Spurious correlation #1,614 · 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 Terre Haute, Indiana and the second variable is Electricity generation in United Kingdom. The chart goes from 1981 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 Terre Haute, Indiana and the second variable is Electricity generation in United Kingdom. The chart goes from 1981 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The smog from Terre Haute wafted over to the UK, sparking a bizarre and electrifying reaction in their power plants. Looks like Terre Haute's air pollution is really giving a shocking performance across the pond!

^{Show image generation prompt} Model: dalle-3
Prompt: Visual Prompt: Generate an image in the style of a Discovery magazine cover, depicting Terre Haute, Indiana with smog hovering over the city due to cars and factories, contrasted with wind turbines in the United Kingdom gracefully turning against a cloudy sky. Emphasize the stark difference in air quality and environmental impact through contrasting visuals of pollution and renewable energy. 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: Less than ideal air quality in Terre Haute, Indiana and Electricity generation in United Kingdom. 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: Cyberpunk Cutsy graphics A Discovery magazine cover image Low poly Photorealism
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Less than ideal air quality in Terre Haute, Indiana and Electricity generation in United Kingdom together. Keep the description simple.
ChatGPT: In a scene in Terre Haute, Indiana, smog hovers over the city as cars and factories contribute to less than ideal air quality. Nearby, wind turbines in the United Kingdom generate electricity, turning gracefully against the backdrop of a cloudy sky.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In a scene in Terre Haute, Indiana, smog hovers over the city as cars and factories contribute to less than ideal air quality. Nearby, wind turbines in the United Kingdom generate electricity, turning gracefully against the backdrop of a cloudy sky. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Visual Prompt: Generate an image in the style of a Discovery magazine cover, depicting Terre Haute, Indiana with smog hovering over the city due to cars and factories, contrasted with wind turbines in the United Kingdom gracefully turning against a cloudy sky. Emphasize the stark difference in air quality and environmental impact through contrasting visuals of pollution and renewable energy.

*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 an increase in Air pollution in Terre Haute, Indiana caused Electricity generation in United Kingdom to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

Journal of Ecological Quirkiness

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 Terre Haute, Indiana and Electricity generation in United Kingdom. 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 cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

[[ABSTRACT]]
This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The investigation of environmental phenomena has long been a serious pursuit in the scientific community, but that doesn't mean it can't also be a hoot. In this study, we dive into the fascinating relationship between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. This unlikely pair has caught our attention due to the intriguing connection we've uncovered—almost as captivating as an episode of "The X-Files," but with more statistical rigor.
As researchers, we are constantly seeking out unexpected associations and connections in our data, much like amateur detectives in a mystery novel, except with more spreadsheets and fewer magnifying glasses. Venturing into the realm of interconnectedness, we aim to shed light on the comical, bewildering, and sometimes downright bizarre relationships that exist in the world of environmental and energy dynamics.
We assure you, dear readers, that we are not simply concocting frivolous theories for academic kicks and giggles. Our findings are firmly rooted in the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration. These organizations provide the hard facts, charts, and tables necessary to lend credibility to our musings about the surprising correlation between two geographically distant yet undeniably linked phenomena.
Our study period spans the years from 1981 to 2021, offering a panoramic view of how these whimsical connections have evolved over time. Through the application of rigorous statistical methods, we have unearthed a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01. These numbers aren't just arbitrary figures; they are the bread and butter of scientific inquiry—a bit like the "magic numbers" in a Sudoku puzzle, only with a touch less magic and a bit more significance.
In presenting our research, we hope to showcase the intriguing cross-continental tango of pollution and power. Prepare to be amused, astounded, and perhaps even a touch bemused as we embark on a journey through the labyrinth of environmental data and energy production statistics. Let us all embrace the whimsy of science and revel in the delightful absurdities that await in the world of empirical inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "The Impact of Air Pollution on Health" by Smith and Doe, the authors find evidence linking air pollution to a variety of health concerns, ranging from respiratory ailments to cardiovascular diseases. This literature underscores the pressing need to mitigate the detrimental effects of air pollution, not just for the sake of public health, but also to avoid breathing in the equivalent of a particulate soufflé.

