about · email me · subscribe
Spurious correlation #3,843 · 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 Prineville, Oregon and the second variable is Number of websites on the internet.  The chart goes from 1991 to 2018, and the two variables track closely in value over that time. Small Image

AI explanation

The smog in Prineville acted as a cloud server, prompting a rise in internet use. As the pollution levels soared, so did the cyber-traffic, creating a 'web' of connections online. It seems the dirty air wasn't the only thing 'networking' in Prineville!

Model: dalle-3
Prompt: Generate an image of a futuristic city casting a warm glow under a crystal-clear sky in Prineville, Oregon. In the foreground, a bustling town is depicted, with sleek, modern architecture and residents engrossed in their computers. The glow from their screens illuminates the surroundings, symbolizing the birth of new websites and creative ideas inspired by the pure, pollution-free air. 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 Prineville, Oregon and Number of websites on the internet. 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: Cute 2D animation A photo-realistic image Hyper-realistic Cute cartoon Futuristic
ChatGPT: Futuristic

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 Prineville, Oregon and Number of websites on the internet, in the following situation: Changes in air pollution in Prineville, Oregon have caused the number of websites on the internet to increase. As the air quality improved, people were able to breathe easier and think more clearly, leading to an influx of brilliant ideas and innovative thinking. With their newfound mental clarity, the residents of Prineville took to the internet to share their creative endeavors, resulting in a boom of new websites. In other words, cleaner air led to cleaner coding and a breath of fresh websites!. Keep the description simple.
ChatGPT: Imagine the clear skies of Prineville, Oregon, where the air is crisp and free from pollution. In the town, residents are busy at their computers, heads filled with fresh ideas. From their screens, a multitude of new websites spring to life, representing the creative surge that has been inspired by the clean air.

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: [ Futuristic ] and depicting this scene: Imagine the clear skies of Prineville, Oregon, where the air is crisp and free from pollution. In the town, residents are busy at their computers, heads filled with fresh ideas. From their screens, a multitude of new websites spring to life, representing the creative surge that has been inspired by the clean air. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic city casting a warm glow under a crystal-clear sky in Prineville, Oregon. In the foreground, a bustling town is depicted, with sleek, modern architecture and residents engrossed in their computers. The glow from their screens illuminates the surroundings, symbolizing the birth of new websites and creative ideas inspired by the pure, pollution-free air.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Air pollution in Prineville, Oregon caused Number of websites on the internet to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

The Journal of Ecological Techonomics

Jan 2024
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 researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from Environmental Protection Agency and Internet Live Stats to assess this nagging question. You found a correlation coefficient of 0.8051678 and p < 0.01 for 1991 to 2018.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Prineville, Oregon, the quaint little city nestled among the pines where the air is so clean, you can practically taste the freshness (but really, don't try that). However, beneath this facade of pristine air lies a surprising and somewhat bemusing link to the digital world - the proliferation of internet websites. Yes, you read that right. This study delves into the uncharted territory of connecting the dots between air pollution and the virtual universe, because who doesn't love a good mental challenge, right?

As we embark on this curious quest, it becomes apparent that the charming town of Prineville is not immune to the modern-day environmental conundrum of air pollution. This, combined with the exponential growth of websites on the internet, brings forth the question: could there be a correlation lurking in the digital ether, or are we merely succumbing to a case of correlation does not imply causation delirium?

The juxtaposition of the idyllic outdoors and the boundless internet poses a paradoxical conundrum that tickles the intellect and ignites curiosity. Could the proverbial digital footprint be leaving behind an environmental trail in the cascading streams of code and pixels? Or are we witnessing a cosmic dance between the tangible earth and the intangible web, where pollution and proliferation perform a paradoxical pas de deux? Oh, the sheer irony of the digital age entwined with the simplicity of breathable air!

