about · email me · subscribe
Spurious correlation #3,638 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Berlin, New Hampshire and the second variable is Kerosene used in Nepal.  The chart goes from 1981 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Perhaps the smog particles formed a telepathic connection with the kerosene molecules, convincing them to burn brighter. "It's like the pollution was the wingman for the kerosene, creating a fiery love connection!"

Model: dalle-3
Prompt: Generate an image that illustrates the contrast between the smog-filled streets of Berlin, New Hampshire, and the remote villages of Nepal. Show the heavy pollution hovering over the urban landscape of Berlin, while kerosene lamps flicker in the night amidst the serene mountains of Nepal. The image should evoke a sense of atmospheric connection as the kerosene molecules seem to embark on a journey from one location to the other. 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: Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. 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: Photorealism Hyper-realistic A Discovery magazine cover image Cyberpunk A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s
ChatGPT: A Discovery magazine cover image

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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal, in the following situation: Because as air pollution increased in Berlin, New Hampshire, it created a unique atmospheric pressure that caused kerosene molecules to develop wanderlust and seek out exotic travel destinations like Nepal. They were just following their dreams, man.. Keep the description simple.
ChatGPT: In the smog-filled streets of Berlin, New Hampshire, the air hung heavy with pollution, creating a unique atmospheric pressure. Meanwhile, in the remote villages of Nepal, kerosene lamps flickered to life, their molecules seemingly filled with wanderlust, yearning for a new adventure. The kerosene, being carried by the winds, made its way from Berlin to Nepal, drawn towards the exotic allure of the distant mountains.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In the smog-filled streets of Berlin, New Hampshire, the air hung heavy with pollution, creating a unique atmospheric pressure. Meanwhile, in the remote villages of Nepal, kerosene lamps flickered to life, their molecules seemingly filled with wanderlust, yearning for a new adventure. The kerosene, being carried by the winds, made its way from Berlin to Nepal, drawn towards the exotic allure of the distant mountains. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that illustrates the contrast between the smog-filled streets of Berlin, New Hampshire, and the remote villages of Nepal. Show the heavy pollution hovering over the urban landscape of Berlin, while kerosene lamps flicker in the night amidst the serene mountains of Nepal. The image should evoke a sense of atmospheric connection as the kerosene molecules seem to embark on a journey from one location to the other.

*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 increases in Air pollution in Berlin, New Hampshire positively influenced Kerosene used in Nepal. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene

The International Journal of Ecological Connections

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 researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.7416928 and p < 0.01 for 1981 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]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As the world grapples with the far-reaching consequences of environmental degradation, it becomes increasingly vital to untangle the intricate web of interrelated factors contributing to air pollution. While much attention has been directed towards local sources of pollution, our study takes a truly global perspective, revealing a fascinating connection between distant locales – Berlin, New Hampshire, and Nepal. This unexpected correlation not only sheds light on the far-reaching implications of kerosene usage but also challenges conventional wisdom in environmental research.

Much like a well-timed dad joke, the connection between air pollution in Berlin and kerosene usage in Nepal sneaks up on us when we least expect it, leaving us both baffled and charmed. The quirkiness of this association underscores the need to delve deeper into the complex interactions between seemingly unrelated phenomena.

The picturesque town of Berlin, nestled in the White Mountains of New Hampshire, may seem worlds apart from the mountains of Nepal where kerosene is a common household fuel. However, as our study unveils, it appears that the winds of change are more far-reaching than initially assumed. The metaphorical winds are indeed blowing the unexpected connection of air pollution across continents, posing thought-provoking questions and opening new avenues for exploration.

While the correlation may seem akin to comparing apples to oranges, the statistical evidence proves otherwise, painting a vivid picture of a world intricately connected by environmental forces. It's akin to realizing that the apple actually did not fall far from the orange tree, leaving us to marvel at the interconnectedness of the world in a way that even Newton wouldn't have predicted.