A comprehensive analysis by Jones in "Electricity Generation and Environmental Impact" emphasizes the complexities of balancing energy demands with environmental preservation. The study delves into the intricate dance of electricity production and its ecological ramifications, painting a detailed picture of the interconnected web of power generation and environmental consequences. It's like a scholarly rendition of "The Hokey Pokey," but with kilowatts and carbon emissions instead of right feet and left feet.

Building on these foundational works, "The Economics of Air Pollution Control" by Anderson provides a detailed examination of the economic factors at play in combating air pollution. The book addresses strategies for achieving greener energy production while navigating the financial landscape, offering insights that are as valuable as finding a winning lottery ticket in a haystack.

Now, let's take a whimsical turn and explore literature that may not immediately seem related but still manages to sneak its way into the realm of our peculiar correlation. From "Great Expectations" by Charles Dickens to "To Kill a Mockingbird" by Harper Lee, fiction has always danced around issues of societal change and environmental consequences. Who knew that an air pollution study could find resonance with literary classics? It's like stumbling upon a scholarly article in the middle of a library while looking for a novel – unexpected, but utterly captivating.

But let's not stop there. How about the quirky connections we can draw from cartoons and children's shows? From "Captain Planet and the Planeteers" to "The Magic School Bus," these vibrant and imaginative portrayals of environmental issues have left an indelible mark on our perception of pollution and its impact. These shows may not be cited in academic journals, but a "Phineas and Ferb" episode about renewable energy might just contain a nugget of wisdom that our scholarly pursuits could benefit from. After all, who wouldn't want a platypus-inspired insight into environmental dynamics?

[...]

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Terre Haute, Indiana and Electricity generation in United Kingdom. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 1981 to 2021

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]]
Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

[[ABSTRACT]]
This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

[[INTRODUCTION]]
INTRODUCTION
The investigation of environmental phenomena has long been a serious pursuit in the scientific community, but that doesn't mean it can't also be a hoot. In this study, we dive into the fascinating relationship between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. This unlikely pair has caught our attention due to the intriguing connection we've uncovered—almost as captivating as an episode of "The X-Files," but with more statistical rigor.
As researchers, we are constantly seeking out unexpected associations and connections in our data, much like amateur detectives in a mystery novel, except with more spreadsheets and fewer magnifying glasses. Venturing into the realm of interconnectedness, we aim to shed light on the comical, bewildering, and sometimes downright bizarre relationships that exist in the world of environmental and energy dynamics.
We assure you, dear readers, that we are not simply concocting frivolous theories for academic kicks and giggles. Our findings are firmly rooted in the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration. These organizations provide the hard facts, charts, and tables necessary to lend credibility to our musings about the surprising correlation between two geographically distant yet undeniably linked phenomena.
Our study period spans the years from 1981 to 2021, offering a panoramic view of how these whimsical connections have evolved over time. Through the application of rigorous statistical methods, we have unearthed a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01. These numbers aren't just arbitrary figures; they are the bread and butter of scientific inquiry—a bit like the "magic numbers" in a Sudoku puzzle, only with a touch less magic and a bit more significance.
In presenting our research, we hope to showcase the intriguing cross-continental tango of pollution and power. Prepare to be amused, astounded, and perhaps even a touch bemused as we embark on a journey through the labyrinth of environmental data and energy production statistics. Let us all embrace the whimsy of science and revel in the delightful absurdities that await in the world of empirical inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

METHODOLOGY

In order to untangle the enigmatic relationship between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom, our research team devised a methodological approach that was as precise as a laser beam but also as flexible as a slinky. We conducted a comprehensive analysis of data spanning the years from 1981 to 2021, utilizing information primarily sourced from the Environmental Protection Agency and the Energy Information Administration. While our approach was rigorous, we also made sure to sprinkle in some good-natured humor and whimsy – after all, what's research without a dash of levity?

Data Collection:

Our data collection process resembled a digital treasure hunt, with the internet serving as our expansive playground. We scoured databases, reports, and official records from the Environmental Protection Agency and the Energy Information Administration, embracing the quirkiness of online research while maintaining our dedication to accuracy and thoroughness. The absurdity of searching high and low for data on pollution and power across geographical boundaries wasn't lost on us, and we approached our digital quest with the spirit of intrepid explorers, albeit ones armed with laptops instead of compasses.

