Spurious correlation #4,849 · 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 Arkadelphia, Arkansas and the second variable is Google searches for 'how to apply a tourniquet'. The chart goes from 2004 to 2013, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Arkadelphia, Arkansas and the second variable is Google searches for 'how to apply a tourniquet'. The chart goes from 2004 to 2013, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air quality worsened, residents started gasping for air, inadvertently exercising their arms in a desperate attempt to fan away the pollution, effectively improving their tourniquet-applying skills. It seems the smog in the air led to a surge in 'tie-dye' enthusiasts, who, in their quest to filter out the filth, unwittingly became experts in 'artery artistry.' Who knew that in Arkadelphia, Arkansas, dirty air would lead to cleaner, safer 'vein' streets!

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate an image of a high-tech, futuristic cityscape in a haze, set in Arkadelphia, Arkansas, with people fanning the air and creating tie-dye patterns to filter out pollution. The city should be filled with tie-dye colors swirling through the streets and buildings as residents work to purify the air. The scene should have a sense of innovation and creativity, with a high-tech twist. 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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. 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: Steampunk High-tech Oragami Cutsy art illustration Surrealism
ChatGPT: High-tech

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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet', in the following situation: As the air quality worsened, residents started gasping for air, inadvertently exercising their arms in a desperate attempt to fan away the pollution, effectively improving their tourniquet-applying skills. It seems the smog in the air led to a surge in 'tie-dye' enthusiasts, who, in their quest to filter out the filth, unwittingly became experts in 'artery artistry.' Who knew that in Arkadelphia, Arkansas, dirty air would lead to cleaner, safer 'vein' streets!. Keep the description simple.
ChatGPT: In a hazy Arkadelphia, Arkansas, folks were seen fanning the air, trying to alleviate the thick pollution while inadvertently mastering their tourniquet skills. Amidst the smog, tie-dye enthusiasts emerged, inadvertently becoming experts in artery artistry as they filtered out the filth, creating cleaner 'vein' streets.

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: [ High-tech ] and depicting this scene: In a hazy Arkadelphia, Arkansas, folks were seen fanning the air, trying to alleviate the thick pollution while inadvertently mastering their tourniquet skills. Amidst the smog, tie-dye enthusiasts emerged, inadvertently becoming experts in artery artistry as they filtered out the filth, creating cleaner 'vein' streets. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a high-tech, futuristic cityscape in a haze, set in Arkadelphia, Arkansas, with people fanning the air and creating tie-dye patterns to filter out pollution. The city should be filled with tie-dye colors swirling through the streets and buildings as residents work to purify the air. The scene should have a sense of innovation and creativity, with a high-tech twist.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Air pollution in Arkadelphia, Arkansas positively influenced how to apply a tourniquet (Google searches for 'how to apply a tourniquet'). Include one good pun.

AI academic paper

(Because p < 0.01)

The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

The Journal of Atmospheric Remediation and Public Health

Jan 2024

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

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

[[ABSTRACT]]
Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.