As we venture deeper into this unexpected nexus, our paper not only aims to elucidate the correlation but also to highlight its staggering implications. Like a good old dad joke, it's time to tease apart the layers of this unexpected relationship, revealing the hidden punchline that has eluded us for so long. So, join us as we unwrap this surprising connection, for we are about to embark on a journey that will leave you both pondering and grinning at the marvels of our shared environmental tapestry.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the world grapples with the far-reaching consequences of environmental degradation, it becomes increasingly vital to untangle the intricate web of interrelated factors contributing to air pollution. While much attention has been directed towards local sources of pollution, our study takes a truly global perspective, revealing a fascinating connection between distant locales – Berlin, New Hampshire, and Nepal. This unexpected correlation not only sheds light on the far-reaching implications of kerosene usage but also challenges conventional wisdom in environmental research.

Much like a well-timed dad joke, the connection between air pollution in Berlin and kerosene usage in Nepal sneaks up on us when we least expect it, leaving us both baffled and charmed. The quirkiness of this association underscores the need to delve deeper into the complex interactions between seemingly unrelated phenomena.
The picturesque town of Berlin, nestled in the White Mountains of New Hampshire, may seem worlds apart from the mountains of Nepal where kerosene is a common household fuel. However, as our study unveils, it appears that the winds of change are more far-reaching than initially assumed. The metaphorical winds are indeed blowing the unexpected connection of air pollution across continents, posing thought-provoking questions and opening new avenues for exploration.
While the correlation may seem akin to comparing apples to oranges, the statistical evidence proves otherwise, painting a vivid picture of a world intricately connected by environmental forces. It's akin to realizing that the apple actually did not fall far from the orange tree, leaving us to marvel at the interconnectedness of the world in a way that even Newton wouldn't have predicted.
As we venture deeper into this unexpected nexus, our paper not only aims to elucidate the correlation but also to highlight its staggering implications. Like a good old dad joke, it's time to tease apart the layers of this unexpected relationship, revealing the hidden punchline that has eluded us for so long. So, join us as we unwrap this surprising connection, for we are about to embark on a journey that will leave you both pondering and grinning at the marvels of our shared environmental tapestry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Air Pollution in Urban Environments," Smith et al. examined the various contributors to air pollution in urban centers, highlighting the impact of industrial activities, vehicular emissions, and biomass burning. Similarly, Doe and Jones, in "The Global Impact of Household Fuel Use," delved into the widespread use of kerosene in developing countries, emphasizing its implications for indoor and outdoor air quality.

It's an enlightening read, really shedding some light! Speaking of shedding light, did you hear about the guy who invented Lifesavers? He made a mint!

Moving on, "Emissions and Their Effects on Atmospheric Composition" by Brown and Green provides comprehensive insight into the chemical composition of air pollutants and their effects on the atmosphere. Likewise, Black and White, in "The Household Energy Transition," delve into the shifting trends in household energy consumption, with a particular focus on the use of traditional fuels such as kerosene.

It's almost like these authors are crafting a narrative as captivating as a Dickens novel. Speaking of, isn't it ironic how Charles Dickens' "Great Expectations" could apply to our lofty hopes of solving environmental issues?

On a slightly different note, "Breaking Bad" and "Alaska: The Last Frontier" are two television series that offer a glimpse into the daily lives of individuals facing environmental challenges, albeit in drastically different settings. As researchers, we found valuable insights in these shows, even if we had to endure a few eye-rolling moments at the same time.

But, wait, there's more! "Dune" by Frank Herbert and "Into Thin Air" by Jon Krakauer, although works of fiction, provided us with a fresh perspective on environmental extremes and the unforeseen consequences of human activities. These books ignited our imaginations and made us ponder the unexpected connections that permeate the natural world, mirroring our own investigation into the Berlin-Nepal correlation.

This literature review brings to light the diverse strands of research that have woven the fabric of our understanding of air pollution and energy consumption. As we dig deeper into the unexpected relationship between air pollution in Berlin, New Hampshire, and kerosene usage in Nepal, we are reminded that even in the world of academia, a well-placed joke can breathe life into our scholarly pursuits.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1981 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]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

[[INTRODUCTION]]
As the world grapples with the far-reaching consequences of environmental degradation, it becomes increasingly vital to untangle the intricate web of interrelated factors contributing to air pollution. While much attention has been directed towards local sources of pollution, our study takes a truly global perspective, revealing a fascinating connection between distant locales – Berlin, New Hampshire, and Nepal. This unexpected correlation not only sheds light on the far-reaching implications of kerosene usage but also challenges conventional wisdom in environmental research.

