Spurious correlation #1,361 · 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 Morgan City, Louisiana and the second variable is Gasoline pumped in Poland. The chart goes from 1983 to 2005, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Morgan City, Louisiana and the second variable is Gasoline pumped in Poland. The chart goes from 1983 to 2005, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the air over Morgan City cleared up, it formed a high-pressure system that migrated eastward. This led to a domino effect of atmospheric changes, ultimately creating a localized anti-gasoline-pumping vortex over Poland. It's like the world's weirdest car fuel conspiracy, straight out of a wacky sci-fi movie! Who knew that the air we breathe and the fuel we pump could be interconnected in such a fantastically ridiculous way?

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image showing a cyberpunk cityscape at dusk, with towering industrial chimneys emitting plumes of smoke in the background. In the foreground, depict a futuristic petrol station in Poland, with sleek vehicles lined up, each emitting a neon glow amidst the scent of gasoline. The setting should convey a contrast between the dystopian atmosphere of Morgan City, Louisiana, and the high-tech, bustling activity of the Polish petrol station. 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: Unhealthy air quality in Morgan City, Louisiana and Gasoline pumped in Poland. 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: Pop art An image that looks like it is a scene from A Disney Movie Woodblock painting Cyberpunk Parallax art
ChatGPT: Cyberpunk

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 Unhealthy air quality in Morgan City, Louisiana and Gasoline pumped in Poland together. Keep the description simple.
ChatGPT: In Morgan City, Louisiana, the air hangs heavy with pollutants as smoke rises from industrial chimneys. Meanwhile, in Poland, the scent of gasoline fills the air as cars line up at a bustling petrol station.

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: [ Cyberpunk ] and depicting this scene: In Morgan City, Louisiana, the air hangs heavy with pollutants as smoke rises from industrial chimneys. Meanwhile, in Poland, the scent of gasoline fills the air as cars line up at a bustling petrol station. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image showing a cyberpunk cityscape at dusk, with towering industrial chimneys emitting plumes of smoke in the background. In the foreground, depict a futuristic petrol station in Poland, with sleek vehicles lined up, each emitting a neon glow amidst the scent of gasoline. The setting should convey a contrast between the dystopian atmosphere of Morgan City, Louisiana, and the high-tech, bustling activity of the Polish petrol station.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in Morgan City, Louisiana caused Gasoline pumped in Poland to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland

The Journal of Atmospheric Anomalies

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Morgan City, Louisiana and Gasoline pumped in Poland. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland

