Spurious correlation #3,396 · 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 Washington, D.C. and the second variable is Kerosene used in Peru. The chart goes from 1980 to 2021, and the two variables track closely in value over that time.

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

Download png, svg

AI explanation

As air pollution decreased in Washington, D.C., it created a domino effect on global environmental consciousness. People were no longer willing to accept filthy air, so they started a 'clean air' movement. This movement took flight and soon reached Peru, where it sparked a 'kerosene clean-up' campaign. Residents in Peru realized they needed to 'kero-clean' their act and find alternative, less polluting fuel sources. As a result, the demand for kerosene in Peru dropped faster than you can say 'smog-free skies,' all thanks to the unexpected pollutant purge in D.C. It seems like even air pollution has the power to 'air-ase' change in the world!

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like it is a scene from 'Star Wars': A clear blue sky hovers over the cityscape of Washington, D.C., with iconic landmarks visible in the distance. Fewer cars are on the roads, emitting minimal exhaust fumes. The skyline appears to be undergoing a transformation as smokestacks release significantly less pollution. Across the world in Peru, a family joyfully cooks using a solar-powered stove. Their kerosene lamp has been replaced with a clean energy alternative, contributing to the clean air revolution. The winds appear to carry the fresh air from Washington, D.C., all the way to Peru, symbolizing a shared stride towards environmental harmony. 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 Washington, D.C. and Kerosene used in Peru. 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: An image that looks like it is a scene from 'Star Wars' 3D Pixar Style Whimsical illustration Oragami Pop art
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Washington, D.C. and Kerosene used in Peru, in the following situation: As air pollution decreased in D.C., the cleaner air made its way down to Peru, inspiring kerosene users to switch to cleaner, more eco-friendly alternatives. It's like a breath of fresh air for the environment!. Keep the description simple.
ChatGPT: In Washington, D.C., a clear blue sky is seen with fewer cars emitting exhaust fumes, and smokestacks releasing less pollution. Meanwhile, in Peru, a family is seen happily cooking with a solar-powered stove, replacing their kerosene lamp with a clean energy alternative. The clean air from D.C. seems to travel south, creating a breath of fresh air for the environment in both places.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In Washington, D.C., a clear blue sky is seen with fewer cars emitting exhaust fumes, and smokestacks releasing less pollution. Meanwhile, in Peru, a family is seen happily cooking with a solar-powered stove, replacing their kerosene lamp with a clean energy alternative. The clean air from D.C. seems to travel south, creating a breath of fresh air for the environment in both places. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from 'Star Wars': A clear blue sky hovers over the cityscape of Washington, D.C., with iconic landmarks visible in the distance. Fewer cars are on the roads, emitting minimal exhaust fumes. The skyline appears to be undergoing a transformation as smokestacks release significantly less pollution. Across the world in Peru, a family joyfully cooks using a solar-powered stove. Their kerosene lamp has been replaced with a clean energy alternative, contributing to the clean air revolution. The winds appear to carry the fresh air from Washington, D.C., all the way to Peru, symbolizing a shared stride towards environmental harmony.

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

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

AI academic paper

(Because p < 0.01)

Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru

The International Journal of Ecological Synchronicity

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 Washington, D.C. and Kerosene used in Peru. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru

[[ABSTRACT]]
The present study delves into the intercontinental relationship between air pollution levels in the esteemed city of Washington, D.C. and the utilization of kerosene in the charming landscapes of Peru. Through a meticulous analysis of data sourced from the revered Environmental Protection Agency and the illustrious Energy Information Administration, a striking correlation emerged. With a correlation coefficient of 0.9031611 and a p-value less than the conventional threshold of 0.01, our findings reveal a compelling association between air pollution in the U.S. capital and the consumption of kerosene in the Peruvian realm from 1980 to 2021.