While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
Air pollution has long been recognized as a significant public health concern, with well-documented associations to respiratory diseases, cardiovascular problems, and the occasional dramatic hair day. However, the breadth of its potential effects continues to astound researchers, policymakers, and anyone unfortunate enough to have experienced the joys of smog-filled air. In this paper, we delve into an unexpected area of inquiry by examining the correlation between air pollution levels in Arkadelphia, Arkansas, and the rather oddly specific Google search query, 'how to apply a tourniquet'. Who knew that haziness in the air could also lead to haziness in the minds of internet users?
The charming town of Arkadelphia, Arkansas, serves as the backdrop for this investigation, its pristine air sometimes marred by the not-so-pleasant by-products of human activities. Through an in-depth analysis of data sourced from both the Environmental Protection Agency and Google Trends, we identified a distinctly robust correlation between air pollution levels and online inquiries about tourniquet application. The correlation coefficient of 0.8585166 and a p-value less than 0.01 over a span of nine years left us wondering: is this a statistical fluke, or is there something more tangible and ligaturely at play here?
While the link between air pollution and googling first-aid techniques might appear tenuous at first glance, our findings unveil a world of intrigue and underscore the delightful unpredictability of human behavior in response to environmental factors. As researchers, we are accustomed to navigating the treacherous currents of data, but the peculiar connections that emerge never fail to amuse and bemuse us. After all, who could have predicted that the invisible dance of particles in the atmosphere could sway someone to search for techniques to staunch their imaginary – or all too real – wounds?
Our investigation not only prompts an interrogation of the relationship between environmental conditions and human behavior but also reinforces the importance of exploring the gamut of potential impacts of air pollution, beyond the immediate physical health implications. By shedding light on this unanticipated correlation, we hope to spark further inquiry into the intricate ways in which the environment influences our actions, motivations, and perhaps even our eccentric internet searches. So, buckle up – or rather, apply a tourniquet – as we journey through the wondrous world of air pollution's unexpected associations.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation of the correlation between environmental factors and human behavior has led researchers down some unexpected rabbit holes, from the influence of temperature on ice cream sales (Smith, 2008) to the effect of cloud cover on online shopping habits (Doe, 2015). However, our own exploration into the relationship between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet' represents a uniquely curious intersection of public health, environmental science, and the enigmatic whims of internet users.

In "Air Pollution and Public Health" by Jones (2012), the established impacts of air pollution on respiratory and cardiovascular health are extensively detailed, providing a solid foundation for understanding the direct implications of poor air quality on human well-being. However, the less tangible effects of atmospheric pollution, particularly those that influence online search behavior, remain relatively uncharted territory. Our study seeks to fill this gap in the literature, adding a quirky footnote to the broader conversation surrounding environmental influences on human behavior.

Moving beyond the realm of academic texts, we turn to non-fiction works like "The Air Quality Crisis" by Environmental Scientist Joe Clean (2017), which delves into the multifaceted repercussions of air pollution, albeit without venturing into the realm of internet search queries for medical procedures. The real-world implications of deteriorating air quality are undeniably serious, yet our research invites a playful consideration of the indirect, and perhaps unexpected, responses that may manifest in the digital domain.

As we prepare to depart from the well-trodden paths of empirical research and scholarly discourse, we encounter fictional works that, while not explicitly related to our topic, offer a whimsical parallel to the unexpected nature of our findings. Authors like J.K. Rowling, in "Harry Potter and the Chamber of Searches" (1998), may not have explicitly documented the characters turning to Google for medical advice, but the element of surprise pervades both the magical and non-magical realms alike.

In the digital realm, social media platforms serve as a mirror to the peculiar and varied interests of the general public. Recent posts on Twitter and Reddit have surfaced, hinting at a potential connection between exposure to air pollution and the inclination to seek online guidance for applying tourniquets. While not peer-reviewed, these informal observations provide an intriguing backdrop to our formal investigation, underscoring the broader curiosity and speculation surrounding this unconventional correlation.

As we intertwine the serious and the whimsical, the empirical and the speculative, it becomes apparent that our study occupies a unique niche within the broader landscape of environmental and public health research. The following sections will shed further light on the methodologies employed, the compelling findings uncovered, and the implications of this peculiar correlation for our understanding of human responses to environmental stimuli. So fasten your seatbelts, or perhaps your tourniquets, as we embark on the unconventional journey through the hazy nexus of air pollution and internet curiosities.

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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 Google Trends . You used data from 2004 to 2013

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]]
The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

[[ABSTRACT]]
Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.

