about · email me · subscribe
Spurious correlation #1,740 · 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 Gadsden, Alabama and the second variable is Liquefied petroleum gas used in Netherlands Antilles.  The chart goes from 1981 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in Gadsden, Alabama led to a decrease in farting, lowering the demand for Liquefied petroleum gas in the Netherlands Antilles, where they are known for their giant, gas-powered whoopee cushions. And that, my friend, is how Gadsden to Netherlands Antilles became the most unexpected environmental duo since PB&J.

Model: dalle-3
Prompt: Create an image resembling a retro Polaroid photo, showing a contrast between two scenes. On one side, capture the hazy skyline of Gadsden, Alabama, depicting thick smog and unhealthy air quality. On the other side, showcase a neat row of Liquefied Petroleum Gas (LPG) tanks in the Netherlands Antilles, with workers inspecting and maintaining them. Enhance the vintage appearance of the photo to contrast the environmental conditions in 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: Unhealthy air quality in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. 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: Symbolism Parallax art A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s a Polaroid photo Symbolism
ChatGPT: a Polaroid photo

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 Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles together. Keep the description simple.
ChatGPT: A hazy sky looms over Gadsden, Alabama, as thick smog blankets the city, indicating unhealthy air quality. In the Netherlands Antilles, a line of Liquefied petroleum gas tanks stand in a neatly arranged row with workers checking and maintaining them.

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 Polaroid photo ] and depicting this scene: A hazy sky looms over Gadsden, Alabama, as thick smog blankets the city, indicating unhealthy air quality. In the Netherlands Antilles, a line of Liquefied petroleum gas tanks stand in a neatly arranged row with workers checking and maintaining them. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image resembling a retro Polaroid photo, showing a contrast between two scenes. On one side, capture the hazy skyline of Gadsden, Alabama, depicting thick smog and unhealthy air quality. On the other side, showcase a neat row of Liquefied Petroleum Gas (LPG) tanks in the Netherlands Antilles, with workers inspecting and maintaining them. Enhance the vintage appearance of the photo to contrast the environmental conditions in 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 Gadsden, Alabama caused Liquefied petroleum gas used in Netherlands Antilles to decrease.

AI academic paper

(Because p < 0.01)
A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles

The Journal of Atmospheric Anomalies

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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns.

Include a pun in the title.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.8792277 and p < 0.01 for 1981 to 2018.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As researchers, we often find ourselves diving into the depths of data, hoping to uncover unexpected connections and correlations. In the case of our study, we ventured into the curious realm of air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Little did we know that this investigation would lead us down a windy path filled with twists, turns, and a surprising amount of gas-related puns.

Now, we understand if you initially raised an eyebrow or even let out a chuckle upon reading our research topic. Air pollution in Gadsden and LPG in the Netherlands Antilles – a match made in statistical heaven, or so it seemed. Yet, armed with our trusty statistical tools and an arsenal of puns, we delved into this quixotic quest with the hope of unearthing a connection that would make even the most stoic researcher gasp with disbelief.

As we navigated through the labyrinth of environmental and energy data, we couldn't help but revel in the irony of our endeavor. Here we were, analyzing the air, while also adding a touch of levity with our statistical analyses and correlations. It was as if we had stumbled upon a cosmic joke – one that left us simultaneously scratching our heads and gasping for fresh air.

The initial findings of our study left us feeling breathless as we uncovered a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. Yes, you read that correctly – a gas-ily high correlation that left our statistical senses tingling with both excitement and disbelief. It was a moment that called for a quick gasp, followed by a round of nerdy science puns to lighten the mood.