Variable Selection:

The selection of variables for analysis was a bit like assembling a jigsaw puzzle, where each piece had the potential to reveal a surprising pattern. In this case, our puzzle pieces were the air pollution data from Terre Haute and the electricity generation statistics from the United Kingdom. Like maestros orchestrating a symphony, we meticulously curated these variables, acknowledging their contrasting origins yet recognizing the harmonious melody they might produce when brought together in our analysis.

Statistical Analysis:

Our statistical analysis was akin to navigating a labyrinth – at times perplexing, but ultimately rewarding. We employed correlation analysis to unravel the intricate dance between air pollution in Terre Haute and electricity generation in the United Kingdom. This involved calculating correlation coefficients with the precision of a master chef measuring ingredients and determining p-values with the steadfastness of a seasoned gambler playing the odds. As we delved into the statistical realm, we remained fervently aware of the curious dance of numbers, keeping an ear out for any statistical punchlines that might emerge from our data.

Data Limitations:

While we aimed to capture the whimsical interplay between air pollution and electricity generation, we acknowledge that our study has limitations. The inherent complexities of environmental and energy dynamics are reminiscent of a thrilling roller coaster ride – exhilarating, yet not without its twists and turns. Our findings should be interpreted with awareness of the data's scope and context, recognizing that the whimsy of correlation does not always imply causation, much like how a sudden rain shower doesn't necessarily mean an impromptu dance party has broken out.

Conclusion:

In crafting our research methodology, we endeavored to maintain a delicate balance between scholarly rigor and lighthearted curiosity. As we ventured into the realm of interconnected environmental and energy phenomena, we heeded the call to uncover the unexpected, all while retaining an appreciation for the playful absurdities that can arise in scientific inquiry. With our methodology in place, we embarked on a journey through data realms, embracing both the whimsy and the intellectual challenge that awaited us.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Terre Haute, Indiana and Electricity generation in United Kingdom. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 .

For the time period 1981 to 2021, you found a correlation 0.8117806, r-squared of 0.6589878, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

[[ABSTRACT]]
This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The investigation of environmental phenomena has long been a serious pursuit in the scientific community, but that doesn't mean it can't also be a hoot. In this study, we dive into the fascinating relationship between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. This unlikely pair has caught our attention due to the intriguing connection we've uncovered—almost as captivating as an episode of "The X-Files," but with more statistical rigor.
As researchers, we are constantly seeking out unexpected associations and connections in our data, much like amateur detectives in a mystery novel, except with more spreadsheets and fewer magnifying glasses. Venturing into the realm of interconnectedness, we aim to shed light on the comical, bewildering, and sometimes downright bizarre relationships that exist in the world of environmental and energy dynamics.
We assure you, dear readers, that we are not simply concocting frivolous theories for academic kicks and giggles. Our findings are firmly rooted in the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration. These organizations provide the hard facts, charts, and tables necessary to lend credibility to our musings about the surprising correlation between two geographically distant yet undeniably linked phenomena.
Our study period spans the years from 1981 to 2021, offering a panoramic view of how these whimsical connections have evolved over time. Through the application of rigorous statistical methods, we have unearthed a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01. These numbers aren't just arbitrary figures; they are the bread and butter of scientific inquiry—a bit like the "magic numbers" in a Sudoku puzzle, only with a touch less magic and a bit more significance.
In presenting our research, we hope to showcase the intriguing cross-continental tango of pollution and power. Prepare to be amused, astounded, and perhaps even a touch bemused as we embark on a journey through the labyrinth of environmental data and energy production statistics. Let us all embrace the whimsy of science and revel in the delightful absurdities that await in the world of empirical inquiry.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

**RESULTS**

The analysis of the data revealed a remarkable correlation between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. The correlation coefficient for the observed period of 1981 to 2021 was calculated to be 0.8117806, indicating a strong positive relationship between the two variables. This finding suggests that as air pollution levels in Terre Haute fluctuated, there was a corresponding impact on electricity generation in the United Kingdom. It's almost as if the emissions from Terre Haute were whispering, "Watt's up?" to the power plants across the pond.

The coefficient of determination (r-squared) of 0.6589878 further corroborates the robustness of this correlation. This implies that approximately 65.90% of the variation in electricity generation in the United Kingdom can be explained by changes in air pollution levels in Terre Haute. It's like finding out that more than half of the ingredients in your favorite recipe are influenced by a dish from a completely different culinary tradition.

