Spurious correlation #3,494 · 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 St. Louis and the second variable is Kerosene used in Norway. The chart goes from 1980 to 2022, 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 St. Louis and the second variable is Kerosene used in Norway. The chart goes from 1980 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The cleaner air in St. Louis led to an increase in productivity and creativity, causing a surge in wacky invention ideas. One such idea was a revolutionary anti-air pollution device using a mix of moose milk and lingonberry jam, but it had an unexpected side effect of neutralizing kerosene fumes in Norway. Who would've thought that the key to cleaner kerosene was hidden in a Scandinavian air-freshening concoction! Keep an eye out for the next big invention coming from the now-clear-aired St. Louis - could it be a jetpack fueled by toasted ravioli power?

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image of a TIME magazine cover with a striking illustration contrasting the clear, vibrant sky over St. Louis with the glowing Northern Lights in Norway. The foreground should show St. Louis with details of a clean atmosphere and clear cityscape, while in the background, the enchanting Northern Lights illuminate the Norwegian night sky. The green and purple hues of the aurora borealis should create a beautiful dance across the horizon. The visual should convey a sense of environmental change and its impact on the reduction of kerosene use. 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 St. Louis and Kerosene used in Norway. 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: Cubism a Polaroid photo Oragami Surrealism A TIME magazine cover image
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in St. Louis and Kerosene used in Norway, in the following situation: Because the decrease in air pollution in St. Louis led to clearer skies, Norwegian households no longer needed to burn kerosene to see the Northern Lights, resulting in a decrease in kerosene use in Norway.. Keep the description simple.
ChatGPT: In St. Louis, the sky is clear and vibrant with shades of blue and white cotton-like clouds. The air is noticeably cleaner, and the cityscape is visible with clarity. In the distance, the majestic Northern Lights illuminate the night sky in Norway, casting a beautiful green and purple dance across the horizon. However, there are fewer households burning kerosene to enjoy this natural wonder, as the decrease in air pollution in St. Louis has led to this reduction in kerosene use.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: In St. Louis, the sky is clear and vibrant with shades of blue and white cotton-like clouds. The air is noticeably cleaner, and the cityscape is visible with clarity. In the distance, the majestic Northern Lights illuminate the night sky in Norway, casting a beautiful green and purple dance across the horizon. However, there are fewer households burning kerosene to enjoy this natural wonder, as the decrease in air pollution in St. Louis has led to this reduction in kerosene use. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a TIME magazine cover with a striking illustration contrasting the clear, vibrant sky over St. Louis with the glowing Northern Lights in Norway. The foreground should show St. Louis with details of a clean atmosphere and clear cityscape, while in the background, the enchanting Northern Lights illuminate the Norwegian night sky. The green and purple hues of the aurora borealis should create a beautiful dance across the horizon. The visual should convey a sense of environmental change and its impact on the reduction of kerosene use.

*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 St. Louis caused Kerosene used in Norway to decrease.

AI academic paper

(Because p < 0.01)

A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

The Journal of Transcontinental Air Quality Relations

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 St. Louis and Kerosene used in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

[[ABSTRACT]]
This study delves into the unexpected link between St. Louis air pollution and kerosene usage in Norway. Utilizing data from the Environmental Protection Agency and the Energy Information Administration spanning from 1980 to 2022, we employ rigorous statistical analysis to unravel the mystery. Our research team uncovered a correlation coefficient of 0.7486429, with p < 0.01, shedding light on the curious connection between seemingly disparate locations.

The findings of our investigation suggest that there exists a significant association between air pollution in St. Louis and the consumption of kerosene in Norway. This intriguing correlation prompts us to consider factors such as international trade and atmospheric circulation patterns, as well as potential cultural influences on energy consumption. Moreover, our analysis underscores the importance of considering global interconnectedness when examining local environmental issues, for the implications reach farther than anticipated - much like a dad joke that catches you off guard.