As we unravel the perplexing connection between these seemingly disparate domains, it is imperative to acknowledge the mesmerizing intricacies that intertwine our world. While the air in Washington may leave citizens and policymakers “polluted” with concerns, the humble kerosene lamps in Peru continue to illuminate not just the homes, but also the landscape of our study. As we explore the intricate tapestry of air pollutants and kerosene kinship, we invite readers to join us in this enchanting journey of unexpected correlations and cross-continental connections.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The enchanting dance of interconnectedness in our world has long captivated the curious minds of researchers. In our quest to untangle the web of cause and effect, we are often drawn to the most unexpected pairings. Enter the mysterious liaison between air pollution in Washington, D.C. and the unassuming kerosene used in Peru. Our journey begins with a seemingly mundane research question: Could there truly be a link between the atmospheric woes of a bustling metropolis and the flickering glow of kerosene lamps in a land renowned for its natural beauty?
As we embark on this scholarly escapade, we are reminded of the sage words of Heraclitus, who famously mused that "The only thing that is constant is change." Our investigation seeks not just to uncover an association, but to embrace the ceaseless ebb and flow of influences that transcend geographical boundaries and cultural divides. While the details may appear esoteric at first glance, we assure the reader that the implications of our findings are far-reaching, much like the tendrils of a creeping vine.
Air pollution, with its ominous veil lingering over urban landscapes, has become a quintessential emblem of industrial progress – a dark cloud, if you will, looming over our collective aspirations for sustainable living. In juxtaposition, the humble kerosene lamp, perched like a steadfast sentry in rural abodes, exudes a warmth that is both literal and metaphorical. It is with this dichotomous backdrop that we embark on our scholarly odyssey, guided not just by data and statistics, but by the whimsy of discovery and the allure of unexpected revelations.
Now, dear reader, let us venture forth into the labyrinthine corridors of statistical analysis, where the cool embrace of correlation coefficients and the enigmatic whispers of p-values shall beckon us further. Like intrepid explorers charting uncharted territories, we gather our tools of inquiry and set our gaze upon the pulsating heartbeats of raw data. Bon voyage!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In the pursuit of unraveling the enigmatic entanglement between air pollution in Washington, D.C. and the utilization of kerosene in Peru, our investigation delves into an array of scholarly works that span diverse disciplines and geographic locales. The journey commences with the seminal work of Smith et al. (2015), whose pioneering study on ambient air quality monitoring provides a solid foundation for comprehending the intricate nuances of atmospheric pollutants. Their diligent efforts in quantifying particulate matter and volatile organic compounds serve as a testament to the meticulous nature of air quality research, as well as a gentle nudge towards the ethereal realm of interconnected environmental phenomena.

Doe and Johnson (2018) further illuminate our path with their exhaustive examination of household energy use in developing nations, shedding light on the pervasive reliance on traditional kerosene-based lighting systems. Their qualitative insights into the socio-economic dimensions of kerosene consumption unveil a veritable tapestry of cultural practices, economic constraints, and environmental repercussions. As we navigate through the annals of scholarly discourse, it is imperative to underscore the profound impact of kerosene on the daily lives of individuals in the Peruvian hinterlands and its stealthy role in the latticework of global energy dynamics.

Venturing beyond the conventional confines of academic literature, our foray into the realm of non-fiction books leads us to “The Energy of Nations: Risk Blindness and the Road to Renaissance” by Jones (2013), a compelling treatise on the vexing conundrums of energy policy and resource allocation. While not directly focused on kerosene, Jones' exploration of energy landscapes invites contemplation of the intricate webs that entwine disparate energy sources and their socio-environmental footprints. This broader perspective prods us to ponder the sublime interplay between the urban pangs of energy demand in Washington and the rustic reliance on kerosene in Peru, as if two protagonists in a cosmic ballet.

Shifting gears, our exploratory trajectory meanders into the realm of fiction, where mysterious narratives beckon us to ponder the unforeseen connections that entwine seemingly unrelated motifs. Consider "The Light Between Oceans" by M. L. Stedman and "The Perks of Being a Wallflower" by Stephen Chbosky, whose evocative prose and captivating plots weave tales of human emotions and interwoven destinies—albeit without direct references to air pollution or kerosene. Yet, in the whimsical tapestry of literary imagination, we find a mirrored reflection of our quest: the inexplicable resonance between disparate elements that evokes a sense of cosmic harmony, much like the uncanny rapport we seek to unearth between pollutants in distant skies and the luminous fervor of kerosene in remote abodes.

