Spurious correlation #4,948 · 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 Anchorage and the second variable is Kerosene used in U.S. Pacific Islands. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Anchorage and the second variable is Kerosene used in U.S. Pacific Islands. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air over Anchorage cleared up, it created a high-pressure system of pristine atmosphere. This atmospheric high five traveled all the way to the Pacific Islands, leading to a decreased demand for kerosene lamps, and leaving the islands lit in more ways than one!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a serene landscape featuring the city of Anchorage with crystal-clear air overhead. Show the transition as the high-pressure system travels to the U.S. Pacific Islands, where the islands are brightly illuminated with electric lights, replacing the need for kerosene lamps. This artwork should reflect a sense of clarity, brightness, and progress, representing the positive impact of improved air quality on the islands' lighting. 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 Anchorage and Kerosene used in U.S. Pacific Islands. 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: Cybernetic art Low poly Hyper-realistic Psychedelic Data cyber art
ChatGPT: Data cyber art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in Anchorage and Kerosene used in U.S. Pacific Islands, in the following situation: As the air over Anchorage cleared up, it created a high-pressure system of pristine atmosphere. This atmospheric high five traveled all the way to the Pacific Islands, leading to a decreased demand for kerosene lamps, and leaving the islands lit in more ways than one!. Keep the description simple.
ChatGPT: The air over Anchorage clears up, creating a pristine high-pressure system. It then travels to the U.S. Pacific Islands, where the decreased demand for kerosene lamps leaves the islands brightly lit in more ways than one.

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: [ Data cyber art ] and depicting this scene: The air over Anchorage clears up, creating a pristine high-pressure system. It then travels to the U.S. Pacific Islands, where the decreased demand for kerosene lamps leaves the islands brightly lit in more ways than one. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a serene landscape featuring the city of Anchorage with crystal-clear air overhead. Show the transition as the high-pressure system travels to the U.S. Pacific Islands, where the islands are brightly illuminated with electric lights, replacing the need for kerosene lamps. This artwork should reflect a sense of clarity, brightness, and progress, representing the positive impact of improved air quality on the islands' lighting.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in Anchorage caused Kerosene used in U.S. Pacific Islands to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

From Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene

The Journal of Atmospheric Chemis-Tree

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Anchorage and Kerosene used in U.S. Pacific Islands. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"From Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene"

[[ABSTRACT]]
In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
In the realm of scientific inquiry, there are moments when the unexpected becomes the norm, the perplexing becomes the predictable, and the downright bizarre becomes, well, a research paper. Today, dear readers, we find ourselves standing at the crossroads of bewildering correlations and mind-boggling connections as we delve into the intriguing relationship between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Yes, you read that right - we're about to untangle the air-link between these seemingly unrelated entities.
As we strap on our statistical snorkels and dive into the sea of data, we can't help but marvel at the sheer audacity of this research endeavor. It's not every day that one gets the opportunity to explore the dynamic interplay between air pollutants and kerosene across vast distances. The mere thought of air molecules sailing through the crisp Alaskan air, only to be joined by kerosene molecules wafting through the tropical breeze of the Pacific Islands, is enough to make even the most stoic researcher crack a smile.
But fear not, fellow adventurers of academia, for we are not embarking on this journey unprepared. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we are equipped to navigate the tumultuous waters of regression analysis, hypothesis testing, and all manner of statistical shenanigans. It's a bit like trying to predict the weather using only a rubber duck and a magic eight ball - equal parts challenging and delightfully absurd.
And what, you may ask, were our intrepid findings in this whimsical escapade? Brace yourself for the revelation of a remarkably robust correlation coefficient of 0.8607575, accompanied by a p-value so minuscule it would make even the most cautious statistician raise an eyebrow. If that doesn't pique your interest, I hear there's a statistically significant relationship between the number of statistical tests performed and the likelihood of developing a sudden craving for a hearty bowl of alphabet soup.
Now, as we navigate through the pages of this paper, prepare yourself for a scientific rollercoaster ride unlike any other. We invite you to join us in unraveling the enigmatic dance of air pollutants and kerosene, from the chilly embrace of the Alaskan atmosphere to the balmy caress of the Pacific Island skies. After all, where else can you witness the statistical waltz of variables while simultaneously pondering the existential implications of a particularly perplexing scatter plot?
So, buckle up, hold onto your hypothesis, and get ready to embark on a journey that will not only expand your scientific horizons but also leave you with a newfound appreciation for the whimsical wonders of statistical exploration.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The literature on the connection between air pollution in Anchorage and kerosene usage in the U.S. Pacific Islands is as varied and peculiar as the relationship itself. Smith et al. (2010) highlighted the environmental impact of air pollution in urban areas, paying particular attention to the unique challenges faced in Alaskan settings. Meanwhile, Doe and Jones (2015) delved into the intricate web of energy consumption patterns in Pacific Island nations, offering insights into the multifaceted nature of fuel sources.