While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

[[INTRODUCTION]]
Introduction
Air pollution has long been recognized as a significant public health concern, with well-documented associations to respiratory diseases, cardiovascular problems, and the occasional dramatic hair day. However, the breadth of its potential effects continues to astound researchers, policymakers, and anyone unfortunate enough to have experienced the joys of smog-filled air. In this paper, we delve into an unexpected area of inquiry by examining the correlation between air pollution levels in Arkadelphia, Arkansas, and the rather oddly specific Google search query, 'how to apply a tourniquet'. Who knew that haziness in the air could also lead to haziness in the minds of internet users?
The charming town of Arkadelphia, Arkansas, serves as the backdrop for this investigation, its pristine air sometimes marred by the not-so-pleasant by-products of human activities. Through an in-depth analysis of data sourced from both the Environmental Protection Agency and Google Trends, we identified a distinctly robust correlation between air pollution levels and online inquiries about tourniquet application. The correlation coefficient of 0.8585166 and a p-value less than 0.01 over a span of nine years left us wondering: is this a statistical fluke, or is there something more tangible and ligaturely at play here?
While the link between air pollution and googling first-aid techniques might appear tenuous at first glance, our findings unveil a world of intrigue and underscore the delightful unpredictability of human behavior in response to environmental factors. As researchers, we are accustomed to navigating the treacherous currents of data, but the peculiar connections that emerge never fail to amuse and bemuse us. After all, who could have predicted that the invisible dance of particles in the atmosphere could sway someone to search for techniques to staunch their imaginary – or all too real – wounds?
Our investigation not only prompts an interrogation of the relationship between environmental conditions and human behavior but also reinforces the importance of exploring the gamut of potential impacts of air pollution, beyond the immediate physical health implications. By shedding light on this unanticipated correlation, we hope to spark further inquiry into the intricate ways in which the environment influences our actions, motivations, and perhaps even our eccentric internet searches. So, buckle up – or rather, apply a tourniquet – as we journey through the wondrous world of air pollution's unexpected associations.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
Our research team embarked on a virtual scavenger hunt across the information superhighway to gather the necessary data for this peculiar investigation. We harnessed the power of the Environmental Protection Agency's air quality reports, sifting through an assortment of pollutant measurements with all the enthusiasm of amateur detectives at a crime scene. Additionally, we turned to the enigmatic oracle that is Google Trends, mining its trove of search query trends with a fervor akin to that of treasure hunters seeking lost booty.

The hunt extended over the period from 2004 to 2013, encompassing nine years of data that carried with them the weight of a thousand unreciprocated Google searches for 'how to apply a tourniquet'. Our trove of virtual artifacts included air pollution metrics such as particulate matter, carbon monoxide, sulfur dioxide, nitrogen dioxide, ozone, and enough esoteric abbreviations to render even the most seasoned Scrabble champion speechless.

Exclusion Criteria:
To ensure the integrity of our analysis, we applied a stringent set of exclusion criteria to our data. We bid a firm adieu to any spurious readings from the EPA reports, casting aside data tainted by equipment malfunctions, human error, or the elusive fingerprints of mischievous air sprites. Similarly, in the Google Trends realm, we purged our dataset of any anomalies that may have arisen from frivolous fluctuations in search behavior, such as viral internet memes or the sudden, inexplicable popularity of tourniquet-themed flash mobs.

Statistical Analysis:
With our quiver full of meticulously gathered data, we embarked on a statistical odyssey to unravel the enigma of air pollution's influence on digital cries for help. Employing the formidable tools of correlation analysis, we sought to unearth the hidden connections between the ethereal dance of atmospheric pollutants and the desperate clatter of keyboard strokes in search of tourniquet wisdom.

Our statistical expedition led us to the calculation of the correlation coefficient, a numerical expression of the strength and direction of the relationship between air pollution levels and 'how to apply a tourniquet' Google searches. The emergence of a robust correlation coefficient of 0.8585166 left us equal parts delighted and dumbfounded, prompting us to question whether our data had undergone some surreptitious training in the art of correlation-building.

In addition to this coefficient of camaraderie between our chosen variables, we seized upon the elusive p-value, a figure that evokes the intrigue of a sphinx's riddle for many a researcher. With a p-value less than 0.01, we found ourselves confronted with a statistical outcome so significant that it would have driven even the most stoic statistician to execute an impromptu victory dance.

Ethical Considerations:
As ardent proponents of academic integrity, we operated within the hallowed confines of ethical research conduct, ensuring that our pursuit of knowledge did not trample upon the sanctity of privacy or intellectual property. Our data collection efforts were conducted with the utmost respect for the principles of data anonymization and confidentiality, safeguarding the identities and search queries of our unwitting participants in the digital theater of tourniquet dilemmas.

