about · email me · subscribe
Spurious correlation #3,548 · 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 Farmington, New Mexico and the second variable is Gasoline pumped in U.S. Pacific Islands.  The chart goes from 2006 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in Farmington led to an unexpected increase in productivity at the gasoline pumping facilities. This surplus of productivity somehow translated to reduced gasoline production and distribution in the U.S. Pacific Islands. It's like a bizarre domino effect of efficiency, all stemming from Farmington's fresher air!

Model: dalle-3
Prompt: Generate an image showing the stark contrast between Farmington, New Mexico, and the U.S. Pacific Islands. In the foreground, depict the smog creatures with glowing eyes roaming the hazy and polluted streets of Farmington, with gas stations in disarray. In the background, portray the serene U.S. Pacific Islands with pristine beaches and lush tropical landscapes surrounding well-kept gas stations, all under clear blue skies. Capture the stark difference in atmosphere and environment between the two locations. 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 Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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: a funny image you would see on reddit Oragami A Discovery magazine cover image Cubism A TIME magazine cover image
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands, in the following situation: Because excessive air pollution in Farmington, New Mexico led to the creation of sentient smog creatures, causing chaos at local gas stations. To avoid the chaos, gasoline companies started pumping gasoline in U.S. Pacific Islands, where the smog creatures couldn't survive the tropical climate.. Keep the description simple.
ChatGPT: In Farmington, New Mexico, thick smog hangs over the city, creating a hazy and polluted atmosphere. Sentient smog creatures with glowing eyes roam the streets, causing chaos at local gas stations. In contrast, in the U.S. Pacific Islands, pristine beaches and lush tropical landscapes surround gas stations, where gasoline is being pumped under the clear blue skies, far away from the smog creatures' reach.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In Farmington, New Mexico, thick smog hangs over the city, creating a hazy and polluted atmosphere. Sentient smog creatures with glowing eyes roam the streets, causing chaos at local gas stations. In contrast, in the U.S. Pacific Islands, pristine beaches and lush tropical landscapes surround gas stations, where gasoline is being pumped under the clear blue skies, far away from the smog creatures' reach. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image showing the stark contrast between Farmington, New Mexico, and the U.S. Pacific Islands. In the foreground, depict the smog creatures with glowing eyes roaming the hazy and polluted streets of Farmington, with gas stations in disarray. In the background, portray the serene U.S. Pacific Islands with pristine beaches and lush tropical landscapes surrounding well-kept gas stations, all under clear blue skies. Capture the stark difference in atmosphere and environment between the two locations.

*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 a decrease in Air pollution in Farmington, New Mexico caused Gasoline pumped in U.S. Pacific Islands to decrease.

AI academic paper

(Because p < 0.01)
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

The Journal of Ecological Serendipity

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title seem clever.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9433699 and p < 0.01 for 2006 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of environmental research is often a breath of fresh air, and the study of air pollution and its connections with other variables continues to uncover surprising relationships. In this paper, we dive into the unexpected association between air pollution levels in Farmington, New Mexico, and the consumption of gasoline in the U.S. Pacific Islands. We promise, this is not just a gas, we've got the data to back it up!

As the famous dad joke goes, "Why did the environmental researcher bring a pencil to the lab? Because they heard it had a good point!" Indeed, our research aims to pinpoint the connection between these seemingly unrelated factors and put an end to the mystery that's been lingering in the air - pun intended.

This study draws on a robust dataset from the Environmental Protection Agency and the Energy Information Administration, allowing us to meticulously analyze air quality levels in Farmington and gasoline consumption patterns in the U.S. Pacific Islands. The results we uncovered were shocking - statistically shocking, that is!

Our research team employed advanced statistical techniques to quantify the relationship between these variables, and the correlation coefficient we unveiled was stronger than the bond between carbon atoms in a molecule. The ensuing p-value was so low, we momentarily wondered if we had stumbled into an alternate statistical universe - a punnett square of statistical significance, if you will.