However, as we venture deeper into the realm of scholarly inquiry, it becomes apparent that our journey is about to take an unexpected turn. In "Lorem Ipsum: The Bizarre Case of Atmospheric Alchemy" (2020), the authors lay the groundwork for a whimsical interpretation of air pollutants and their potential for intercontinental travel. They propose a theory so outrageous it might just make you reconsider your stance on the transboundary movement of atmospheric compounds.

The plot thickens as we encounter "Kerosene Chronicles: From Anchorage to Aloha" (2013), a non-fiction work that promises to unravel the enigmatic narrative of kerosene's oceanic odyssey. The authors, H. G. Wells and Jules Verne (yes, that H. G. Wells and Jules Verne), draw parallels between kerosene molecules and intrepid adventurers, painting a picture of seafaring escapades that will leave you questioning the very fabric of reality.

In a surprising twist, the literature veers into the realm of fiction with "The Mystical Chemistry of Alaskan Air" (2017). This novel, written by an anonymous author known only as "The Mad Scientist of the Tundra," weaves a tale of love, betrayal, and chemical reactions in the sub-zero temperatures of Anchorage. While it may be light on empirical evidence, it certainly does not lack in imaginative flair.

Turning to the virtual realm, we find ourselves confronted with a meme that has taken the internet by storm - the "Kerosene Wave." This viral sensation features a playful reimagining of kerosene molecules riding the waves of the Pacific, complete with sunglasses and tiny umbrellas. While its scientific accuracy may be questionable, its ability to spark joy is undeniable.

As we wade through this whimsical assortment of literature, one thing becomes abundantly clear: the air-link between air pollution in Anchorage and kerosene usage in the U.S. Pacific Islands is a peculiar and captivating phenomenon. It beckons us to navigate the quirky corridors of scientific investigation with a sense of wonder and a healthy dose of humor. So, dear reader, fasten your seatbelt and prepare for a research journey unlike any other - where the ordinary becomes extraordinary and the mundane transforms into marvel.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Anchorage and Kerosene used in U.S. Pacific Islands. 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 Environmental Protection Agency and Energy Information Administration . You used data from 1980 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 Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene"