As we traverse through the disparate realms of writing, we take a moment to glance at celluloid fantasies that, although removed from the austere sanctum of academic discourse, subtly echo the spirit of our scholarly pursuit. "Up in the Air" (2009), a film that chronicles the peripatetic odyssey of a corporate downsizing expert, juxtaposes the ethereal vistas of airborne escapades against the dense fabric of human connections—a tenuous parallel to the ethereal dance of pollutants amidst Washington's urban expanse and the understated glow of kerosene in Peru. While our cinematic expedition may seem tangential, it evokes the spirit of unexpected correlations and concealed threads that animate our journey.

With this whimsical interplay of scholarly endeavors, societal reflections, fictional musings, and cinematic reveries, we set our gaze upon the impending synthesis of evidence and the impending unveiling of patterns. As we stride forth, let us not forget that even in the most earnest pursuit of knowledge, the camaraderie of humor and the charm of unexpected juxtapositions linger as steadfast companions.

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 Washington, D.C. and Kerosene used in Peru. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru

[[ABSTRACT]]
The present study delves into the intercontinental relationship between air pollution levels in the esteemed city of Washington, D.C. and the utilization of kerosene in the charming landscapes of Peru. Through a meticulous analysis of data sourced from the revered Environmental Protection Agency and the illustrious Energy Information Administration, a striking correlation emerged. With a correlation coefficient of 0.9031611 and a p-value less than the conventional threshold of 0.01, our findings reveal a compelling association between air pollution in the U.S. capital and the consumption of kerosene in the Peruvian realm from 1980 to 2021.

As we unravel the perplexing connection between these seemingly disparate domains, it is imperative to acknowledge the mesmerizing intricacies that intertwine our world. While the air in Washington may leave citizens and policymakers “polluted” with concerns, the humble kerosene lamps in Peru continue to illuminate not just the homes, but also the landscape of our study. As we explore the intricate tapestry of air pollutants and kerosene kinship, we invite readers to join us in this enchanting journey of unexpected correlations and cross-continental connections.

[[LITERATURE REVIEW]]
In the pursuit of unraveling the enigmatic entanglement between air pollution in Washington, D.C. and the utilization of kerosene in Peru, our investigation delves into an array of scholarly works that span diverse disciplines and geographic locales. The journey commences with the seminal work of Smith et al. (2015), whose pioneering study on ambient air quality monitoring provides a solid foundation for comprehending the intricate nuances of atmospheric pollutants. Their diligent efforts in quantifying particulate matter and volatile organic compounds serve as a testament to the meticulous nature of air quality research, as well as a gentle nudge towards the ethereal realm of interconnected environmental phenomena.
Doe and Johnson (2018) further illuminate our path with their exhaustive examination of household energy use in developing nations, shedding light on the pervasive reliance on traditional kerosene-based lighting systems. Their qualitative insights into the socio-economic dimensions of kerosene consumption unveil a veritable tapestry of cultural practices, economic constraints, and environmental repercussions. As we navigate through the annals of scholarly discourse, it is imperative to underscore the profound impact of kerosene on the daily lives of individuals in the Peruvian hinterlands and its stealthy role in the latticework of global energy dynamics.
Venturing beyond the conventional confines of academic literature, our foray into the realm of non-fiction books leads us to “The Energy of Nations: Risk Blindness and the Road to Renaissance” by Jones (2013), a compelling treatise on the vexing conundrums of energy policy and resource allocation. While not directly focused on kerosene, Jones' exploration of energy landscapes invites contemplation of the intricate webs that entwine disparate energy sources and their socio-environmental footprints. This broader perspective prods us to ponder the sublime interplay between the urban pangs of energy demand in Washington and the rustic reliance on kerosene in Peru, as if two protagonists in a cosmic ballet.
Shifting gears, our exploratory trajectory meanders into the realm of fiction, where mysterious narratives beckon us to ponder the unforeseen connections that entwine seemingly unrelated motifs. Consider "The Light Between Oceans" by M. L. Stedman and "The Perks of Being a Wallflower" by Stephen Chbosky, whose evocative prose and captivating plots weave tales of human emotions and interwoven destinies—albeit without direct references to air pollution or kerosene. Yet, in the whimsical tapestry of literary imagination, we find a mirrored reflection of our quest: the inexplicable resonance between disparate elements that evokes a sense of cosmic harmony, much like the uncanny rapport we seek to unearth between pollutants in distant skies and the luminous fervor of kerosene in remote abodes.
As we traverse through the disparate realms of writing, we take a moment to glance at celluloid fantasies that, although removed from the austere sanctum of academic discourse, subtly echo the spirit of our scholarly pursuit. "Up in the Air" (2009), a film that chronicles the peripatetic odyssey of a corporate downsizing expert, juxtaposes the ethereal vistas of airborne escapades against the dense fabric of human connections—a tenuous parallel to the ethereal dance of pollutants amidst Washington's urban expanse and the understated glow of kerosene in Peru. While our cinematic expedition may seem tangential, it evokes the spirit of unexpected correlations and concealed threads that animate our journey.
With this whimsical interplay of scholarly endeavors, societal reflections, fictional musings, and cinematic reveries, we set our gaze upon the impending synthesis of evidence and the impending unveiling of patterns. As we stride forth, let us not forget that even in the most earnest pursuit of knowledge, the camaraderie of humor and the charm of unexpected juxtapositions linger as steadfast companions.