But, beyond the puns and the gas-related humor, there lies a serious and compelling correlation that begs for further scrutiny. So, join us in embracing the unexpected and the gas-tounding as we unravel the mysterious connection between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. It's a breath of fresh air, laced with statistical intrigue and a dash of absurdity – and we wouldn't have it any other way. Let's dive in and prepare to be gas-lighted by the curious correlation that awaits.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As researchers, we often find ourselves diving into the depths of data, hoping to uncover unexpected connections and correlations. In the case of our study, we ventured into the curious realm of air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Little did we know that this investigation would lead us down a windy path filled with twists, turns, and a surprising amount of gas-related puns.
Now, we understand if you initially raised an eyebrow or even let out a chuckle upon reading our research topic. Air pollution in Gadsden and LPG in the Netherlands Antilles – a match made in statistical heaven, or so it seemed. Yet, armed with our trusty statistical tools and an arsenal of puns, we delved into this quixotic quest with the hope of unearthing a connection that would make even the most stoic researcher gasp with disbelief.
As we navigated through the labyrinth of environmental and energy data, we couldn't help but revel in the irony of our endeavor. Here we were, analyzing the air, while also adding a touch of levity with our statistical analyses and correlations. It was as if we had stumbled upon a cosmic joke – one that left us simultaneously scratching our heads and gasping for fresh air.
The initial findings of our study left us feeling breathless as we uncovered a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. Yes, you read that correctly – a gas-ily high correlation that left our statistical senses tingling with both excitement and disbelief. It was a moment that called for a quick gasp, followed by a round of nerdy science puns to lighten the mood.
But, beyond the puns and the gas-related humor, there lies a serious and compelling correlation that begs for further scrutiny. So, join us in embracing the unexpected and the gas-tounding as we unravel the mysterious connection between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. It's a breath of fresh air, laced with statistical intrigue and a dash of absurdity – and we wouldn't have it any other way. Let's dive in and prepare to be gas-lighted by the curious correlation that awaits.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the seemingly whimsical correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles led us to a myriad of scholarly and not-so-scholarly sources. At the outset, our pursuit for academic rigor led us to scholarly works such as "The Paradox of Polluted Air" by Smith, which delves into the complexities of air pollution and its unforeseen connections, and "The Gas Chronicles" by Doe, which offers a historical perspective on the evolution of liquefied petroleum gas usage across the world.

However, while trawling through the pool of academic literature, we could not help but stumble upon sources that added an unexpected layer of whimsy to our research. "Gassy Tales: A Collection of Gas-Related Anecdotes" by Jones, although not directly related to environmental research, provided a much-needed laugh amidst the sea of scholarly seriousness. Additionally, "The Unbearable Lightness of Being...Powered by LPG" by Kundera, though a work of fiction, offered a peculiar insight into the potential metaphysical connections between air quality and the use of liquefied petroleum gas.

As if that wasn't enough, our journey through the scholarly landscape took an even more unexpected turn when we encountered social media posts that seemed to uncannily touch upon our research topic. Tweets like "Just watched my LPG-powered stove produce more smoke than an 18th-century locomotive #airpollutionwoes" and "Gadsden's air quality has me considering wearing a gas mask as a fashion statement #justbreathe" provided a quirky, yet oddly relevant, perspective on the intersection between air pollution in Gadsden, Alabama, and LPG use in the Netherlands Antilles.

In essence, our foray into the literature – both serious and whimsical – has provided an eclectic mix of perspectives that mirror the unexpected and gas-tly nature of our research. As we embark on this gas-ifying journey, it becomes abundantly clear that while the pursuit of knowledge is undoubtedly serious, a touch of humor and absurdity can illuminate even the most unexpected correlations. So, with a dash of scholarly seriousness and a sprinkle of whimsy, we venture forth to unravel the enigmatic ties between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1981 to 2018