In statistical terms, the p-value obtained was less than 0.01, indicating a high level of significance for the correlation. This means that the likelihood of observing such a strong relationship between air pollution in Terre Haute and electricity generation in the United Kingdom by random chance alone is exceedingly low. It's as if the statistical gods themselves have given this correlation their stamp of approval, accompanied by a jovial wink and a nod.

Figure 1 visually illustrates the striking correlation between air pollution in Terre Haute and electricity generation in the United Kingdom. The scatterplot showcases the data points dancing around the best-fit line, almost as if they are engaged in an elaborate waltz of pollution and power. This whimsical visual depiction encapsulates the inexplicable yet undeniable link that exists between these seemingly disparate variables.

Overall, our results not only substantiate the existence of a substantial correlation between air pollution in Terre Haute and electricity generation in the United Kingdom but also underscore the whimsical nature of environmental and energy dynamics. As we embrace the whimsy of this connection, we invite fellow researchers to revel in the delightful absurdities that abound in the world of empirical inquiry. It's moments like these that remind us that science can be both profound and playfully puzzling, much like a mind-bending riddle whispered by the winds of Terre Haute to the turbines of the United Kingdom's power grid.

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 Terre Haute, Indiana and Electricity generation in United Kingdom. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

[[ABSTRACT]]
This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

[[LITERATURE REVIEW]]
In "The Impact of Air Pollution on Health" by Smith and Doe, the authors find evidence linking air pollution to a variety of health concerns, ranging from respiratory ailments to cardiovascular diseases. This literature underscores the pressing need to mitigate the detrimental effects of air pollution, not just for the sake of public health, but also to avoid breathing in the equivalent of a particulate soufflé.
A comprehensive analysis by Jones in "Electricity Generation and Environmental Impact" emphasizes the complexities of balancing energy demands with environmental preservation. The study delves into the intricate dance of electricity production and its ecological ramifications, painting a detailed picture of the interconnected web of power generation and environmental consequences. It's like a scholarly rendition of "The Hokey Pokey," but with kilowatts and carbon emissions instead of right feet and left feet.
Building on these foundational works, "The Economics of Air Pollution Control" by Anderson provides a detailed examination of the economic factors at play in combating air pollution. The book addresses strategies for achieving greener energy production while navigating the financial landscape, offering insights that are as valuable as finding a winning lottery ticket in a haystack.
Now, let's take a whimsical turn and explore literature that may not immediately seem related but still manages to sneak its way into the realm of our peculiar correlation. From "Great Expectations" by Charles Dickens to "To Kill a Mockingbird" by Harper Lee, fiction has always danced around issues of societal change and environmental consequences. Who knew that an air pollution study could find resonance with literary classics? It's like stumbling upon a scholarly article in the middle of a library while looking for a novel – unexpected, but utterly captivating.
But let's not stop there. How about the quirky connections we can draw from cartoons and children's shows? From "Captain Planet and the Planeteers" to "The Magic School Bus," these vibrant and imaginative portrayals of environmental issues have left an indelible mark on our perception of pollution and its impact. These shows may not be cited in academic journals, but a "Phineas and Ferb" episode about renewable energy might just contain a nugget of wisdom that our scholarly pursuits could benefit from. After all, who wouldn't want a platypus-inspired insight into environmental dynamics?
[...]

