about · email me · subscribe
Spurious correlation #1,509 · 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 Tupelo, Mississippi and the second variable is Tornados in Oklahoma.  The chart goes from 1990 to 2007, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The smog from Tupelo, Mississippi acted as a tornado repellent, giving Oklahoma a breath of fresh air when it came to dodging twisters. It seems like when it comes to tornadoes, Okla-homie might just be in a 'whirl' of trouble without that added pollution protection from Tupelo!

Model: dalle-3
Prompt: Generate an image of an apocalyptic scene in Tupelo, Mississippi, depicting a thick haze filling the air as a tornado swirls ominously in the distance. The poor air quality should reduce visibility, adding a sense of impending danger. Capture the dramatic atmosphere using bold contrasts and dynamic composition to convey the devastating impact of the tornado's annual appearance. 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: Poor air quality in Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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: Woodblock painting Cutsy graphics a Polaroid photo A Discovery magazine cover image Magic realism
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Poor air quality in Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics together. Keep the description simple.
ChatGPT: In Tupelo, Mississippi, a thick haze fills the air as a tornado twirls in the distance. The air quality is poor, causing visibility to be low as the tornado makes its annual appearance.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In Tupelo, Mississippi, a thick haze fills the air as a tornado twirls in the distance. The air quality is poor, causing visibility to be low as the tornado makes its annual appearance. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of an apocalyptic scene in Tupelo, Mississippi, depicting a thick haze filling the air as a tornado swirls ominously in the distance. The poor air quality should reduce visibility, adding a sense of impending danger. Capture the dramatic atmosphere using bold contrasts and dynamic composition to convey the devastating impact of the tornado's annual appearance.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Air pollution in Tupelo, Mississippi positively influenced Oklahoma's Annual Tornado Statistics. Include one good pun.

AI academic paper

(Because p < 0.01)
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

The Journal of Ecological Chaos Studies

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from Environmental Protection Agency and NOAA to assess this nagging question. You found a correlation coefficient of 0.6063199 and p < 0.01 for 1990 to 2007.

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]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific 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 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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Greetings, esteemed colleagues and fellow weather enthusiasts! Today, we embark on a scientific escapade that will blow you away – quite possibly in a literal sense. We have all been intrigued by the capricious nature of tornadoes, those swirling spectacles of sheer destruction and awe. Equally captivating, albeit in a less catastrophic manner, is the phenomenon of air pollution, an issue that often leaves us breathless for entirely different reasons. But what if, just what if, these two disparate elements of nature were connected in some mysterious way?

Our study delves into the intriguing relationship between air pollution in Tupelo, Mississippi, and the annual tornado statistics of Oklahoma. Imagine, if you will, a whimsical dance of atmospheric chaos, where pollutants pirouette with tornadoes in a waltz of statistical significance. As we embark on this unlikely expedition, let us not forget to bring along our pun-proof umbrellas, for we are about to weather a storm of data and draw conclusions that may just blow your mind.

The delightful city of Tupelo, nestled in the heart of Mississippi, known for its charming Southern hospitality and Elvis Presley's birthplace, becomes the focal point of our atmospheric odyssey. Meanwhile, Oklahoma, with its sprawling plains and tumultuous weather, provides the backdrop for our investigation into the annual occurrences of nature's most infamous twisters. As we untangle the threads of environmental data, we cannot help but marvel at the whirlwind of statistics, the tempest of numbers, and the gusts of correlation that may just rock the very foundations of our atmospheric understanding.

While some may doubt the connection between air pollution and tornadoes, we refuse to be swept away by skepticism. Instead, we approach this topic with a sense of scientific curiosity and a dash of whimsy, eager to uncover the truth behind this peculiar pairing. So, buckle up, hold on to your hats, and let’s soar into the tempestuous skies of data analysis and scholarly silliness. Join us as we embark on this merry meteorological adventure, seeking to decipher the stormy secrets that lie hidden amidst the winds of change.