In this paper, we present the findings of our expedition into this unexplored territory, where we sought to unravel the complex relationship between Prineville's air quality and the internet's ever-expanding web of wonderment. So, fasten your mental seatbelts and prepare to be virtually transported through the wilderness of data analysis, where p-values, correlation coefficients, and environmental eurekas await.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Prineville, Oregon, the quaint little city nestled among the pines where the air is so clean, you can practically taste the freshness (but really, don't try that). However, beneath this facade of pristine air lies a surprising and somewhat bemusing link to the digital world - the proliferation of internet websites. Yes, you read that right. This study delves into the uncharted territory of connecting the dots between air pollution and the virtual universe, because who doesn't love a good mental challenge, right?
As we embark on this curious quest, it becomes apparent that the charming town of Prineville is not immune to the modern-day environmental conundrum of air pollution. This, combined with the exponential growth of websites on the internet, brings forth the question: could there be a correlation lurking in the digital ether, or are we merely succumbing to a case of correlation does not imply causation delirium?
The juxtaposition of the idyllic outdoors and the boundless internet poses a paradoxical conundrum that tickles the intellect and ignites curiosity. Could the proverbial digital footprint be leaving behind an environmental trail in the cascading streams of code and pixels? Or are we witnessing a cosmic dance between the tangible earth and the intangible web, where pollution and proliferation perform a paradoxical pas de deux? Oh, the sheer irony of the digital age entwined with the simplicity of breathable air!
In this paper, we present the findings of our expedition into this unexplored territory, where we sought to unravel the complex relationship between Prineville's air quality and the internet's ever-expanding web of wonderment. So, fasten your mental seatbelts and prepare to be virtually transported through the wilderness of data analysis, where p-values, correlation coefficients, and environmental eurekas await.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "The Impact of Air Pollution on Internet Usage" by Smith, the authors find a surprising correlation between air pollution levels in various regions and the number of internet users. While this study did not specifically focus on the number of websites on the internet, it opens up the possibility of a connection between environmental factors and digital usage.

Doe et al. in "Digital Footprints: The Environmental Impact of Internet Usage" delve into the environmental footprint of internet usage, exploring energy consumption and electronic waste. Despite not directly investigating air pollution, their work sheds light on the broader relationship between environmental factors and digital phenomena.

Jones' study, "The Internet Ecosystem: A Holistic View," provides insights into the growth and evolution of the internet. While this work primarily focuses on the structural aspects of the internet, it hints at the potential for external influences, such as environmental conditions, to impact the digital realm.

Turning to non-fiction books, "The Sixth Extinction" by Elizabeth Kolbert offers a chilling account of how human activities have led to environmental degradation. Although not directly related to digital expansion, this work underscores the profound impact of human actions on the natural world.

A fictional twist in "Neuromancer" by William Gibson introduces readers to a cyberpunk world, where the boundaries between the physical and digital realms blur. While this novel may seem far removed from the realities of Prineville, Oregon, it sparks the imagination and invites contemplation of the interconnectedness of environmental and digital spheres.

In the pursuit of a comprehensive literature review, our team also ventured into unconventional sources, such as the back of shampoo bottles and fortune cookie messages. While these endeavors yielded peculiar anecdotes and whimsical quips, they did not contribute substantively to the scholarly discourse on air pollution and internet proliferation. Nevertheless, the lighthearted diversion served as a reminder that even rigorous research can benefit from a sprinkle of humor.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Internet Live Stats . You used data from 1991 to 2018

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]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

[[INTRODUCTION]]
Prineville, Oregon, the quaint little city nestled among the pines where the air is so clean, you can practically taste the freshness (but really, don't try that). However, beneath this facade of pristine air lies a surprising and somewhat bemusing link to the digital world - the proliferation of internet websites. Yes, you read that right. This study delves into the uncharted territory of connecting the dots between air pollution and the virtual universe, because who doesn't love a good mental challenge, right?
As we embark on this curious quest, it becomes apparent that the charming town of Prineville is not immune to the modern-day environmental conundrum of air pollution. This, combined with the exponential growth of websites on the internet, brings forth the question: could there be a correlation lurking in the digital ether, or are we merely succumbing to a case of correlation does not imply causation delirium?
The juxtaposition of the idyllic outdoors and the boundless internet poses a paradoxical conundrum that tickles the intellect and ignites curiosity. Could the proverbial digital footprint be leaving behind an environmental trail in the cascading streams of code and pixels? Or are we witnessing a cosmic dance between the tangible earth and the intangible web, where pollution and proliferation perform a paradoxical pas de deux? Oh, the sheer irony of the digital age entwined with the simplicity of breathable air!
In this paper, we present the findings of our expedition into this unexplored territory, where we sought to unravel the complex relationship between Prineville's air quality and the internet's ever-expanding web of wonderment. So, fasten your mental seatbelts and prepare to be virtually transported through the wilderness of data analysis, where p-values, correlation coefficients, and environmental eurekas await.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To tackle the perplexing puzzle of Prineville's air pollution and its intriguing correlation with the number of internet websites, our research team donned our metaphorical Sherlock Holmes deerstalkers and embarked on a riveting quest through data land. Our methodological maelstrom centered on collecting and analyzing historical data spanning from 1991 to 2018, sourced from the illustrious archives of the Environmental Protection Agency and the captivating cobwebs of Internet Live Stats.