[[ABSTRACT]]
In this study, we delved into the unexpected relationship between air pollution in Morgan City, Louisiana, and the gasoline consumption patterns in Poland. While this pairing may seem as mismatched as mismatched socks, our findings reveal a surprising correlation between the two seemingly unrelated variables. Utilizing data from the Environmental Protection Agency and the Energy Information Administration, our research team applied statistical analysis to unearth some truly jaw-dropping results. With a correlation coefficient of 0.6819323 and a p-value less than 0.01 for the period spanning from 1983 to 2005, the evidence pointing to a connection between these two seemingly disparate entities is nothing short of astonishing. Our research provides a quirky twist to the otherwise mundane world of air pollution and gasoline consumption, demonstrating that sometimes, the most unexpected correlations can be found lurking beneath the surface. This study not only sheds light on this peculiar relationship but also serves as a reminder that in the world of research, surprises are always just around the corner.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Welcome, dear reader, to the wacky world of air pollution and gasoline consumption correlations. While most connections in the scientific realm seem as straightforward as a one-way street, our study will take you on a wild ride down a two-way avenue paved with unexpected twists and turns.
As we all know, air pollution is no laughing matter. It's the kind of thing that can take your breath away, quite literally. But what if we told you that the air pollution in Morgan City, Louisiana, and the gasoline pumped in Poland are in cahoots? Yes, you read that right, we're not pulling your leg here. We were just as surprised as you are.
Picture this: a quaint town in Louisiana, known for its seafood and Southern charm, joins hands with a country in Europe, famous for its pierogis and medieval castles. What could these two places possibly have in common, you ask? Well, the answer may leave you more breathless than a steep hike up the Carpathian Mountains.
Now, before you think we've gone off the deep end, let's dive into the nitty-gritty of our research. We gathered data from the Environmental Protection Agency and the Energy Information Administration, and we crunched those numbers like they were jellybeans on a rainy day. And what did we find? Hold onto your lab coats, because the results are as mind-boggling as a Rubik's Cube in a tornado.
Our study uncovered a correlation coefficient of 0.6819323 and a p-value less than 0.01 from 1983 to 2005. In plain English, this means that the connection between air pollution in Morgan City and gasoline consumption in Poland is no mere figment of our imagination. It's as real as the cholesterol in a plate of deep-fried Oreos.
As we elaborate on the details of our findings, we invite you to keep an open mind. After all, in the world of research, the unexpected is always hiding behind the corner, ready to leap out like a jack-in-the-box. So, buckle up and get ready for a journey through the uncharted territory where air pollution and gasoline go hand in hand.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The unlikely pairing of air pollution in Morgan City, Louisiana, and gasoline consumption in Poland has spurred a flurry of inquiry and curiosity in the academic world. Smith and colleagues (2010) first broached the topic in their seminal work titled "Air Quality and Global Energy Trends," revealing early inklings of a potential connection between these disparate entities. Doe (2014) continued this line of investigation in their comprehensive study "Gasoline Markets and Environmental Impacts," delving into the intricate web of factors influencing gasoline consumption and its environmental ramifications. Furthermore, Jones et al. (2017) shed light on the nuanced interplay between air pollution and international fuel usage in their groundbreaking research paper "From Louisiana to Poland: A Cross-Continental Analysis."

Turning to non-fiction literature, "The Air We Breathe" by Andrea Barrett provides a comprehensive overview of air quality and its impact on human health, offering insightful parallels to our current study. Additionally, "The Big Rig: Trucking and the Decline of the American Dream" by Steve Viscelli examines the complex dynamics of fuel consumption and its reverberations in a global context, offering a tangential perspective to our investigation.

In the realm of fiction, works such as "The Air Affair" by Jasper Fforde and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon may not appear directly related to our topic at first glance, but their exploration of interconnectedness and unexpected correlations strikes a chord with the essence of our research.

To broaden the scope of our inquiry, our research team embarked on an unconventional journey that involved delving into unorthodox sources of information. From analyzing the back labels of household cleaning products to meticulously scrutinizing the ingredients listed on shampoo bottles, we left no stone unturned in our quest for understanding. While these unconventional sources may raise eyebrows in traditional academic circles, they provided invaluable insights that added a touch of whimsy to our otherwise serious pursuit of knowledge.

As we navigate through this hodgepodge of literature and ancillary sources, the whimsical nature of our research underscores the unconventional path we have taken in unraveling the enigmatic relationship between air pollution in Morgan City and gasoline consumption in Poland. With each turn of the page, we invite our readers to join us in this offbeat adventure, where the unexpected thrives, and the mundane takes a backseat to the delightfully peculiar.

The idiosyncratic nature of our investigation has not only broadened our horizons but has also highlighted the potential for unconventional approaches to yield insightful discoveries. As we forge ahead in our analysis, we remain steadfast in our commitment to unearthing the offbeat connections that permeate the tapestry of our world, infusing scholarly pursuits with a dose of humor and mirth along the way.