[[ABSTRACT]]
In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

[[INTRODUCTION]]
Introduction
In the realm of scientific inquiry, there are moments when the unexpected becomes the norm, the perplexing becomes the predictable, and the downright bizarre becomes, well, a research paper. Today, dear readers, we find ourselves standing at the crossroads of bewildering correlations and mind-boggling connections as we delve into the intriguing relationship between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Yes, you read that right - we're about to untangle the air-link between these seemingly unrelated entities.
As we strap on our statistical snorkels and dive into the sea of data, we can't help but marvel at the sheer audacity of this research endeavor. It's not every day that one gets the opportunity to explore the dynamic interplay between air pollutants and kerosene across vast distances. The mere thought of air molecules sailing through the crisp Alaskan air, only to be joined by kerosene molecules wafting through the tropical breeze of the Pacific Islands, is enough to make even the most stoic researcher crack a smile.
But fear not, fellow adventurers of academia, for we are not embarking on this journey unprepared. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we are equipped to navigate the tumultuous waters of regression analysis, hypothesis testing, and all manner of statistical shenanigans. It's a bit like trying to predict the weather using only a rubber duck and a magic eight ball - equal parts challenging and delightfully absurd.
And what, you may ask, were our intrepid findings in this whimsical escapade? Brace yourself for the revelation of a remarkably robust correlation coefficient of 0.8607575, accompanied by a p-value so minuscule it would make even the most cautious statistician raise an eyebrow. If that doesn't pique your interest, I hear there's a statistically significant relationship between the number of statistical tests performed and the likelihood of developing a sudden craving for a hearty bowl of alphabet soup.
Now, as we navigate through the pages of this paper, prepare yourself for a scientific rollercoaster ride unlike any other. We invite you to join us in unraveling the enigmatic dance of air pollutants and kerosene, from the chilly embrace of the Alaskan atmosphere to the balmy caress of the Pacific Island skies. After all, where else can you witness the statistical waltz of variables while simultaneously pondering the existential implications of a particularly perplexing scatter plot?
So, buckle up, hold onto your hypothesis, and get ready to embark on a journey that will not only expand your scientific horizons but also leave you with a newfound appreciation for the whimsical wonders of statistical exploration.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To undertake the daunting task of unraveling the mystical connection between air pollution in Anchorage and the consumption of kerosene in the U.S. Pacific Islands, our research team embarked on an odyssey of data collection, statistical analysis, and a touch of whimsy. Our primary data sources included the Environmental Protection Agency (EPA), which provided a treasure trove of air pollution data, and the Energy Information Administration (EIA), which furnished us with valuable insights into kerosene consumption. After arming ourselves with an ample supply of geeky science jokes and a robust arsenal of statistical tools, we set sail through the murky seas of correlation, regression, and hypothesis testing.

First and foremost, we dived into the EPA's air quality data for Anchorage, Alaska, from 1980 to 2021. Armed with spreadsheets and a periscope for clarity, we meticulously combed through the atmospheric measurements of pollutants, capturing everything from nitrogen dioxide to suspended particulate matter. It was a bit like searching for a floating penguin in a sea of statistical icebergs, but we emerged victorious with a comprehensive dataset that would make even the most intrepid data miner nod in approval.

Simultaneously, we turned our attention to the EIA's records of kerosene consumption in the U.S. Pacific Islands. As we navigated through decades of energy statistics, we couldn't help but marvel at the sheer variety of kerosene-related insights at our disposal. From the flickering glow of kerosene lamps to the rhythmic hum of jet fuel consumption, we encountered a dazzling array of data points that would have made even the most stoic statistician raise an eyebrow in sheer curiosity.

With our datasets in tow, we found ourselves at the crossroads of regression analysis, where we crafted a mathematical symphony to explore the relationship between air pollution in Anchorage and kerosene consumption in the U.S. Pacific Islands. Employing the majestic powers of correlation coefficients, scatter plots, and p-values, we summoned the statistical spirits to unveil the enigmatic dance of air pollutants and kerosene molecules.

Our statistical odyssey led us to the astonishing revelation of a correlation coefficient of 0.8607575, accompanied by a p-value so minuscule it would have made even the most skeptical statistician crack a wry smile. This prodigious correlation signified a robust connection between the atmospheric nuances of Anchorage and the kerosene-laden winds that traversed the Pacific, affirming the unexpected bond between these disparate elements.

In summary, our methodology was a daring expedition through the labyrinthine paths of data collection, statistical analysis, and a sprinkle of statistical sorcery, resulting in the revelation of an astonishing correlation between air pollution in Anchorage and kerosene consumption in the U.S. Pacific Islands. Join us in celebrating the whimsical wonders of scientific discovery, where each statistical test serves as a stepping stone to unraveling the quirky mysteries of our world.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Anchorage and Kerosene used in U.S. Pacific Islands. 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 Environmental Protection Agency and Energy Information Administration .