[[RESULTS]]
The quantitative analysis conducted in this study unearthed a robust correlation between air pollution levels in Washington, D.C. and kerosene consumption in Peru. The correlation coefficient of 0.9031611 suggests a strong positive relationship between these seemingly disparate variables. The coefficient of determination (r-squared) of 0.8156999 indicates that approximately 81.6% of the variability in kerosene consumption can be explained by the changes in air pollution levels. With a p-value lower than the conventional threshold of 0.01, the evidence overwhelmingly supports the existence of a significant association between the two phenomena.
The visual representation of this noteworthy correlation is encapsulated in Figure 1, a scatterplot that vividly portrays the mesmerizing dance of intercontinental connections. Through this figure, the audience is invited to marvel at the compelling relationship between the atmospheric burdens of one nation and the luminous presence of kerosene in another, as if the two were engaged in a cosmic waltz across time and space.
The implications of these findings extend beyond the realm of statistical conventions, offering a whimsical glimpse into the entangled tapestry of our world. Just as the moon exerts its captivating influence on the ebb and flow of tides, so too do the forces of air pollution in a bustling city intertwine with the flickering glow of kerosene lamps in a distant countryside. This correlation, not bound by geographical limitations, invites us to ponder the harmonious resonance of seemingly incongruent elements.
As we acknowledge the robustness of these results, it is incumbent upon us to recognize the enchanting nature of this relationship. While air pollution in Washington, D.C. may seem to drift in the air of policy discussions, the utilization of kerosene in Peru continues to illuminate not just the homes, but also the pathway to unexpected revelations. The precise mechanism underlying this link remains a subject of further inquiry, perhaps weaving an intriguing narrative akin to a mystery novel that captivates readers with each unforeseen twist.
In summary, the empirical evidence presented in this study underscores the captivating connection between air pollution in Washington, D.C. and the consumption of kerosene in Peru. The sheer magnitude of this correlation invites researchers and enthusiasts alike to ponder the kaleidoscopic network of influences that shapes our world, beckoning them to embrace the unexpected and celebrate the grand symphony of intercontinental kinship.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

The robust correlation between air pollution in Washington, D.C. and the consumption of kerosene in Peru, as demonstrated in our study, is a testament to the unexpected connections that permeate our world. Building on the literature review's subtle nods to unexpected correlations, our findings not only support previous research but also unravel an enthralling narrative of intercontinental kinship.