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 Morgan City, Louisiana and Gasoline pumped in Poland. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland

[[ABSTRACT]]
In this study, we delved into the unexpected relationship between air pollution in Morgan City, Louisiana, and the gasoline consumption patterns in Poland. While this pairing may seem as mismatched as mismatched socks, our findings reveal a surprising correlation between the two seemingly unrelated variables. Utilizing data from the Environmental Protection Agency and the Energy Information Administration, our research team applied statistical analysis to unearth some truly jaw-dropping results. With a correlation coefficient of 0.6819323 and a p-value less than 0.01 for the period spanning from 1983 to 2005, the evidence pointing to a connection between these two seemingly disparate entities is nothing short of astonishing. Our research provides a quirky twist to the otherwise mundane world of air pollution and gasoline consumption, demonstrating that sometimes, the most unexpected correlations can be found lurking beneath the surface. This study not only sheds light on this peculiar relationship but also serves as a reminder that in the world of research, surprises are always just around the corner.

[[LITERATURE REVIEW]]
The unlikely pairing of air pollution in Morgan City, Louisiana, and gasoline consumption in Poland has spurred a flurry of inquiry and curiosity in the academic world. Smith and colleagues (2010) first broached the topic in their seminal work titled "Air Quality and Global Energy Trends," revealing early inklings of a potential connection between these disparate entities. Doe (2014) continued this line of investigation in their comprehensive study "Gasoline Markets and Environmental Impacts," delving into the intricate web of factors influencing gasoline consumption and its environmental ramifications. Furthermore, Jones et al. (2017) shed light on the nuanced interplay between air pollution and international fuel usage in their groundbreaking research paper "From Louisiana to Poland: A Cross-Continental Analysis."
Turning to non-fiction literature, "The Air We Breathe" by Andrea Barrett provides a comprehensive overview of air quality and its impact on human health, offering insightful parallels to our current study. Additionally, "The Big Rig: Trucking and the Decline of the American Dream" by Steve Viscelli examines the complex dynamics of fuel consumption and its reverberations in a global context, offering a tangential perspective to our investigation.
In the realm of fiction, works such as "The Air Affair" by Jasper Fforde and "The Curious Incident of the Dog in the Night-Time" by Mark Haddon may not appear directly related to our topic at first glance, but their exploration of interconnectedness and unexpected correlations strikes a chord with the essence of our research.
To broaden the scope of our inquiry, our research team embarked on an unconventional journey that involved delving into unorthodox sources of information. From analyzing the back labels of household cleaning products to meticulously scrutinizing the ingredients listed on shampoo bottles, we left no stone unturned in our quest for understanding. While these unconventional sources may raise eyebrows in traditional academic circles, they provided invaluable insights that added a touch of whimsy to our otherwise serious pursuit of knowledge.
As we navigate through this hodgepodge of literature and ancillary sources, the whimsical nature of our research underscores the unconventional path we have taken in unraveling the enigmatic relationship between air pollution in Morgan City and gasoline consumption in Poland. With each turn of the page, we invite our readers to join us in this offbeat adventure, where the unexpected thrives, and the mundane takes a backseat to the delightfully peculiar.
The idiosyncratic nature of our investigation has not only broadened our horizons but has also highlighted the potential for unconventional approaches to yield insightful discoveries. As we forge ahead in our analysis, we remain steadfast in our commitment to unearthing the offbeat connections that permeate the tapestry of our world, infusing scholarly pursuits with a dose of humor and mirth along the way.

[[RESULTS]]
Our analysis of the data revealed a striking correlation coefficient of 0.6819323 between air pollution in Morgan City, Louisiana, and gasoline consumption in Poland for the period from 1983 to 2005. This unexpected relationship raised more eyebrows than a surprise birthday party at a barbershop, leaving our research team both astounded and amused.
Furthermore, the calculated r-squared value of 0.4650317 indicated that a substantial portion of the variability in gasoline consumption in Poland could be explained by the levels of air pollution in Morgan City during the specified time frame. It's as if these two variables were engaged in a synchronized dance, moving in harmony like a well-rehearsed flash mob.
The p-value of less than 0.01 provided strong evidence against the null hypothesis, supporting the existence of a meaningful connection between the air we breathe in Louisiana and the gasoline guzzled in Poland. This statistical significance hit us with the force of a punchline in a comedy club – unexpected, yet undeniably impactful.
To visually encapsulate this extraordinary linkage, we present Fig. 1, a scatterplot showcasing the robust relationship between air pollution in Morgan City and gasoline consumption in Poland. This graphical representation illuminates the coupling of these unlikely bedfellows, serving as a visual punchline to the punchy connection our research uncovered.
In summary, our findings unveil a correlation as surprising as an unexpected plot twist in a mystery novel, demonstrating that sometimes, the most peculiar connections can emerge from the unlikeliest of sources. The world of research sure knows how to keep us on our toes, serving up surprises that are as unpredictable as a game of musical chairs in a room full of cats.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The documented correlation between air pollution in Morgan City, Louisiana, and gasoline consumption in Poland is as unexpected as finding a unicorn at a gas station. Our findings not only corroborate but also build upon prior research, providing empirical evidence for the whimsical hypotheses proposed in the academic and non-fictional literature.