For the time period 1980 to 2021, you found a correlation 0.8607575, r-squared of 0.7409035, 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 Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene"

[[ABSTRACT]]
In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
In the realm of scientific inquiry, there are moments when the unexpected becomes the norm, the perplexing becomes the predictable, and the downright bizarre becomes, well, a research paper. Today, dear readers, we find ourselves standing at the crossroads of bewildering correlations and mind-boggling connections as we delve into the intriguing relationship between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Yes, you read that right - we're about to untangle the air-link between these seemingly unrelated entities.
As we strap on our statistical snorkels and dive into the sea of data, we can't help but marvel at the sheer audacity of this research endeavor. It's not every day that one gets the opportunity to explore the dynamic interplay between air pollutants and kerosene across vast distances. The mere thought of air molecules sailing through the crisp Alaskan air, only to be joined by kerosene molecules wafting through the tropical breeze of the Pacific Islands, is enough to make even the most stoic researcher crack a smile.
But fear not, fellow adventurers of academia, for we are not embarking on this journey unprepared. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we are equipped to navigate the tumultuous waters of regression analysis, hypothesis testing, and all manner of statistical shenanigans. It's a bit like trying to predict the weather using only a rubber duck and a magic eight ball - equal parts challenging and delightfully absurd.
And what, you may ask, were our intrepid findings in this whimsical escapade? Brace yourself for the revelation of a remarkably robust correlation coefficient of 0.8607575, accompanied by a p-value so minuscule it would make even the most cautious statistician raise an eyebrow. If that doesn't pique your interest, I hear there's a statistically significant relationship between the number of statistical tests performed and the likelihood of developing a sudden craving for a hearty bowl of alphabet soup.
Now, as we navigate through the pages of this paper, prepare yourself for a scientific rollercoaster ride unlike any other. We invite you to join us in unraveling the enigmatic dance of air pollutants and kerosene, from the chilly embrace of the Alaskan atmosphere to the balmy caress of the Pacific Island skies. After all, where else can you witness the statistical waltz of variables while simultaneously pondering the existential implications of a particularly perplexing scatter plot?
So, buckle up, hold onto your hypothesis, and get ready to embark on a journey that will not only expand your scientific horizons but also leave you with a newfound appreciation for the whimsical wonders of statistical exploration.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The results of our whimsical escapade into the land of statistical sorcery have unveiled a correlation coefficient that would make even the most skeptical of researchers raise an intrigued eyebrow. We found a remarkably strong correlation of 0.8607575 between air pollution in Anchorage and kerosene consumption in the U.S. Pacific Islands for the time period spanning 1980 to 2021. This correlation was further bolstered by an r-squared value of 0.7409035, confirming that the relationship between these two seemingly disparate variables was no statistical fluke.

Now, if you'll direct your attention to the intrigue-laden Fig. 1, you will behold a scatterplot so entwined with the dance of correlation that it might just leave you pondering the existential implications of a particularly perplexing plot twist. In this scatterplot, the data points exhibit a visually striking alignment, as though the molecules of air pollution and kerosene were engaged in a synchronized waltz across the canvas of statistical exploration – a sight to behold, indeed.

It seems that the tale of air pollutants and kerosene is one of unexpected harmony, akin to a scientific symphony that transcends the boundaries of geographic expanse. The statistical evidence we uncovered serves as a reminder that in the realm of research, the most offbeat connections can often lead to the most enlightening discoveries. So, as we bid adieu to this peculiar rendezvous between air pollution and kerosene, we are left not only with a robust correlation coefficient but also with a newfound appreciation for the whimsical wonders of statistical exploration.

In conclusion, our findings paint a picture of a world where air pollutants and kerosene engage in an uncharted tango, defying the conventional constraints of geographical separation. As we close this chapter of our scientific sojourn, we invite fellow enthusiasts of statistical shenanigans to marvel at the unexpected connections that await in the unlikeliest of places. After all, who knows what other curious correlations lie in wait, ready to unravel the fabric of our scientific understanding with their own peculiar brand of statistical charm.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Anchorage and Kerosene used in U.S. Pacific Islands. 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]]
"From Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene"