First, to measure the air pollution levels in Prineville, we cherry-picked data on various air pollutants such as carbon monoxide, nitrogen dioxide, ozone, and particulate matter. We then stirred this concoction of pollutants into a digital cauldron, brewing up an average air quality index (AQI) for Prineville. This allowed us to gauge the ambient air pollution and conjure up a numerical representation of Prineville's atmospheric woes.

As for tracking the expansion of the internet, our digital explorers scoured the virtual terrain for numbers on the total count of websites across the globe. We employed the arcane arts of web analytics to track the internet's meteoric growth, recording the number of websites from the early days of the World Wide Web to the expansive network it is today.

With a flourish, we smelted this amalgamation of data into a correlation analysis, churning through statistical tests to unveil the hidden link between air pollution and internet proliferation. This culminated in the grand reveal of a correlation coefficient of 0.8051678, alongside a p-value that winked at us with statistical significance - less than 0.01. If you’re not impressed by that, perhaps we should add a drumroll for dramatic effect?

To ensure the robustness of our findings, we also conducted sensitivity analyses and even threw in a few statistical acrobatics, just to keep things interesting. After all, in the realm of research, a bit of statistical flair adds a certain je ne sais quoi to the findings.

Now, armed with our trusty numbers and statistical wand, we're prepared to unveil the abracadabra connection between Prineville's air quality and the internet's digital dominion. So gather 'round, dear readers, for the magical unveiling of the mysterious linkage between pollution and pixels!


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Internet Live Stats .

For the time period 1991 to 2018, you found a correlation 0.8051678, r-squared of 0.6482952, 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]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Prineville, Oregon, the quaint little city nestled among the pines where the air is so clean, you can practically taste the freshness (but really, don't try that). However, beneath this facade of pristine air lies a surprising and somewhat bemusing link to the digital world - the proliferation of internet websites. Yes, you read that right. This study delves into the uncharted territory of connecting the dots between air pollution and the virtual universe, because who doesn't love a good mental challenge, right?
As we embark on this curious quest, it becomes apparent that the charming town of Prineville is not immune to the modern-day environmental conundrum of air pollution. This, combined with the exponential growth of websites on the internet, brings forth the question: could there be a correlation lurking in the digital ether, or are we merely succumbing to a case of correlation does not imply causation delirium?
The juxtaposition of the idyllic outdoors and the boundless internet poses a paradoxical conundrum that tickles the intellect and ignites curiosity. Could the proverbial digital footprint be leaving behind an environmental trail in the cascading streams of code and pixels? Or are we witnessing a cosmic dance between the tangible earth and the intangible web, where pollution and proliferation perform a paradoxical pas de deux? Oh, the sheer irony of the digital age entwined with the simplicity of breathable air!
In this paper, we present the findings of our expedition into this unexplored territory, where we sought to unravel the complex relationship between Prineville's air quality and the internet's ever-expanding web of wonderment. So, fasten your mental seatbelts and prepare to be virtually transported through the wilderness of data analysis, where p-values, correlation coefficients, and environmental eurekas await.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a strong positive correlation between air pollution in Prineville, Oregon, and the number of websites on the internet. Over the period of 1991 to 2018, our research team found a correlation coefficient of 0.8051678, indicating a robust relationship between these seemingly unrelated variables. In simpler terms, as air pollution levels in Prineville increased, so did the number of websites on the internet, and vice versa. It's almost as if the digital world is gasping for breath in response to the environmental challenges faced by Prineville.

Furthermore, the calculated r-squared value of 0.6482952 suggests that approximately 65% of the variation in internet proliferation can be explained by changes in air pollution levels. This means that while we can't attribute all web development to the quality of the air, there's certainly a notable connection worth exploring further. The p-value of less than 0.01 solidifies the statistical significance of this correlation, indicating that the likelihood of observing such a strong relationship by chance is highly improbable.

Looking at Fig. 1, you can observe the scatterplot illustrating the unmistakable trend between air pollution and the number of websites. The upward trajectory of the data points reinforces the notion that as air pollution levels rise or fall, so does the growth of the internet's digital domain. It's like a dance of data points twirling around a polluted ballroom, where the music is composed of 0s and 1s and the participants are websites and particulate matter.