The analysis of our findings was conducted with a fervent commitment to accuracy and transparency, reflecting our unwavering dedication to the pursuit of knowledge for the betterment of humankind – and perhaps the occasional chuckle in the face of perplexing correlations.

In no uncertain terms, our research methodology was crafted with a reverence for curiosity and a touch of whimsy, embodying the spirit of scientific inquiry while whimsically pondering the quirks of human behavior in the digital age.

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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 Google Trends .

For the time period 2004 to 2013, you found a correlation 0.8585166, r-squared of 0.7370507, 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]]
The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

[[ABSTRACT]]
Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.

While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
Air pollution has long been recognized as a significant public health concern, with well-documented associations to respiratory diseases, cardiovascular problems, and the occasional dramatic hair day. However, the breadth of its potential effects continues to astound researchers, policymakers, and anyone unfortunate enough to have experienced the joys of smog-filled air. In this paper, we delve into an unexpected area of inquiry by examining the correlation between air pollution levels in Arkadelphia, Arkansas, and the rather oddly specific Google search query, 'how to apply a tourniquet'. Who knew that haziness in the air could also lead to haziness in the minds of internet users?
The charming town of Arkadelphia, Arkansas, serves as the backdrop for this investigation, its pristine air sometimes marred by the not-so-pleasant by-products of human activities. Through an in-depth analysis of data sourced from both the Environmental Protection Agency and Google Trends, we identified a distinctly robust correlation between air pollution levels and online inquiries about tourniquet application. The correlation coefficient of 0.8585166 and a p-value less than 0.01 over a span of nine years left us wondering: is this a statistical fluke, or is there something more tangible and ligaturely at play here?
While the link between air pollution and googling first-aid techniques might appear tenuous at first glance, our findings unveil a world of intrigue and underscore the delightful unpredictability of human behavior in response to environmental factors. As researchers, we are accustomed to navigating the treacherous currents of data, but the peculiar connections that emerge never fail to amuse and bemuse us. After all, who could have predicted that the invisible dance of particles in the atmosphere could sway someone to search for techniques to staunch their imaginary – or all too real – wounds?
Our investigation not only prompts an interrogation of the relationship between environmental conditions and human behavior but also reinforces the importance of exploring the gamut of potential impacts of air pollution, beyond the immediate physical health implications. By shedding light on this unanticipated correlation, we hope to spark further inquiry into the intricate ways in which the environment influences our actions, motivations, and perhaps even our eccentric internet searches. So, buckle up – or rather, apply a tourniquet – as we journey through the wondrous world of air pollution's unexpected associations.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data revealed a surprisingly robust correlation between air pollution levels in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet'. The correlation coefficient of 0.8585166 indicated a strong positive relationship between these two variables, as did the r-squared value of 0.7370507. The p-value of less than 0.01 further supported the statistical significance of this relationship, suggesting that it is highly unlikely to have occurred by chance alone.

Fig. 1 displays a scatterplot illustrating the compelling correlation between air pollution levels and the frequency of Google searches for tourniquet application techniques. This visually striking representation highlights the coherence between these seemingly disparate phenomena, inviting contemplation on the curious confluence of atmospheric conditions and online information-seeking behavior.

The robustness of the correlation prompts contemplation on the potential underlying mechanisms driving this unexpected connection. While the precise reasons behind why individuals in Arkadelphia, Arkansas, exhibited an increased interest in tourniquet application techniques in response to elevated air pollution levels remain elusive, it is clear that the relationship merits further investigation. Could it be that the foggy air spurred a surge of caution in residents, leading them to seek out first-aid knowledge as a preemptive measure against unforeseen mishaps?

It is worth noting that this correlation, although statistically significant, raises more questions than it answers. The intriguing nature of this association emphasizes the need for a multidisciplinary approach to understanding the nuanced interplay between environmental factors and human behavior. As researchers, we are acutely aware of the unexpected twists and turns that scientific inquiry can take, and this well-documented correlation serves as a compelling testament to the charming unpredictability of our world.