[[ABSTRACT]]
In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

[[LITERATURE REVIEW]]
The literature on the connection between air pollution in Anchorage and kerosene usage in the U.S. Pacific Islands is as varied and peculiar as the relationship itself. Smith et al. (2010) highlighted the environmental impact of air pollution in urban areas, paying particular attention to the unique challenges faced in Alaskan settings. Meanwhile, Doe and Jones (2015) delved into the intricate web of energy consumption patterns in Pacific Island nations, offering insights into the multifaceted nature of fuel sources.
However, as we venture deeper into the realm of scholarly inquiry, it becomes apparent that our journey is about to take an unexpected turn. In "Lorem Ipsum: The Bizarre Case of Atmospheric Alchemy" (2020), the authors lay the groundwork for a whimsical interpretation of air pollutants and their potential for intercontinental travel. They propose a theory so outrageous it might just make you reconsider your stance on the transboundary movement of atmospheric compounds.
The plot thickens as we encounter "Kerosene Chronicles: From Anchorage to Aloha" (2013), a non-fiction work that promises to unravel the enigmatic narrative of kerosene's oceanic odyssey. The authors, H. G. Wells and Jules Verne (yes, that H. G. Wells and Jules Verne), draw parallels between kerosene molecules and intrepid adventurers, painting a picture of seafaring escapades that will leave you questioning the very fabric of reality.
In a surprising twist, the literature veers into the realm of fiction with "The Mystical Chemistry of Alaskan Air" (2017). This novel, written by an anonymous author known only as "The Mad Scientist of the Tundra," weaves a tale of love, betrayal, and chemical reactions in the sub-zero temperatures of Anchorage. While it may be light on empirical evidence, it certainly does not lack in imaginative flair.
Turning to the virtual realm, we find ourselves confronted with a meme that has taken the internet by storm - the "Kerosene Wave." This viral sensation features a playful reimagining of kerosene molecules riding the waves of the Pacific, complete with sunglasses and tiny umbrellas. While its scientific accuracy may be questionable, its ability to spark joy is undeniable.
As we wade through this whimsical assortment of literature, one thing becomes abundantly clear: the air-link between air pollution in Anchorage and kerosene usage in the U.S. Pacific Islands is a peculiar and captivating phenomenon. It beckons us to navigate the quirky corridors of scientific investigation with a sense of wonder and a healthy dose of humor. So, dear reader, fasten your seatbelt and prepare for a research journey unlike any other - where the ordinary becomes extraordinary and the mundane transforms into marvel.

[[RESULTS]]
The results of our whimsical escapade into the land of statistical sorcery have unveiled a correlation coefficient that would make even the most skeptical of researchers raise an intrigued eyebrow. We found a remarkably strong correlation of 0.8607575 between air pollution in Anchorage and kerosene consumption in the U.S. Pacific Islands for the time period spanning 1980 to 2021. This correlation was further bolstered by an r-squared value of 0.7409035, confirming that the relationship between these two seemingly disparate variables was no statistical fluke.
Now, if you'll direct your attention to the intrigue-laden Fig. 1, you will behold a scatterplot so entwined with the dance of correlation that it might just leave you pondering the existential implications of a particularly perplexing plot twist. In this scatterplot, the data points exhibit a visually striking alignment, as though the molecules of air pollution and kerosene were engaged in a synchronized waltz across the canvas of statistical exploration – a sight to behold, indeed.
It seems that the tale of air pollutants and kerosene is one of unexpected harmony, akin to a scientific symphony that transcends the boundaries of geographic expanse. The statistical evidence we uncovered serves as a reminder that in the realm of research, the most offbeat connections can often lead to the most enlightening discoveries. So, as we bid adieu to this peculiar rendezvous between air pollution and kerosene, we are left not only with a robust correlation coefficient but also with a newfound appreciation for the whimsical wonders of statistical exploration.
In conclusion, our findings paint a picture of a world where air pollutants and kerosene engage in an uncharted tango, defying the conventional constraints of geographical separation. As we close this chapter of our scientific sojourn, we invite fellow enthusiasts of statistical shenanigans to marvel at the unexpected connections that await in the unlikeliest of places. After all, who knows what other curious correlations lie in wait, ready to unravel the fabric of our scientific understanding with their own peculiar brand of statistical charm.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

In this zany and whimsical discussion section, we find ourselves at the intersection of statistical sorcery and scientific marvel. Our findings have cast a spotlight on the enigmatic connection between air pollution in Anchorage and the kerosene odyssey in the U.S. Pacific Islands, echoing the quirky sentiments expressed in the literature review.

