about · email me · subscribe
Spurious correlation #4,752 · 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 San Francisco, California and the second variable is Kerosene used in United States.  The chart goes from 1980 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The fresh sea breeze in San Francisco was actually made up of tiny, microscopic environmental activists who were on a mission to clean up the air. As they dispersed throughout the city, they also organized peaceful protests in the form of air particles holding tiny signs that said "Cleaner Skies Now!" This sparked a chain reaction of positivity, leading to a nationwide movement where even the kerosene couldn't help but join in on reducing its own usage. It turns out, when it comes to cleaning up the environment, every little molecule matters!

Model: dalle-3
Prompt: Generate an image of a sleek, futuristic San Francisco skyline depicted as a beautiful coronal mass of golden light, with shimmering air particles giving off a bright, glowing aura. Within the skyline, tiny microscopic activists resembling luminescent, ethereal beings are seen dispersing into the city, along with air particles carrying miniature signs with the message "Cleaner Skies Now!" in a visually compelling and serene depiction. 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 San Francisco, California and Kerosene used in United States. 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: a funny image macro Realistic A TIME magazine cover image Brutalism Charcoal
ChatGPT: A TIME 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 San Francisco, California and Kerosene used in United States, in the following situation: The fresh sea breeze in San Francisco was actually made up of tiny, microscopic environmental activists who were on a mission to clean up the air. As they dispersed throughout the city, they also organized peaceful protests in the form of air particles holding tiny signs that said "Cleaner Skies Now!" This sparked a chain reaction of positivity, leading to a nationwide movement where even the kerosene couldn't help but join in on reducing its own usage. It turns out, when it comes to cleaning up the environment, every little molecule matters!. Keep the description simple.
ChatGPT: In San Francisco, tiny microscopic activists made up the sea breeze, dispersing throughout the city to clean the air. Air particles held miniature signs saying "Cleaner Skies Now!" In response, kerosene across the United States joined the movement, reducing its usage. Every molecule played a part in the environmental clean-up.

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 TIME magazine cover image ] and depicting this scene: In San Francisco, tiny microscopic activists made up the sea breeze, dispersing throughout the city to clean the air. Air particles held miniature signs saying "Cleaner Skies Now!" In response, kerosene across the United States joined the movement, reducing its usage. Every molecule played a part in the environmental clean-up. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a sleek, futuristic San Francisco skyline depicted as a beautiful coronal mass of golden light, with shimmering air particles giving off a bright, glowing aura. Within the skyline, tiny microscopic activists resembling luminescent, ethereal beings are seen dispersing into the city, along with air particles carrying miniature signs with the message "Cleaner Skies Now!" in a visually compelling and serene depiction.

*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 a decrease in Air pollution in San Francisco, California caused Kerosene used in United States to decrease.

AI academic paper

(Because p < 0.01)
Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States

The Journal of Atmospheric Alchemy

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 silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

Include a pun in the title.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.8266929 and p < 0.01 for 1980 to 2022.

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]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

Ladies and gentlemen, fasten your seatbelts and prepare for a bumpy yet delightful ride through the hazy clouds of air pollution and the flickering flames of kerosene consumption. Our study embarks on a whimsical journey to unravel the enchanting connection between these two seemingly unrelated phenomena. Like a magician's sleight of hand, the correlation we uncovered between air pollution in San Francisco and kerosene usage in the United States is nothing short of spellbinding.

As we delve into the depths of this atmospheric puzzle, we cannot help but marvel at the charming dance between data points and statistical analyses. We invite you to roam the smog-filled corridors of our findings, where correlation coefficients and p-values adorn the walls like shimmering mistletoe at a scientific soirée.

The relationship we uncovered between air pollution and kerosene consumption is reminiscent of a classic love story – one that makes you chuckle and scratch your head in equal measure. Picture this: the alluring mist of kerosene fumes softly embracing the swirling currents of San Francisco's air, like star-crossed lovers destined to entwine in a statistical tango. Our findings evoke both chuckles and contemplation as we tiptoe through the minefield of causal convolution, where every statistical significance is shrouded in p-value haze.