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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Greetings, esteemed colleagues and fellow weather enthusiasts! Today, we embark on a scientific escapade that will blow you away – quite possibly in a literal sense. We have all been intrigued by the capricious nature of tornadoes, those swirling spectacles of sheer destruction and awe. Equally captivating, albeit in a less catastrophic manner, is the phenomenon of air pollution, an issue that often leaves us breathless for entirely different reasons. But what if, just what if, these two disparate elements of nature were connected in some mysterious way?
Our study delves into the intriguing relationship between air pollution in Tupelo, Mississippi, and the annual tornado statistics of Oklahoma. Imagine, if you will, a whimsical dance of atmospheric chaos, where pollutants pirouette with tornadoes in a waltz of statistical significance. As we embark on this unlikely expedition, let us not forget to bring along our pun-proof umbrellas, for we are about to weather a storm of data and draw conclusions that may just blow your mind.
The delightful city of Tupelo, nestled in the heart of Mississippi, known for its charming Southern hospitality and Elvis Presley's birthplace, becomes the focal point of our atmospheric odyssey. Meanwhile, Oklahoma, with its sprawling plains and tumultuous weather, provides the backdrop for our investigation into the annual occurrences of nature's most infamous twisters. As we untangle the threads of environmental data, we cannot help but marvel at the whirlwind of statistics, the tempest of numbers, and the gusts of correlation that may just rock the very foundations of our atmospheric understanding.
While some may doubt the connection between air pollution and tornadoes, we refuse to be swept away by skepticism. Instead, we approach this topic with a sense of scientific curiosity and a dash of whimsy, eager to uncover the truth behind this peculiar pairing. So, buckle up, hold on to your hats, and let’s soar into the tempestuous skies of data analysis and scholarly silliness. Join us as we embark on this merry meteorological adventure, seeking to decipher the stormy secrets that lie hidden amidst the winds of change.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The exploration of the relationship between air pollution and tornado statistics has left many researchers scratching their heads, much like a confused cat caught in a sudden gust of wind. Smith et al. (2010) conducted a comprehensive analysis of air quality in various regions of the United States, but alas, their study did not extend to investigating the potential influence of air pollutants on tornado activity. Similarly, Doe and Jones (2015) focused on the frequency and intensity of tornadoes, yet remained blissfully unaware of any potential dalliance with air pollution. These early studies left a tornado-sized gap in our understanding, prompting this present inquiry into the juxtaposition of these two seemingly unrelated phenomena.

Venturing into more colorful avenues of inquiry, we turn to the literary landscape for inspiration. In "Stormy Skies: The Correlation Chronicles" by Weatherly Wanda, the author whimsically speculates about the capricious connection between air pollution and tornadoes, offering a tempest of anecdotal evidence and a downpour of puns along the way. Adding to the mix, "Blown Away: A Tornado's Tale" by Gale Force is a fictional narrative that weaves a tantalizing tale of a sentient tornado's musings on air pollution, set against a backdrop of meteorological mayhem and atmospheric angst. While these literary works may not offer empirical evidence, they certainly blow a breath of fresh air into our discussion, and provide a tornado of entertainment for those willing to weather the storm of imagination.

Turning to an unexpected source of insight, we find that the board game "Tornado Trouble" covertly hints at the subtle interplay between atmospheric conditions and environmental factors, offering players a whirlwind experience that mirrors the complexity of real-world weather phenomena. This delightful diversion provides a playful reminder that even in the realm of scientific inquiry, a touch of whimsy can sometimes lead us to unexpected discoveries – or at the very least, a good time.

As we navigate through the scholarly whirlpool of literature and prepare to confront the swirling winds of data analysis, it becomes abundantly clear that our quest to understand the relationship between air pollution and tornado statistics is anything but a breeze. Nevertheless, armed with an academic spirit and a sprinkle of humor, we forge ahead, ready to face the gusts of uncertainty and the tempest of scientific inquiry with a twirl and a smile.


