about · email me · subscribe
Spurious correlation #2,862 · 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 Ann Arbor and the second variable is Jet fuel used in Sierra Leone.  The chart goes from 1980 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As air pollution in Ann Arbor increased, it created a demand for cleaner air, leading to a surge in the production and export of jet fuel to Sierra Leone, where it was mistakenly believed that importing air from Ann Arbor would offset their own pollution levels. This led to a comical mix-up as the planes were being fueled by the very air they were supposed to be cleaning!

Model: dalle-3
Prompt: Generate an image of a futuristic cityscape with Ann Arbor blanketed in thick smog, the skyline obscured by pollution. In the foreground, show workers in Sierra Leone busily producing jet fuel with large barrels lined up. At the center of the image, depict a sleek, futuristic plane taking off from a runway, leaving a trail of clean exhaust as it ascends into the sky, contrasting with the polluted city below. The overall scene should capture the stark contrast between pollution and industrial activity in Ann Arbor and the futuristic, sustainable transportation taking off from Sierra Leone. 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 Ann Arbor and Jet fuel used in Sierra Leone. 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: Data cyber art Photorealism Futuristic Futuristic Whimsical illustration
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 Ann Arbor and Jet fuel used in Sierra Leone, in the following situation: Because as air pollution increases in Ann Arbor, it creates a need for cleaner air, prompting the production of jet fuel from Sierra Leone to fuel planes to escape the pollution. This results in a direct correlation between increased air pollution in one location and the production and use of jet fuel in another.. Keep the description simple.
ChatGPT: In Ann Arbor, thick smog hangs over the city, indicating high air pollution. In contrast, in Sierra Leone, workers are busy producing jet fuel, with large barrels lined up ready for distribution. A plane takes off from a runway, leaving a trail of clean exhaust as it escapes the polluted city and heads towards the 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: [ Futuristic ] and depicting this scene: In Ann Arbor, thick smog hangs over the city, indicating high air pollution. In contrast, in Sierra Leone, workers are busy producing jet fuel, with large barrels lined up ready for distribution. A plane takes off from a runway, leaving a trail of clean exhaust as it escapes the polluted city and heads towards the sky. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic cityscape with Ann Arbor blanketed in thick smog, the skyline obscured by pollution. In the foreground, show workers in Sierra Leone busily producing jet fuel with large barrels lined up. At the center of the image, depict a sleek, futuristic plane taking off from a runway, leaving a trail of clean exhaust as it ascends into the sky, contrasting with the polluted city below. The overall scene should capture the stark contrast between pollution and industrial activity in Ann Arbor and the futuristic, sustainable transportation taking off from Sierra Leone.

*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 increases in Air pollution in Ann Arbor positively influenced Jet fuel used in Sierra Leone.

AI academic paper

(Because p < 0.01)
Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel

The Journal of Transcontinental Atmospheric Connections

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You 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 Ann Arbor and Jet fuel used in Sierra Leone. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title a clever pun.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.7044480 and p < 0.01 for 1980 to 2021.

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]]
"Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"


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

Here is the title and abstract of the paper:
[[TITLE]]
"Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Air pollution and its impact on human health and the environment have been the subject of extensive research and public concern. Similarly, the use of jet fuel and its environmental ramifications have been studied and scrutinized by experts in the field. However, the thought of a potential connection between the two seemingly unrelated phenomena might make some raise an eyebrow - or perhaps two, depending on their level of skepticism.

As we all know, correlation does not imply causation, but it sure can make for some interesting dinner conversations. Our research seeks to unveil the unexpected ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, shedding light on a curious relationship that has flown under the radar for far too long. This endeavor is not merely an exercise in statistical analysis; it's an exploration of the interconnectedness of environmental variables across continents and industries.

It might seem like a stretch to connect air pollution in one part of the world to jet fuel consumption in another, but as they say in statistical circles, "When in doubt, plot it out!" And that's exactly what we did. We dived into the depths of data from the Environmental Protection Agency and the Energy Information Administration, armed with our trusty statistical tools and an unabashed enthusiasm for uncovering unexpected correlations.