This eyebrow-raising discovery opens the door to a myriad of questions and possibilities, provoking contemplation on the intricate interplay between the environment and digital evolution. Our findings emphasize the need for further investigation into the influence of environmental factors on internet development, and vice versa. Who knew that behind the screen's glow, there could be a whiff of pollution, or that amidst the clear air, a digital symphony could be in full swing?


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

[[LITERATURE REVIEW]]
In "The Impact of Air Pollution on Internet Usage" by Smith, the authors find a surprising correlation between air pollution levels in various regions and the number of internet users. While this study did not specifically focus on the number of websites on the internet, it opens up the possibility of a connection between environmental factors and digital usage.
Doe et al. in "Digital Footprints: The Environmental Impact of Internet Usage" delve into the environmental footprint of internet usage, exploring energy consumption and electronic waste. Despite not directly investigating air pollution, their work sheds light on the broader relationship between environmental factors and digital phenomena.
Jones' study, "The Internet Ecosystem: A Holistic View," provides insights into the growth and evolution of the internet. While this work primarily focuses on the structural aspects of the internet, it hints at the potential for external influences, such as environmental conditions, to impact the digital realm.
Turning to non-fiction books, "The Sixth Extinction" by Elizabeth Kolbert offers a chilling account of how human activities have led to environmental degradation. Although not directly related to digital expansion, this work underscores the profound impact of human actions on the natural world.
A fictional twist in "Neuromancer" by William Gibson introduces readers to a cyberpunk world, where the boundaries between the physical and digital realms blur. While this novel may seem far removed from the realities of Prineville, Oregon, it sparks the imagination and invites contemplation of the interconnectedness of environmental and digital spheres.
In the pursuit of a comprehensive literature review, our team also ventured into unconventional sources, such as the back of shampoo bottles and fortune cookie messages. While these endeavors yielded peculiar anecdotes and whimsical quips, they did not contribute substantively to the scholarly discourse on air pollution and internet proliferation. Nevertheless, the lighthearted diversion served as a reminder that even rigorous research can benefit from a sprinkle of humor.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between air pollution in Prineville, Oregon, and the number of websites on the internet. Over the period of 1991 to 2018, our research team found a correlation coefficient of 0.8051678, indicating a robust relationship between these seemingly unrelated variables. In simpler terms, as air pollution levels in Prineville increased, so did the number of websites on the internet, and vice versa. It's almost as if the digital world is gasping for breath in response to the environmental challenges faced by Prineville.
Furthermore, the calculated r-squared value of 0.6482952 suggests that approximately 65% of the variation in internet proliferation can be explained by changes in air pollution levels. This means that while we can't attribute all web development to the quality of the air, there's certainly a notable connection worth exploring further. The p-value of less than 0.01 solidifies the statistical significance of this correlation, indicating that the likelihood of observing such a strong relationship by chance is highly improbable.
Looking at Fig. 1, you can observe the scatterplot illustrating the unmistakable trend between air pollution and the number of websites. The upward trajectory of the data points reinforces the notion that as air pollution levels rise or fall, so does the growth of the internet's digital domain. It's like a dance of data points twirling around a polluted ballroom, where the music is composed of 0s and 1s and the participants are websites and particulate matter.
This eyebrow-raising discovery opens the door to a myriad of questions and possibilities, provoking contemplation on the intricate interplay between the environment and digital evolution. Our findings emphasize the need for further investigation into the influence of environmental factors on internet development, and vice versa. Who knew that behind the screen's glow, there could be a whiff of pollution, or that amidst the clear air, a digital symphony could be in full swing?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our results have provided remarkable support for prior research that initially seemed as improbable as an ostrich navigating a minefield. To the astonishment of many, the correlation we observed between air pollution in Prineville, Oregon, and the proliferation of websites on the internet echoes the findings of Smith, who, like a digital-ecological Sherlock Holmes, detected a relationship between air pollution and internet usage. It seems the digital age has become a smoggy port city, with internet ships docking in polluted harbors.

Moreover, the interconnectedness of environmental factors and digital phenomena, as alluded to by Doe et al., has been substantiated by our study. It appears that the digital footprint left by internet usage not only manifests as electronic waste but also exhibits susceptibility to environmental conditions, essentially resembling a high-tech Cinderella, awaiting the stroke of midnight to reveal its humble environmental origins.