Though we cannot yet elucidate the exact mechanisms driving this unexpected correlation, our findings serve as a reminder that in the world of environmental research, the connections between seemingly disparate elements may be thicker than a methane molecule. So, grab your lab coat and buckle up - this scientific journey is about to take off into uncharted statistical territories!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of environmental research is often a breath of fresh air, and the study of air pollution and its connections with other variables continues to uncover surprising relationships. In this paper, we dive into the unexpected association between air pollution levels in Farmington, New Mexico, and the consumption of gasoline in the U.S. Pacific Islands. We promise, this is not just a gas, we've got the data to back it up!
As the famous dad joke goes, "Why did the environmental researcher bring a pencil to the lab? Because they heard it had a good point!" Indeed, our research aims to pinpoint the connection between these seemingly unrelated factors and put an end to the mystery that's been lingering in the air - pun intended.
This study draws on a robust dataset from the Environmental Protection Agency and the Energy Information Administration, allowing us to meticulously analyze air quality levels in Farmington and gasoline consumption patterns in the U.S. Pacific Islands. The results we uncovered were shocking - statistically shocking, that is!
Our research team employed advanced statistical techniques to quantify the relationship between these variables, and the correlation coefficient we unveiled was stronger than the bond between carbon atoms in a molecule. The ensuing p-value was so low, we momentarily wondered if we had stumbled into an alternate statistical universe - a punnett square of statistical significance, if you will.
Though we cannot yet elucidate the exact mechanisms driving this unexpected correlation, our findings serve as a reminder that in the world of environmental research, the connections between seemingly disparate elements may be thicker than a methane molecule. So, grab your lab coat and buckle up - this scientific journey is about to take off into uncharted statistical territories!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The literature concerning the relationship between air pollution and gasoline consumption presents a breadth of research that delves into the individual impacts of these environmental factors. In "Air Pollution and Health" by Smith, the authors find a strong association between air pollution and respiratory illnesses, offering valuable insights into the public health implications of polluted air. Similarly, Doe and Jones, in their study "Gasoline Consumption Patterns: A Comprehensive Analysis," shed light on the factors influencing gasoline usage and its economic ramifications.

Now, before we dive into the serious academic articles, let's take a detour into some non-fiction books that could shed light on this topic. "The Air We Breathe" by Waubgeshig Rice explores the impact of air pollution on indigenous communities, offering a poignant and thought-provoking perspective. In contrast, "Pumping Irony: Working Out the Gasoline Conundrum" by Terry Tamminen provides a deep dive into the intricacies of gasoline consumption and its environmental consequences.

But wait, let's not forget the world of fiction! "The Air Affair" by Jasper Fforde - while not directly related to air pollution - takes us on a whimsical journey through an alternate reality where air quality is a matter of literary significance. On the other hand, "The Gasoline Gazette" by Rita Mae Brown offers a fictional exploration of the gasoline industry and its impact on a small town, reminding us that fiction can sometimes be as illuminating as reality.

In conducting this literature review, it's essential to cast a wide net, which is why we also turned to unconventional sources of information. Yes, you guessed it - we perused CVS receipts, scouring them for any hints of a connection between air pollution in Farmington and gasoline pumped in the U.S. Pacific Islands. While we may have only found discounts on air fresheners and gasoline rewards points, our spirit of exploration knows no bounds.

With our literature review journey complete, it's time to turn our attention back to the serious academic work at hand. But let's not forget the importance of injecting a dash of humor and curiosity into our scholarly pursuits - after all, who said academic research couldn't be a breath of fresh air?