The journey that ensued was filled with surprises, challenges, and a fair share of head-scratching moments. However, as with any good research endeavor, perseverance paid off. The results we obtained not only raised eyebrows but also prompted us to reconsider the traditional boundaries of environmental impact assessment. After all, as scientists, it's our duty to stay grounded in the data while also reaching for the sky.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Jet fuel used in Sierra Leone. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then 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]]
"Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Air pollution and its impact on human health and the environment have been the subject of extensive research and public concern. Similarly, the use of jet fuel and its environmental ramifications have been studied and scrutinized by experts in the field. However, the thought of a potential connection between the two seemingly unrelated phenomena might make some raise an eyebrow - or perhaps two, depending on their level of skepticism.
As we all know, correlation does not imply causation, but it sure can make for some interesting dinner conversations. Our research seeks to unveil the unexpected ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, shedding light on a curious relationship that has flown under the radar for far too long. This endeavor is not merely an exercise in statistical analysis; it's an exploration of the interconnectedness of environmental variables across continents and industries.
It might seem like a stretch to connect air pollution in one part of the world to jet fuel consumption in another, but as they say in statistical circles, "When in doubt, plot it out!" And that's exactly what we did. We dived into the depths of data from the Environmental Protection Agency and the Energy Information Administration, armed with our trusty statistical tools and an unabashed enthusiasm for uncovering unexpected correlations.
The journey that ensued was filled with surprises, challenges, and a fair share of head-scratching moments. However, as with any good research endeavor, perseverance paid off. The results we obtained not only raised eyebrows but also prompted us to reconsider the traditional boundaries of environmental impact assessment. After all, as scientists, it's our duty to stay grounded in the data while also reaching for the sky.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The authors find that air pollution has been a topic of concern for many years, with studies by Smith et al. (2015) highlighting its detrimental effects on human health and the environment. Similarly, Doe and Jones (2018) delve into the environmental consequences of jet fuel consumption, emphasizing the need for sustainable aviation practices.

Now, it may seem like a lofty endeavor to connect these two unrelated topics, but as they say in the world of research, "Where there's air, there's a way!" Our investigation led us to explore works such as "Air Pollution and Its Impacts" by Environmental Research Group and "Aviation Fuels: From Crude Oil to Jet Fuel" by Energy Analysis Association.

Venturing beyond non-fiction, our exploration touched upon fictional works that seemed alarmingly relevant, such as "The Polluted Skies" by A. Q. Nonymous and "Jet Fuel Mysteries: The Case of the Vanishing Emissions" by P. Lotalot. While these titles may sound like the stuff of whimsical imagination, we found ourselves drawing unexpected parallels to our own research.

In the pursuit of thoroughness, we expanded our sources to include unconventional literature, drawing inspiration from the unlikeliest of places. After exhaustively perusing the backs of shampoo bottles, it became apparent that the ingredients listed were unhelpful – although we did acquire soft, luscious hair in the process.

It is evident that the intersection of air pollution in Ann Arbor and jet fuel consumption in Sierra Leone has sparked curiosity across a wide range of literary realms. As the saying goes, "When life gives you jets, make jet fuel lemonade – just make sure the emissions don't sour it!"

The juxtaposition of seemingly incongruent elements has provided a unique lens through which to examine the interconnectedness of environmental variables. As researchers, we must not only look to established sources but also cast our net wide, for you never know where the winds of knowledge might carry you.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Jet fuel used in Sierra Leone. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1980 to 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 We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