Join us as we embark on a curious quest to untangle this kerosene-coated conundrum, where the aroma of statistical significance intermingles with the faint scent of aviation fuel. Together, let us waltz through the unpredictable whirlwind of environmental factors, where every correlation is clouded with complexity and every insight is illuminated by the flickering glow of a kerosene lamp. This is not your average academic pursuit – it's a whimsical adventure through the alleyways of air pollution and kerosene consumption, where curiosity fuels our journey and data points guide our way.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
Ladies and gentlemen, fasten your seatbelts and prepare for a bumpy yet delightful ride through the hazy clouds of air pollution and the flickering flames of kerosene consumption. Our study embarks on a whimsical journey to unravel the enchanting connection between these two seemingly unrelated phenomena. Like a magician's sleight of hand, the correlation we uncovered between air pollution in San Francisco and kerosene usage in the United States is nothing short of spellbinding.
As we delve into the depths of this atmospheric puzzle, we cannot help but marvel at the charming dance between data points and statistical analyses. We invite you to roam the smog-filled corridors of our findings, where correlation coefficients and p-values adorn the walls like shimmering mistletoe at a scientific soirée.
The relationship we uncovered between air pollution and kerosene consumption is reminiscent of a classic love story – one that makes you chuckle and scratch your head in equal measure. Picture this: the alluring mist of kerosene fumes softly embracing the swirling currents of San Francisco's air, like star-crossed lovers destined to entwine in a statistical tango. Our findings evoke both chuckles and contemplation as we tiptoe through the minefield of causal convolution, where every statistical significance is shrouded in p-value haze.
Join us as we embark on a curious quest to untangle this kerosene-coated conundrum, where the aroma of statistical significance intermingles with the faint scent of aviation fuel. Together, let us waltz through the unpredictable whirlwind of environmental factors, where every correlation is clouded with complexity and every insight is illuminated by the flickering glow of a kerosene lamp. This is not your average academic pursuit – it's a whimsical adventure through the alleyways of air pollution and kerosene consumption, where curiosity fuels our journey and data points guide our way.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe (2018)," the authors find a significant positive correlation between air pollution in urban areas and kerosene consumption in the United States. This study provides a compelling basis for our exploration into the interconnected realms of atmospheric contamination and kerosene utilization. Building upon this foundation, "Jones et al. (2020)" highlight the intricate web of environmental factors that contribute to air pollution, shedding light on the potential influence of kerosene-based activities on air quality.

Furthermore, "Environmental Impact of Kerosene Usage" by Green (2015) offers detailed insights into the environmental repercussions of kerosene utilization, laying the groundwork for understanding its potential contribution to air pollution. Additionally, "The Economic Dynamics of Energy Consumption" by Black (2019) delves into the socioeconomic factors influencing fuel choices, providing valuable context for our investigation into kerosene consumption patterns in the United States.

Venturing beyond the realms of non-fiction, we turn to the classics for inspiration. "The Great Kerosene Crisis" by Dickens (1856) may not offer direct insights into our research topic, but it certainly ignites the imagination with its gripping portrayal of societal upheaval in the face of energy shortages. Similarly, "Air Pollution and Other Misadventures" by Austen (1818) invites readers to ponder the societal implications of atmospheric contamination in a satirical and whimsical manner.

In our quest for knowledge, we also explored unconventional sources, including the back labels of household products and the enigmatic musings of ancient cave paintings. While the former provided no scholarly insights, the latter left us with more questions than answers, particularly regarding the primitive use of kerosene lamps and their potential impact on early air quality.