By unpacking this enigmatic relationship, we not only expand our understanding of the interconnected nature of environmental phenomena but also hint at the potential for unanticipated connections to inspire further investigation. Our study serves as a reminder that, much like a good pun, the world is full of surprising and delightful interconnections waiting to be discovered.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The mystique of science lies not only in the pursuit of knowledge but also in the unearthing of unexpected correlations and relationships, akin to finding a hidden treasure amidst the data. In this research endeavor, we embark on a journey that unites seemingly unrelated entities – Air pollution in St. Louis and Kerosene usage in Norway. Much like a good dad joke, this venture promises to be both surprising and full of intrigue.

Air pollution, the bane of urban existence, encompasses an array of pollutants suspended in the atmosphere, from particulate matter to volatile organic compounds. The complexity of its composition rivals that of a convoluted play on words, offering endless possibilities for investigation. In parallel, kerosene maintains its reputation as a versatile energy source, lighting up the world with its warm glow. These two distinct elements, much like the setup and punchline of a classic dad joke, appear worlds apart at first glance.
However, as we delve into the statistical realm, we are drawn to the allure of uncovering connections that are as surprising as a well-timed pun. Our exploration uncovers a correlation coefficient that captures the imagination – a staggering 0.7486429, with a p-value of less than 0.01. This revelation draws parallels to a perfectly timed punchline, leaving us in awe of the hidden link between St. Louis air pollution and Norwegian kerosene usage.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The discovery of unexpected connections between seemingly unrelated phenomena has long intrigued researchers. Smith et al. (2015) delved into the complexities of air pollution in urban environments, examining the intricate interplay of various pollutants. Concurrently, Doe and Jones (2018) conducted a comprehensive analysis of energy consumption patterns in Scandinavian countries, shedding light on the prevalent use of kerosene in Norway. These studies initially appear as unrelated as a moose in a desert, yet the current investigation brings these disparate strands together in an unexpected union akin to a well-crafted dad joke.

In "Air Pollution and Its Effects on Urban Populations," Smith et al. (2015) uncover the intricate web of air pollutants that plague bustling cities, painting a detailed portrait of atmospheric challenges. Similarly, "Norwegian Energy Landscape: A Comprehensive Analysis," authored by Doe and Jones (2018), illuminates the unique energy dynamics in Norway, where kerosene holds a significant position. The juxtaposition of these works sets the stage for the unforeseen correlation uncovered in the present study, demonstrating the surprise element akin to an unexpected dad joke.

As we venture further into the literature, we encounter non-fiction works such as "The Economics of Air Pollution" by John Smith, delving into the economic ramifications of urban air pollution. Additionally, "Energy Shift: A Cultural Analysis of Scandinavian Energy Practices" by Sarah Doe offers insights into the societal dynamics influencing energy consumption in the region. These credible sources anchor the current investigation within a web of scholarly discourse, albeit with a pinch of humor akin to a dad joke's pun.

Beyond the realm of non-fiction, literature offers further insights that, though fictional, hold relevance to the present inquiry. "The Polluted City Chronicles" by A. P. Novelist presents a dystopian vision of urban air pollution, underscoring the overarching impact of environmental degradation. Another fictional work, "Kerosene Tales: Stories of Illumination and Intrigue" by J. K. Rowling, provides a whimsical exploration of kerosene's role in imaginative narratives. Such literary diversions serve as a lighthearted parallel to the unexpected link between the air pollution in St. Louis and the use of kerosene in Norway.

Moreover, cinematic engagements add a visual dimension to our exploration, with movies like "The Foggy Affair" and "The Luminous Trail" offering metaphorical windows into the atmospheric and energy landscapes. These cinematic depictions, much like a good dad joke, serve as a delightful twist on the serious subject matter at hand, injecting a moment of levity into the rigorous pursuit of scholarly inquiry.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 St. Louis and Kerosene used in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1980 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

[[ABSTRACT]]
This study delves into the unexpected link between St. Louis air pollution and kerosene usage in Norway. Utilizing data from the Environmental Protection Agency and the Energy Information Administration spanning from 1980 to 2022, we employ rigorous statistical analysis to unravel the mystery. Our research team uncovered a correlation coefficient of 0.7486429, with p < 0.01, shedding light on the curious connection between seemingly disparate locations.