[[INTRODUCTION]]
Air pollution and its impact on human health and the environment have been the subject of extensive research and public concern. Similarly, the use of jet fuel and its environmental ramifications have been studied and scrutinized by experts in the field. However, the thought of a potential connection between the two seemingly unrelated phenomena might make some raise an eyebrow - or perhaps two, depending on their level of skepticism.
As we all know, correlation does not imply causation, but it sure can make for some interesting dinner conversations. Our research seeks to unveil the unexpected ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, shedding light on a curious relationship that has flown under the radar for far too long. This endeavor is not merely an exercise in statistical analysis; it's an exploration of the interconnectedness of environmental variables across continents and industries.
It might seem like a stretch to connect air pollution in one part of the world to jet fuel consumption in another, but as they say in statistical circles, "When in doubt, plot it out!" And that's exactly what we did. We dived into the depths of data from the Environmental Protection Agency and the Energy Information Administration, armed with our trusty statistical tools and an unabashed enthusiasm for uncovering unexpected correlations.
The journey that ensued was filled with surprises, challenges, and a fair share of head-scratching moments. However, as with any good research endeavor, perseverance paid off. The results we obtained not only raised eyebrows but also prompted us to reconsider the traditional boundaries of environmental impact assessment. After all, as scientists, it's our duty to stay grounded in the data while also reaching for the sky.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In order to investigate the intriguing connection between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, a multidimensional approach was employed. First, data on air pollution levels in Ann Arbor was obtained from the Environmental Protection Agency, while information on jet fuel usage in Sierra Leone was gathered from the Energy Information Administration. Following the scientific tradition of "digging deep," our research team embarked on a virtual spelunking expedition through the annals of data repositories, using the trusty flashlight of statistical software to illuminate potential correlations.

Having collected the data from 1980 to 2021, we harnessed the power of statistical analysis, donning our metaphorical lab coats and safety goggles as we delved into the sea of numbers. We conducted a thorough examination of the time series data, employing sophisticated statistical methods including correlation analysis and time series modeling. One might say we were "jet-set" on uncovering any hidden patterns in the data - pun very much intended.

To establish the relationship between air pollution levels in Ann Arbor and jet fuel usage in Sierra Leone, we calculated the correlation coefficient between the two variables. This statistical endeavor was marked by an air of anticipation, much like waiting for a delayed flight, as we eagerly anticipated the results. True to the whims of scientific inquiry, the correlation coefficient unveiled itself, clocking in at a surprising 0.7044480. This finding elicited a collective "air-raising" moment of astonishment among the research team, as we realized the unexpected strength of the correlation.

Furthermore, we conducted hypothesis testing to ascertain the statistical significance of the observed connection. With a p-value of less than 0.01, our findings provided compelling evidence in support of a meaningful link between air pollution in Ann Arbor and jet fuel consumption in Sierra Leone. This statistical significance was not merely a number on a screen; it was a spark of insight igniting curiosity and challenging established boundaries, much like a scientific "Eureka!" moment amidst data analysis.

The approach taken in this study was not without its challenges, as navigating the terrain of cross-continental variables required a nuanced understanding and a keen eye for detail. In the spirit of scientific inquiry, we remained steadfast in our pursuit of uncovering unexpected correlations, recognizing that research endeavors, much like flights, can encounter occasional turbulence.

In summary, the methodology employed in this research endeavor combined a meticulous exploration of data, statistical analysis, and a touch of scientific whimsy to unravel the unlikely ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone. As we continue to expand the frontiers of environmental interconnectedness, let us remember that in the world of scientific inquiry, as in aviation, the sky's the limit for unexpected correlations.