In sum, our analysis indicates a strong correlation between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet', shedding light on the uncharted territory of environmental influence on online behavior. This finding prompts contemplation on the full spectrum of potential impacts of air pollution, from the physical to the psychological, and underscores the imperative of continued exploration into the multifaceted effects of our atmospheric surroundings.

So, as we wrap up this section, let us not only acknowledge the empirical strength of the observed relationship but also marvel at the peculiar and mystifying ways in which our environment intertwines with our everyday choices – and perhaps, our internet search history.

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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

[[ABSTRACT]]
Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.

While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

[[LITERATURE REVIEW]]
The investigation of the correlation between environmental factors and human behavior has led researchers down some unexpected rabbit holes, from the influence of temperature on ice cream sales (Smith, 2008) to the effect of cloud cover on online shopping habits (Doe, 2015). However, our own exploration into the relationship between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet' represents a uniquely curious intersection of public health, environmental science, and the enigmatic whims of internet users.
In "Air Pollution and Public Health" by Jones (2012), the established impacts of air pollution on respiratory and cardiovascular health are extensively detailed, providing a solid foundation for understanding the direct implications of poor air quality on human well-being. However, the less tangible effects of atmospheric pollution, particularly those that influence online search behavior, remain relatively uncharted territory. Our study seeks to fill this gap in the literature, adding a quirky footnote to the broader conversation surrounding environmental influences on human behavior.
Moving beyond the realm of academic texts, we turn to non-fiction works like "The Air Quality Crisis" by Environmental Scientist Joe Clean (2017), which delves into the multifaceted repercussions of air pollution, albeit without venturing into the realm of internet search queries for medical procedures. The real-world implications of deteriorating air quality are undeniably serious, yet our research invites a playful consideration of the indirect, and perhaps unexpected, responses that may manifest in the digital domain.
As we prepare to depart from the well-trodden paths of empirical research and scholarly discourse, we encounter fictional works that, while not explicitly related to our topic, offer a whimsical parallel to the unexpected nature of our findings. Authors like J.K. Rowling, in "Harry Potter and the Chamber of Searches" (1998), may not have explicitly documented the characters turning to Google for medical advice, but the element of surprise pervades both the magical and non-magical realms alike.
In the digital realm, social media platforms serve as a mirror to the peculiar and varied interests of the general public. Recent posts on Twitter and Reddit have surfaced, hinting at a potential connection between exposure to air pollution and the inclination to seek online guidance for applying tourniquets. While not peer-reviewed, these informal observations provide an intriguing backdrop to our formal investigation, underscoring the broader curiosity and speculation surrounding this unconventional correlation.
As we intertwine the serious and the whimsical, the empirical and the speculative, it becomes apparent that our study occupies a unique niche within the broader landscape of environmental and public health research. The following sections will shed further light on the methodologies employed, the compelling findings uncovered, and the implications of this peculiar correlation for our understanding of human responses to environmental stimuli. So fasten your seatbelts, or perhaps your tourniquets, as we embark on the unconventional journey through the hazy nexus of air pollution and internet curiosities.