As we wade through the smog of literature surrounding air pollution and kerosene consumption, our endeavor is not merely an academic pursuit – it's a humorous expedition through the hazy corridors of environmental interconnectedness, where every discovery is shrouded in statistical fog and every insight is illuminated by the flickering glow of a kerosene lamp.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

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 2022

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]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

[[INTRODUCTION]]
INTRODUCTION
Ladies and gentlemen, fasten your seatbelts and prepare for a bumpy yet delightful ride through the hazy clouds of air pollution and the flickering flames of kerosene consumption. Our study embarks on a whimsical journey to unravel the enchanting connection between these two seemingly unrelated phenomena. Like a magician's sleight of hand, the correlation we uncovered between air pollution in San Francisco and kerosene usage in the United States is nothing short of spellbinding.
As we delve into the depths of this atmospheric puzzle, we cannot help but marvel at the charming dance between data points and statistical analyses. We invite you to roam the smog-filled corridors of our findings, where correlation coefficients and p-values adorn the walls like shimmering mistletoe at a scientific soirée.
The relationship we uncovered between air pollution and kerosene consumption is reminiscent of a classic love story – one that makes you chuckle and scratch your head in equal measure. Picture this: the alluring mist of kerosene fumes softly embracing the swirling currents of San Francisco's air, like star-crossed lovers destined to entwine in a statistical tango. Our findings evoke both chuckles and contemplation as we tiptoe through the minefield of causal convolution, where every statistical significance is shrouded in p-value haze.
Join us as we embark on a curious quest to untangle this kerosene-coated conundrum, where the aroma of statistical significance intermingles with the faint scent of aviation fuel. Together, let us waltz through the unpredictable whirlwind of environmental factors, where every correlation is clouded with complexity and every insight is illuminated by the flickering glow of a kerosene lamp. This is not your average academic pursuit – it's a whimsical adventure through the alleyways of air pollution and kerosene consumption, where curiosity fuels our journey and data points guide our way.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the tantalizing connection between air pollution in San Francisco and kerosene consumption in the United States, our research team embarked on a peculiar pilgrimage through the convoluted corridors of data analysis and statistical inference. Our methodology can be likened to untangling a string of Christmas lights – at first, it may seem a tangled mess, but with a bit of patience and a good sense of humor, clarity eventually prevails.

First and foremost, we gathered data from a myriad of sources, but let's face it – the Environmental Protection Agency and the Energy Information Administration were our main squeeze. We tiptoed through their databases like elated elves on an information treasure hunt, sifting through decades' worth of data from 1980 to 2022. It was a bit like trying to find the perfect avocado in a supermarket – a task requiring both precision and a keen eye for detail.

Now for the analytical antics – we indulged in a tantalizing smorgasbord of statistical analyses, including but not limited to correlation coefficients, regression analyses, and perhaps a dash of magic to spice things up. Our statistical toolbox was as diverse as a buffet spread at a quirky carnival, offering an eclectic mix of techniques to tease out the underlying patterns lurking within the haze of data.

To quantify the relationship between air pollution in San Francisco and kerosene consumption, our eyes remained fixated on the prize – a high correlation coefficient and a p-value that would make even the most fastidious statistician do a double-take. Like puzzle enthusiasts unraveling a web of riddles, we reveled in the euphoria of uncovering a remarkable correlation coefficient of 0.8266929 and a p-value of less than 0.01, signaling a connection doused in empirical significance.

In the spirit of scientific good humor, our methodology was infused with equal parts rigor and whimsy, much like a fusion dish blending the analytical precision of a mathematician with the creative flair of an artist. Through this methodological concoction, we sought to navigate the labyrinthine landscape of environmental factors with a spring in our step and a twinkle in our eyes, knowing that every twist and turn would unveil a new layer of insight, much like unwrapping a present on a delightful scavenger hunt.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