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

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

For the time period 1980 to 2021, you found a correlation 0.7044480, r-squared of 0.4962470, 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 We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Air pollution and its impact on human health and the environment have been the subject of extensive research and public concern. Similarly, the use of jet fuel and its environmental ramifications have been studied and scrutinized by experts in the field. However, the thought of a potential connection between the two seemingly unrelated phenomena might make some raise an eyebrow - or perhaps two, depending on their level of skepticism.
As we all know, correlation does not imply causation, but it sure can make for some interesting dinner conversations. Our research seeks to unveil the unexpected ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, shedding light on a curious relationship that has flown under the radar for far too long. This endeavor is not merely an exercise in statistical analysis; it's an exploration of the interconnectedness of environmental variables across continents and industries.
It might seem like a stretch to connect air pollution in one part of the world to jet fuel consumption in another, but as they say in statistical circles, "When in doubt, plot it out!" And that's exactly what we did. We dived into the depths of data from the Environmental Protection Agency and the Energy Information Administration, armed with our trusty statistical tools and an unabashed enthusiasm for uncovering unexpected correlations.
The journey that ensued was filled with surprises, challenges, and a fair share of head-scratching moments. However, as with any good research endeavor, perseverance paid off. The results we obtained not only raised eyebrows but also prompted us to reconsider the traditional boundaries of environmental impact assessment. After all, as scientists, it's our duty to stay grounded in the data while also reaching for the sky.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a significant correlation between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. The correlation coefficient of 0.7044480 indicates a moderately strong positive relationship between these variables. This unexpected connection certainly gives new meaning to the phrase, "what's Air pollution in Ann Arbor has to do with Jet fuel used in Sierra Leone?"

The r-squared value of 0.4962470 suggests that approximately 49.6% of the variability in air pollution levels in Ann Arbor can be explained by the consumption of jet fuel in Sierra Leone. As for the remaining 50.4%, well, we're not just blowing smoke when we say that it's still up in the air.

Furthermore, with a p-value of less than 0.01, the results are statistically significant, providing compelling evidence of the relationship between these seemingly unrelated variables. It seems that when it comes to factors influencing air quality, the plot thickens, or in this case, thins out depending on particulate matter levels.

The scatterplot (Fig. 1) visually illustrates the positive correlation between air pollution in Ann Arbor and jet fuel consumption in Sierra Leone. For those who may doubt the veracity of our findings, we assure them that this relationship is as real as the air we breathe - albeit, in varying levels of purity.

These results challenge conventional wisdom and prompt us to consider the ripple effects of industrial activities across global scales. In the words of the great scientific humorist, "If two variables are correlated and nobody's around to witness it, can we still make a graph about it?" Well, the answer is a resounding yes, and we did just that - uncovering a surprising connection that leaves us both puzzled and inspired.

In conclusion, our findings not only contribute to the scientific understanding of environmental interconnectedness but also remind us that in the realm of research, the most unexpected ties may turn out to be the most enlightening. After all, as researchers, we're always ready to jet set into uncharted territory, especially when it yields such striking results.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Jet fuel used in Sierra Leone. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

[[LITERATURE REVIEW]]
The authors find that air pollution has been a topic of concern for many years, with studies by Smith et al. (2015) highlighting its detrimental effects on human health and the environment. Similarly, Doe and Jones (2018) delve into the environmental consequences of jet fuel consumption, emphasizing the need for sustainable aviation practices.
Now, it may seem like a lofty endeavor to connect these two unrelated topics, but as they say in the world of research, "Where there's air, there's a way!" Our investigation led us to explore works such as "Air Pollution and Its Impacts" by Environmental Research Group and "Aviation Fuels: From Crude Oil to Jet Fuel" by Energy Analysis Association.
Venturing beyond non-fiction, our exploration touched upon fictional works that seemed alarmingly relevant, such as "The Polluted Skies" by A. Q. Nonymous and "Jet Fuel Mysteries: The Case of the Vanishing Emissions" by P. Lotalot. While these titles may sound like the stuff of whimsical imagination, we found ourselves drawing unexpected parallels to our own research.
In the pursuit of thoroughness, we expanded our sources to include unconventional literature, drawing inspiration from the unlikeliest of places. After exhaustively perusing the backs of shampoo bottles, it became apparent that the ingredients listed were unhelpful – although we did acquire soft, luscious hair in the process.
It is evident that the intersection of air pollution in Ann Arbor and jet fuel consumption in Sierra Leone has sparked curiosity across a wide range of literary realms. As the saying goes, "When life gives you jets, make jet fuel lemonade – just make sure the emissions don't sour it!"
The juxtaposition of seemingly incongruent elements has provided a unique lens through which to examine the interconnectedness of environmental variables. As researchers, we must not only look to established sources but also cast our net wide, for you never know where the winds of knowledge might carry you.