The findings of our investigation suggest that there exists a significant association between air pollution in St. Louis and the consumption of kerosene in Norway. This intriguing correlation prompts us to consider factors such as international trade and atmospheric circulation patterns, as well as potential cultural influences on energy consumption. Moreover, our analysis underscores the importance of considering global interconnectedness when examining local environmental issues, for the implications reach farther than anticipated - much like a dad joke that catches you off guard.

By unpacking this enigmatic relationship, we not only expand our understanding of the interconnected nature of environmental phenomena but also hint at the potential for unanticipated connections to inspire further investigation. Our study serves as a reminder that, much like a good pun, the world is full of surprising and delightful interconnections waiting to be discovered.

[[INTRODUCTION]]
The mystique of science lies not only in the pursuit of knowledge but also in the unearthing of unexpected correlations and relationships, akin to finding a hidden treasure amidst the data. In this research endeavor, we embark on a journey that unites seemingly unrelated entities – Air pollution in St. Louis and Kerosene usage in Norway. Much like a good dad joke, this venture promises to be both surprising and full of intrigue.

Air pollution, the bane of urban existence, encompasses an array of pollutants suspended in the atmosphere, from particulate matter to volatile organic compounds. The complexity of its composition rivals that of a convoluted play on words, offering endless possibilities for investigation. In parallel, kerosene maintains its reputation as a versatile energy source, lighting up the world with its warm glow. These two distinct elements, much like the setup and punchline of a classic dad joke, appear worlds apart at first glance.
However, as we delve into the statistical realm, we are drawn to the allure of uncovering connections that are as surprising as a well-timed pun. Our exploration uncovers a correlation coefficient that captures the imagination – a staggering 0.7486429, with a p-value of less than 0.01. This revelation draws parallels to a perfectly timed punchline, leaving us in awe of the hidden link between St. Louis air pollution and Norwegian kerosene usage.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data utilized in this study was collected from a variety of sources, with the primary contributors being the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA). These sources offered a wealth of information ranging from air pollutant levels in St. Louis to kerosene consumption statistics in Norway. The data, spanning from 1980 to 2022, provided a robust foundation for the analysis, not unlike a sturdy set of dad jokes to bring levity to a serious discussion.

Unusual Data Sources:
In addition to the EPA and EIA, our research team explored unique and unconventional sources, including weather patterns, global trade trends, and even the occasional folklore about Scandinavian energy habits. We approached data collection with a spirit of open-mindedness, recognizing that sometimes the most insightful discoveries arise from unexpected places, much like stumbling upon a pun that catches everyone by surprise.

Statistical Analysis:
To unravel the enigmatic relationship between St. Louis air pollution and Norwegian kerosene usage, we employed rigorous statistical techniques, including correlation analysis, regression models, and time series analysis. Nor did we shy away from the more unconventional statistical methods, such as the "Monte Carlo Mingle," where data points are randomized and allowed to intermingle freely in a statistical dance akin to a lively social gathering.

Causality Considerations:
Recognizing that correlation does not imply causation, we cautiously examined the direction and strength of the relationship between air pollution in St. Louis and kerosene usage in Norway. Amidst our analysis, we employed structural equation modeling and Granger causality tests to explore the potential pathways and dependencies, much like untangling the setup and punchline of a particularly elaborate dad joke to trace its logical progression.

Sensitivity Analysis:
Given the complex and multifaceted nature of environmental and energy data, we conducted sensitivity analyses to test the robustness of our findings. Sensitivity checks involved perturbing the data inputs and model specifications, similar to a comedic timing check to ensure that our statistical conclusions were not overly reliant on specific assumptions or outliers.

Ethical Considerations:
As ardent proponents of academic integrity and responsible research conduct, we ensured that our data collection and analysis adhered to ethical standards and regulatory guidelines, akin to the meticulous care taken to craft a tasteful and appropriate dad joke that respects its audience.

Overall, our methodological approach aimed to unravel the surprising relationship between air pollution in St. Louis and kerosene usage in Norway with the same level of meticulousness and dedication as crafting a well-crafted, unexpected dad joke.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 St. Louis and Kerosene used in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

[[ABSTRACT]]
This study delves into the unexpected link between St. Louis air pollution and kerosene usage in Norway. Utilizing data from the Environmental Protection Agency and the Energy Information Administration spanning from 1980 to 2022, we employ rigorous statistical analysis to unravel the mystery. Our research team uncovered a correlation coefficient of 0.7486429, with p < 0.01, shedding light on the curious connection between seemingly disparate locations.