As Smith et al. (2015) paved the way for understanding atmospheric pollutants, and Doe and Johnson (2018) shed light on kerosene reliance in developing nations, our study adds a whimsical twist by showcasing how the pollutants in the capital of the United States engage in an intricate dance with the humble kerosene lamps in the Peruvian hinterlands. This correlation, akin to the unpredictable twists in fiction and cinematic reveries, captures the imagination with its unexpected symphony of influence.

Furthermore, our results echo Jones' (2013) exploration of energy landscapes, hinting at a parallel between the urban demands of Washington and the rural reliance on kerosene in Peru – as if two protagonists in a cosmic ballet, playing out their extraordinary connection across continental boundaries. The unexpected resonance between disparate elements, much like the serendipitous connections in literature, unveils a grand narrative of harmonious interplay.

In light of these findings, it is imperative to recognize the sheer magnitude of this correlation and the tantalizing allure of the uncharted territory it represents. While the precise mechanism underlying this link remains a subject of further inquiry, it beckons researchers to embrace the unexpected and revel in the grand symphony of intercontinental kinship, akin to a mystery novel that captivates readers with each unforeseen twist.

This study, with its quantitatively robust findings, not only complements the existing scholarly discourse but also infuses it with a touch of whimsy and wonder. As the audience marvels at the compelling relationship between air pollution in one nation and the luminous presence of kerosene in another, we invite them to partake in this enchanting journey of unexpected correlations and cross-continental connections.

The correlation unearthed in this study, while humorously unlikely in some respects, underscores the interconnectedness of seemingly disparate elements, creating an enchanting narrative of intercontinental kinship that piques the imagination and fosters a deeper appreciation for the manifold interactions that shape our world.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Washington, D.C. and Kerosene used in Peru. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 300 tokens. At the very end, assert that no more research is needed in this area.

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru

[[ABSTRACT]]
The present study delves into the intercontinental relationship between air pollution levels in the esteemed city of Washington, D.C. and the utilization of kerosene in the charming landscapes of Peru. Through a meticulous analysis of data sourced from the revered Environmental Protection Agency and the illustrious Energy Information Administration, a striking correlation emerged. With a correlation coefficient of 0.9031611 and a p-value less than the conventional threshold of 0.01, our findings reveal a compelling association between air pollution in the U.S. capital and the consumption of kerosene in the Peruvian realm from 1980 to 2021.

As we unravel the perplexing connection between these seemingly disparate domains, it is imperative to acknowledge the mesmerizing intricacies that intertwine our world. While the air in Washington may leave citizens and policymakers “polluted” with concerns, the humble kerosene lamps in Peru continue to illuminate not just the homes, but also the landscape of our study. As we explore the intricate tapestry of air pollutants and kerosene kinship, we invite readers to join us in this enchanting journey of unexpected correlations and cross-continental connections.

[[INTRDUCTION]]
The enchanting dance of interconnectedness in our world has long captivated the curious minds of researchers. In our quest to untangle the web of cause and effect, we are often drawn to the most unexpected pairings. Enter the mysterious liaison between air pollution in Washington, D.C. and the unassuming kerosene used in Peru. Our journey begins with a seemingly mundane research question: Could there truly be a link between the atmospheric woes of a bustling metropolis and the flickering glow of kerosene lamps in a land renowned for its natural beauty?
As we embark on this scholarly escapade, we are reminded of the sage words of Heraclitus, who famously mused that "The only thing that is constant is change." Our investigation seeks not just to uncover an association, but to embrace the ceaseless ebb and flow of influences that transcend geographical boundaries and cultural divides. While the details may appear esoteric at first glance, we assure the reader that the implications of our findings are far-reaching, much like the tendrils of a creeping vine.
Air pollution, with its ominous veil lingering over urban landscapes, has become a quintessential emblem of industrial progress – a dark cloud, if you will, looming over our collective aspirations for sustainable living. In juxtaposition, the humble kerosene lamp, perched like a steadfast sentry in rural abodes, exudes a warmth that is both literal and metaphorical. It is with this dichotomous backdrop that we embark on our scholarly odyssey, guided not just by data and statistics, but by the whimsy of discovery and the allure of unexpected revelations.
Now, dear reader, let us venture forth into the labyrinthine corridors of statistical analysis, where the cool embrace of correlation coefficients and the enigmatic whispers of p-values shall beckon us further. Like intrepid explorers charting uncharted territories, we gather our tools of inquiry and set our gaze upon the pulsating heartbeats of raw data. Bon voyage!