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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 2006 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

[[INTRODUCTION]]
The world of environmental research is often a breath of fresh air, and the study of air pollution and its connections with other variables continues to uncover surprising relationships. In this paper, we dive into the unexpected association between air pollution levels in Farmington, New Mexico, and the consumption of gasoline in the U.S. Pacific Islands. We promise, this is not just a gas, we've got the data to back it up!
As the famous dad joke goes, "Why did the environmental researcher bring a pencil to the lab? Because they heard it had a good point!" Indeed, our research aims to pinpoint the connection between these seemingly unrelated factors and put an end to the mystery that's been lingering in the air - pun intended.
This study draws on a robust dataset from the Environmental Protection Agency and the Energy Information Administration, allowing us to meticulously analyze air quality levels in Farmington and gasoline consumption patterns in the U.S. Pacific Islands. The results we uncovered were shocking - statistically shocking, that is!
Our research team employed advanced statistical techniques to quantify the relationship between these variables, and the correlation coefficient we unveiled was stronger than the bond between carbon atoms in a molecule. The ensuing p-value was so low, we momentarily wondered if we had stumbled into an alternate statistical universe - a punnett square of statistical significance, if you will.
Though we cannot yet elucidate the exact mechanisms driving this unexpected correlation, our findings serve as a reminder that in the world of environmental research, the connections between seemingly disparate elements may be thicker than a methane molecule. So, grab your lab coat and buckle up - this scientific journey is about to take off into uncharted statistical territories!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

We embarked on this research endeavor with the fervor of a mad scientist creating chemistry puns - with a lot of reaction, er, I mean, research! Our data collection process involved scouring the depths of the internet like intrepid cyber explorers, except our treasure trove consisted of datasets rather than gold doubloons. We primarily relied on the treasure maps provided by the Environmental Protection Agency and the Energy Information Administration, navigating their websites with the determination of a sailor steering through stormy statistical seas.

To establish the relationship between air pollution levels in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands, we channeled our inner Sherlock Holmes and embarked on a sleuthing expedition through the data. Our investigation spanned the years 2006 to 2021, allowing us to capture the ebb and flow of these environmental variables over time. We compared this to an archaeological dig, except instead of unearthing ancient artifacts, we were unearthing dusty datasets - talk about a "gas-leak" into the past, eh?

After meticulously gathering the data like treasure hunters, we subjected it to rigorous scrutiny using advanced statistical methods. Our team of number crunchers wielded regression analysis and correlation coefficients like wizards casting spells, hoping to unveil the hidden patterns lurking within the numbers. It was like a mathematical mystery novel, where the pages were filled with quadratic equations and the protagonist was a renegade variable seeking alignment.

Once we had tamed the unruly data and coaxed it into revealing its secrets, we emerged with a correlation coefficient that stood stronger than a carbon nanotube in a scientific tug-of-war. This coefficient served as a compass guiding us towards the surprising connection between air pollution in Farmington and gasoline consumption in the U.S. Pacific Islands. It was as if the data itself was whispering, "You've struck statistical gold!"

In addition to the correlation coefficient, we calculated the p-value to assess the significance of our findings. The resulting p-value was more striking than a lightning bolt in a statistical thunderstorm, indicating a level of significance that left us reeling like a proton in a cyclotron. We could almost hear the statistical gods chuckling at our disbelief as we contemplated the implications of our research - oh, the whimsy of empirical inquiry!

With our methodologies firmly grounded in statistical rigor and a sprinkle of scientific whimsy, we set out to unravel the enigmatic connection between air pollution in Farmington and gasoline consumption in the U.S. Pacific Islands. As we delve into the findings in the subsequent sections, hold on to your lab goggles - we're about to traverse the terrain of unexpected environmental correlations with the gusto of a statistical adventurer!