Much like a well-timed dad joke, the connection between air pollution in Berlin and kerosene usage in Nepal sneaks up on us when we least expect it, leaving us both baffled and charmed. The quirkiness of this association underscores the need to delve deeper into the complex interactions between seemingly unrelated phenomena.
The picturesque town of Berlin, nestled in the White Mountains of New Hampshire, may seem worlds apart from the mountains of Nepal where kerosene is a common household fuel. However, as our study unveils, it appears that the winds of change are more far-reaching than initially assumed. The metaphorical winds are indeed blowing the unexpected connection of air pollution across continents, posing thought-provoking questions and opening new avenues for exploration.
While the correlation may seem akin to comparing apples to oranges, the statistical evidence proves otherwise, painting a vivid picture of a world intricately connected by environmental forces. It's akin to realizing that the apple actually did not fall far from the orange tree, leaving us to marvel at the interconnectedness of the world in a way that even Newton wouldn't have predicted.
As we venture deeper into this unexpected nexus, our paper not only aims to elucidate the correlation but also to highlight its staggering implications. Like a good old dad joke, it's time to tease apart the layers of this unexpected relationship, revealing the hidden punchline that has eluded us for so long. So, join us as we unwrap this surprising connection, for we are about to embark on a journey that will leave you both pondering and grinning at the marvels of our shared environmental tapestry.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the intriguing connection between air pollution in Berlin, New Hampshire, and kerosene consumption in Nepal, our research team ventured into uncharted territory, armed with an arsenal of statistical tools and an unyielding sense of curiosity. Our data collection extravaganza commenced with meticulous extraction from databases of the Environmental Protection Agency and the Energy Information Administration, serving as our trusty treasure maps in this odyssey of discovery. Utilizing data spanning from 1981 to 2021, we delved into the depths of cyberspace, navigating the digital seas in search of the elusive correlation.

In a series of events that might seem straight out of a detective novel, we immersed ourselves in the art of data wrangling, employing convolutional neural networks to sift through terabytes of information with the precision of a bloodhound on the scent of a curious case. Through an ingenious amalgamation of complex algorithms and a touch of good old-fashioned intuition, we meticulously sieved through the sea of data, uncovering patterns that had long eluded the grasp of conventional analysis. It was a bit like untangling a ball of yarn only to find a surprising cat's toy at its core – unexpected, yet undeniably thrilling.

Employing advanced statistical analyses, including linear regression models and Pearson correlation coefficients, we sought to gauge the strength and direction of the relationship between air pollution in Berlin and kerosene usage in Nepal. With each calculation and iteration, we dissected the data like expert puzzle solvers, assembling the pieces into a coherent picture that would ultimately reveal the surprising connection that had lain hidden in plain sight. Like a well-crafted dad joke, our methods combined meticulous precision with a dash of unexpected humor, keeping us on our toes as we navigated the maze of data.

Furthermore, we engaged in a rigorous exercise of sensitivity analysis, exploring the robustness of our findings across different time periods and sub-samples. This process was akin to adjusting the focus on a camera lens, honing in on the crux of the relationship while ensuring that our conclusions stood the test of time and circumstance. Much like a classic dad joke, our analyses aimed to deliver a punchline that left an indelible impression, giving credence to the surprising connection we had uncovered.

In the spirit of a scientific expedition, we acknowledge the limitations of our study, as no research endeavor is without its challenges and uncertainties. However, armed with our trusty statistical compass and a healthy dose of academic rigor, we ventured forth, poised to shed light on the curious link between air pollution and kerosene usage, knowing that we were about to embark on an intellectual journey that would both unravel mysteries and impart a healthy dose of scientific amusement.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1981 to 2021, you found a correlation 0.7416928, r-squared of 0.5501082, 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]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the world grapples with the far-reaching consequences of environmental degradation, it becomes increasingly vital to untangle the intricate web of interrelated factors contributing to air pollution. While much attention has been directed towards local sources of pollution, our study takes a truly global perspective, revealing a fascinating connection between distant locales – Berlin, New Hampshire, and Nepal. This unexpected correlation not only sheds light on the far-reaching implications of kerosene usage but also challenges conventional wisdom in environmental research.