Smith and colleagues (2010) hinted at a potential relationship between air quality and global energy trends, setting the stage for our study's groundbreaking revelations. Doe (2014) delved into the labyrinthine world of gasoline markets and environmental impacts, laying the groundwork for our unexpected association between distant locales. Our results uphold these pioneering works, affirming the interconnectedness of seemingly unrelated environmental and energy phenomena.

Delving into the unconventional sources of information mentioned in the literature review, our research team channeled the spirit of Sherlock Holmes to uncover correlations lurking beneath the surface. Just as Watson's observations illuminated the mysteries in Sir Arthur Conan Doyle's tales, our analysis shed light on the enigmatic bond between air pollution and gasoline consumption. The idiosyncratic sources we tapped into, much like Alice's journey through Wonderland, led us down a rabbit hole of unexpected discoveries that added layers of complexity and delight to the pursuit of knowledge.

The statistically significant correlation coefficient and p-value from our study serve as the empirical punchlines to the theoretical setups crafted by prior researchers. As if weaving a narrative akin to Douglas Adams' "The Hitchhiker's Guide to the Galaxy," our results unveil a cosmic joke, demonstrating that the universe of data is filled with surprising twists and turns. It is as if the statistical tests themselves were performing a grand jest, challenging conventional wisdom and inviting researchers to embrace the unconventional with open arms and a hint of mischief.

In essence, this study takes an exceptional phenomenon and delivers it with the flair of a stand-up comedian. Through the unexpected link we have unearthed, we not only contribute to the growing body of knowledge in environmental and energy studies but also infuse scholarly pursuits with a dash of humor and mirth. After all, in the words of Mark Twain, "Humor is the great thing, the saving thing after all." Therefore, we invite fellow researchers to join us in this quirky adventure, where surprises are uncovered, and the unexpected reigns supreme.

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 Morgan City, Louisiana and Gasoline pumped in Poland. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland

[[ABSTRACT]]
In this study, we delved into the unexpected relationship between air pollution in Morgan City, Louisiana, and the gasoline consumption patterns in Poland. While this pairing may seem as mismatched as mismatched socks, our findings reveal a surprising correlation between the two seemingly unrelated variables. Utilizing data from the Environmental Protection Agency and the Energy Information Administration, our research team applied statistical analysis to unearth some truly jaw-dropping results. With a correlation coefficient of 0.6819323 and a p-value less than 0.01 for the period spanning from 1983 to 2005, the evidence pointing to a connection between these two seemingly disparate entities is nothing short of astonishing. Our research provides a quirky twist to the otherwise mundane world of air pollution and gasoline consumption, demonstrating that sometimes, the most unexpected correlations can be found lurking beneath the surface. This study not only sheds light on this peculiar relationship but also serves as a reminder that in the world of research, surprises are always just around the corner.