Jones' investigation into the internet ecosystem, though predominantly centered around the architecture of the internet, hinted at external influences affecting the digital realm. Our findings have not only illuminated this possibility but have boldly underscored the significant role that air pollution plays in the very fabric of the internet's expansion. It's as if the digital realm and the physical environment have become dance partners in an intricate tango, with air pollution orchestrating the steps of internet proliferation.

The seemingly fictional elements that we incorporated from "The Sixth Extinction" and "Neuromancer" have transcended the boundaries of fiction, with our real-world data illustrating the tangible consequences of human activities on the digital and natural worlds. It's as if reality has taken a cue from fiction, snatching the narrative baton to reveal the surreal correlation between air pollution and internet growth.

Even our whimsical foray into unconventional sources, such as the back of shampoo bottles and fortune cookie messages, albeit not yielding substantive contributions, served as a whimsical reminder that amidst the seriousness of scholarly pursuit, a sprinkle of humor and creativity can aid in reinvigorating academic discourse. Just as a dash of humor adds spice to the academic endeavor, our research has infused an unexpected twist into the conventional narrative of environmental and digital interplay.

Given the weight of our results, it's evident that the relationship between air pollution in Prineville and the number of websites on the internet is not to be taken lightly. This curious connection warrants further investigation, just as a detective follows the elusive trail of clues, to unveil the intricate web of relations between the environment and the digital domain. Our findings add a breath of fresh air to the dialogue on environmental impact and digital evolution, encouraging scholars to contemplate the unexpected yet resolute connection between the invisible particles in the air and the virtual particles on the web.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Prineville, Oregon and Number of websites on the internet. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation

[[ABSTRACT]]
In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

[[INTRDUCTION]]
Prineville, Oregon, the quaint little city nestled among the pines where the air is so clean, you can practically taste the freshness (but really, don't try that). However, beneath this facade of pristine air lies a surprising and somewhat bemusing link to the digital world - the proliferation of internet websites. Yes, you read that right. This study delves into the uncharted territory of connecting the dots between air pollution and the virtual universe, because who doesn't love a good mental challenge, right?
As we embark on this curious quest, it becomes apparent that the charming town of Prineville is not immune to the modern-day environmental conundrum of air pollution. This, combined with the exponential growth of websites on the internet, brings forth the question: could there be a correlation lurking in the digital ether, or are we merely succumbing to a case of correlation does not imply causation delirium?
The juxtaposition of the idyllic outdoors and the boundless internet poses a paradoxical conundrum that tickles the intellect and ignites curiosity. Could the proverbial digital footprint be leaving behind an environmental trail in the cascading streams of code and pixels? Or are we witnessing a cosmic dance between the tangible earth and the intangible web, where pollution and proliferation perform a paradoxical pas de deux? Oh, the sheer irony of the digital age entwined with the simplicity of breathable air!
In this paper, we present the findings of our expedition into this unexplored territory, where we sought to unravel the complex relationship between Prineville's air quality and the internet's ever-expanding web of wonderment. So, fasten your mental seatbelts and prepare to be virtually transported through the wilderness of data analysis, where p-values, correlation coefficients, and environmental eurekas await.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between air pollution in Prineville, Oregon, and the number of websites on the internet. Over the period of 1991 to 2018, our research team found a correlation coefficient of 0.8051678, indicating a robust relationship between these seemingly unrelated variables. In simpler terms, as air pollution levels in Prineville increased, so did the number of websites on the internet, and vice versa. It's almost as if the digital world is gasping for breath in response to the environmental challenges faced by Prineville.
Furthermore, the calculated r-squared value of 0.6482952 suggests that approximately 65% of the variation in internet proliferation can be explained by changes in air pollution levels. This means that while we can't attribute all web development to the quality of the air, there's certainly a notable connection worth exploring further. The p-value of less than 0.01 solidifies the statistical significance of this correlation, indicating that the likelihood of observing such a strong relationship by chance is highly improbable.
Looking at Fig. 1, you can observe the scatterplot illustrating the unmistakable trend between air pollution and the number of websites. The upward trajectory of the data points reinforces the notion that as air pollution levels rise or fall, so does the growth of the internet's digital domain. It's like a dance of data points twirling around a polluted ballroom, where the music is composed of 0s and 1s and the participants are websites and particulate matter.
This eyebrow-raising discovery opens the door to a myriad of questions and possibilities, provoking contemplation on the intricate interplay between the environment and digital evolution. Our findings emphasize the need for further investigation into the influence of environmental factors on internet development, and vice versa. Who knew that behind the screen's glow, there could be a whiff of pollution, or that amidst the clear air, a digital symphony could be in full swing?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unveiled an unexpected and robust connection between the air pollution levels in Prineville, Oregon, and the proliferation of websites on the internet. While it may seem like a breath of fresh air, this correlation has left us digitally astounded. The statistically significant relationship, as evidenced by the correlation coefficient of 0.8051678 and a p-value of less than 0.01, suggests a compelling interplay between these seemingly disparate variables.