Let's address the rather peculiar literature thread that introduced the notion of atmospheric alchemy and kerosene's oceanic odyssey with a pinch of seriousness. While "Lorem Ipsum: The Bizarre Case of Atmospheric Alchemy" may have initially seemed like a flight of fancy, our results align with its whimsical proposal of intercontinental atmospheric escapades. Similarly, the "Kerosene Chronicles: From Anchorage to Aloha" by the eminent duo H. G. Wells and Jules Verne, though seemingly outlandish, unexpectedly resonates with our empirical revelations of kerosene's journey across the waves.

Our correlation coefficient of 0.8607575, with a p-value of less than 0.01, serves as a resounding validation of the peculiar yet captivating notion of an air-link between Anchorage's atmospheric nuances and the kerosene-consumption patterns in the Pacific Islands. The literary dalliance with the improbable has found an unlikely ally in our statistical analysis, compelling us to ponder the unconventional yet compelling nature of this intercontinental narrative.

As we navigate the whimsical corridors of scientific inquiry, it becomes increasingly evident that our findings serve as a delightful testament to the unexpected harmonies that permeate the fabric of our statistical landscape. The visually striking alignment of data points in our scatterplot, akin to a synchronized waltz between air pollutants and kerosene, underlines the lyrical dance of correlation between these seemingly distant variables.

Our findings, coupled with the offbeat literature, beckon the scientific community to embrace the unconventional and cherish the peculiarities that thrive in the undercurrent of statistical exploration. Perhaps our encounter with the air-link between Anchorage's pollution and Pacific kerosene consumption serves as a whimsical reminder that beneath the surface of conventional correlation lies a world of uncharted statistical tango, ready to enthrall and astonish even the most skeptical of researchers.

With a nod to the absurd and a tip of the statistical hat to the whimsical, we bid adieu to this chapter of our research journey, eager to unravel the myriad of curious correlations that await. After all, in the realm of statistical shenanigans, who knows what peculiar charm the next set of variables may bring to our scientific symphony of discovery?

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Anchorage and Kerosene used in U.S. Pacific Islands. 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]]
"From Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene"

[[ABSTRACT]]
In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

[[INTRDUCTION]]
Introduction
In the realm of scientific inquiry, there are moments when the unexpected becomes the norm, the perplexing becomes the predictable, and the downright bizarre becomes, well, a research paper. Today, dear readers, we find ourselves standing at the crossroads of bewildering correlations and mind-boggling connections as we delve into the intriguing relationship between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Yes, you read that right - we're about to untangle the air-link between these seemingly unrelated entities.
As we strap on our statistical snorkels and dive into the sea of data, we can't help but marvel at the sheer audacity of this research endeavor. It's not every day that one gets the opportunity to explore the dynamic interplay between air pollutants and kerosene across vast distances. The mere thought of air molecules sailing through the crisp Alaskan air, only to be joined by kerosene molecules wafting through the tropical breeze of the Pacific Islands, is enough to make even the most stoic researcher crack a smile.
But fear not, fellow adventurers of academia, for we are not embarking on this journey unprepared. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we are equipped to navigate the tumultuous waters of regression analysis, hypothesis testing, and all manner of statistical shenanigans. It's a bit like trying to predict the weather using only a rubber duck and a magic eight ball - equal parts challenging and delightfully absurd.
And what, you may ask, were our intrepid findings in this whimsical escapade? Brace yourself for the revelation of a remarkably robust correlation coefficient of 0.8607575, accompanied by a p-value so minuscule it would make even the most cautious statistician raise an eyebrow. If that doesn't pique your interest, I hear there's a statistically significant relationship between the number of statistical tests performed and the likelihood of developing a sudden craving for a hearty bowl of alphabet soup.
Now, as we navigate through the pages of this paper, prepare yourself for a scientific rollercoaster ride unlike any other. We invite you to join us in unraveling the enigmatic dance of air pollutants and kerosene, from the chilly embrace of the Alaskan atmosphere to the balmy caress of the Pacific Island skies. After all, where else can you witness the statistical waltz of variables while simultaneously pondering the existential implications of a particularly perplexing scatter plot?
So, buckle up, hold onto your hypothesis, and get ready to embark on a journey that will not only expand your scientific horizons but also leave you with a newfound appreciation for the whimsical wonders of statistical exploration.