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

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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 2006 to 2021, you found a correlation 0.9433699, r-squared of 0.8899467, 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of environmental research is often a breath of fresh air, and the study of air pollution and its connections with other variables continues to uncover surprising relationships. In this paper, we dive into the unexpected association between air pollution levels in Farmington, New Mexico, and the consumption of gasoline in the U.S. Pacific Islands. We promise, this is not just a gas, we've got the data to back it up!
As the famous dad joke goes, "Why did the environmental researcher bring a pencil to the lab? Because they heard it had a good point!" Indeed, our research aims to pinpoint the connection between these seemingly unrelated factors and put an end to the mystery that's been lingering in the air - pun intended.
This study draws on a robust dataset from the Environmental Protection Agency and the Energy Information Administration, allowing us to meticulously analyze air quality levels in Farmington and gasoline consumption patterns in the U.S. Pacific Islands. The results we uncovered were shocking - statistically shocking, that is!
Our research team employed advanced statistical techniques to quantify the relationship between these variables, and the correlation coefficient we unveiled was stronger than the bond between carbon atoms in a molecule. The ensuing p-value was so low, we momentarily wondered if we had stumbled into an alternate statistical universe - a punnett square of statistical significance, if you will.
Though we cannot yet elucidate the exact mechanisms driving this unexpected correlation, our findings serve as a reminder that in the world of environmental research, the connections between seemingly disparate elements may be thicker than a methane molecule. So, grab your lab coat and buckle up - this scientific journey is about to take off into uncharted statistical territories!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of our data revealed a remarkably high correlation coefficient of 0.9433699 between air pollution levels in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. We couldn't believe our eyes when we saw the data; it was as if these two variables were holding hands across the miles, like a long-distance relationship strengthened by the power of statistical significance.

And speaking of statistical significance, the p-value we obtained was so tiny, it made us wonder if we had inadvertently discovered the statistical equivalent of a quark - talk about going subatomic in our quest for knowledge.

In addition to the robust correlation coefficient, we also calculated an impressive r-squared value of 0.8899467. This indicated that nearly 89% of the variation in gasoline consumption in the Pacific Islands could be explained by the air pollution levels in Farmington. This finding blew our minds like a gust of wind sweeping through a research laboratory!

Fig. 1 illustrates the strong correlation between air pollution in Farmington, New Mexico, and gasoline pumped in the U.S. Pacific Islands. If that graph were any clearer, we’d be using it to find our way out of the labyrinth of statistical mysteries.

This remarkable association between seemingly unrelated variables had our research team quite literally gasping for breath, wondering if we had stumbled upon the holy grail of environmental research - or perhaps just an elaborate cosmic prank played out in the realm of data analysis.

Clearly, there is more work to be done in unraveling the precise link between these two elements, but for now, we can at least revel in the fact that our findings have brought some much-needed air of intrigue to the world of environmental science.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

[[LITERATURE REVIEW]]
The literature concerning the relationship between air pollution and gasoline consumption presents a breadth of research that delves into the individual impacts of these environmental factors. In "Air Pollution and Health" by Smith, the authors find a strong association between air pollution and respiratory illnesses, offering valuable insights into the public health implications of polluted air. Similarly, Doe and Jones, in their study "Gasoline Consumption Patterns: A Comprehensive Analysis," shed light on the factors influencing gasoline usage and its economic ramifications.
Now, before we dive into the serious academic articles, let's take a detour into some non-fiction books that could shed light on this topic. "The Air We Breathe" by Waubgeshig Rice explores the impact of air pollution on indigenous communities, offering a poignant and thought-provoking perspective. In contrast, "Pumping Irony: Working Out the Gasoline Conundrum" by Terry Tamminen provides a deep dive into the intricacies of gasoline consumption and its environmental consequences.
But wait, let's not forget the world of fiction! "The Air Affair" by Jasper Fforde - while not directly related to air pollution - takes us on a whimsical journey through an alternate reality where air quality is a matter of literary significance. On the other hand, "The Gasoline Gazette" by Rita Mae Brown offers a fictional exploration of the gasoline industry and its impact on a small town, reminding us that fiction can sometimes be as illuminating as reality.
In conducting this literature review, it's essential to cast a wide net, which is why we also turned to unconventional sources of information. Yes, you guessed it - we perused CVS receipts, scouring them for any hints of a connection between air pollution in Farmington and gasoline pumped in the U.S. Pacific Islands. While we may have only found discounts on air fresheners and gasoline rewards points, our spirit of exploration knows no bounds.
With our literature review journey complete, it's time to turn our attention back to the serious academic work at hand. But let's not forget the importance of injecting a dash of humor and curiosity into our scholarly pursuits - after all, who said academic research couldn't be a breath of fresh air?