The findings of our study prompt consideration of the environmental impact on the virtual landscape and vice versa. It seems that as the air in Prineville becomes hazier, the internet appears to expand with a vigor akin to a lungful of fresh oxygen. It's as though the digital realm takes a deep breath in response to the inhalation of pollutants by the physical environment. Perhaps the internet is not just a vast network of data but also an embodiment of the world's collective gasp in the face of climate challenges.

As we take one last lungful of fresh data, it becomes evident that further investigation into this curious relationship is warranted. The implications of our findings are as vast and expansive as the digital realm itself. However, let's not let this correlation get too inflated, for as with all research, a healthy dose of skepticism will continue to be our best filter. We can comfortably conclude that the relationship between air pollution in Prineville and internet proliferation doesn't just vanish into thin air. It warrants a chuckle and a raised eyebrow, but let's not cloud the issue any further. It's time to take a breath and say, "No more research needed in this area."


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 Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Techonomics


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 Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Digital Atmosphere Studies


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 Breathe Easy: Connecting the Dots Between Prineville's Air Pollution and Internet Proliferation with an abstract of In this study, we breathe fresh air into the realm of environmental and digital correlations by examining the relationship between air pollution in Prineville, Oregon, and the number of websites on the internet. Our research team utilized data from the Environmental Protection Agency and Internet Live Stats to delve into this unexpected connection. Surprisingly, our findings revealed a correlation coefficient of 0.8051678, with a p-value of less than 0.01 for the period spanning 1991 to 2018. This wacky discovery prompts further investigation into the interplay between environmental factors and the digital landscape. Let's just hope that in the battle between pollution and web proliferation, the internet doesn't become a virtual smog.

ChatGPT:

Prineville air pollution, internet proliferation, correlation, environmental data, digital landscape, relationship, air quality, web development, internet growth, pollution effects, digital expansion, EPA data, internet statistics, Prineville, Oregon, website numbers

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

Number of websites on the internet
Detailed data title: Number of websites, measured by unique hostnames
Source: Internet Live Stats
See what else correlates with Number of websites on the internet

Correlation r = 0.8051678 (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 = 0.6482952 (Coefficient of determination)
This means 64.8% of the change in the one variable (i.e., Number of websites on the internet) is predictable based on the change in the other (i.e., Air pollution in Prineville, Oregon) over the 28 years from 1991 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.4E-7. 0.0000002380359647510762700000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.81 in 2.4E-5% of random cases. Said differently, if you correlated 4,201,046 random variables You don't actually need 4 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 27 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 27 because we have two variables measured over a period of 28 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.

[ 0.62, 0.91 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
1991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018
Air pollution in Prineville, Oregon (Bad air quality days)0000000000000000001.369860.2785511.685390.5555563.561642.739732.209940.2873564.481791.92837
Number of websites on the internet (Websites)11013027382350025760111172602410070317745017087200292544003876040040912300516116006478060085507300121893000172339000238028000206957000346004000697089000672985000968882000863106000104553000017669300001630320000




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Outlandish outliers: There are "outliers" in this data. 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. 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([0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1.36986,0.278551,1.68539,0.555556,3.56164,2.73973,2.20994,0.287356,4.48179,1.92837,])
array_2 = np.array([1,10,130,2738,23500,257601,1117260,2410070,3177450,17087200,29254400,38760400,40912300,51611600,64780600,85507300,121893000,172339000,238028000,206957000,346004000,697089000,672985000,968882000,863106000,1045530000,1766930000,1630320000,])
array_1_name = "Air pollution in Prineville, Oregon"
array_2_name = "Number of websites on the internet"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Big thanks for reviewing!


Correlation ID: 3843 · Black Variable ID: 21091 · Red Variable ID: 370
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0