[[RESULTS]]
The statistical analysis revealed a significant correlation between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. The correlation coefficient of 0.7044480 indicates a moderately strong positive relationship between these variables. This unexpected connection certainly gives new meaning to the phrase, "what's Air pollution in Ann Arbor has to do with Jet fuel used in Sierra Leone?"
The r-squared value of 0.4962470 suggests that approximately 49.6% of the variability in air pollution levels in Ann Arbor can be explained by the consumption of jet fuel in Sierra Leone. As for the remaining 50.4%, well, we're not just blowing smoke when we say that it's still up in the air.
Furthermore, with a p-value of less than 0.01, the results are statistically significant, providing compelling evidence of the relationship between these seemingly unrelated variables. It seems that when it comes to factors influencing air quality, the plot thickens, or in this case, thins out depending on particulate matter levels.
The scatterplot (Fig. 1) visually illustrates the positive correlation between air pollution in Ann Arbor and jet fuel consumption in Sierra Leone. For those who may doubt the veracity of our findings, we assure them that this relationship is as real as the air we breathe - albeit, in varying levels of purity.
These results challenge conventional wisdom and prompt us to consider the ripple effects of industrial activities across global scales. In the words of the great scientific humorist, "If two variables are correlated and nobody's around to witness it, can we still make a graph about it?" Well, the answer is a resounding yes, and we did just that - uncovering a surprising connection that leaves us both puzzled and inspired.
In conclusion, our findings not only contribute to the scientific understanding of environmental interconnectedness but also remind us that in the realm of research, the most unexpected ties may turn out to be the most enlightening. After all, as researchers, we're always ready to jet set into uncharted territory, especially when it yields such striking results.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study have illuminated an intriguing relationship between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. The significant correlation coefficient and p-value below 0.01 not only support our hypothesis but also emphasize the importance of considering unexpected variables in environmental research. It's safe to say that the connection between these two seemingly unrelated factors is quite "plane" to see – a dad joke that even the most seasoned researcher would appreciate.

Building on the literature review, which playfully dabbled in unconventional sources, our results underscore the serious implications of understanding cross-sectoral impacts on environmental variables. This unexpected correlation between air pollution and jet fuel consumption reminds us of the adage, "When it comes to research, sometimes you have to jet fuel yourself with a sense of humor to uncover the most surprising findings."

The statistical analysis, with its moderately strong positive relationship and r-squared value explaining nearly half of the variability, emphasizes the influential role of jet fuel consumption in Sierra Leone on air pollution levels in Ann Arbor. It's almost as if the link between these two variables was hiding in plain sight, just waiting for us to "jet" on over and uncover it.

What seems like a whimsical and improbable connection at first glance has profound implications for understanding the interconnectedness of global environmental factors. As researchers, we must always be prepared to "jet" off into uncharted territory, armed with a good sense of humor and a keen eye for unexpected correlations. After all, as the old saying goes, "When you're dealing with statistics, it's always best to hedge your bets – unless, of course, you're researching shrubbery."

In essence, our study expands the boundaries of environmental research by highlighting the interplay between air pollution in one corner of the world and jet fuel consumption in another. As we continue to unravel the mysteries of our planet's interconnected systems, it's clear that with the right approach, even the "sky's the limit" for uncovering surprising and meaningful associations.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Jet fuel used in Sierra Leone. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Air We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel"

[[ABSTRACT]]
This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.

Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.

This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!"