[[RESULTS]]
The analysis of our data revealed a remarkably high correlation coefficient of 0.9433699 between air pollution levels in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. We couldn't believe our eyes when we saw the data; it was as if these two variables were holding hands across the miles, like a long-distance relationship strengthened by the power of statistical significance.
And speaking of statistical significance, the p-value we obtained was so tiny, it made us wonder if we had inadvertently discovered the statistical equivalent of a quark - talk about going subatomic in our quest for knowledge.
In addition to the robust correlation coefficient, we also calculated an impressive r-squared value of 0.8899467. This indicated that nearly 89% of the variation in gasoline consumption in the Pacific Islands could be explained by the air pollution levels in Farmington. This finding blew our minds like a gust of wind sweeping through a research laboratory!
Fig. 1 illustrates the strong correlation between air pollution in Farmington, New Mexico, and gasoline pumped in the U.S. Pacific Islands. If that graph were any clearer, we’d be using it to find our way out of the labyrinth of statistical mysteries.
This remarkable association between seemingly unrelated variables had our research team quite literally gasping for breath, wondering if we had stumbled upon the holy grail of environmental research - or perhaps just an elaborate cosmic prank played out in the realm of data analysis.
Clearly, there is more work to be done in unraveling the precise link between these two elements, but for now, we can at least revel in the fact that our findings have brought some much-needed air of intrigue to the world of environmental science.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings have certainly sparked some lively discussion amongst our research team. Who would have thought that air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands would be as interconnected as Bert and Ernie? It's like witnessing a scientific buddy cop movie - "The Smoggy and the Furious" - where these two unlikely partners in environmental crime join forces to perplex and delight researchers.

The correlation we uncovered aligns with prior research that has illuminated the far-reaching impact of air pollution on various aspects of human and environmental health. As Smith et al. emphasized in their work on air pollution and health, the adverse effects of polluted air extend beyond the visible haze, permeating our respiratory systems with as much subtlety as a stealthy ninja. Our findings bolster this perspective, demonstrating that the ramifications of air pollution may extend even further than previously imagined, reaching across oceans to influence gasoline consumption patterns in distant lands. It's as if air pollution is the Claire Voyant of environmental factors, foreseeing its impact on gasoline usage in a crystal ball of statistical significance.

In a similar vein, the research by Doe and Jones shed light on the economic dimensions of gasoline consumption patterns, emphasizing the intricate interplay of factors that shape our petrol-pumping behaviors. Our study adds a new dimension to this understanding by unveiling a compelling association between air pollution in Farmington and gasoline consumption in the Pacific Islands. It's like the missing puzzle piece in a jigsaw puzzle of environmental influences, slotting in snugly to complete the big picture with a satisfying *click* of statistical validation.

Our journey through the literature review, punctuated with a few unconventional stops along the way, has indeed paid dividends. We ventured into the realms of non-fiction and fiction, exploring the impacts of air pollution and gasoline through multifaceted lenses. And just like a versatile superhero, our research has taken inspiration from these diverse sources, adopting a hybrid approach to uncover the unexpected connection between seemingly distant environmental variables.

The robust correlation coefficient and r-squared value we have unearthed reinforce the substantial influence of air pollution in Farmington on gasoline consumption in the U.S. Pacific Islands. This revelation is as significant as discovering that one's pet cat and dog are secret best friends, covertly collaborating in their nighttime escapades. It challenges us to rethink the boundaries of environmental causality and consider the intricate web of connections that underlie seemingly disparate phenomena.

As we navigate the uncharted territory of this peculiar correlation, we must resist the temptation to simply shrug it off as a statistical oddity. Instead, we should embrace the curiosity it ignites and persist in unraveling the nuanced mechanisms that link these environmental variables together. After all, in the wild and wonderful world of scientific inquiry, the most unexpected connections often lead to the most fascinating discoveries.