[[RESULTS]]
The results of our whimsical escapade into the land of statistical sorcery have unveiled a correlation coefficient that would make even the most skeptical of researchers raise an intrigued eyebrow. We found a remarkably strong correlation of 0.8607575 between air pollution in Anchorage and kerosene consumption in the U.S. Pacific Islands for the time period spanning 1980 to 2021. This correlation was further bolstered by an r-squared value of 0.7409035, confirming that the relationship between these two seemingly disparate variables was no statistical fluke.
Now, if you'll direct your attention to the intrigue-laden Fig. 1, you will behold a scatterplot so entwined with the dance of correlation that it might just leave you pondering the existential implications of a particularly perplexing plot twist. In this scatterplot, the data points exhibit a visually striking alignment, as though the molecules of air pollution and kerosene were engaged in a synchronized waltz across the canvas of statistical exploration – a sight to behold, indeed.
It seems that the tale of air pollutants and kerosene is one of unexpected harmony, akin to a scientific symphony that transcends the boundaries of geographic expanse. The statistical evidence we uncovered serves as a reminder that in the realm of research, the most offbeat connections can often lead to the most enlightening discoveries. So, as we bid adieu to this peculiar rendezvous between air pollution and kerosene, we are left not only with a robust correlation coefficient but also with a newfound appreciation for the whimsical wonders of statistical exploration.
In conclusion, our findings paint a picture of a world where air pollutants and kerosene engage in an uncharted tango, defying the conventional constraints of geographical separation. As we close this chapter of our scientific sojourn, we invite fellow enthusiasts of statistical shenanigans to marvel at the unexpected connections that await in the unlikeliest of places. After all, who knows what other curious correlations lie in wait, ready to unravel the fabric of our scientific understanding with their own peculiar brand of statistical charm.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In wrapping up this quirky expedition into the interplay of air pollution and Pacific Island kerosene consumption, we find ourselves with a statistical saga that could make even the most skeptical of researchers crack a bemused smile. The correlation coefficient of 0.8607575 and a p-value that's rarer than a statistically significant unicorn point to a relationship that's as strong as statistical coffee – bold, robust, and capable of keeping any hypothesis wide awake.

As we bid adieu to this statistical tango and head back to more conventional research endeavors, it's clear that the unexpected dance between Anchorage's air pollutants and kerosene from the Pacific Islands has left an indelible mark on our scientific sensibilities. We've witnessed a statistical waltz that puts even the most graceful dancers to shame, and it's a reminder that in the whimsical world of statistical exploration, the most seemingly unrelated entities can come together in a statistical pas de deux that leaves us pondering the strangest of correlations.

It's time to put the rubber duck of regression analysis and the magic eight ball of hypothesis testing back in their academic toy chest and bid adieu to this statistical rollercoaster. With a correlation so strong, it would make even the most seasoned statistician raise an impressed eyebrow, we can confidently assert that no further research in this field is needed. After all, we've unraveled the enigmatic dance of air pollutants and kerosene, and now, it's time for bolder statistical adventures to take the stage. Onward, to new statistical frontiers!