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 2022, you found a correlation 0.8266929, r-squared of 0.6834212, 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]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
Ladies and gentlemen, fasten your seatbelts and prepare for a bumpy yet delightful ride through the hazy clouds of air pollution and the flickering flames of kerosene consumption. Our study embarks on a whimsical journey to unravel the enchanting connection between these two seemingly unrelated phenomena. Like a magician's sleight of hand, the correlation we uncovered between air pollution in San Francisco and kerosene usage in the United States is nothing short of spellbinding.
As we delve into the depths of this atmospheric puzzle, we cannot help but marvel at the charming dance between data points and statistical analyses. We invite you to roam the smog-filled corridors of our findings, where correlation coefficients and p-values adorn the walls like shimmering mistletoe at a scientific soirée.
The relationship we uncovered between air pollution and kerosene consumption is reminiscent of a classic love story – one that makes you chuckle and scratch your head in equal measure. Picture this: the alluring mist of kerosene fumes softly embracing the swirling currents of San Francisco's air, like star-crossed lovers destined to entwine in a statistical tango. Our findings evoke both chuckles and contemplation as we tiptoe through the minefield of causal convolution, where every statistical significance is shrouded in p-value haze.
Join us as we embark on a curious quest to untangle this kerosene-coated conundrum, where the aroma of statistical significance intermingles with the faint scent of aviation fuel. Together, let us waltz through the unpredictable whirlwind of environmental factors, where every correlation is clouded with complexity and every insight is illuminated by the flickering glow of a kerosene lamp. This is not your average academic pursuit – it's a whimsical adventure through the alleyways of air pollution and kerosene consumption, where curiosity fuels our journey and data points guide our way.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analyses conducted on the data extracted from the Environmental Protection Agency and the Energy Information Administration revealed a compelling connection between air pollution in San Francisco, California, and kerosene consumption in the United States. The correlation coefficient of 0.8266929 indicated a strong positive relationship between these seemingly unrelated phenomena. This statistical revelation had our research team on the edge of their seats, like spectators at a suspenseful magic show, eagerly waiting for the next trick.

The r-squared value of 0.6834212 further emphasized the close association between air pollution levels in San Francisco and the consumption of kerosene across the United States. It was as if the statistical universe had conspired to unravel this enchanting relationship, leaving us both baffled and amused by the seeming dance of the data points.

Moreover, the p-value of less than 0.01 added a touch of drama to our findings, akin to a plot twist in a riveting novel. The significance of this p-value shimmered like a glittering treasure amidst the haze of statistical significance, prompting us to marvel at the unexpected bond between air pollution and kerosene usage.

As the climax of our analysis, we present Figure 1, a scatterplot illustrating the robust correlation between air pollution in San Francisco and kerosene consumption in the United States. The data points in this visualization formed a visual representation of the entwined nature of these environmental elements, akin to a celestial waltz of statistical significance and atmospheric influence.

In conclusion, our findings not only unveiled the mesmerizing connection between air pollution in San Francisco and kerosene consumption in the United States but also underscored the whimsical nature of statistical inquiry. As we navigate the hazy landscape of environmental interplay, we are reminded that every correlation is clouded with complexity, yet holds the potential for intriguing insights.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

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]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

[[LITERATURE REVIEW]]
In "Smith and Doe (2018)," the authors find a significant positive correlation between air pollution in urban areas and kerosene consumption in the United States. This study provides a compelling basis for our exploration into the interconnected realms of atmospheric contamination and kerosene utilization. Building upon this foundation, "Jones et al. (2020)" highlight the intricate web of environmental factors that contribute to air pollution, shedding light on the potential influence of kerosene-based activities on air quality.
Furthermore, "Environmental Impact of Kerosene Usage" by Green (2015) offers detailed insights into the environmental repercussions of kerosene utilization, laying the groundwork for understanding its potential contribution to air pollution. Additionally, "The Economic Dynamics of Energy Consumption" by Black (2019) delves into the socioeconomic factors influencing fuel choices, providing valuable context for our investigation into kerosene consumption patterns in the United States.
Venturing beyond the realms of non-fiction, we turn to the classics for inspiration. "The Great Kerosene Crisis" by Dickens (1856) may not offer direct insights into our research topic, but it certainly ignites the imagination with its gripping portrayal of societal upheaval in the face of energy shortages. Similarly, "Air Pollution and Other Misadventures" by Austen (1818) invites readers to ponder the societal implications of atmospheric contamination in a satirical and whimsical manner.
In our quest for knowledge, we also explored unconventional sources, including the back labels of household products and the enigmatic musings of ancient cave paintings. While the former provided no scholarly insights, the latter left us with more questions than answers, particularly regarding the primitive use of kerosene lamps and their potential impact on early air quality.
As we wade through the smog of literature surrounding air pollution and kerosene consumption, our endeavor is not merely an academic pursuit – it's a humorous expedition through the hazy corridors of environmental interconnectedness, where every discovery is shrouded in statistical fog and every insight is illuminated by the flickering glow of a kerosene lamp.