And now, dear reader, we must leave you with one final parting thought - as we navigate the murky waters of research, let's remember that a good dad joke is like a test tube of levity in the serious laboratory of scholarly pursuit: essential for balance and bound to elicit a groan or two.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Farmington, New Mexico and Gasoline pumped in U.S. Pacific Islands. 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]]
Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands

[[ABSTRACT]]
In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!

Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?

While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

[[INTRDUCTION]]
The world of environmental research is often a breath of fresh air, and the study of air pollution and its connections with other variables continues to uncover surprising relationships. In this paper, we dive into the unexpected association between air pollution levels in Farmington, New Mexico, and the consumption of gasoline in the U.S. Pacific Islands. We promise, this is not just a gas, we've got the data to back it up!
As the famous dad joke goes, "Why did the environmental researcher bring a pencil to the lab? Because they heard it had a good point!" Indeed, our research aims to pinpoint the connection between these seemingly unrelated factors and put an end to the mystery that's been lingering in the air - pun intended.
This study draws on a robust dataset from the Environmental Protection Agency and the Energy Information Administration, allowing us to meticulously analyze air quality levels in Farmington and gasoline consumption patterns in the U.S. Pacific Islands. The results we uncovered were shocking - statistically shocking, that is!
Our research team employed advanced statistical techniques to quantify the relationship between these variables, and the correlation coefficient we unveiled was stronger than the bond between carbon atoms in a molecule. The ensuing p-value was so low, we momentarily wondered if we had stumbled into an alternate statistical universe - a punnett square of statistical significance, if you will.
Though we cannot yet elucidate the exact mechanisms driving this unexpected correlation, our findings serve as a reminder that in the world of environmental research, the connections between seemingly disparate elements may be thicker than a methane molecule. So, grab your lab coat and buckle up - this scientific journey is about to take off into uncharted statistical territories!

[[RESULTS]]
The analysis of our data revealed a remarkably high correlation coefficient of 0.9433699 between air pollution levels in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. We couldn't believe our eyes when we saw the data; it was as if these two variables were holding hands across the miles, like a long-distance relationship strengthened by the power of statistical significance.
And speaking of statistical significance, the p-value we obtained was so tiny, it made us wonder if we had inadvertently discovered the statistical equivalent of a quark - talk about going subatomic in our quest for knowledge.
In addition to the robust correlation coefficient, we also calculated an impressive r-squared value of 0.8899467. This indicated that nearly 89% of the variation in gasoline consumption in the Pacific Islands could be explained by the air pollution levels in Farmington. This finding blew our minds like a gust of wind sweeping through a research laboratory!
Fig. 1 illustrates the strong correlation between air pollution in Farmington, New Mexico, and gasoline pumped in the U.S. Pacific Islands. If that graph were any clearer, we’d be using it to find our way out of the labyrinth of statistical mysteries.
This remarkable association between seemingly unrelated variables had our research team quite literally gasping for breath, wondering if we had stumbled upon the holy grail of environmental research - or perhaps just an elaborate cosmic prank played out in the realm of data analysis.
Clearly, there is more work to be done in unraveling the precise link between these two elements, but for now, we can at least revel in the fact that our findings have brought some much-needed air of intrigue to the world of environmental science.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unearthed a surprising and undeniably robust correlation between air pollution levels in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. The statistical bond we've uncovered between these distant variables is as strong as the chemical bonds that hold together a molecule of methane – methane be the real MVP in this unlikely partnership!

Our findings not only provide empirical evidence of this unexpected relationship but also fuel further speculation about what could be driving this correlation. The statistical ties between these variables are so tight, they make a molecule of oxygen and two molecules of hydrogen look positively distant in comparison - talk about a chemical reaction of data!

It's no small feat to unveil such a substantial association between elements that, at first glance, seem as unrelated as a periodic table and a grocery list. I guess you could say we've turned the tables on conventional wisdom – science, after all, is full of surprises, much like a good magic trick at a scientific conference!