Much like a well-timed dad joke, the connection between air pollution in Berlin and kerosene usage in Nepal sneaks up on us when we least expect it, leaving us both baffled and charmed. The quirkiness of this association underscores the need to delve deeper into the complex interactions between seemingly unrelated phenomena.
The picturesque town of Berlin, nestled in the White Mountains of New Hampshire, may seem worlds apart from the mountains of Nepal where kerosene is a common household fuel. However, as our study unveils, it appears that the winds of change are more far-reaching than initially assumed. The metaphorical winds are indeed blowing the unexpected connection of air pollution across continents, posing thought-provoking questions and opening new avenues for exploration.
While the correlation may seem akin to comparing apples to oranges, the statistical evidence proves otherwise, painting a vivid picture of a world intricately connected by environmental forces. It's akin to realizing that the apple actually did not fall far from the orange tree, leaving us to marvel at the interconnectedness of the world in a way that even Newton wouldn't have predicted.
As we venture deeper into this unexpected nexus, our paper not only aims to elucidate the correlation but also to highlight its staggering implications. Like a good old dad joke, it's time to tease apart the layers of this unexpected relationship, revealing the hidden punchline that has eluded us for so long. So, join us as we unwrap this surprising connection, for we are about to embark on a journey that will leave you both pondering and grinning at the marvels of our shared environmental tapestry.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of data from the Environmental Protection Agency and the Energy Information Administration revealed a strong positive correlation between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. The correlation coefficient of 0.7416928 and an r-squared of 0.5501082 for the period from 1981 to 2021 unequivocally demonstrates the association between these seemingly distant phenomena.

Fig. 1 presents a scatterplot illustrating the robust relationship between air pollution in Berlin and the use of kerosene in Nepal. The data points hug the trend line as closely as a bear hug, leaving little room for doubt about the compelling connection between the two variables.

It's truly a gas to see such a strong correlation emerge between air pollution in Berlin and kerosene usage in Nepal, proving that when it comes to environmental impacts, the world is indeed smaller than we think.

The statistical significance of the correlation, with a p-value less than 0.01, further solidifies the unexpected nexus between these two geographically distant areas. This revelation prompts a reevaluation of our understanding of the global reach of environmental influences, reminding us that even across continents, our actions and choices are intimately intertwined.

The discovery of this unlikely link serves as a reminder that in the intricate tapestry of environmental phenomena, there are hidden threads that connect the seemingly unconnected. It's like finding out that your neighbor's cat and your best friend's dog are actually distant cousins – a surprising revelation that forces us to rethink our assumptions and consider the broader implications of seemingly isolated activities.

In summary, our findings not only unveil a remarkable correlation between air pollution in Berlin and kerosene consumption in Nepal, but they also beckon us to explore the myriad ways in which our choices reverberate across the globe. Like a well-crafted dad joke, this unexpected connection adds an element of surprise and delight to the otherwise somber landscape of environmental research.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

[[LITERATURE REVIEW]]
In "Air Pollution in Urban Environments," Smith et al. examined the various contributors to air pollution in urban centers, highlighting the impact of industrial activities, vehicular emissions, and biomass burning. Similarly, Doe and Jones, in "The Global Impact of Household Fuel Use," delved into the widespread use of kerosene in developing countries, emphasizing its implications for indoor and outdoor air quality.
It's an enlightening read, really shedding some light! Speaking of shedding light, did you hear about the guy who invented Lifesavers? He made a mint!
Moving on, "Emissions and Their Effects on Atmospheric Composition" by Brown and Green provides comprehensive insight into the chemical composition of air pollutants and their effects on the atmosphere. Likewise, Black and White, in "The Household Energy Transition," delve into the shifting trends in household energy consumption, with a particular focus on the use of traditional fuels such as kerosene.
It's almost like these authors are crafting a narrative as captivating as a Dickens novel. Speaking of, isn't it ironic how Charles Dickens' "Great Expectations" could apply to our lofty hopes of solving environmental issues?
On a slightly different note, "Breaking Bad" and "Alaska: The Last Frontier" are two television series that offer a glimpse into the daily lives of individuals facing environmental challenges, albeit in drastically different settings. As researchers, we found valuable insights in these shows, even if we had to endure a few eye-rolling moments at the same time.
But, wait, there's more! "Dune" by Frank Herbert and "Into Thin Air" by Jon Krakauer, although works of fiction, provided us with a fresh perspective on environmental extremes and the unforeseen consequences of human activities. These books ignited our imaginations and made us ponder the unexpected connections that permeate the natural world, mirroring our own investigation into the Berlin-Nepal correlation.
This literature review brings to light the diverse strands of research that have woven the fabric of our understanding of air pollution and energy consumption. As we dig deeper into the unexpected relationship between air pollution in Berlin, New Hampshire, and kerosene usage in Nepal, we are reminded that even in the world of academia, a well-placed joke can breathe life into our scholarly pursuits.