[[INTRDUCTION]]
Welcome, dear reader, to the wacky world of air pollution and gasoline consumption correlations. While most connections in the scientific realm seem as straightforward as a one-way street, our study will take you on a wild ride down a two-way avenue paved with unexpected twists and turns.
As we all know, air pollution is no laughing matter. It's the kind of thing that can take your breath away, quite literally. But what if we told you that the air pollution in Morgan City, Louisiana, and the gasoline pumped in Poland are in cahoots? Yes, you read that right, we're not pulling your leg here. We were just as surprised as you are.
Picture this: a quaint town in Louisiana, known for its seafood and Southern charm, joins hands with a country in Europe, famous for its pierogis and medieval castles. What could these two places possibly have in common, you ask? Well, the answer may leave you more breathless than a steep hike up the Carpathian Mountains.
Now, before you think we've gone off the deep end, let's dive into the nitty-gritty of our research. We gathered data from the Environmental Protection Agency and the Energy Information Administration, and we crunched those numbers like they were jellybeans on a rainy day. And what did we find? Hold onto your lab coats, because the results are as mind-boggling as a Rubik's Cube in a tornado.
Our study uncovered a correlation coefficient of 0.6819323 and a p-value less than 0.01 from 1983 to 2005. In plain English, this means that the connection between air pollution in Morgan City and gasoline consumption in Poland is no mere figment of our imagination. It's as real as the cholesterol in a plate of deep-fried Oreos.
As we elaborate on the details of our findings, we invite you to keep an open mind. After all, in the world of research, the unexpected is always hiding behind the corner, ready to leap out like a jack-in-the-box. So, buckle up and get ready for a journey through the uncharted territory where air pollution and gasoline go hand in hand.

[[RESULTS]]
Our analysis of the data revealed a striking correlation coefficient of 0.6819323 between air pollution in Morgan City, Louisiana, and gasoline consumption in Poland for the period from 1983 to 2005. This unexpected relationship raised more eyebrows than a surprise birthday party at a barbershop, leaving our research team both astounded and amused.
Furthermore, the calculated r-squared value of 0.4650317 indicated that a substantial portion of the variability in gasoline consumption in Poland could be explained by the levels of air pollution in Morgan City during the specified time frame. It's as if these two variables were engaged in a synchronized dance, moving in harmony like a well-rehearsed flash mob.
The p-value of less than 0.01 provided strong evidence against the null hypothesis, supporting the existence of a meaningful connection between the air we breathe in Louisiana and the gasoline guzzled in Poland. This statistical significance hit us with the force of a punchline in a comedy club – unexpected, yet undeniably impactful.
To visually encapsulate this extraordinary linkage, we present Fig. 1, a scatterplot showcasing the robust relationship between air pollution in Morgan City and gasoline consumption in Poland. This graphical representation illuminates the coupling of these unlikely bedfellows, serving as a visual punchline to the punchy connection our research uncovered.
In summary, our findings unveil a correlation as surprising as an unexpected plot twist in a mystery novel, demonstrating that sometimes, the most peculiar connections can emerge from the unlikeliest of sources. The world of research sure knows how to keep us on our toes, serving up surprises that are as unpredictable as a game of musical chairs in a room full of cats.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has exposed a correlation between air pollution in Morgan City, Louisiana, and gasoline consumption in Poland that is as unexpected as finding a pineapple on a pizza in Warsaw. The evidence we've amassed reveals a connection between these two seemingly unrelated entities that is as mind-boggling as a Sudoku puzzle in a funhouse.

The statistical marvel of a correlation coefficient of 0.6819323 and a p-value less than 0.01 from 1983 to 2005 has left us pondering the mysteries of the universe more than a physicist at a magic show. The robust r-squared value of 0.4650317 indicated that a substantial portion of the variation in gasoline consumption in Poland could be attributed to the air pollution levels in Morgan City, taking us on an intellectual rollercoaster ride wilder than a moose on a unicycle.

Our findings underscore the delightful unpredictability of scientific inquiry, showcasing that in the realm of research, the most unexpected connections can arise from the unlikeliest of sources. It's a bit like stumbling upon a penguin in a desert – unlikely, yet undeniably captivating.

Therefore, we assert with the confidence of a tightrope walker with a safety net that no further research is needed in this area. The enigmatic bond between air pollution in Morgan City and gasoline consumption in Poland has been sufficiently unraveled, leaving us breathless in the best possible way.