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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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 NOAA . You used data from 1990 to 2007

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]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

[[INTRODUCTION]]
Greetings, esteemed colleagues and fellow weather enthusiasts! Today, we embark on a scientific escapade that will blow you away – quite possibly in a literal sense. We have all been intrigued by the capricious nature of tornadoes, those swirling spectacles of sheer destruction and awe. Equally captivating, albeit in a less catastrophic manner, is the phenomenon of air pollution, an issue that often leaves us breathless for entirely different reasons. But what if, just what if, these two disparate elements of nature were connected in some mysterious way?
Our study delves into the intriguing relationship between air pollution in Tupelo, Mississippi, and the annual tornado statistics of Oklahoma. Imagine, if you will, a whimsical dance of atmospheric chaos, where pollutants pirouette with tornadoes in a waltz of statistical significance. As we embark on this unlikely expedition, let us not forget to bring along our pun-proof umbrellas, for we are about to weather a storm of data and draw conclusions that may just blow your mind.
The delightful city of Tupelo, nestled in the heart of Mississippi, known for its charming Southern hospitality and Elvis Presley's birthplace, becomes the focal point of our atmospheric odyssey. Meanwhile, Oklahoma, with its sprawling plains and tumultuous weather, provides the backdrop for our investigation into the annual occurrences of nature's most infamous twisters. As we untangle the threads of environmental data, we cannot help but marvel at the whirlwind of statistics, the tempest of numbers, and the gusts of correlation that may just rock the very foundations of our atmospheric understanding.
While some may doubt the connection between air pollution and tornadoes, we refuse to be swept away by skepticism. Instead, we approach this topic with a sense of scientific curiosity and a dash of whimsy, eager to uncover the truth behind this peculiar pairing. So, buckle up, hold on to your hats, and let’s soar into the tempestuous skies of data analysis and scholarly silliness. Join us as we embark on this merry meteorological adventure, seeking to decipher the stormy secrets that lie hidden amidst the winds of change.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To delve into the curious connection between air pollution in Tupelo, Mississippi, and the annual tornado statistics in Oklahoma, we employed a meticulously curated combination of data collection, statistical analysis, and a touch of whimsy. Our approach aimed to capture the essence of scientific inquiry while maintaining a sense of lighthearted curiosity, not unlike chasing after a mischievous tornado with a net made of statistical formulas.

Data Collection:
Our research team scoured the depths of the internet, navigating virtual whirlwinds of information in search of relevant data. The primary sources of our atmospheric treasure trove were the archives of the Environmental Protection Agency (EPA) and the National Oceanic and Atmospheric Administration (NOAA). Through their digital archives, we captured datasets spanning the years 1990 to 2007, ensuring a comprehensive glimpse into the temporal tapestry of air pollution and tornado occurrences. As we combed through the data, we couldn't help but feel a gust of anticipation, akin to setting sail into uncharted weather patterns.

Air Pollution Metrics:
In Tupelo, Mississippi, the measure of air pollution levels became a focal point of our inquiry. We harnessed the power of particulate matter (PM), ozone (O3), sulfur dioxide (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO) concentrations, transforming these seemingly mundane numbers into a symphony of atmospheric harmonies. Our data collection process was as thorough as a tornado's path, ensuring that no particulate matter or gaseous compound escaped our scientific clutches.

Tornado Statistics:
On the plains of Oklahoma, the annual occurrence of tornadoes awaited our scrutiny. We meticulously recorded the frequency, intensity, and spatial distribution of these tempestuous vortices, treating each data point as a unique swirl in the grand choreography of atmospheric phenomena. As we wrangled with the complexities of tornado data, we couldn't help but feel a whirlwind of scientific exhilaration, likening each dataset to a dramatic twist in the meteorological plot.

Statistical Analysis:
Armed with our arsenal of data, we embarked on a statistical odyssey, aiming to uncover the elusive relationship between air pollution in Tupelo and Oklahoma's annual tornado statistics. We unleashed the mighty forces of correlation analysis, wielding Pearson's correlation coefficient like a tempestuous mathematical wizard. Our calculations danced with the significance level of p < 0.01, ensuring that our findings were not mere statistical flotsam adrift in a sea of uncertainty.

While our concoction of methodology may appear to be an eccentric blend of scientific rigor and whimsical flair, we assure the skeptical reader that our approach was as steadfast as a weather vane in a storm. With the data firmly in hand and a glint of scholarly silliness in our eyes, we navigated the convoluted currents of scientific exploration, driven by a fervent desire to unearth the stormy secrets that lie embedded within the windswept landscapes of nature's mysteries.


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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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 NOAA .

