - now that's what I call spreading the love! Additionally, the p-value was less than 0.01, indicating a statistically significant association. It seems that this unlikely duo isn't just a fling in the world of statistics; they're in it for the long haul.

But don't just take our word for it; let's take a look at the data. The scatterplot in Fig. 1 illustrates the strong positive correlation between butter consumption and nuclear power generation. It's almost as if the butter and nuclear power are holding hands, skipping through a field of statistical significance together. I mean, who would've thought that a stick of butter and a uranium atom could have so much in common?

Our findings not only add a dollop of humor to the sometimes bland world of statistical research but also highlight the potential interplay between dietary choices and energy production. Clearly, the creamy goodness of butter and the electrifying power of nuclear energy have more in common than meets the eye. It's like finding out that peanut butter and jelly are secretly best friends – an unexpected and delightful revelation.

As our study demonstrates, statistical research can uncover unexpected connections and delve into the quirky and enigmatic relationships between seemingly unrelated variables. It's all about adding some flavor to the world of numbers and data, and boy, did we hit the jackpot with this one. So, let's raise a toast – slathered with butter, of course – to the unlikely romance of butter consumption and nuclear power generation in China. After all, as researchers, it's our duty to churn up the unexpected and spread the joy of statistical discovery.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Nuclear power generation in China. 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 the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find that butter consumption has been a staple of the Western diet for centuries, with its rich, creamy texture and versatile culinary applications. Meanwhile, Doe and Jones analyze the complex landscape of nuclear power generation, highlighting its role in the global energy sector and its potential impact on climate change mitigation.
Turning to non-fiction sources, the works of "The China Study" by T. Colin Campbell and "Nuclear Power: A Very Short Introduction" by Maxwell Irvine provide valuable insights into the dietary and energy dynamics of China. These texts offer a serious examination of nutritional habits and power generation, setting the stage for our exploration of the unforeseen intersection between butter consumption and nuclear power generation.
In the realm of fiction, Michael Crichton's "Prey" and Dan Brown's "Digital Fortress" present compelling narratives that involve technological and scientific elements, albeit in fictional contexts. While not directly related to our study, these literary works underscore the captivating allure of technological phenomena, lending an air of intrigue to our discussion.
In a departure from conventional scholarly sources, the researchers also conducted a thorough review of unconventional texts. This included perusing the backs of shampoo bottles, hoping to stumble upon hidden revelations of the butter-nuclear power nexus. Alas, the results were lathered in disappointment, as the bottles remained silent on the matter, offering nothing but promises of silky-smooth hair.
Unfazed by this setback, our investigation persisted, venturing into the uncharted territory of conspiracy theories and urban legends. This peculiar exploration yielded wild tales of clandestine butter-powered reactors and covert dairy initiatives, painting a picture of a world where creamy substances and atomic energy coalesce in clandestine collaborations.
As we wade through these peculiar and diverse sources, it becomes evident that the connection between butter consumption and nuclear power generation in China is not merely a matter of statistics and data analysis. It transcends traditional academic boundaries, inviting us to ponder the delightful absurdity of life's juxtapositions and to embrace the whimsical dance of correlation that defies conventional logic.

[[RESULTS]]
Our analysis of the relationship between butter consumption and nuclear power generation in China revealed a rather unexpected and buttery smooth correlation. The correlation coefficient between these seemingly unrelated variables was found to be 0.9393633, with an r-squared value of 0.8824033 - now that's what I call spreading the love! Additionally, the p-value was less than 0.01, indicating a statistically significant association. It seems that this unlikely duo isn't just a fling in the world of statistics; they're in it for the long haul.
But don't just take our word for it; let's take a look at the data. The scatterplot in Fig. 1 illustrates the strong positive correlation between butter consumption and nuclear power generation. It's almost as if the butter and nuclear power are holding hands, skipping through a field of statistical significance together. I mean, who would've thought that a stick of butter and a uranium atom could have so much in common?
Our findings not only add a dollop of humor to the sometimes bland world of statistical research but also highlight the potential interplay between dietary choices and energy production. Clearly, the creamy goodness of butter and the electrifying power of nuclear energy have more in common than meets the eye. It's like finding out that peanut butter and jelly are secretly best friends – an unexpected and delightful revelation.
As our study demonstrates, statistical research can uncover unexpected connections and delve into the quirky and enigmatic relationships between seemingly unrelated variables. It's all about adding some flavor to the world of numbers and data, and boy, did we hit the jackpot with this one. So, let's raise a toast – slathered with butter, of course – to the unlikely romance of butter consumption and nuclear power generation in China. After all, as researchers, it's our duty to churn up the unexpected and spread the joy of statistical discovery.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Well, well, well, if it isn't a creamy conundrum we've stumbled upon! Our findings have certainly churned up some unexpected connections between butter consumption and nuclear power generation in China. It's safe to say that this study has brought a whole new meaning to the term "nuclear fusion!"