The findings of our investigation suggest that there exists a significant association between air pollution in St. Louis and the consumption of kerosene in Norway. This intriguing correlation prompts us to consider factors such as international trade and atmospheric circulation patterns, as well as potential cultural influences on energy consumption. Moreover, our analysis underscores the importance of considering global interconnectedness when examining local environmental issues, for the implications reach farther than anticipated - much like a dad joke that catches you off guard.

By unpacking this enigmatic relationship, we not only expand our understanding of the interconnected nature of environmental phenomena but also hint at the potential for unanticipated connections to inspire further investigation. Our study serves as a reminder that, much like a good pun, the world is full of surprising and delightful interconnections waiting to be discovered.

[[LITERATURE REVIEW]]
The discovery of unexpected connections between seemingly unrelated phenomena has long intrigued researchers. Smith et al. (2015) delved into the complexities of air pollution in urban environments, examining the intricate interplay of various pollutants. Concurrently, Doe and Jones (2018) conducted a comprehensive analysis of energy consumption patterns in Scandinavian countries, shedding light on the prevalent use of kerosene in Norway. These studies initially appear as unrelated as a moose in a desert, yet the current investigation brings these disparate strands together in an unexpected union akin to a well-crafted dad joke.
In "Air Pollution and Its Effects on Urban Populations," Smith et al. (2015) uncover the intricate web of air pollutants that plague bustling cities, painting a detailed portrait of atmospheric challenges. Similarly, "Norwegian Energy Landscape: A Comprehensive Analysis," authored by Doe and Jones (2018), illuminates the unique energy dynamics in Norway, where kerosene holds a significant position. The juxtaposition of these works sets the stage for the unforeseen correlation uncovered in the present study, demonstrating the surprise element akin to an unexpected dad joke.
As we venture further into the literature, we encounter non-fiction works such as "The Economics of Air Pollution" by John Smith, delving into the economic ramifications of urban air pollution. Additionally, "Energy Shift: A Cultural Analysis of Scandinavian Energy Practices" by Sarah Doe offers insights into the societal dynamics influencing energy consumption in the region. These credible sources anchor the current investigation within a web of scholarly discourse, albeit with a pinch of humor akin to a dad joke's pun.
Beyond the realm of non-fiction, literature offers further insights that, though fictional, hold relevance to the present inquiry. "The Polluted City Chronicles" by A. P. Novelist presents a dystopian vision of urban air pollution, underscoring the overarching impact of environmental degradation. Another fictional work, "Kerosene Tales: Stories of Illumination and Intrigue" by J. K. Rowling, provides a whimsical exploration of kerosene's role in imaginative narratives. Such literary diversions serve as a lighthearted parallel to the unexpected link between the air pollution in St. Louis and the use of kerosene in Norway.
Moreover, cinematic engagements add a visual dimension to our exploration, with movies like "The Foggy Affair" and "The Luminous Trail" offering metaphorical windows into the atmospheric and energy landscapes. These cinematic depictions, much like a good dad joke, serve as a delightful twist on the serious subject matter at hand, injecting a moment of levity into the rigorous pursuit of scholarly inquiry.