For the time period 1990 to 2007, you found a correlation 0.6063199, r-squared of 0.3676239, 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]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Greetings, esteemed colleagues and fellow weather enthusiasts! Today, we embark on a scientific escapade that will blow you away – quite possibly in a literal sense. We have all been intrigued by the capricious nature of tornadoes, those swirling spectacles of sheer destruction and awe. Equally captivating, albeit in a less catastrophic manner, is the phenomenon of air pollution, an issue that often leaves us breathless for entirely different reasons. But what if, just what if, these two disparate elements of nature were connected in some mysterious way?
Our study delves into the intriguing relationship between air pollution in Tupelo, Mississippi, and the annual tornado statistics of Oklahoma. Imagine, if you will, a whimsical dance of atmospheric chaos, where pollutants pirouette with tornadoes in a waltz of statistical significance. As we embark on this unlikely expedition, let us not forget to bring along our pun-proof umbrellas, for we are about to weather a storm of data and draw conclusions that may just blow your mind.
The delightful city of Tupelo, nestled in the heart of Mississippi, known for its charming Southern hospitality and Elvis Presley's birthplace, becomes the focal point of our atmospheric odyssey. Meanwhile, Oklahoma, with its sprawling plains and tumultuous weather, provides the backdrop for our investigation into the annual occurrences of nature's most infamous twisters. As we untangle the threads of environmental data, we cannot help but marvel at the whirlwind of statistics, the tempest of numbers, and the gusts of correlation that may just rock the very foundations of our atmospheric understanding.
While some may doubt the connection between air pollution and tornadoes, we refuse to be swept away by skepticism. Instead, we approach this topic with a sense of scientific curiosity and a dash of whimsy, eager to uncover the truth behind this peculiar pairing. So, buckle up, hold on to your hats, and let’s soar into the tempestuous skies of data analysis and scholarly silliness. Join us as we embark on this merry meteorological adventure, seeking to decipher the stormy secrets that lie hidden amidst the winds of change.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon analyzing the data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we uncovered a tantalizing correlation coefficient of 0.6063199 between air pollution in Tupelo, Mississippi, and Oklahoma's annual tornado statistics for the time period 1990 to 2007. With an r-squared value of 0.3676239 and a significance level of p < 0.01, our findings suggest that there may indeed be a windy, twisty connection between these seemingly unrelated phenomena.

As displayed in Fig. 1 (which we promise is not just a whimsical doodle of dust devils and smog clouds), our scatterplot vividly illustrates the strong correlation between air pollution levels in Tupelo and the annual occurrence of tornadoes in Oklahoma. The points on the plot whirl and twirl like a turbulent tango, hinting at the atmospheric intrigue that lies within.

It's important to note that while our findings reveal a significant correlation, we must resist the urge to jump to hasty conclusions. As we navigate this maze of meteorological data, we must heed the cautionary tale of correlation not necessarily implying causation. Nonetheless, the results of our analysis beckon us to explore the possibility that air pollution and tornadoes may be more than reluctant neighbors in the great symphony of weather events.

In light of these findings, we invite our esteemed readers to join us in this merry meteorological dance, as we waltz through the winds of statistical significance and whirl through the wonder of weather-related correlations. Together, let us uncover the stormy secrets that lie hidden amidst the tempestuous skies of scientific inquiry. And remember, folks, when it comes to unravelling the mysteries of the atmosphere, it's always best to expect the unexpected. After all, who would've thought that air pollution and tornadoes could make such a dynamic duo?


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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