In our exploration of the whimsical interplay between these two disparate factors, we found that our results not only supported the prior research but also added a thick layer of statistical intrigue to the mix. The correlation coefficient of 0.9393633 with a p-value less than 0.01 not only buttered up the significance of this unlikely relationship but also spread a generous helping of statistical validity onto our findings.

Harking back to the peculiar items in our literature review, it's rather delightful to note that our results have buttered up the serious insights of Smith et al. and Doe and Jones. While they may have not anticipated the butter-nuclear power nexus, our findings have certainly provided a rich and creamy extension to their scholarly work. Our revelations have truly been a buttery addition to the serious narratives of technological phenomena.

It seems that as researchers, we've managed to whip up a delectable empirical batter, incorporating the serious and the whimsical into a delightful statistical soufflé. Our study underscores the importance of embracing the unexpected in scientific inquiry and serves as a reminder that even the most seemingly unrelated variables can dance to the same statistical tune.

In conclusion, our study has served as a gentle reminder that scientific research doesn't always have to be a dry and uninspired endeavor. Sometimes, all it takes is a dollop of curiosity, a pinch of whimsy, and a generous serving of statistical rigor to uncover the hidden delights of statistical correlation. After all, in the world of research, it's not just about churning the data; it's about savoring the creamy nuances of statistical discovery.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics 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 Nuclear power generation in China. 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 the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

[[INTRDUCTION]]
In the annals of statistical research, it is not uncommon for unlikely pairs to find themselves in the embrace of correlation coefficients. These amorous entanglements often leave researchers scratching their heads, wondering whether causation exists or if it's all just a statistical fling. Our current study is no exception, as we delve into the curious combination of butter consumption and nuclear power generation in the vast and enigmatic land of China.
The idea that butter and nuclear power could have anything in common may seem like a spread too thin. However, as we embark on this scientific journey, we aim to unravel the creamy mysteries that lay hidden within the confines of seemingly unrelated variables. After all, when life gives you correlations, make correlation-ade, right?
Before we delve into the rich and flavorful depths of butter and the electrifying world of nuclear power, it's crucial to acknowledge the element of surprise that often accompanies statistical research. Just when you think you've seen it all, a statistician's world will be flipped on its axis by a correlation so unexpected, it's as if a black swan flew into the lab and started doing the cha-cha with the null hypothesis.
We begin with butter, the golden elixir of palatables. Butter, that creamy and delectable companion to toast, pastries, and life's other simple pleasures, has long been the stuff of dreams for both chefs and dairy enthusiasts alike. Despite its charm, this dairy delight has found itself dragged into the realm of statistical analysis. It seems that butter's allure knows no bounds, even extending to the cold, unyielding world of numbers and data.
On the other hand, nuclear power — the enigmatic source of energy that holds both the promise of endless electricity and the eerie specter of atomic annihilation. It's the ultimate power couple of protons and neutrons, mingling in a high-stakes game of energy production. The marriage of nuclear power and its potential hazards has kept researchers busy for decades, and now, it finds itself intertwined with the world of butter consumption. What a peculiar duet!
In this paper, we strive not just to churn out numbers, but to bypass the superficial and dive deep into the undercurrents of statistical intrigue. With a pat of butter in one hand and a Geiger counter in the other, we march forth into the land of correlation, armed with both curiosity and skepticism. The statistical stage is set, the variables are waiting, and the puns are ripe for the picking. It's time to spread the connection between butter consumption and nuclear power generation in China like nobody's business.

[[RESULTS]]
Our analysis of the relationship between butter consumption and nuclear power generation in China revealed a rather unexpected and buttery smooth correlation. The correlation coefficient between these seemingly unrelated variables was found to be 0.9393633, with an r-squared value of 0.8824033 - now that's what I call spreading the love! Additionally, the p-value was less than 0.01, indicating a statistically significant association. It seems that this unlikely duo isn't just a fling in the world of statistics; they're in it for the long haul.
But don't just take our word for it; let's take a look at the data. The scatterplot in Fig. 1 illustrates the strong positive correlation between butter consumption and nuclear power generation. It's almost as if the butter and nuclear power are holding hands, skipping through a field of statistical significance together. I mean, who would've thought that a stick of butter and a uranium atom could have so much in common?
Our findings not only add a dollop of humor to the sometimes bland world of statistical research but also highlight the potential interplay between dietary choices and energy production. Clearly, the creamy goodness of butter and the electrifying power of nuclear energy have more in common than meets the eye. It's like finding out that peanut butter and jelly are secretly best friends – an unexpected and delightful revelation.
As our study demonstrates, statistical research can uncover unexpected connections and delve into the quirky and enigmatic relationships between seemingly unrelated variables. It's all about adding some flavor to the world of numbers and data, and boy, did we hit the jackpot with this one. So, let's raise a toast – slathered with butter, of course – to the unlikely romance of butter consumption and nuclear power generation in China. After all, as researchers, it's our duty to churn up the unexpected and spread the joy of statistical discovery.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our findings have churned up quite the discovery in the world of statistics. The buttery smooth correlation between butter consumption and nuclear power generation in China has certainly spread a rich layer of intrigue over the seemingly unrelated realms of dietary habits and energy production. It's like discovering that two seemingly random strangers at a dinner party are actually long-lost cousins – an unexpected connection that leaves everyone feeling a little perplexed but pleasantly surprised.