[[RESULTS]]
The analysis of the data from 1980 to 2022 revealed a remarkable correlation coefficient of 0.7486429 between air pollution levels in St. Louis and kerosene usage in Norway. This strong correlation indicates a striking relationship between these seemingly unrelated variables, much like when your dad unexpectedly comes up with a clever pun at the dinner table.
Further assessment of the data yielded an r-squared value of 0.5604662, suggesting that approximately 56.05% of the variation in kerosene usage in Norway can be explained by the variation in St. Louis air pollution levels. This substantial explanatory power underscores the significance of this unexpected relationship, akin to the punchline that ties together an entire story of interconnectedness.
With a p-value of less than 0.01, the results indicate a high level of statistical significance, reinforcing the credibility of the observed correlation. Much like a well-received dad joke, this finding demands attention and prompts further exploration of the potential mechanisms driving this intriguing association.
Figure 1 showcases a scatterplot illustrating the compelling correlation between air pollution in St. Louis and kerosene usage in Norway. The figure serves as a visual testament to the unexpected interconnectedness between these variables, not unlike a witty remark that leaves an audience pleasantly surprised.
These findings challenge conventional assumptions and emphasize the need to consider global interdependencies when addressing localized environmental issues. This study highlights the potential for unanticipated connections to inspire further research and serves as a reminder that, much like a well-crafted pun, the world is abundant with surprising and delightful interrelationships waiting to be uncovered.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study support the previous research by Smith et al. (2015) and Doe and Jones (2018), thus confirming the surprising relationship between St. Louis air pollution and Norwegian kerosene usage. This unexpected correlation, much like a sudden dad joke, challenges conventional assumptions and underscores the intricacies of global interconnectedness. The substantial correlation coefficient and the high level of statistical significance, akin to a well-received dad joke, add weight to the legitimacy of the observed association.

The literature review laid the foundation for our investigation, bridging unrelated phenomena in a manner reminiscent of a well-crafted dad joke. The unexpected union of urban air pollution dynamics with energy consumption patterns in Norway, initially as unrelated as a moose in a desert, exemplifies the delight of uncovering unanticipated connections. By juxtaposing the fictional and cinematic works alongside scholarly discourse, we lent a lighthearted dimension to the seriousness of our inquiry, akin to the brief levity of a carefully timed dad joke.

The strong correlation coefficient of 0.7486429, quite like a dad joke catching you off guard, implies that there is a substantial relationship between air pollution in St. Louis and kerosene usage in Norway. The r-squared value of 0.5604662 indicates that a considerable proportion of the variation in kerosene usage in Norway can be ascribed to the variation in St. Louis air pollution levels. This statistical relationship underscores the unexpected interconnectedness of these variables, much like the punchline that brings together seemingly unrelated elements of a joke.

The visual representation of the correlation through the scatterplot, akin to a witty retort that surprises the audience, provides a compelling testament to the unanticipated interconnectedness between air pollution in St. Louis and kerosene usage in Norway. This unexpected relationship challenges conventional assumptions, much like a clever pun, and underscores the need to consider global interdependencies when addressing localized environmental issues.

In conclusion, our study not only confirms the unexpected relationship between St. Louis air pollution and Norwegian kerosene usage but also emphasizes the potential for unanticipated connections to inspire further research. The intertwining of seemingly unrelated phenomena, much like a well-crafted dad joke, serves as a reminder of the surprising and delightful interconnections waiting to be discovered in the world of scientific inquiry.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 St. Louis and Kerosene used in Norway. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

[[ABSTRACT]]
This study delves into the unexpected link between St. Louis air pollution and kerosene usage in Norway. Utilizing data from the Environmental Protection Agency and the Energy Information Administration spanning from 1980 to 2022, we employ rigorous statistical analysis to unravel the mystery. Our research team uncovered a correlation coefficient of 0.7486429, with p < 0.01, shedding light on the curious connection between seemingly disparate locations.

The findings of our investigation suggest that there exists a significant association between air pollution in St. Louis and the consumption of kerosene in Norway. This intriguing correlation prompts us to consider factors such as international trade and atmospheric circulation patterns, as well as potential cultural influences on energy consumption. Moreover, our analysis underscores the importance of considering global interconnectedness when examining local environmental issues, for the implications reach farther than anticipated - much like a dad joke that catches you off guard.

By unpacking this enigmatic relationship, we not only expand our understanding of the interconnected nature of environmental phenomena but also hint at the potential for unanticipated connections to inspire further investigation. Our study serves as a reminder that, much like a good pun, the world is full of surprising and delightful interconnections waiting to be discovered.

[[INTRDUCTION]]
The mystique of science lies not only in the pursuit of knowledge but also in the unearthing of unexpected correlations and relationships, akin to finding a hidden treasure amidst the data. In this research endeavor, we embark on a journey that unites seemingly unrelated entities – Air pollution in St. Louis and Kerosene usage in Norway. Much like a good dad joke, this venture promises to be both surprising and full of intrigue.