[[RESULTS]]
The analysis of the data revealed a remarkable correlation between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. The correlation coefficient for the observed period of 1981 to 2021 was calculated to be 0.8117806, indicating a strong positive relationship between the two variables. This finding suggests that as air pollution levels in Terre Haute fluctuated, there was a corresponding impact on electricity generation in the United Kingdom. It's almost as if the emissions from Terre Haute were whispering, "Watt's up?" to the power plants across the pond.
The coefficient of determination (r-squared) of 0.6589878 further corroborates the robustness of this correlation. This implies that approximately 65.90% of the variation in electricity generation in the United Kingdom can be explained by changes in air pollution levels in Terre Haute. It's like finding out that more than half of the ingredients in your favorite recipe are influenced by a dish from a completely different culinary tradition.
In statistical terms, the p-value obtained was less than 0.01, indicating a high level of significance for the correlation. This means that the likelihood of observing such a strong relationship between air pollution in Terre Haute and electricity generation in the United Kingdom by random chance alone is exceedingly low. It's as if the statistical gods themselves have given this correlation their stamp of approval, accompanied by a jovial wink and a nod.
Figure 1 visually illustrates the striking correlation between air pollution in Terre Haute and electricity generation in the United Kingdom. The scatterplot showcases the data points dancing around the best-fit line, almost as if they are engaged in an elaborate waltz of pollution and power. This whimsical visual depiction encapsulates the inexplicable yet undeniable link that exists between these seemingly disparate variables.
Overall, our results not only substantiate the existence of a substantial correlation between air pollution in Terre Haute and electricity generation in the United Kingdom but also underscore the whimsical nature of environmental and energy dynamics. As we embrace the whimsy of this connection, we invite fellow researchers to revel in the delightful absurdities that abound in the world of empirical inquiry. It's moments like these that remind us that science can be both profound and playfully puzzling, much like a mind-bending riddle whispered by the winds of Terre Haute to the turbines of the United Kingdom's power grid.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The correlation between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom may initially seem as bewildering as a cat finding itself in a room full of cucumbers. However, our findings corroborate the whimsical yet statistically robust association we hypothesized. We stand like a scientific Sherlock, proudly declaring, "Elementary, my dear data points!"

Our results align with prior research highlighting the impact of air pollution on diverse realms, from public health to environmental sustainability. Just as Smith and Doe emphasized the need to prevent the inhalation of particulate soufflés, our study draws attention to the transcendental link between distant geographies and their environmental ramifications. It's like discovering that your favorite author and your favorite musician are distant relatives – a serendipitous connection indeed!

Jones' metaphorical "Hokey Pokey" of electricity production and ecological consequences resonates deeply with our findings. The intricate dance of pollution and power, much like a tango between kilowatts and carbon emissions, exemplifies the captivating complexity of the environmental and energy landscape. It's as if the universe choreographed a celestial ballet, with pollutants and power stations gracefully twirling around one another in harmonious discord.

Furthermore, our results lend credence to the economic and environmental considerations illuminated by Anderson. In navigating the financial terrain of greener energy production, our study acts as a compass in this expansive landscape. It's like stumbling upon a pot of gold at the end of a statistical rainbow – rewarding and delightfully unexpected.

The whimsical connections we drew from literature and pop culture may appear unconventional, but they mirror the unanticipated synchronization we uncovered between air pollution in Terre Haute and electricity generation in the United Kingdom. These unexpected parallels, akin to stumbling upon a koala in a library, enrich our understanding of the web of environmental interdependencies.

Our findings not only support prior research but also encapsulate the delightful absurdities that permeate the realms of empirical inquiry. Science, as we have demonstrated, is not merely a pursuit of knowledge, but a journey through a wonderland of intangible connections and enigmatic correlations. It's akin to solving a convoluted riddle that leaves us both perplexed and exhilarated, reminding us that, as researchers, we navigate the exhilarating landscape of knowledge with a dash of whimsy and a sprinkle of statistical stardust.

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 Terre Haute, Indiana and Electricity generation in United Kingdom. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

[[ABSTRACT]]
This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

[[INTRDUCTION]]
INTRODUCTION
The investigation of environmental phenomena has long been a serious pursuit in the scientific community, but that doesn't mean it can't also be a hoot. In this study, we dive into the fascinating relationship between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. This unlikely pair has caught our attention due to the intriguing connection we've uncovered—almost as captivating as an episode of "The X-Files," but with more statistical rigor.
As researchers, we are constantly seeking out unexpected associations and connections in our data, much like amateur detectives in a mystery novel, except with more spreadsheets and fewer magnifying glasses. Venturing into the realm of interconnectedness, we aim to shed light on the comical, bewildering, and sometimes downright bizarre relationships that exist in the world of environmental and energy dynamics.
We assure you, dear readers, that we are not simply concocting frivolous theories for academic kicks and giggles. Our findings are firmly rooted in the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration. These organizations provide the hard facts, charts, and tables necessary to lend credibility to our musings about the surprising correlation between two geographically distant yet undeniably linked phenomena.
Our study period spans the years from 1981 to 2021, offering a panoramic view of how these whimsical connections have evolved over time. Through the application of rigorous statistical methods, we have unearthed a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01. These numbers aren't just arbitrary figures; they are the bread and butter of scientific inquiry—a bit like the "magic numbers" in a Sudoku puzzle, only with a touch less magic and a bit more significance.
In presenting our research, we hope to showcase the intriguing cross-continental tango of pollution and power. Prepare to be amused, astounded, and perhaps even a touch bemused as we embark on a journey through the labyrinth of environmental data and energy production statistics. Let us all embrace the whimsy of science and revel in the delightful absurdities that await in the world of empirical inquiry.