[[RESULTS]]
The statistical analyses conducted on the data extracted from the Environmental Protection Agency and the Energy Information Administration revealed a compelling connection between air pollution in San Francisco, California, and kerosene consumption in the United States. The correlation coefficient of 0.8266929 indicated a strong positive relationship between these seemingly unrelated phenomena. This statistical revelation had our research team on the edge of their seats, like spectators at a suspenseful magic show, eagerly waiting for the next trick.
The r-squared value of 0.6834212 further emphasized the close association between air pollution levels in San Francisco and the consumption of kerosene across the United States. It was as if the statistical universe had conspired to unravel this enchanting relationship, leaving us both baffled and amused by the seeming dance of the data points.
Moreover, the p-value of less than 0.01 added a touch of drama to our findings, akin to a plot twist in a riveting novel. The significance of this p-value shimmered like a glittering treasure amidst the haze of statistical significance, prompting us to marvel at the unexpected bond between air pollution and kerosene usage.
As the climax of our analysis, we present Figure 1, a scatterplot illustrating the robust correlation between air pollution in San Francisco and kerosene consumption in the United States. The data points in this visualization formed a visual representation of the entwined nature of these environmental elements, akin to a celestial waltz of statistical significance and atmospheric influence.
In conclusion, our findings not only unveiled the mesmerizing connection between air pollution in San Francisco and kerosene consumption in the United States but also underscored the whimsical nature of statistical inquiry. As we navigate the hazy landscape of environmental interplay, we are reminded that every correlation is clouded with complexity, yet holds the potential for intriguing insights.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings have brought to light a veritable smorgasbord of intriguing revelations, like uncovering a hidden treasure trove beneath a mundane carpet. The correlation coefficient of 0.8266929 didn't just raise eyebrows; it raised a whole spectrum of facial expressions, from quizzical smirks to wide-eyed astonishment. This statistical feat not only supported the previous work of Smith and Doe (2018) but also acted as a robust high-five to the notion that kerosene consumption in the United States indeed waltzes hand in hand with air pollution in San Francisco.

Speaking of waltzes, our scatterplot in Figure 1 could rival the elegance of a ballroom dance, with data points twirling gracefully in their display of the undeniable link between the two phenomena. The r-squared value of 0.6834212 further solidified this partnership, as if to say, "If air pollution were a superhero, kerosene consumption would be its trusty sidekick, both saving the day with their dramatic statistical prowess."

The p-value of less than 0.01 served as the pièce de résistance, the unexpected twist that would make even the most seasoned mystery novel aficionado sit up and take notice. It was as if the statistical universe pulled off a daring heist and left us all in awe of its cunning revelation. Our results not only echoed with the findings of Jones et al. (2020) but also added a touch of p-value drama, akin to a theatrically charged Broadway production where statistical significance took center stage.

This dandy correlation indeed embodies the whimsical spirit of our investigation, reminiscent of a topsy-turvy rollercoaster ride where every statistical significance is punctuated with a modicum of curiosity and surprise. Like a seasoned detective solving a riddle or a comedian delivering a punchline, our research has proven that even in the midst of hazy environmental landscapes, statistical inquiry remains a vibrant and endlessly fascinating endeavor. So, ladies and gentlemen, let's raise our glasses of statistical significance and toast to the enchanting dance of air pollution and kerosene consumption—a true spectacle in the theater of environmental interconnectedness. Cheers to statistical discovery with a dash of whimsy!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 San Francisco, California and Kerosene used in United States. Make lots of jokes, goofy observations, and puns.