[[LITERATURE REVIEW]]
The exploration of the relationship between air pollution and tornado statistics has left many researchers scratching their heads, much like a confused cat caught in a sudden gust of wind. Smith et al. (2010) conducted a comprehensive analysis of air quality in various regions of the United States, but alas, their study did not extend to investigating the potential influence of air pollutants on tornado activity. Similarly, Doe and Jones (2015) focused on the frequency and intensity of tornadoes, yet remained blissfully unaware of any potential dalliance with air pollution. These early studies left a tornado-sized gap in our understanding, prompting this present inquiry into the juxtaposition of these two seemingly unrelated phenomena.
Venturing into more colorful avenues of inquiry, we turn to the literary landscape for inspiration. In "Stormy Skies: The Correlation Chronicles" by Weatherly Wanda, the author whimsically speculates about the capricious connection between air pollution and tornadoes, offering a tempest of anecdotal evidence and a downpour of puns along the way. Adding to the mix, "Blown Away: A Tornado's Tale" by Gale Force is a fictional narrative that weaves a tantalizing tale of a sentient tornado's musings on air pollution, set against a backdrop of meteorological mayhem and atmospheric angst. While these literary works may not offer empirical evidence, they certainly blow a breath of fresh air into our discussion, and provide a tornado of entertainment for those willing to weather the storm of imagination.
Turning to an unexpected source of insight, we find that the board game "Tornado Trouble" covertly hints at the subtle interplay between atmospheric conditions and environmental factors, offering players a whirlwind experience that mirrors the complexity of real-world weather phenomena. This delightful diversion provides a playful reminder that even in the realm of scientific inquiry, a touch of whimsy can sometimes lead us to unexpected discoveries – or at the very least, a good time.
As we navigate through the scholarly whirlpool of literature and prepare to confront the swirling winds of data analysis, it becomes abundantly clear that our quest to understand the relationship between air pollution and tornado statistics is anything but a breeze. Nevertheless, armed with an academic spirit and a sprinkle of humor, we forge ahead, ready to face the gusts of uncertainty and the tempest of scientific inquiry with a twirl and a smile.

[[RESULTS]]
Upon analyzing the data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we uncovered a tantalizing correlation coefficient of 0.6063199 between air pollution in Tupelo, Mississippi, and Oklahoma's annual tornado statistics for the time period 1990 to 2007. With an r-squared value of 0.3676239 and a significance level of p < 0.01, our findings suggest that there may indeed be a windy, twisty connection between these seemingly unrelated phenomena.
As displayed in Fig. 1 (which we promise is not just a whimsical doodle of dust devils and smog clouds), our scatterplot vividly illustrates the strong correlation between air pollution levels in Tupelo and the annual occurrence of tornadoes in Oklahoma. The points on the plot whirl and twirl like a turbulent tango, hinting at the atmospheric intrigue that lies within.
It's important to note that while our findings reveal a significant correlation, we must resist the urge to jump to hasty conclusions. As we navigate this maze of meteorological data, we must heed the cautionary tale of correlation not necessarily implying causation. Nonetheless, the results of our analysis beckon us to explore the possibility that air pollution and tornadoes may be more than reluctant neighbors in the great symphony of weather events.
In light of these findings, we invite our esteemed readers to join us in this merry meteorological dance, as we waltz through the winds of statistical significance and whirl through the wonder of weather-related correlations. Together, let us uncover the stormy secrets that lie hidden amidst the tempestuous skies of scientific inquiry. And remember, folks, when it comes to unravelling the mysteries of the atmosphere, it's always best to expect the unexpected. After all, who would've thought that air pollution and tornadoes could make such a dynamic duo?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our study has blown the lid off the traditional concepts of weather patterns and air quality, unraveling a whirlwind correlation between air pollution in Tupelo, Mississippi, and Oklahoma's annual tornado statistics from 1990 to 2007. As we tangoed through the data, our findings jive with previous research in some delightfully unexpected ways.

First, let's revisit our literature review where we whimsically explored the connections between air pollution and tornadoes. Our findings align with the whimsical speculations of Weatherly Wanda in "Stormy Skies: The Correlation Chronicles" and the tantalizing tale of a sentient tornado in "Blown Away: A Tornado's Tale" by Gale Force. Call it a twist of fate, but our data supports the notion that there may indeed be a tempestuous relationship between air pollution and tornado activity. Perhaps these light-hearted literary works were onto something after all.

Additionally, while we must tread lightly when interpreting correlations, the winds of statistical significance cannot be ignored. Our correlation coefficient of 0.6063199 and the r-squared value of 0.3676239 point to a more substantial relationship than a casual breeze. These findings lend support to the notion that atmospheric conditions, specifically air pollution levels, may play a role in shaping the tumultuous tornado landscape of Oklahoma.

As intrepid explorers of the scientific unknown, we invite our esteemed colleagues to join us in this meteorological dance, where the unexpected pairs with the empirically sound. It's refreshing to find that even in the realm of serious scientific inquiry, a touch of whimsy and humor can provide unexpected pathways to discovery and insight. The stormy secrets of our atmosphere are as complex and engaging as any grand narrative, and it seems that the plot thickens with each gust of wind and cloud of pollution.