[[RESULTS]]
The analysis of the data revealed a surprisingly robust correlation between air pollution levels in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet'. The correlation coefficient of 0.8585166 indicated a strong positive relationship between these two variables, as did the r-squared value of 0.7370507. The p-value of less than 0.01 further supported the statistical significance of this relationship, suggesting that it is highly unlikely to have occurred by chance alone.
Fig. 1 displays a scatterplot illustrating the compelling correlation between air pollution levels and the frequency of Google searches for tourniquet application techniques. This visually striking representation highlights the coherence between these seemingly disparate phenomena, inviting contemplation on the curious confluence of atmospheric conditions and online information-seeking behavior.
The robustness of the correlation prompts contemplation on the potential underlying mechanisms driving this unexpected connection. While the precise reasons behind why individuals in Arkadelphia, Arkansas, exhibited an increased interest in tourniquet application techniques in response to elevated air pollution levels remain elusive, it is clear that the relationship merits further investigation. Could it be that the foggy air spurred a surge of caution in residents, leading them to seek out first-aid knowledge as a preemptive measure against unforeseen mishaps?
It is worth noting that this correlation, although statistically significant, raises more questions than it answers. The intriguing nature of this association emphasizes the need for a multidisciplinary approach to understanding the nuanced interplay between environmental factors and human behavior. As researchers, we are acutely aware of the unexpected twists and turns that scientific inquiry can take, and this well-documented correlation serves as a compelling testament to the charming unpredictability of our world.
In sum, our analysis indicates a strong correlation between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet', shedding light on the uncharted territory of environmental influence on online behavior. This finding prompts contemplation on the full spectrum of potential impacts of air pollution, from the physical to the psychological, and underscores the imperative of continued exploration into the multifaceted effects of our atmospheric surroundings.
So, as we wrap up this section, let us not only acknowledge the empirical strength of the observed relationship but also marvel at the peculiar and mystifying ways in which our environment intertwines with our everyday choices – and perhaps, our internet search history.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unveiled a rather striking association between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet'. This finding is in line with a long history of unexpected correlations in scientific research, akin to the discovery of a correlation between the number of Nicolas Cage movies released in a year and the number of swimming pool drownings (not an actual study, by the way - just an amusing hypothetical).

Building on the work of Jones (2012), who emphasized the known impacts of air pollution on respiratory and cardiovascular health, our research expands on the less tangible but still influential effects of atmospheric pollution on human behavior. The robust correlation coefficient and strong statistical significance we uncovered provide compelling support for the notion that our online search behavior may be more responsive to environmental conditions than we previously considered. It's as if the digital wilderness of the internet is teeming with unexpected creatures, much like a surreptitious Jackalope grazing on the lawn of traditional assumptions.

As we delved into the literature, including the fictional realm of Harry Potter, we encountered a myriad of seemingly disparate pieces of evidence that, when pieced together, predispose us to believe in the encompassing nature of our findings. Much like the inextricable relationship between peanut butter and jelly, the correlation between air pollution and tourniquet inquiries appears to be an inseparable duo, despite its initial appearance of being as haphazard as the pairing of peanut butter and pickles.

The scatterplot visually exemplifies the strength of the relationship we uncovered, with every data point serving as a testament to the interconnectedness of environmental conditions and human inquisitiveness. It's a bit like watching an unexpected friendship bloom in the unlikeliest of places - a beautiful, heartwarming and statistically significant relationship between two inanimate things.

While our study may seem like a departure from standard research inquiries, it underscores the subtle ways in which our environment may influence our behaviors, even in the digital realm. We're reminded of the pointed wisdom of Mary Poppins when she proclaimed, "In every job that must be done, there is an element of fun – the unexpected research findings, if you will."

In conclusion - er, I mean, to sum up, our exploration has not only substantiated a previously uncharted correlation but has also opened the floodgates for further inquiry into the whimsical world of online search behavior and its peculiar interactions with atmospheric conditions. Like Sherlock Holmes unraveling a truly baffling mystery, we eagerly anticipate the next chapters in this delightful saga of environmental influence on human curiosity.

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 Arkadelphia, Arkansas and Google searches for 'how to apply a tourniquet'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

[[ABSTRACT]]
Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.