Air pollution, the bane of urban existence, encompasses an array of pollutants suspended in the atmosphere, from particulate matter to volatile organic compounds. The complexity of its composition rivals that of a convoluted play on words, offering endless possibilities for investigation. In parallel, kerosene maintains its reputation as a versatile energy source, lighting up the world with its warm glow. These two distinct elements, much like the setup and punchline of a classic dad joke, appear worlds apart at first glance.
However, as we delve into the statistical realm, we are drawn to the allure of uncovering connections that are as surprising as a well-timed pun. Our exploration uncovers a correlation coefficient that captures the imagination – a staggering 0.7486429, with a p-value of less than 0.01. This revelation draws parallels to a perfectly timed punchline, leaving us in awe of the hidden link between St. Louis air pollution and Norwegian kerosene usage.

[[RESULTS]]
The analysis of the data from 1980 to 2022 revealed a remarkable correlation coefficient of 0.7486429 between air pollution levels in St. Louis and kerosene usage in Norway. This strong correlation indicates a striking relationship between these seemingly unrelated variables, much like when your dad unexpectedly comes up with a clever pun at the dinner table.
Further assessment of the data yielded an r-squared value of 0.5604662, suggesting that approximately 56.05% of the variation in kerosene usage in Norway can be explained by the variation in St. Louis air pollution levels. This substantial explanatory power underscores the significance of this unexpected relationship, akin to the punchline that ties together an entire story of interconnectedness.
With a p-value of less than 0.01, the results indicate a high level of statistical significance, reinforcing the credibility of the observed correlation. Much like a well-received dad joke, this finding demands attention and prompts further exploration of the potential mechanisms driving this intriguing association.
Figure 1 showcases a scatterplot illustrating the compelling correlation between air pollution in St. Louis and kerosene usage in Norway. The figure serves as a visual testament to the unexpected interconnectedness between these variables, not unlike a witty remark that leaves an audience pleasantly surprised.
These findings challenge conventional assumptions and emphasize the need to consider global interdependencies when addressing localized environmental issues. This study highlights the potential for unanticipated connections to inspire further research and serves as a reminder that, much like a well-crafted pun, the world is abundant with surprising and delightful interrelationships waiting to be uncovered.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the connection between St. Louis air pollution and Norwegian kerosene usage has unearthed a surprising and robust correlation, not unlike stumbling upon a hidden gem in a pile of data. This unexpected relationship, much like a well-timed dad joke, has broad implications for our understanding of global environmental interconnectivity.

The significant correlation coefficient and high level of statistical significance point to a compelling association between these variables, reminiscent of a clever pun that ties together seemingly unrelated elements. The r-squared value further emphasizes the substantial explanatory power of St. Louis air pollution levels on kerosene usage in Norway, serving as a solid punchline to this intriguing scientific investigation.

The results not only challenge traditional assumptions but also highlight the intricate web of global dependencies, much like a complex scientific formula waiting to be unraveled. Our study serves as a reminder that the world is full of unexpected and delightful connections, not unlike a well-crafted dad joke that catches you pleasantly off guard.

Given the compelling findings of this research, it is clear that no further exploration in this area is warranted. The correlation between St. Louis air pollution and Norwegian kerosene usage has been established with great certainty, leaving us with no more questions to answer - pun intended.

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 A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Transcontinental Air Quality Relations

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 A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Global Air Quality and Aviation Study

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 A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage with an abstract of This study delves into the unexpected link between St. Louis air pollution and kerosene usage in Norway. Utilizing data from the Environmental Protection Agency and the Energy Information Administration spanning from 1980 to 2022, we employ rigorous statistical analysis to unravel the mystery. Our research team uncovered a correlation coefficient of 0.7486429, with p < 0.01, shedding light on the curious connection between seemingly disparate locations.
The findings of our investigation suggest that there exists a significant association between air pollution in St. Louis and the consumption of kerosene in Norway. This intriguing correlation prompts us to consider factors such as international trade and atmospheric circulation patterns, as well as potential cultural influences on energy consumption. Moreover, our analysis underscores the importance of considering global interconnectedness when examining local environmental issues, for the implications reach farther than anticipated - much like a dad joke that catches you off guard.
By unpacking this enigmatic relationship, we not only expand our understanding of the interconnected nature of environmental phenomena but also hint at the potential for unanticipated connections to inspire further investigation. Our study serves as a reminder that, much like a good pun, the world is full of surprising and delightful interconnections waiting to be discovered.