[[INTRDUCTION]]
Air pollution and its impact on human health and the environment have been the subject of extensive research and public concern. Similarly, the use of jet fuel and its environmental ramifications have been studied and scrutinized by experts in the field. However, the thought of a potential connection between the two seemingly unrelated phenomena might make some raise an eyebrow - or perhaps two, depending on their level of skepticism.
As we all know, correlation does not imply causation, but it sure can make for some interesting dinner conversations. Our research seeks to unveil the unexpected ties between air pollution in Ann Arbor and the consumption of jet fuel in Sierra Leone, shedding light on a curious relationship that has flown under the radar for far too long. This endeavor is not merely an exercise in statistical analysis; it's an exploration of the interconnectedness of environmental variables across continents and industries.
It might seem like a stretch to connect air pollution in one part of the world to jet fuel consumption in another, but as they say in statistical circles, "When in doubt, plot it out!" And that's exactly what we did. We dived into the depths of data from the Environmental Protection Agency and the Energy Information Administration, armed with our trusty statistical tools and an unabashed enthusiasm for uncovering unexpected correlations.
The journey that ensued was filled with surprises, challenges, and a fair share of head-scratching moments. However, as with any good research endeavor, perseverance paid off. The results we obtained not only raised eyebrows but also prompted us to reconsider the traditional boundaries of environmental impact assessment. After all, as scientists, it's our duty to stay grounded in the data while also reaching for the sky.

[[RESULTS]]
The statistical analysis revealed a significant correlation between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. The correlation coefficient of 0.7044480 indicates a moderately strong positive relationship between these variables. This unexpected connection certainly gives new meaning to the phrase, "what's Air pollution in Ann Arbor has to do with Jet fuel used in Sierra Leone?"
The r-squared value of 0.4962470 suggests that approximately 49.6% of the variability in air pollution levels in Ann Arbor can be explained by the consumption of jet fuel in Sierra Leone. As for the remaining 50.4%, well, we're not just blowing smoke when we say that it's still up in the air.
Furthermore, with a p-value of less than 0.01, the results are statistically significant, providing compelling evidence of the relationship between these seemingly unrelated variables. It seems that when it comes to factors influencing air quality, the plot thickens, or in this case, thins out depending on particulate matter levels.
The scatterplot (Fig. 1) visually illustrates the positive correlation between air pollution in Ann Arbor and jet fuel consumption in Sierra Leone. For those who may doubt the veracity of our findings, we assure them that this relationship is as real as the air we breathe - albeit, in varying levels of purity.
These results challenge conventional wisdom and prompt us to consider the ripple effects of industrial activities across global scales. In the words of the great scientific humorist, "If two variables are correlated and nobody's around to witness it, can we still make a graph about it?" Well, the answer is a resounding yes, and we did just that - uncovering a surprising connection that leaves us both puzzled and inspired.
In conclusion, our findings not only contribute to the scientific understanding of environmental interconnectedness but also remind us that in the realm of research, the most unexpected ties may turn out to be the most enlightening. After all, as researchers, we're always ready to jet set into uncharted territory, especially when it yields such striking results.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unveiled an unexpected and statistically significant correlation between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. This surprising relationship has left us both breathless and jet-lagged, as we never anticipated such a strong link between these two seemingly disparate variables.

This discovery reminds us of the old adage, "When it comes to environmental research, sometimes the truth really does take flight!" It's clear that the impact of industrial activities in one part of the world can have far-reaching consequences on air quality in another. One might even say it's a "plane" reminder of the global nature of environmental interconnectedness.

Furthermore, our findings highlight the importance of considering cross-sectoral impacts on environmental variables. As researchers, it's crucial for us to "stay grounded" in the data while also keeping our sights set high, much like a commercial airliner navigating through turbulent statistical analyses.

Ultimately, this study challenges traditional perspectives and encourages a broader, more interconnected approach to environmental impact assessment. It goes to show that, in the vast and complex world of scientific research, sometimes the most unexpected correlations can take off and soar to new heights of understanding.

In light of these compelling findings, we firmly assert that no further research is needed in this area. We are confident that this study has taken our understanding of the relationship between air pollution in Ann Arbor and jet fuel consumption in Sierra Leone to new heights, and any additional investigation would simply be "plane" unnecessary.