The statistical love affair between butter and nuclear power not only adds a dollop of humor to the rather serious business of research but also underscores the potential interplay between what we consume and how we generate energy. It's a bit like realizing that a slice of toast and a nuclear reactor have more in common than meets the eye – a delightful revelation indeed.

As we wrap up this exploration of the buttery and nuclear landscapes, it's clear that statistical research can be full of unexpected twists and turns. From black swans doing the cha-cha with null hypotheses to peanut butter and jelly revealing their best friendship, the world of statistics is a playground of delightful surprises.

So, as we bid adieu to this quirky correlation, it's safe to say that no further research in this area is needed. The butter has been spread, the nuclear energy has been harnessed, and the statistical stage has been graced with a truly unlikely romance. It's time to let this love story stand as a testament to the whimsical nature of statistical discovery. After all, when it comes to statistical love affairs, there's no need for a sequel – we've already found the perfect pairing!


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 the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Unconventional Correlations


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 the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China. Respond only with the name of a fictional organization.

ChatGPT:

The Society for the Advancement of Dairy Energy Research


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 the Connection: A Margarinal Analysis of Butter Consumption and Nuclear Power Generation in China with an abstract of This study delves into the unexpected and seemingly unrelated realms of butter consumption and nuclear power generation in China to elucidate any potential correlation. By analyzing data from the USDA for butter consumption and the Energy Information Administration for nuclear power generation from 1992 to 2021, we uncovered a surprising correlation coefficient of 0.9393633 with p < 0.01. Our findings reveal a buttery smooth relationship between these two disparate factors, suggesting that there may be more to this seemingly whimsical pairing than meets the eye. This research not only sheds light on the quirky connections within the world of statistics, but also provides a creamy insight into the potential interplay between dietary habits and energy production.

ChatGPT:

butter consumption, nuclear power generation, China, correlation, USDA data, Energy Information Administration, 1992-2021, correlation coefficient, statistical analysis, dietary habits, energy production

*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

Nuclear power generation in China
Detailed data title: Total nuclear power generation in China in billion kWh
Source: Energy Information Administration
See what else correlates with Nuclear power generation in China

Correlation r = 0.9393633 (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 = 0.8824033 (Coefficient of determination)
This means 88.2% of the change in the one variable (i.e., Nuclear power generation in China) is predictable based on the change in the other (i.e., Butter consumption) over the 30 years from 1992 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-14. 0.0000000000000153204379537248
The p-value is a measure of how probable it is that we would randomly find a result this extreme. 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 0.94 in 1.5E-12% of random cases. Said differently, if you correlated 65,272,285,493,436 random variables You don't actually need 65 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 29 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 29 because we have two variables measured over a period of 30 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.

[ 0.88, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Butter consumption (Pounds per person)4.34.74.74.64.34.24.34.64.54.34.44.54.54.54.74.7554.95.45.55.55.55.65.75.766.26.36.5
Nuclear power generation in China (Billion kWh)0.52.4713.512.3813.6211.3513.4614.08915.90316.59725.16641.66147.94650.33251.8159.29965.32565.71373.8886.3597.39111.61132.54170.79213.29248.07294.36348.35366.25407.52




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 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.
  4. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. 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. 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. 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([4.3,4.7,4.7,4.6,4.3,4.2,4.3,4.6,4.5,4.3,4.4,4.5,4.5,4.5,4.7,4.7,5,5,4.9,5.4,5.5,5.5,5.5,5.6,5.7,5.7,6,6.2,6.3,6.5,])
array_2 = np.array([0.5,2.47,13.5,12.38,13.62,11.35,13.46,14.089,15.903,16.597,25.166,41.661,47.946,50.332,51.81,59.299,65.325,65.713,73.88,86.35,97.39,111.61,132.54,170.79,213.29,248.07,294.36,348.35,366.25,407.52,])
array_1_name = "Butter consumption"
array_2_name = "Nuclear power generation in China"

# 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. 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:


View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!


Correlation ID: 3368 · Black Variable ID: 557 · Red Variable ID: 23587
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0