[[RESULTS]]
The quantitative analysis conducted in this study unearthed a robust correlation between air pollution levels in Washington, D.C. and kerosene consumption in Peru. The correlation coefficient of 0.9031611 suggests a strong positive relationship between these seemingly disparate variables. The coefficient of determination (r-squared) of 0.8156999 indicates that approximately 81.6% of the variability in kerosene consumption can be explained by the changes in air pollution levels. With a p-value lower than the conventional threshold of 0.01, the evidence overwhelmingly supports the existence of a significant association between the two phenomena.
The visual representation of this noteworthy correlation is encapsulated in Figure 1, a scatterplot that vividly portrays the mesmerizing dance of intercontinental connections. Through this figure, the audience is invited to marvel at the compelling relationship between the atmospheric burdens of one nation and the luminous presence of kerosene in another, as if the two were engaged in a cosmic waltz across time and space.
The implications of these findings extend beyond the realm of statistical conventions, offering a whimsical glimpse into the entangled tapestry of our world. Just as the moon exerts its captivating influence on the ebb and flow of tides, so too do the forces of air pollution in a bustling city intertwine with the flickering glow of kerosene lamps in a distant countryside. This correlation, not bound by geographical limitations, invites us to ponder the harmonious resonance of seemingly incongruent elements.
As we acknowledge the robustness of these results, it is incumbent upon us to recognize the enchanting nature of this relationship. While air pollution in Washington, D.C. may seem to drift in the air of policy discussions, the utilization of kerosene in Peru continues to illuminate not just the homes, but also the pathway to unexpected revelations. The precise mechanism underlying this link remains a subject of further inquiry, perhaps weaving an intriguing narrative akin to a mystery novel that captivates readers with each unforeseen twist.
In summary, the empirical evidence presented in this study underscores the captivating connection between air pollution in Washington, D.C. and the consumption of kerosene in Peru. The sheer magnitude of this correlation invites researchers and enthusiasts alike to ponder the kaleidoscopic network of influences that shapes our world, beckoning them to embrace the unexpected and celebrate the grand symphony of intercontinental kinship.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our enthralling journey through the labyrinthine corridors of statistical analysis has culminated in the revelation of a striking connection between air pollution in Washington, D.C. and the consumption of kerosene in Peru. The robust correlation coefficient and the alluring dance of intercontinental connections depicted in Figure 1 beckon us to ponder the whimsical tapestry of global interdependencies.

While the precise mechanisms underlying this connection remain shrouded in mystery, perhaps as enigmatic as the allure of a magician's disappearing act, we cannot discount the bewitching influence of this kerosene-tinged symphony that transcends geographical boundaries. As we bid adieu to this beguiling exploration, it is imperative to acknowledge the profound impact of our findings and their potential to illuminate not just homes, but the very essence of unexpected kinship.

With the tantalizing dance of correlation and causation guiding us, we assert that no more research is needed in this area. The interconnectedness of our world has been unraveled, leaving us with a sense of awe akin to witnessing a rare celestial alignment. As we reflect on this study, let us embrace the unexpected revelations and celebrate the grand symphony of intercontinental kinship, for in the words of Carl Sagan, "Somewhere, something incredible is waiting to be known."