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 We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Transcontinental Atmospheric Connections


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 We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Environmental Incongruity 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 We Go Again: Unlikely Ties Between Ann Arbor's Air Pollution and Sierra Leone's Jet Fuel with an abstract of This paper explores the unexpected connection between air pollution levels in Ann Arbor and the consumption of jet fuel in Sierra Leone. While seemingly unrelated, our research team delved into the data from the Environmental Protection Agency and the Energy Information Administration, uncovering a surprising relationship between these seemingly disparate factors.
Our findings revealed a correlation coefficient of 0.7044480 and p < 0.01 for the years 1980 to 2021, indicating a statistically significant link between air pollution in Ann Arbor and the usage of jet fuel in Sierra Leone. It appears that these two phenomena, separated by continents and industries, may indeed be intertwined in ways previously unimagined.
This study challenges conventional wisdom and encourages a broader consideration of global interconnectedness, emphasizing the importance of analyzing cross-sectoral impacts on environmental variables. As the saying goes, "When it comes to air quality and aviation fuel, the sky's the limit for unexpected correlations!

ChatGPT:

Air pollution, jet fuel consumption, Ann Arbor air pollution, Sierra Leone jet fuel, cross-sectoral impacts, environmental variables, correlation coefficient, global interconnectedness, unexpected correlations

*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 Ann Arbor
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Ann Arbor, MI
Source: Environmental Protection Agency
See what else correlates with Air pollution in Ann Arbor

Jet fuel used in Sierra Leone
Detailed data title: Volume of jet fuel used consumed in Sierra Leone in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Jet fuel used in Sierra Leone

Correlation r = 0.7044480 (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 = 0.4962470 (Coefficient of determination)
This means 49.6% of the change in the one variable (i.e., Jet fuel used in Sierra Leone) is predictable based on the change in the other (i.e., Air pollution in Ann Arbor) over the 42 years from 1980 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.9E-7. 0.0000001926398211368799000000
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 0.7 in 1.9E-5% of random cases. Said differently, if you correlated 5,191,035 random variables You don't actually need 5 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 41 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 41 because we have two variables measured over a period of 42 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.51, 0.83 ] 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.
198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Air pollution in Ann Arbor (Bad air quality days)1.769910.4149380.5434780.48780500.6024101.8779312.14951.408451.923082.777781.648350.8241760.8720931.865672.181820.5494511.440923.29670.5479452.259893.01371.3966501.1080300.2747250000.2801120.54945100000000.2732240
Jet fuel used in Sierra Leone (Million Barrels/Day)0.2583230.2583230.2789890.2583230.2583230.2841550.30.30.50.30.30.30.30.30.20.30.30.40.40.40.2389860.2346410.2324680.2324680.2309480.2324680.2504140.217260.2129150.2107420.2063970.208570.2107420.2042250.2020520.1977070.1846710.1890160.1716360.1750680.1671920.176416




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. 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. 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.
  5. 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([1.76991,0.414938,0.543478,0.487805,0,0.60241,0,1.87793,12.1495,1.40845,1.92308,2.77778,1.64835,0.824176,0.872093,1.86567,2.18182,0.549451,1.44092,3.2967,0.547945,2.25989,3.0137,1.39665,0,1.10803,0,0.274725,0,0,0,0.280112,0.549451,0,0,0,0,0,0,0,0.273224,0,])
array_2 = np.array([0.258323,0.258323,0.278989,0.258323,0.258323,0.284155,0.3,0.3,0.5,0.3,0.3,0.3,0.3,0.3,0.2,0.3,0.3,0.4,0.4,0.4,0.238986,0.234641,0.232468,0.232468,0.230948,0.232468,0.250414,0.21726,0.212915,0.210742,0.206397,0.20857,0.210742,0.204225,0.202052,0.197707,0.184671,0.189016,0.171636,0.175068,0.167192,0.176416,])
array_1_name = "Air pollution in Ann Arbor"
array_2_name = "Jet fuel used in Sierra Leone"

# 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?

You're a rater extraordinaire!


Correlation ID: 2862 · Black Variable ID: 20269 · Red Variable ID: 24897
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0