So, fellow seekers of truth and humor, let's venture forth into the atmospheric unknown, armed with curiosity, data, and a dash of lightheartedness. After all, when it comes to unraveling nature's mysteries, sometimes it takes more than just the force of the wind; it takes a twirl of whimsy and a pinch of puns to truly weather the storm.


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 Tupelo, Mississippi and Oklahoma's Annual Tornado Statistics. 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]]
Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion

[[ABSTRACT]]
In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

[[INTRDUCTION]]
Greetings, esteemed colleagues and fellow weather enthusiasts! Today, we embark on a scientific escapade that will blow you away – quite possibly in a literal sense. We have all been intrigued by the capricious nature of tornadoes, those swirling spectacles of sheer destruction and awe. Equally captivating, albeit in a less catastrophic manner, is the phenomenon of air pollution, an issue that often leaves us breathless for entirely different reasons. But what if, just what if, these two disparate elements of nature were connected in some mysterious way?
Our study delves into the intriguing relationship between air pollution in Tupelo, Mississippi, and the annual tornado statistics of Oklahoma. Imagine, if you will, a whimsical dance of atmospheric chaos, where pollutants pirouette with tornadoes in a waltz of statistical significance. As we embark on this unlikely expedition, let us not forget to bring along our pun-proof umbrellas, for we are about to weather a storm of data and draw conclusions that may just blow your mind.
The delightful city of Tupelo, nestled in the heart of Mississippi, known for its charming Southern hospitality and Elvis Presley's birthplace, becomes the focal point of our atmospheric odyssey. Meanwhile, Oklahoma, with its sprawling plains and tumultuous weather, provides the backdrop for our investigation into the annual occurrences of nature's most infamous twisters. As we untangle the threads of environmental data, we cannot help but marvel at the whirlwind of statistics, the tempest of numbers, and the gusts of correlation that may just rock the very foundations of our atmospheric understanding.
While some may doubt the connection between air pollution and tornadoes, we refuse to be swept away by skepticism. Instead, we approach this topic with a sense of scientific curiosity and a dash of whimsy, eager to uncover the truth behind this peculiar pairing. So, buckle up, hold on to your hats, and let’s soar into the tempestuous skies of data analysis and scholarly silliness. Join us as we embark on this merry meteorological adventure, seeking to decipher the stormy secrets that lie hidden amidst the winds of change.

[[RESULTS]]
Upon analyzing the data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we uncovered a tantalizing correlation coefficient of 0.6063199 between air pollution in Tupelo, Mississippi, and Oklahoma's annual tornado statistics for the time period 1990 to 2007. With an r-squared value of 0.3676239 and a significance level of p < 0.01, our findings suggest that there may indeed be a windy, twisty connection between these seemingly unrelated phenomena.
As displayed in Fig. 1 (which we promise is not just a whimsical doodle of dust devils and smog clouds), our scatterplot vividly illustrates the strong correlation between air pollution levels in Tupelo and the annual occurrence of tornadoes in Oklahoma. The points on the plot whirl and twirl like a turbulent tango, hinting at the atmospheric intrigue that lies within.
It's important to note that while our findings reveal a significant correlation, we must resist the urge to jump to hasty conclusions. As we navigate this maze of meteorological data, we must heed the cautionary tale of correlation not necessarily implying causation. Nonetheless, the results of our analysis beckon us to explore the possibility that air pollution and tornadoes may be more than reluctant neighbors in the great symphony of weather events.
In light of these findings, we invite our esteemed readers to join us in this merry meteorological dance, as we waltz through the winds of statistical significance and whirl through the wonder of weather-related correlations. Together, let us uncover the stormy secrets that lie hidden amidst the tempestuous skies of scientific inquiry. And remember, folks, when it comes to unravelling the mysteries of the atmosphere, it's always best to expect the unexpected. After all, who would've thought that air pollution and tornadoes could make such a dynamic duo?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our findings have blown the lid off the mysterious dance between air pollution in Tupelo, Mississippi, and Oklahoma's annual tornado statistics, revealing a correlation that's more twisted than a funnel cloud at a square dance convention. This research has taken us on a whirlwind of statistical significance, prompting us to question the atmospheric status quo and inspiring a veritable tornado of puns. It's clear that the air pollution and tornado relationship is as complex and enigmatic as the plot of a Christopher Nolan film – you never quite know where it's headed, but you're always on the edge of your seat.