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 Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Ecological Synchronicity

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 Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Environmental Epidemiology

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 Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru with an abstract of The present study delves into the intercontinental relationship between air pollution levels in the esteemed city of Washington, D.C. and the utilization of kerosene in the charming landscapes of Peru. Through a meticulous analysis of data sourced from the revered Environmental Protection Agency and the illustrious Energy Information Administration, a striking correlation emerged. With a correlation coefficient of 0.9031611 and a p-value less than the conventional threshold of 0.01, our findings reveal a compelling association between air pollution in the U.S. capital and the consumption of kerosene in the Peruvian realm from 1980 to 2021.
As we unravel the perplexing connection between these seemingly disparate domains, it is imperative to acknowledge the mesmerizing intricacies that intertwine our world. While the air in Washington may leave citizens and policymakers “polluted” with concerns, the humble kerosene lamps in Peru continue to illuminate not just the homes, but also the landscape of our study. As we explore the intricate tapestry of air pollutants and kerosene kinship, we invite readers to join us in this enchanting journey of unexpected correlations and cross-continental connections.

ChatGPT:

air pollution, Washington D.C., kerosene consumption, Peru, intercontinental relationship, environmental protection agency, energy information administration, correlation coefficient, p-value, air pollutants, kerosene lamps, cross-continental connections

*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 Washington, D.C.
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Washington-Arlington-Alexandria, DC-VA-MD-WV
Source: Environmental Protection Agency
See what else correlates with Air pollution in Washington, D.C.

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

Correlation r = 0.9031611 (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 = 0.8156999 (Coefficient of determination)
This means 81.6% of the change in the one variable (i.e., Kerosene used in Peru) is predictable based on the change in the other (i.e., Air pollution in Washington, D.C.) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.8E-16.^Show 0.0000000000000002822499603295
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 0.9 in 2.8E-14% of random cases. Said differently, if you correlated 3,542,958,868,205,314 random variables^Note You don't actually need 3 quadrillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 41 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 41 because we have two variables measured over a period of 42 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.83, 0.95 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1980	1981	1982	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Air pollution in Washington, D.C. (Bad air quality days)	30.0546	24.3836	24.3836	30.411	26.776	28.4932	26.5753	29.3151	25.6831	22.7397	23.8356	30.411	15.847	25.7534	21.0959	20	16.6667	18.9041	23.8356	24.3836	17.4863	21.3699	22.4658	13.1507	11.2022	16.1644	15.0685	18.0822	10.3825	3.56164	13.6986	10.6849	9.83607	3.28767	2.73973	3.83562	4.37158	2.19178	2.73973	3.0137	0.819672	2.73973
Kerosene used in Peru (Million Barrels/Day)	18.6082	19.1679	19.028	17.349	17.7688	17.489	19	22	22	18	16	15	6.9	15	13	14	14	14	14	14	14.0449	14.8882	14.9517	10.8008	6.84295	4.42622	1.77896	1.16479	0.97153	1.52482	1.41893	1.39775	1.03489	1.14362	1.24951	1	1	0.782137	0.412795	0.0651781	0.0434521	0.0434521

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([30.0546,24.3836,24.3836,30.411,26.776,28.4932,26.5753,29.3151,25.6831,22.7397,23.8356,30.411,15.847,25.7534,21.0959,20,16.6667,18.9041,23.8356,24.3836,17.4863,21.3699,22.4658,13.1507,11.2022,16.1644,15.0685,18.0822,10.3825,3.56164,13.6986,10.6849,9.83607,3.28767,2.73973,3.83562,4.37158,2.19178,2.73973,3.0137,0.819672,2.73973,])
array_2 = np.array([18.6082,19.1679,19.028,17.349,17.7688,17.489,19,22,22,18,16,15,6.9,15,13,14,14,14,14,14,14.0449,14.8882,14.9517,10.8008,6.84295,4.42622,1.77896,1.16479,0.97153,1.52482,1.41893,1.39775,1.03489,1.14362,1.24951,1,1,0.782137,0.412795,0.0651781,0.0434521,0.0434521,])
array_1_name = "Air pollution in Washington, D.C."
array_2_name = "Kerosene used in Peru"

# 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 Washington, D.C.
Line chart for only Kerosene used in Peru
AI-generated correlation image
The spurious research paper: Kerosene Kismet: Connecting Air Pollution in Washington, D.C. to Kerosene Consumption in Peru

View another random correlation

How fun was this correlation?

Big thanks for reviewing!

Correlation ID: 3396 · Black Variable ID: 21421 · Red Variable ID: 24811


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