In the immortal words of Shakespeare, "All's well that ends well." And in the immortal words of our research team, "All's well that ends with a surprising correlation coefficient and a good laugh."

No further research is needed in this area.

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric Anomalies

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Transnational Environmental Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland with an abstract of In this study, we delved into the unexpected relationship between air pollution in Morgan City, Louisiana, and the gasoline consumption patterns in Poland. While this pairing may seem as mismatched as mismatched socks, our findings reveal a surprising correlation between the two seemingly unrelated variables. Utilizing data from the Environmental Protection Agency and the Energy Information Administration, our research team applied statistical analysis to unearth some truly jaw-dropping results. With a correlation coefficient of 0.6819323 and a p-value less than 0.01 for the period spanning from 1983 to 2005, the evidence pointing to a connection between these two seemingly disparate entities is nothing short of astonishing. Our research provides a quirky twist to the otherwise mundane world of air pollution and gasoline consumption, demonstrating that sometimes, the most unexpected correlations can be found lurking beneath the surface. This study not only sheds light on this peculiar relationship but also serves as a reminder that in the world of research, surprises are always just around the corner.

ChatGPT:

air pollution, gasoline consumption, Morgan City Louisiana, Poland, environmental protection agency data, energy information administration data, statistical analysis, correlation coefficient, p-value, 1983-2005, research, unexpected correlation

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

Air pollution in Morgan City, Louisiana
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Morgan City, LA
Source: Environmental Protection Agency
See what else correlates with Air pollution in Morgan City, Louisiana

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

Correlation r = 0.6819323 (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 = 0.4650317 (Coefficient of determination)
This means 46.5% of the change in the one variable (i.e., Gasoline pumped in Poland) is predictable based on the change in the other (i.e., Air pollution in Morgan City, Louisiana) over the 23 years from 1983 through 2005.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00034.^Show 0.0003386094069275706000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.68 in 0.034% of random cases. Said differently, if you correlated 2,953 random variables^Note Which I absolutely did.
with the same 22 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 22 because we have two variables measured over a period of 23 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.

[ 0.38, 0.85 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	1983	1984	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005
Air pollution in Morgan City, Louisiana (Bad air quality days)	0.0775194	0.019802	0	0	0	0	0.0261628	0.0308989	0.0027933	0	0.0136986	0.00824176	0.123596	0.0168067	0.0853994	0.0764873	0.0710227	0.0782123	0.0497238	0.00849858	0.0380117	0.0286533	0.0502793
Gasoline pumped in Poland (Million Barrels/Day)	97	72.918	68.3836	71.9671	68.0548	69.9344	77.5233	71.474	83.211	87.7705	90.5178	99.9178	101.49	105.462	114.504	115.707	128.463	115.552	107.167	97.8356	94.663	95.0301	92.7863

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.0775194,0.019802,0,0,0,0,0.0261628,0.0308989,0.0027933,0,0.0136986,0.00824176,0.123596,0.0168067,0.0853994,0.0764873,0.0710227,0.0782123,0.0497238,0.00849858,0.0380117,0.0286533,0.0502793,])
array_2 = np.array([97,72.918,68.3836,71.9671,68.0548,69.9344,77.5233,71.474,83.211,87.7705,90.5178,99.9178,101.49,105.462,114.504,115.707,128.463,115.552,107.167,97.8356,94.663,95.0301,92.7863,])
array_1_name = "Air pollution in Morgan City, Louisiana"
array_2_name = "Gasoline pumped in Poland"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in Morgan City, Louisiana
Line chart for only Gasoline pumped in Poland
AI-generated correlation image
The spurious research paper: A Breath of Fresh Air? The Unlikely Link Between Pollution in Morgan City and Gasoline in Poland

View another random correlation

How fun was this correlation?

Hats off to you for rating!

Correlation ID: 1361 · Black Variable ID: 21671 · Red Variable ID: 24819


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