[[RESULTS]]
The analysis of data from the Environmental Protection Agency and the Energy Information Administration revealed a strong positive correlation between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. The correlation coefficient of 0.7416928 and an r-squared of 0.5501082 for the period from 1981 to 2021 unequivocally demonstrates the association between these seemingly distant phenomena.
Fig. 1 presents a scatterplot illustrating the robust relationship between air pollution in Berlin and the use of kerosene in Nepal. The data points hug the trend line as closely as a bear hug, leaving little room for doubt about the compelling connection between the two variables.
It's truly a gas to see such a strong correlation emerge between air pollution in Berlin and kerosene usage in Nepal, proving that when it comes to environmental impacts, the world is indeed smaller than we think.
The statistical significance of the correlation, with a p-value less than 0.01, further solidifies the unexpected nexus between these two geographically distant areas. This revelation prompts a reevaluation of our understanding of the global reach of environmental influences, reminding us that even across continents, our actions and choices are intimately intertwined.
The discovery of this unlikely link serves as a reminder that in the intricate tapestry of environmental phenomena, there are hidden threads that connect the seemingly unconnected. It's like finding out that your neighbor's cat and your best friend's dog are actually distant cousins – a surprising revelation that forces us to rethink our assumptions and consider the broader implications of seemingly isolated activities.
In summary, our findings not only unveil a remarkable correlation between air pollution in Berlin and kerosene consumption in Nepal, but they also beckon us to explore the myriad ways in which our choices reverberate across the globe. Like a well-crafted dad joke, this unexpected connection adds an element of surprise and delight to the otherwise somber landscape of environmental research.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The striking correlation between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal has left us in awe, akin to the feeling of stumbling upon a well-timed pun. Our results not only bolster previous research, but they also unearth a connection that has eluded the scrutiny of environmental scholars.

Our findings echo the sentiments of Smith et al. and Doe and Jones, shedding light on the substantial impact of household fuel use on outdoor air quality. Just like a good dad joke, the correlation coefficient of 0.7416928 and the p-value less than 0.01 for the years from 1981 to 2021 pack a punch, leaving little room for doubt about the significance of this relationship.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. The correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021 shed light on a connection previously overlooked, much like a clever play on words that unexpectedly resonates with the audience.

Our study serves as a reminder that in the intricate tapestry of environmental influences, there are hidden threads that connect the seemingly unconnected. It's like finding out that your neighbor's cat and your best friend's dog are actually distant cousins – a surprising revelation that forces us to rethink our assumptions and consider the broader implications of seemingly isolated activities. Just as a well-crafted dad joke adds an element of surprise and delight, this unexpected connection beckons us to explore the myriad ways in which our choices reverberate across the globe.

In the context of kerosene usage in Nepal and its impact on air quality in Berlin, this study demonstrates the ubiquitous influence of human activities on environmental conditions. It's a kerosene-cidence that such an unexpected relationship exists, underscoring the interconnectedness of global phenomena and prompting a nuanced understanding of the far-reaching consequences of seemingly local decisions.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Air pollution in Berlin, New Hampshire and Kerosene used in Nepal. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 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]]
"From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene"

[[ABSTRACT]]
In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.

Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.

As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

[[INTRDUCTION]]
As the world grapples with the far-reaching consequences of environmental degradation, it becomes increasingly vital to untangle the intricate web of interrelated factors contributing to air pollution. While much attention has been directed towards local sources of pollution, our study takes a truly global perspective, revealing a fascinating connection between distant locales – Berlin, New Hampshire, and Nepal. This unexpected correlation not only sheds light on the far-reaching implications of kerosene usage but also challenges conventional wisdom in environmental research.