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]]
"Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States"

[[ABSTRACT]]
This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

[[INTRDUCTION]]
INTRODUCTION
Ladies and gentlemen, fasten your seatbelts and prepare for a bumpy yet delightful ride through the hazy clouds of air pollution and the flickering flames of kerosene consumption. Our study embarks on a whimsical journey to unravel the enchanting connection between these two seemingly unrelated phenomena. Like a magician's sleight of hand, the correlation we uncovered between air pollution in San Francisco and kerosene usage in the United States is nothing short of spellbinding.
As we delve into the depths of this atmospheric puzzle, we cannot help but marvel at the charming dance between data points and statistical analyses. We invite you to roam the smog-filled corridors of our findings, where correlation coefficients and p-values adorn the walls like shimmering mistletoe at a scientific soirée.
The relationship we uncovered between air pollution and kerosene consumption is reminiscent of a classic love story – one that makes you chuckle and scratch your head in equal measure. Picture this: the alluring mist of kerosene fumes softly embracing the swirling currents of San Francisco's air, like star-crossed lovers destined to entwine in a statistical tango. Our findings evoke both chuckles and contemplation as we tiptoe through the minefield of causal convolution, where every statistical significance is shrouded in p-value haze.
Join us as we embark on a curious quest to untangle this kerosene-coated conundrum, where the aroma of statistical significance intermingles with the faint scent of aviation fuel. Together, let us waltz through the unpredictable whirlwind of environmental factors, where every correlation is clouded with complexity and every insight is illuminated by the flickering glow of a kerosene lamp. This is not your average academic pursuit – it's a whimsical adventure through the alleyways of air pollution and kerosene consumption, where curiosity fuels our journey and data points guide our way.

[[RESULTS]]
The statistical analyses conducted on the data extracted from the Environmental Protection Agency and the Energy Information Administration revealed a compelling connection between air pollution in San Francisco, California, and kerosene consumption in the United States. The correlation coefficient of 0.8266929 indicated a strong positive relationship between these seemingly unrelated phenomena. This statistical revelation had our research team on the edge of their seats, like spectators at a suspenseful magic show, eagerly waiting for the next trick.
The r-squared value of 0.6834212 further emphasized the close association between air pollution levels in San Francisco and the consumption of kerosene across the United States. It was as if the statistical universe had conspired to unravel this enchanting relationship, leaving us both baffled and amused by the seeming dance of the data points.
Moreover, the p-value of less than 0.01 added a touch of drama to our findings, akin to a plot twist in a riveting novel. The significance of this p-value shimmered like a glittering treasure amidst the haze of statistical significance, prompting us to marvel at the unexpected bond between air pollution and kerosene usage.
As the climax of our analysis, we present Figure 1, a scatterplot illustrating the robust correlation between air pollution in San Francisco and kerosene consumption in the United States. The data points in this visualization formed a visual representation of the entwined nature of these environmental elements, akin to a celestial waltz of statistical significance and atmospheric influence.
In conclusion, our findings not only unveiled the mesmerizing connection between air pollution in San Francisco and kerosene consumption in the United States but also underscored the whimsical nature of statistical inquiry. As we navigate the hazy landscape of environmental interplay, we are reminded that every correlation is clouded with complexity, yet holds the potential for intriguing insights.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

Just like the perfect pair of jeans, our findings fit snugly into the intricate web of air pollution and kerosene consumption. The statistical tango between these two seemingly unrelated phenomena has left us both in awe and in stitches. It's as if they were destined to be together, like a matching set of socks in the dresser of environmental factors.

As we bid adieu to this marvelous journey, we can't help but appreciate the whimsical nature of statistical inquiry. Like a compelling mystery novel, our data points have unfolded an enthralling tale of correlation, p-values, and unexpected twists. The plot thickened with each statistical revelation, drawing us into an exhilarating dance of significance and haze.

With a correlation coefficient as robust as a sturdy oak tree and a p-value as rare as a unicorn sighting, our findings have painted a vivid picture of the inseparable bond between air pollution in San Francisco and kerosene consumption in the United States. The statistical universe has indeed conspired to weave an enchanting narrative that tickles the fancy of both scholars and jesters alike.

In the spirit of whimsy and statistical merriment, we declare that no further research is needed in this area. Our findings stand as a testament to the delightful unpredictability of environmental statistics, and we shall leave the stage open for other curious minds to explore the myriad wonders of the statistical world. As the curtain falls on this kerosene-coated conundrum, we bid adieu to statistical significance and causal convolution, with a twinkle in our eyes and a fondness for the haze of environmental interplay.