ChatGPT:

St. Louis air pollution, Norwegian kerosene usage, environmental impact of kerosene, international trade and air pollution, atmospheric circulation patterns and energy consumption, global interconnectedness in environmental issues, surprising correlations in environmental data, cultural influences on energy consumption, interconnected nature of environmental phenomena

*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 St. Louis
Detailed data title: Percentage of days 'unhealthy' or worse air quality in St. Louis, MO-IL
Source: Environmental Protection Agency
See what else correlates with Air pollution in St. Louis

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

Correlation r = 0.7486429 (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 = 0.5604662 (Coefficient of determination)
This means 56% of the change in the one variable (i.e., Kerosene used in Norway) is predictable based on the change in the other (i.e., Air pollution in St. Louis) over the 43 years from 1980 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.8E-9.^Show 0.0000000078048318511571720000
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 0.75 in 7.8E-7% of random cases. Said differently, if you correlated 128,125,758 random variables^Note You don't actually need 128 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 42 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 42 because we have two variables measured over a period of 43 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.58, 0.86 ] 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	2022
Air pollution in St. Louis (Bad air quality days)	18.0328	5.47945	4.38356	14.5205	9.83607	6.0274	6.84932	9.86301	13.9344	6.30137	6.84932	8.49315	3.55191	2.19178	8.76712	11.2329	6.01093	3.56164	6.57534	7.94521	4.64481	4.10959	8.49315	3.0137	0.546448	7.67123	4.65753	6.30137	0.273224	0.273973	1.91781	3.0137	5.46448	0.547945	0	0.547945	0.546448	0.273973	0.547945	0.547945	0.273224	0.547945	0
Kerosene used in Norway (Million Barrels/Day)	14	10	7	8	3.72404	4.46849	5.09589	5.37534	4.95082	4.10411	3.43836	3.2137	3.27322	3.30411	3.58356	3.45753	4.04918	3.73699	3.38356	3.32603	2.45082	2.7452	2.76438	3.21096	2.71585	2.24658	2.24658	1.76712	1.3306	1.16164	1.42466	1.0411	0.73224	0.942466	0.69589	0.558904	0.530055	0.260274	0.260274	0.076712	0.032787	0.032877	0.021918

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.
Outlandish outliers: There are "outliers" in this data.^Note In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

(This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.

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([18.0328,5.47945,4.38356,14.5205,9.83607,6.0274,6.84932,9.86301,13.9344,6.30137,6.84932,8.49315,3.55191,2.19178,8.76712,11.2329,6.01093,3.56164,6.57534,7.94521,4.64481,4.10959,8.49315,3.0137,0.546448,7.67123,4.65753,6.30137,0.273224,0.273973,1.91781,3.0137,5.46448,0.547945,0,0.547945,0.546448,0.273973,0.547945,0.547945,0.273224,0.547945,0,])
array_2 = np.array([14,10,7,8,3.72404,4.46849,5.09589,5.37534,4.95082,4.10411,3.43836,3.2137,3.27322,3.30411,3.58356,3.45753,4.04918,3.73699,3.38356,3.32603,2.45082,2.7452,2.76438,3.21096,2.71585,2.24658,2.24658,1.76712,1.3306,1.16164,1.42466,1.0411,0.73224,0.942466,0.69589,0.558904,0.530055,0.260274,0.260274,0.076712,0.032787,0.032877,0.021918,])
array_1_name = "Air pollution in St. Louis"
array_2_name = "Kerosene used in Norway"

# 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 St. Louis
Line chart for only Kerosene used in Norway
AI-generated correlation image
The spurious research paper: A Breath of Fresh Flare: Unveiling the Surprising Relationship Between St. Louis Air Pollution and Norwegian Kerosene Usage

View another random correlation

How fun was this correlation?

Cheers to you for rating this correlation!

Correlation ID: 3494 · Black Variable ID: 21309 · Red Variable ID: 24781


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