Much like a well-timed dad joke, the connection between air pollution in Berlin and kerosene usage in Nepal sneaks up on us when we least expect it, leaving us both baffled and charmed. The quirkiness of this association underscores the need to delve deeper into the complex interactions between seemingly unrelated phenomena.
The picturesque town of Berlin, nestled in the White Mountains of New Hampshire, may seem worlds apart from the mountains of Nepal where kerosene is a common household fuel. However, as our study unveils, it appears that the winds of change are more far-reaching than initially assumed. The metaphorical winds are indeed blowing the unexpected connection of air pollution across continents, posing thought-provoking questions and opening new avenues for exploration.
While the correlation may seem akin to comparing apples to oranges, the statistical evidence proves otherwise, painting a vivid picture of a world intricately connected by environmental forces. It's akin to realizing that the apple actually did not fall far from the orange tree, leaving us to marvel at the interconnectedness of the world in a way that even Newton wouldn't have predicted.
As we venture deeper into this unexpected nexus, our paper not only aims to elucidate the correlation but also to highlight its staggering implications. Like a good old dad joke, it's time to tease apart the layers of this unexpected relationship, revealing the hidden punchline that has eluded us for so long. So, join us as we unwrap this surprising connection, for we are about to embark on a journey that will leave you both pondering and grinning at the marvels of our shared environmental tapestry.

[[RESULTS]]
The analysis of data from the Environmental Protection Agency and the Energy Information Administration revealed a strong positive correlation between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. The correlation coefficient of 0.7416928 and an r-squared of 0.5501082 for the period from 1981 to 2021 unequivocally demonstrates the association between these seemingly distant phenomena.
Fig. 1 presents a scatterplot illustrating the robust relationship between air pollution in Berlin and the use of kerosene in Nepal. The data points hug the trend line as closely as a bear hug, leaving little room for doubt about the compelling connection between the two variables.
It's truly a gas to see such a strong correlation emerge between air pollution in Berlin and kerosene usage in Nepal, proving that when it comes to environmental impacts, the world is indeed smaller than we think.
The statistical significance of the correlation, with a p-value less than 0.01, further solidifies the unexpected nexus between these two geographically distant areas. This revelation prompts a reevaluation of our understanding of the global reach of environmental influences, reminding us that even across continents, our actions and choices are intimately intertwined.
The discovery of this unlikely link serves as a reminder that in the intricate tapestry of environmental phenomena, there are hidden threads that connect the seemingly unconnected. It's like finding out that your neighbor's cat and your best friend's dog are actually distant cousins – a surprising revelation that forces us to rethink our assumptions and consider the broader implications of seemingly isolated activities.
In summary, our findings not only unveil a remarkable correlation between air pollution in Berlin and kerosene consumption in Nepal, but they also beckon us to explore the myriad ways in which our choices reverberate across the globe. Like a well-crafted dad joke, this unexpected connection adds an element of surprise and delight to the otherwise somber landscape of environmental research.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unmasked an extraordinary correlation between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. This unexpected relationship, akin to discovering that the chicken really did come before the egg, has profound implications for our understanding of global environmental dynamics.

The statistical rigor of our findings, accompanied by a correlation coefficient of 0.7416928 and a p-value less than 0.01, leaves little room for doubt about the robust intertwining of these seemingly distant factors. It's truly remarkable how a small change in one part of the world, like switching to cleaner energy sources in Nepal, can ripple across the globe and impact air quality in a picturesque town like Berlin, New Hampshire. Talk about a twist in the wind!

Our study underscores the need for a broader perspective on environmental research, one that recognizes the intricate interplay between diverse regions and their distinct environmental behaviors. It's not just a drop in the ocean – every action, no matter how small or seemingly isolated, can send ripples through the atmosphere, much like a stone creating circles in a pond.

As we reflect on this unexpected convergence, it brings to mind an old dad joke - "Why do environmental researchers always carry a map? Because they like to envision the world as one big, interconnected playground!" Our findings emphasize the mirthful yet profound reality that the choices we make, whether in Nepal or New Hampshire, hold the power to shape the air we all share.

With that said, we assert confidently that further research is not needed in this area. The results of this study have uncovered a connection that is not only statistically robust but also conceptually enlightening. It's time for us to take this revelation and spread it around like clean air – because, after all, when it comes to the environment, knowledge is the wind beneath our wings.