While our results hint at a fascinating connection, we must avoid the temptation to leap to conclusions like a gazelle avoiding a tornado (and potentially air pollution) in the wild. Correlation doesn't always imply causation, and we must approach this topic with caution, just like storm chasers approaching an ominous-looking cloud.

So, where do we go from here? Well, it might be time to shift our research focus to lighter topics, like the correlation between ice cream consumption and shark attacks – just to give those wacky statisticians something to chew on. In the meantime, let's bask in the whirlwind of discoveries that this study has unearthed and appreciate the complexities of Mother Nature's meteorological marvels.

As we close the chapter on this tornado of research, we assert with absolute certainty that no further investigation is required in this peculiar area of study. After all, the connection between air pollution in Tupelo and tornado shenanigans in Oklahoma has been untangled, and we've blown the lid off this windy mystery.

So, let's bid adieu to this atmospheric escapade and move on to less breezy research inquiries. Who knows, maybe next time we'll uncover the staggering connection between sunshine and smiles or the mind-blowing correlation between coffee consumption and academic productivity. Until then, stay breezy, my research comrades!


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 Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Chaos Studies


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 Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Atmospheric and Climate Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Tupelo's Air Pollution and Tornado Commotion: A Data-Driven Locomotion with an abstract of In this whimsical yet scientifically rigorous research paper, we explore the captivating connection between air pollution in the delightful city of Tupelo, Mississippi, and the annual tornado statistics of the splendid state of Oklahoma. By analyzing data from the Environmental Protection Agency and the National Oceanic and Atmospheric Administration, we have uncovered a correlation coefficient of 0.6063199 with a significance level of p < 0.01 for the years 1990 to 2007. Our findings suggest that there may be more to the air pollution and tornado relationship than meets the eye, prompting a tornado of questions and a whirlwind of pun opportunities. Join us on this research adventure as we endeavor to untangle the atmospheric enigma and, in the process, explore the stormy weather of scientific discovery.

ChatGPT:

Tupelo, Mississippi, air pollution, tornado, correlation, Environmental Protection Agency, National Oceanic and Atmospheric Administration, data analysis, significance level, atmospheric enigma, stormy weather, scientific discovery

*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 Tupelo, Mississippi
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Tupelo, MS
Source: Environmental Protection Agency
See what else correlates with Air pollution in Tupelo, Mississippi

Tornados in Oklahoma
Detailed data title: Oklahoma's Annual Tornado Statistics
Source: NOAA
See what else correlates with Tornados in Oklahoma

Correlation r = 0.6063199 (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 = 0.3676239 (Coefficient of determination)
This means 36.8% of the change in the one variable (i.e., Tornados in Oklahoma) is predictable based on the change in the other (i.e., Air pollution in Tupelo, Mississippi) over the 18 years from 1990 through 2007.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0076. 0.0076416411560690095000000000
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 0.61 in 0.76% of random cases. Said differently, if you correlated 131 random variables Which I absolutely did.
with the same 17 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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.

[ 0.19, 0.84 ] 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.
199019911992199319941995199619971998199920002001200220032004200520062007
Air pollution in Tupelo, Mississippi (Bad air quality days)0.007490640000.00363636000.002739730.02941180.0317460.01052630.003533570.003496500000.00274725
Tornados in Oklahoma (Total Tornados)3073646440794855831454461187862272749




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([0.00749064,0,0,0,0.00363636,0,0,0.00273973,0.0294118,0.031746,0.0105263,0.00353357,0.0034965,0,0,0,0,0.00274725,])
array_2 = np.array([30,73,64,64,40,79,48,55,83,145,44,61,18,78,62,27,27,49,])
array_1_name = "Air pollution in Tupelo, Mississippi"
array_2_name = "Tornados in Oklahoma"

# 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?

Big thanks for reviewing!


Correlation ID: 1509 · Black Variable ID: 22134 · Red Variable ID: 505
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0