[[RESULTS]]
The analysis of the data revealed a remarkable correlation between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. The correlation coefficient for the observed period of 1981 to 2021 was calculated to be 0.8117806, indicating a strong positive relationship between the two variables. This finding suggests that as air pollution levels in Terre Haute fluctuated, there was a corresponding impact on electricity generation in the United Kingdom. It's almost as if the emissions from Terre Haute were whispering, "Watt's up?" to the power plants across the pond.
The coefficient of determination (r-squared) of 0.6589878 further corroborates the robustness of this correlation. This implies that approximately 65.90% of the variation in electricity generation in the United Kingdom can be explained by changes in air pollution levels in Terre Haute. It's like finding out that more than half of the ingredients in your favorite recipe are influenced by a dish from a completely different culinary tradition.
In statistical terms, the p-value obtained was less than 0.01, indicating a high level of significance for the correlation. This means that the likelihood of observing such a strong relationship between air pollution in Terre Haute and electricity generation in the United Kingdom by random chance alone is exceedingly low. It's as if the statistical gods themselves have given this correlation their stamp of approval, accompanied by a jovial wink and a nod.
Figure 1 visually illustrates the striking correlation between air pollution in Terre Haute and electricity generation in the United Kingdom. The scatterplot showcases the data points dancing around the best-fit line, almost as if they are engaged in an elaborate waltz of pollution and power. This whimsical visual depiction encapsulates the inexplicable yet undeniable link that exists between these seemingly disparate variables.
Overall, our results not only substantiate the existence of a substantial correlation between air pollution in Terre Haute and electricity generation in the United Kingdom but also underscore the whimsical nature of environmental and energy dynamics. As we embrace the whimsy of this connection, we invite fellow researchers to revel in the delightful absurdities that abound in the world of empirical inquiry. It's moments like these that remind us that science can be both profound and playfully puzzling, much like a mind-bending riddle whispered by the winds of Terre Haute to the turbines of the United Kingdom's power grid.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has not only unraveled the enigmatic correlation between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom, but it has also highlighted the whimsical dance of pollution and power, transcending geographical barriers and tickling the intellect of researchers. Much like a surprising plot twist in a classic detective novel or an unexpected punchline at a scientific stand-up comedy show, this correlation has left us both astounded and amused.

The substantial correlation coefficient of 0.8117806 and the statistically robust p-value of less than 0.01 have not only provided strong evidence for the link between these seemingly disparate variables but also invoked a sense of wonder at the mystifying harmony between environmental emissions and electrical output. It's as if the laws of physics have a mischievous sense of humor, weaving an intricate tale of interconnectedness that never ceases to amaze.

From a statistical standpoint, the coefficient of determination (r-squared) of 0.6589878 and the whimsical waltz of data points in the scatterplot further emphasize the captivating nature of this correlation. It's almost as if the numbers themselves are whispering anecdotes of environmental intrigue and power production prowess, begging to be deciphered by curious minds.

As we reflect on the comical, bewildering, and sometimes downright bizarre relationships that exist in the world of environmental and energy dynamics, it is clear that this study has significantly contributed to the footprint of whimsical scientific inquiry. However, it is our firm assertion that no further research is needed in this particular area, as it seems the universe has already provided us with a cosmic joke of interconnectedness—one that we can appreciate with equal parts amusement and analytical rigor. Let's leave this correlation to bask in its own quirky spotlight, much like a stand-up comedian whose punchline has landed with resounding applause - no need to beat a dead horse, or should we say, a defunct dinosaur?