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 From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Ecological Connections


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 From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Environmental Alchemy and Global Connections


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 From Berlin to Nepal: The Unexpected Connection Between Air Pollution and Kerosene with an abstract of In this study, we delve into the unforeseen connection between air pollution in Berlin, New Hampshire, and the consumption of kerosene in Nepal. Armed with data from the Environmental Protection Agency and the Energy Information Administration, our research scrutinizes the correlation between these seemingly disparate factors. Lo and behold, we discovered a correlation coefficient of 0.7416928 and a p-value less than 0.01 for the years spanning 1981 to 2021.
Venturing into uncharted territories, we sought to unearth the mystery behind this unlikely link. Much to our surprise, the results revealed a compelling relationship that would leave even the most seasoned researchers gasping for breath. Our findings underscore the impact of kerosene usage in Nepal on the air quality in Berlin, New Hampshire, shedding light on a connection previously overlooked.
As we embarked on this quest for knowledge, we couldn't help but marvel at the convergence of these two distant entities. It's a kerosene-cidence that such an unexpected relationship exists, providing a fresh perspective in the realm of environmental research. Buoyed by these revelations, we invite fellow researchers to join us in unraveling the intricate web of interconnected global phenomena.

ChatGPT:

air pollution, kerosene consumption, correlation, Environmental Protection Agency, Energy Information Administration, Nepal, Berlin, New Hampshire, correlation coefficient, p-value, 1981-2021, environmental research, global phenomena

*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

Air pollution in Berlin, New Hampshire
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Berlin, NH-VT
Source: Environmental Protection Agency
See what else correlates with Air pollution in Berlin, New Hampshire

Kerosene used in Nepal
Detailed data title: Volume of kerosene used consumed in Nepal in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Nepal

Correlation r = 0.7416928 (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 = 0.5501082 (Coefficient of determination)
This means 55% of the change in the one variable (i.e., Kerosene used in Nepal) is predictable based on the change in the other (i.e., Air pollution in Berlin, New Hampshire) over the 41 years from 1981 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.9E-8. 0.0000000288882315643510350000
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 0.74 in 2.9E-6% of random cases. Said differently, if you correlated 34,616,172 random variables You don't actually need 34 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 40 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 40 because we have two variables measured over a period of 41 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.

[ 0.56, 0.85 ] 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.
19811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Air pollution in Berlin, New Hampshire (Bad air quality days)0.02312140.03225810.01030930.01376150.006688960.002857140.017751500.0028985500.04651160.01779360.03428570.03932580.07017540.06211180.06285710.0355030.09178740.004950490.07281550.08636360.05714290.04471540.0573770.01224490.06198350.03846150.003289470.01381220.005617980.01095890.0054794500.0197740.01095890.008426970.0110701000.00555556
Kerosene used in Nepal (Million Barrels/Day)0.5774930.8662390.8662390.8662390.7218661.11.31.21.41.51.7222.32.33455.85.343426.438145.802796.332254.752054.765073.176712.499011.288330.8683010.7200550.6776990.4012840.3176710.3176710.2329580.3168030.3600270.4023840.3041640.2882960.297701




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. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




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([0.0231214,0.0322581,0.0103093,0.0137615,0.00668896,0.00285714,0.0177515,0,0.00289855,0,0.0465116,0.0177936,0.0342857,0.0393258,0.0701754,0.0621118,0.0628571,0.035503,0.0917874,0.00495049,0.0728155,0.0863636,0.0571429,0.0447154,0.057377,0.0122449,0.0619835,0.0384615,0.00328947,0.0138122,0.00561798,0.0109589,0.00547945,0,0.019774,0.0109589,0.00842697,0.0110701,0,0,0.00555556,])
array_2 = np.array([0.577493,0.866239,0.866239,0.866239,0.721866,1.1,1.3,1.2,1.4,1.5,1.7,2,2,2.3,2.3,3,4,5,5.8,5.34342,6.43814,5.80279,6.33225,4.75205,4.76507,3.17671,2.49901,1.28833,0.868301,0.720055,0.677699,0.401284,0.317671,0.317671,0.232958,0.316803,0.360027,0.402384,0.304164,0.288296,0.297701,])
array_1_name = "Air pollution in Berlin, New Hampshire"
array_2_name = "Kerosene used in Nepal"

# 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?

Your rating is pure awesomeness!


Correlation ID: 3638 · Black Variable ID: 21506 · Red Variable ID: 24733
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0