However, as much as we've enjoyed this statistical rollercoaster, our investigation into this unlikely connection has uncovered more questions than answers. We may have connected the dots, but the ultimate explanation for this correlation remains as mysterious as dark matter (or my college research notes) – a real head-scratcher!

Nonetheless, in the spirit of scientific inquiry, we've rolled up our lab coats and proudly proclaimed: "No more research is needed in this area, we've got this correlation covered!" After all, there's only so much awkward statistical tension one can handle, and we've surely pushed the limits of science's capacity for unexpected connections. It's time to hand over the baton to the next intrepid researchers and watch them grapple with this statistical puzzle – we've already had our fill of puzzling correlations and unexpected statistical flings!


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 Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Serendipity


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 Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Ecological Connections and Anomalies (SECA)


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 Up in the Air: Uncovering the Unlikely Link Between Air Pollution in Farmington, New Mexico, and Gasoline Pumped in U.S. Pacific Islands with an abstract of In this paper, we delve into the unexpected connection between two seemingly disparate elements: air pollution in Farmington, New Mexico, and gasoline consumption in the U.S. Pacific Islands. As we embark on this journey through data analysis and statistical inference, we can't help but wonder if this correlation is a mere coincidence or a breath of fresh air in the world of environmental research - pun intended!
Drawing on data from the Environmental Protection Agency and the Energy Information Administration, our research team sought to quantify the relationship between air pollution levels in Farmington and the amount of gasoline pumped in the Pacific Islands. Our findings revealed a striking correlation coefficient of 0.9433699 and a p-value that was lower than a sea level gas station's prices. The correlation spanned the time period from 2006 to 2021, leaving us gasping for air in the face of this unexpected association - another pun, anyone?
While the exact mechanism underlying this correlation remains unclear, our results raise intriguing questions about the interconnectedness of environmental phenomena across seemingly isolated regions. As we conclude this study, we can't help but contemplate the implications of our findings - after all, when it comes to air pollution and gasoline consumption, the link between Farmington and the U.S. Pacific Islands may not be as thin as the air itself.

ChatGPT:

air pollution, Farmington New Mexico, gasoline consumption, US Pacific Islands, correlation, data analysis, statistical inference, environmental research, Environmental Protection Agency, Energy Information Administration, correlation coefficient, p-value, environmental phenomena, interconnectedness, implications

*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 Farmington, New Mexico
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Farmington, NM
Source: Environmental Protection Agency
See what else correlates with Air pollution in Farmington, New Mexico

Gasoline pumped in U.S. Pacific Islands
Detailed data title: Volume of gasoline pumped consumed in U.S. Pacific Islands in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Gasoline pumped in U.S. Pacific Islands

Correlation r = 0.9433699 (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 = 0.8899467 (Coefficient of determination)
This means 89% of the change in the one variable (i.e., Gasoline pumped in U.S. Pacific Islands) is predictable based on the change in the other (i.e., Air pollution in Farmington, New Mexico) over the 16 years from 2006 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.31E-8. 0.0000000430887842743156630000
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 0.94 in 4.31E-6% of random cases. Said differently, if you correlated 23,207,895 random variables You don't actually need 23 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 15 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.84, 0.98 ] 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.
2006200720082009201020112012201320142015201620172018201920202021
Air pollution in Farmington, New Mexico (Bad air quality days)0.2739730001.09589000.27397300000000
Gasoline pumped in U.S. Pacific Islands (Million Barrels/Day)0.580.580.580.580.70.580.580.580.580.580.580.580.580.580.580.58




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.




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([0.273973,0,0,0,1.09589,0,0,0.273973,0,0,0,0,0,0,0,0,])
array_2 = np.array([0.58,0.58,0.58,0.58,0.7,0.58,0.58,0.58,0.58,0.58,0.58,0.58,0.58,0.58,0.58,0.58,])
array_1_name = "Air pollution in Farmington, New Mexico"
array_2_name = "Gasoline pumped in U.S. Pacific Islands"

# 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?

I'm grateful for your review!


Correlation ID: 3548 · Black Variable ID: 20619 · Red Variable ID: 25025
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0