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 Air Pollution in Terre Haute: A Hoot for UK Electricity's Route. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Ecological Quirkiness

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 Air Pollution in Terre Haute: A Hoot for UK Electricity's Route. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Sustainable Energy and Environmental Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Air Pollution in Terre Haute: A Hoot for UK Electricity's Route with an abstract of This research delves into the peculiar interconnectedness between air pollution in Terre Haute, Indiana, and electricity generation in the United Kingdom. Through the meticulous analysis of data sourced from the Environmental Protection Agency and the Energy Information Administration, we unearth a substantial correlation coefficient of 0.8117806 and a statistically robust p-value of less than 0.01 for the years spanning 1981 to 2021. Our findings not only reveal a surprising link between seemingly disparate locations but also emphasize the whimsical nature of environmental and energy dynamics. As we unravel this whimsical correlation, we invite readers to join us in chuckling at the cosmic dance of pollution and power that transcends national boundaries and tickles the curious minds of researchers.

ChatGPT:

Air pollution, Terre Haute Indiana, electricity generation, United Kingdom, correlation coefficient, p-value, EPA data, EIA data, environmental dynamics, energy dynamics, pollution and power, national boundaries, whimsical correlation

*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 Terre Haute, Indiana
Detailed data title: Percentage of days with moderate or worse air quality in Terre Haute, IN
Source: Environmental Protection Agency
See what else correlates with Air pollution in Terre Haute, Indiana

Electricity generation in United Kingdom
Detailed data title: Total electricity generation in United Kingdom in billion kWh
Source: Energy Information Administration
See what else correlates with Electricity generation in United Kingdom

Correlation r = 0.8117806 (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 = 0.6589878 (Coefficient of determination)
This means 65.9% of the change in the one variable (i.e., Electricity generation in United Kingdom) is predictable based on the change in the other (i.e., Air pollution in Terre Haute, Indiana) over the 41 years from 1981 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.2E-10.^Show 0.0000000001196391460663486200
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 0.81 in 1.2E-8% of random cases. Said differently, if you correlated 8,358,468,218 random variables^Note You don't actually need 8 billion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 40 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 40 because we have two variables measured over a period of 41 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.

[ 0.67, 0.9 ] 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.

	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 Terre Haute, Indiana (Bad air quality days)	0.824176	1.09589	17.6796	24.3169	26.5753	20.5479	33.9483	25.614	27.9221	28.2209	26.7296	11.254	15.4676	33.4375	25.6983	25.1366	19.5055	43.9252	44.9782	43.9834	55.3279	56.3786	42.562	37.7049	47.9508	39.3443	59.7101	40.9471	30.916	52.4862	53.6111	45.9155	41.1602	45.1977	37.0166	30.5785	37.2603	33.6986	35.0685	19.6721	30.137
Electricity generation in United Kingdom (Billion kWh)	258.792	253.864	257.115	261.707	274.562	279.07	283.498	288.315	294.582	297.67	301.413	299.641	300.042	302.355	307.633	328.457	326.543	340.133	344.024	352.587	360.262	362.428	372.629	368.741	370.651	368.446	367.648	360.715	349.019	363.598	350.05	344.692	339.349	321.331	328.137	326.045	324.556	320.147	313.544	303.464	288.609

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.824176,1.09589,17.6796,24.3169,26.5753,20.5479,33.9483,25.614,27.9221,28.2209,26.7296,11.254,15.4676,33.4375,25.6983,25.1366,19.5055,43.9252,44.9782,43.9834,55.3279,56.3786,42.562,37.7049,47.9508,39.3443,59.7101,40.9471,30.916,52.4862,53.6111,45.9155,41.1602,45.1977,37.0166,30.5785,37.2603,33.6986,35.0685,19.6721,30.137,])
array_2 = np.array([258.792,253.864,257.115,261.707,274.562,279.07,283.498,288.315,294.582,297.67,301.413,299.641,300.042,302.355,307.633,328.457,326.543,340.133,344.024,352.587,360.262,362.428,372.629,368.741,370.651,368.446,367.648,360.715,349.019,363.598,350.05,344.692,339.349,321.331,328.137,326.045,324.556,320.147,313.544,303.464,288.609,])
array_1_name = "Air pollution in Terre Haute, Indiana"
array_2_name = "Electricity generation in United Kingdom"

# 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 Terre Haute, Indiana
Line chart for only Electricity generation in United Kingdom
AI-generated correlation image
The spurious research paper: Air Pollution in Terre Haute: A Hoot for UK Electricity's Route

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 1614 · Black Variable ID: 21335 · Red Variable ID: 24068


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