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 Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric Chemis-Tree

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 Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Airborne Environmental Research and Exploration (IIAERE)

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 Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene with an abstract of In this paper, we embark on a quest to unravel the mysterious connection between air pollution in Anchorage and the kerosene consumption in the U.S. Pacific Islands. Armed with data from the Environmental Protection Agency and the Energy Information Administration, we dive deep into the sea of statistical analysis to unearth the truth behind this puzzling relationship. Our findings reveal a remarkably strong correlation coefficient of 0.8607575, with a p-value of less than 0.01 for the years 1980 to 2021. Join us on this zany adventure as we shed light on the unexpected dance of air pollutants and kerosene in the air and across the waves.

ChatGPT:

Anchorage air pollution, Pacific kerosene consumption, pollution correlation analysis, Environmental Protection Agency data, Energy Information Administration data, air pollutants and kerosene, statistical analysis air pollution and kerosene

*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 Anchorage
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Anchorage, AK
Source: Environmental Protection Agency
See what else correlates with Air pollution in Anchorage

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

Correlation r = 0.8607575 (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 = 0.7409035 (Coefficient of determination)
This means 74.1% of the change in the one variable (i.e., Kerosene used in U.S. Pacific Islands) is predictable based on the change in the other (i.e., Air pollution in Anchorage) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.7E-13.^Show 0.0000000000002685345763785863
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.86 in 2.7E-11% of random cases. Said differently, if you correlated 3,723,915,234,626 random variables^Note You don't actually need 3 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 41 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 41 because we have two variables measured over a period of 42 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.

[ 0.75, 0.92 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	1980	1981	1982	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Air pollution in Anchorage (Bad air quality days)	12.8415	9.58904	12.6027	18.3562	10.929	5.75342	4.10959	2.58621	3.28767	2.27273	4.40771	1.64835	4.67033	2.76243	2.20994	1.37741	1.7094	0	0.828729	1.91693	0.327869	0.655738	0.657895	1.6129	0.651466	0.990099	1.2987	0.322581	0.320513	0.550964	1.36986	0.821918	1.36612	1.36986	3.56164	3.0137	1.0929	1.64384	1.09589	3.28767	0.273224	1.09589
Kerosene used in U.S. Pacific Islands (Million Barrels/Day)	0.1375	0.1375	0.1375	0.1375	0.125	0.1125	0.1	0.1	0.1	0.04235	0.04235	0.04235	0.04224	0.04235	0.04235	0.04235	0.04224	0.04235	0.04235	0.0423562	0.0422404	0.0423562	0.0423562	0.0423562	0.0422404	0.0423562	0.05	0.05	0.05	0.05	0.06	0.05	0.05	0.05	0.05	0.05	0.05	0.05	0.05	0.05	0.05	0.05

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([12.8415,9.58904,12.6027,18.3562,10.929,5.75342,4.10959,2.58621,3.28767,2.27273,4.40771,1.64835,4.67033,2.76243,2.20994,1.37741,1.7094,0,0.828729,1.91693,0.327869,0.655738,0.657895,1.6129,0.651466,0.990099,1.2987,0.322581,0.320513,0.550964,1.36986,0.821918,1.36612,1.36986,3.56164,3.0137,1.0929,1.64384,1.09589,3.28767,0.273224,1.09589,])
array_2 = np.array([0.1375,0.1375,0.1375,0.1375,0.125,0.1125,0.1,0.1,0.1,0.04235,0.04235,0.04235,0.04224,0.04235,0.04235,0.04235,0.04224,0.04235,0.04235,0.0423562,0.0422404,0.0423562,0.0423562,0.0423562,0.0422404,0.0423562,0.05,0.05,0.05,0.05,0.06,0.05,0.05,0.05,0.05,0.05,0.05,0.05,0.05,0.05,0.05,0.05,])
array_1_name = "Air pollution in Anchorage"
array_2_name = "Kerosene used in U.S. Pacific Islands"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in Anchorage
Line chart for only Kerosene used in U.S. Pacific Islands
AI-generated correlation image
The spurious research paper: From Anchorage to Aloha: Uncovering the Air-Link between Pollution and Pacific Kerosene

View another random correlation

How fun was this correlation?

I'm grateful for your review!

Correlation ID: 4948 · Black Variable ID: 20266 · Red Variable ID: 25027


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