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 Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric Alchemy


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 Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Sustainable Air Quality Research (ISQAR)


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 Up in the Air: A Fumes-y Connection Between Air Pollution in San Francisco and Kerosene Consumption in the United States with an abstract of This study delves into the intriguing correlation between air pollution in San Francisco, California, and the consumption of kerosene in the United States. Our research team pored over data from the Environmental Protection Agency and the Energy Information Administration to shed light on this kerosene-coated conundrum. Utilizing statistical analyses, we uncovered a remarkably high correlation coefficient of 0.8266929 and a p-value of less than 0.01 for the years spanning from 1980 to 2022. Our findings evoke both chuckles and contemplation as we navigate the smog-filled labyrinth of interconnected environmental elements. Join us on a whimsical journey through the hazy landscape of air pollution and kerosene consumption, where every statistical significance is shrouded in p-value haze and every correlation is clouded with causal convolution.

ChatGPT:

air pollution, San Francisco, kerosene consumption, United States, correlation, statistical analysis, Environmental Protection Agency, Energy Information Administration, smog, environmental elements

*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 San Francisco, California
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in San Francisco-Oakland-Hayward, CA
Source: Environmental Protection Agency
See what else correlates with Air pollution in San Francisco, California

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

Correlation r = 0.8266929 (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 = 0.6834212 (Coefficient of determination)
This means 68.3% of the change in the one variable (i.e., Kerosene used in United States) is predictable based on the change in the other (i.e., Air pollution in San Francisco, California) over the 43 years from 1980 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.5E-12. 0.0000000000085284354482795550
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 0.83 in 8.5E-10% of random cases. Said differently, if you correlated 117,254,800,844 random variables You don't actually need 117 billion 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 42 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 42 because we have two variables measured over a period of 43 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.

[ 0.7, 0.9 ] 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.
1980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in San Francisco, California (Bad air quality days)13.38811.50689.04119.3150712.84159.8630111.506813.424711.20229.315075.479456.849324.918034.931513.287676.575347.377052.191786.5753410.68497.92358.7671211.50687.123296.83065.753427.945214.109595.464484.657533.835623.287671.912572.465752.739733.835624.098364.383565.205482.465756.010932.739731.36986
Kerosene used in United States (Million Barrels/Day)158126.882128.559127.008115.123113.83698.358994.569996.117584.142542.567146.369941.423549.646649.032954.06361.789666.030178.098673.112367.327972.290443.347954.627464.295169.808353.682632.139114.228617.547419.929212.24085.275915.197138.996046.385858.670625.177475.412616.771427.493625.943435.25028




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.




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([13.388,11.5068,9.0411,9.31507,12.8415,9.86301,11.5068,13.4247,11.2022,9.31507,5.47945,6.84932,4.91803,4.93151,3.28767,6.57534,7.37705,2.19178,6.57534,10.6849,7.9235,8.76712,11.5068,7.12329,6.8306,5.75342,7.94521,4.10959,5.46448,4.65753,3.83562,3.28767,1.91257,2.46575,2.73973,3.83562,4.09836,4.38356,5.20548,2.46575,6.01093,2.73973,1.36986,])
array_2 = np.array([158,126.882,128.559,127.008,115.123,113.836,98.3589,94.5699,96.1175,84.1425,42.5671,46.3699,41.4235,49.6466,49.0329,54.063,61.7896,66.0301,78.0986,73.1123,67.3279,72.2904,43.3479,54.6274,64.2951,69.8083,53.6826,32.1391,14.2286,17.5474,19.9292,12.2408,5.27591,5.19713,8.99604,6.38585,8.67062,5.17747,5.41261,6.77142,7.49362,5.94343,5.25028,])
array_1_name = "Air pollution in San Francisco, California"
array_2_name = "Kerosene used in United States"

# 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?

You're a rater extraordinaire!


Correlation ID: 4752 · Black Variable ID: 21211 · Red Variable ID: 25053
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0