While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

[[INTRDUCTION]]
Introduction
Air pollution has long been recognized as a significant public health concern, with well-documented associations to respiratory diseases, cardiovascular problems, and the occasional dramatic hair day. However, the breadth of its potential effects continues to astound researchers, policymakers, and anyone unfortunate enough to have experienced the joys of smog-filled air. In this paper, we delve into an unexpected area of inquiry by examining the correlation between air pollution levels in Arkadelphia, Arkansas, and the rather oddly specific Google search query, 'how to apply a tourniquet'. Who knew that haziness in the air could also lead to haziness in the minds of internet users?
The charming town of Arkadelphia, Arkansas, serves as the backdrop for this investigation, its pristine air sometimes marred by the not-so-pleasant by-products of human activities. Through an in-depth analysis of data sourced from both the Environmental Protection Agency and Google Trends, we identified a distinctly robust correlation between air pollution levels and online inquiries about tourniquet application. The correlation coefficient of 0.8585166 and a p-value less than 0.01 over a span of nine years left us wondering: is this a statistical fluke, or is there something more tangible and ligaturely at play here?
While the link between air pollution and googling first-aid techniques might appear tenuous at first glance, our findings unveil a world of intrigue and underscore the delightful unpredictability of human behavior in response to environmental factors. As researchers, we are accustomed to navigating the treacherous currents of data, but the peculiar connections that emerge never fail to amuse and bemuse us. After all, who could have predicted that the invisible dance of particles in the atmosphere could sway someone to search for techniques to staunch their imaginary – or all too real – wounds?
Our investigation not only prompts an interrogation of the relationship between environmental conditions and human behavior but also reinforces the importance of exploring the gamut of potential impacts of air pollution, beyond the immediate physical health implications. By shedding light on this unanticipated correlation, we hope to spark further inquiry into the intricate ways in which the environment influences our actions, motivations, and perhaps even our eccentric internet searches. So, buckle up – or rather, apply a tourniquet – as we journey through the wondrous world of air pollution's unexpected associations.

[[RESULTS]]
The analysis of the data revealed a surprisingly robust correlation between air pollution levels in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet'. The correlation coefficient of 0.8585166 indicated a strong positive relationship between these two variables, as did the r-squared value of 0.7370507. The p-value of less than 0.01 further supported the statistical significance of this relationship, suggesting that it is highly unlikely to have occurred by chance alone.
Fig. 1 displays a scatterplot illustrating the compelling correlation between air pollution levels and the frequency of Google searches for tourniquet application techniques. This visually striking representation highlights the coherence between these seemingly disparate phenomena, inviting contemplation on the curious confluence of atmospheric conditions and online information-seeking behavior.
The robustness of the correlation prompts contemplation on the potential underlying mechanisms driving this unexpected connection. While the precise reasons behind why individuals in Arkadelphia, Arkansas, exhibited an increased interest in tourniquet application techniques in response to elevated air pollution levels remain elusive, it is clear that the relationship merits further investigation. Could it be that the foggy air spurred a surge of caution in residents, leading them to seek out first-aid knowledge as a preemptive measure against unforeseen mishaps?
It is worth noting that this correlation, although statistically significant, raises more questions than it answers. The intriguing nature of this association emphasizes the need for a multidisciplinary approach to understanding the nuanced interplay between environmental factors and human behavior. As researchers, we are acutely aware of the unexpected twists and turns that scientific inquiry can take, and this well-documented correlation serves as a compelling testament to the charming unpredictability of our world.
In sum, our analysis indicates a strong correlation between air pollution in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet', shedding light on the uncharted territory of environmental influence on online behavior. This finding prompts contemplation on the full spectrum of potential impacts of air pollution, from the physical to the psychological, and underscores the imperative of continued exploration into the multifaceted effects of our atmospheric surroundings.
So, as we wrap up this section, let us not only acknowledge the empirical strength of the observed relationship but also marvel at the peculiar and mystifying ways in which our environment intertwines with our everyday choices – and perhaps, our internet search history.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our examination of the relationship between air pollution levels in Arkadelphia, Arkansas, and Google searches for 'how to apply a tourniquet' has revealed a remarkably stout correlation, sure to tourni-quette the attention of both researchers and internet surfers alike. The robust correlation coefficient of 0.8585166, accompanied by a p-value less than 0.01, underscores the intriguing connection between atmospheric haziness and virtual first-aid curiosity. This quirky link between smoggy airs and search engine queries not only highlights the unpredictably whimsical nature of human behavior but also showcases the quirky idiosyncrasies of our interconnected world – where even the most unexpected elements converge in a perplexing manner.

While our results may leave one breathless with curiosity, it is important to acknowledge that correlation does not imply causation. The reasons driving this peculiar association may remain shrouded in as much mystery as the smog itself. However, the statistical rigor of our findings compels us to acknowledge the need for further exploration into the delightful enigma of how environmental conditions can influence online inquiry patterns.

As we consider the implications of our study, it becomes apparent that the impact of air pollution extends beyond mere lungfuls of dismay, and reaches into the digital spaces where curious minds seek solace in digital tourniquet tutorials. This unexpected convergence invites a medley of questions and speculations, urging us to ponder the curious ways in which environmental conditions interact with human behavior, and perhaps, prompting Arkadelphia residents to ponder the finer points of emergency response.

In the grand scheme of scientific inquiry, it is these offbeat, unanticipated connections that remind us of the jocular, almost capricious nature of the universe. As such, we posit that further research in this area may not only yield meaningful insights but also a fair share of entertaining eyebrow-raises and wry chuckles. Therefore, we assert, with a nod to the statistical significance of our findings and a twinkle in our eyes, that the investigation of this correlation between air pollution and tourniquet inquiries has reached a satisfying conclusion. Thus, we confidently declare that no further research is needed in this entertainingly bizarre area of study.

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 The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric Remediation and Public Health

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 The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Environmental Health and Public Safety

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 The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet' with an abstract of Air pollution's impact on public health has been well-documented, but its less obvious consequences continue to be a source of intrigue and concern. In this study, we examine the curious correlation between air pollution levels in the charming town of Arkadelphia, Arkansas, and Google searches for the rather specific query 'how to apply a tourniquet'. Using data from the Environmental Protection Agency and Google Trends, our research team discerned a surprisingly robust correlation coefficient of 0.8585166 and a p-value less than 0.01 over the period spanning 2004 to 2013.
While it may seem like a stretch – pun intended – to connect air pollution with first-aid inquiries, our findings raise thought-provoking questions about the public's online behavior in response to environmental factors. The results of this study serve as a reminder of the diverse and unexpected ways in which environmental conditions can influence human behavior and health-seeking patterns. We encourage further investigation into the potential psychological and physiological effects of atmospheric pollution, beyond the more traditional respiratory and cardiovascular impacts.

ChatGPT:

air pollution, Arkadelphia Arkansas, Google searches, tourniquet applications, Environmental Protection Agency data, Google Trends, correlation coefficient, p-value, public health, environmental factors, human behavior, health-seeking patterns, atmospheric pollution, physiological effects

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

Google searches for 'how to apply a tourniquet'
Detailed data title: Relative volume of Google searches for 'how to apply a tourniquet' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'how to apply a tourniquet'

Correlation r = 0.8585166 (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 = 0.7370507 (Coefficient of determination)
This means 73.7% of the change in the one variable (i.e., Google searches for 'how to apply a tourniquet') is predictable based on the change in the other (i.e., Air pollution in Arkadelphia, Arkansas) over the 10 years from 2004 through 2013.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0015.^Show 0.0014726294570936572000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.86 in 0.15% of random cases. Said differently, if you correlated 679 random variables^Note Which I absolutely did.
with the same 9 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 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.

[ 0.5, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013
Air pollution in Arkadelphia, Arkansas (Bad air quality days)	0.00574713	0.0232558	0	0.00558659	0	0	0.0111421	0	0.00323625	0.00314465
Google searches for 'how to apply a tourniquet' (Rel. search volume)	8.33333	19	4.41667	5.66667	0	4.25	4.75	6.08333	3.41667	6.33333

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.00574713,0.0232558,0,0.00558659,0,0,0.0111421,0,0.00323625,0.00314465,])
array_2 = np.array([8.33333,19,4.41667,5.66667,0,4.25,4.75,6.08333,3.41667,6.33333,])
array_1_name = "Air pollution in Arkadelphia, Arkansas"
array_2_name = "Google searches for 'how to apply a tourniquet'"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in Arkadelphia, Arkansas
Line chart for only Google searches for 'how to apply a tourniquet'
AI-generated correlation image
The spurious research paper: The Smoggy Suture: Investigating the Relationship Between Air Pollution in Arkadelphia, Arkansas and Google Searches for 'How to Apply a Tourniquet'

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 4849 · Black Variable ID: 22151 · Red Variable ID: 1360


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