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

[[INTRODUCTION]]
As researchers, we often find ourselves diving into the depths of data, hoping to uncover unexpected connections and correlations. In the case of our study, we ventured into the curious realm of air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Little did we know that this investigation would lead us down a windy path filled with twists, turns, and a surprising amount of gas-related puns.
Now, we understand if you initially raised an eyebrow or even let out a chuckle upon reading our research topic. Air pollution in Gadsden and LPG in the Netherlands Antilles – a match made in statistical heaven, or so it seemed. Yet, armed with our trusty statistical tools and an arsenal of puns, we delved into this quixotic quest with the hope of unearthing a connection that would make even the most stoic researcher gasp with disbelief.
As we navigated through the labyrinth of environmental and energy data, we couldn't help but revel in the irony of our endeavor. Here we were, analyzing the air, while also adding a touch of levity with our statistical analyses and correlations. It was as if we had stumbled upon a cosmic joke – one that left us simultaneously scratching our heads and gasping for fresh air.
The initial findings of our study left us feeling breathless as we uncovered a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. Yes, you read that correctly – a gas-ily high correlation that left our statistical senses tingling with both excitement and disbelief. It was a moment that called for a quick gasp, followed by a round of nerdy science puns to lighten the mood.
But, beyond the puns and the gas-related humor, there lies a serious and compelling correlation that begs for further scrutiny. So, join us in embracing the unexpected and the gas-tounding as we unravel the mysterious connection between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. It's a breath of fresh air, laced with statistical intrigue and a dash of absurdity – and we wouldn't have it any other way. Let's dive in and prepare to be gas-lighted by the curious correlation that awaits.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To begin our investigation, we took a deep breath and immersed ourselves in the smog of data collection and analysis. Our first task was to gather environmental and energy consumption data from the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA). We combed through countless reports, datasets, and spreadsheets, navigating the digital terrain with the precision of a cartographer and the tenacity of a determined treasure hunter.

Armed with our trusty statistical compass and the spirit of adventurous explorers, we meticulously selected the data related to air quality in Gadsden, Alabama, and the consumption of liquefied petroleum gas (LPG) in the Netherlands Antilles.

Now, when it came to analyzing the air pollution data, we couldn't just wing it like a flock of migrating birds. So, we employed the tried-and-true methods of statistical analysis, including correlation coefficients, regression models, and time series analysis. We also dipped our toes into the murky waters of geographical information systems (GIS) to map out the spatial distribution of air pollution in Gadsden, uncovering patterns with the sharp eyes of explorers charting unknown territories.

As for the LPG consumption data in the Netherlands Antilles, we didn't just dive in headfirst; we donned our metaphorical scuba gear and plunged into the depths of energy consumption statistics. We applied econometric models, trend analysis, and even went as far as conjuring up a crystal ball, hoping to peer into the future of LPG usage with the mystical powers of forecasting techniques.

But let's not forget about the statistical software we utilized. It was our trusty companion, our loyal sidekick in the adventure of data analysis. We unleashed the algorithms and formulas of software packages such as R, SAS, and SPSS, harnessing their computational prowess to wrangle the data and extract insights, much like wielding a magic wand to unveil the secrets hidden within the numbers.

Now, here's where things get a bit wacky – in our quest to add a dash of quirkiness to our scientific journey, we may or may not have consulted a fortune teller to divine the mystical energies of the data. Their crystal ball, or rather, crystal beaker, provided a mystifying spectacle of future trends, which we promptly filed under "fun but not scientifically recognized" in our methodology report.

Finally, once we had navigated through the turbulent seas of data collection and analysis, we arrived at the shores of statistical significance, where we conducted hypothesis testing and p-value calculations with the precision of potion-makers concocting a magical elixir. Our statistical rituals resulted in a correlation coefficient of 0.8792277 with a p-value of less than 0.01, a gas-toundingly high correlation that left us both flabbergasted and exhilarated.

So, dear reader, fasten your seatbelt and prepare for a wild ride as we take you through the uncharted territory of our methodology, peppered with a sprinkling of whimsy and statistical eccentricity. It's a journey like no other, and we invite you to join us in this trip filled with unexpected twists and a hearty dose of scientific absurdity. Onward we go, into the heart of statistical curiosity!


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

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1981 to 2018, you found a correlation 0.8792277, r-squared of 0.7730414, 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]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As researchers, we often find ourselves diving into the depths of data, hoping to uncover unexpected connections and correlations. In the case of our study, we ventured into the curious realm of air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Little did we know that this investigation would lead us down a windy path filled with twists, turns, and a surprising amount of gas-related puns.
Now, we understand if you initially raised an eyebrow or even let out a chuckle upon reading our research topic. Air pollution in Gadsden and LPG in the Netherlands Antilles – a match made in statistical heaven, or so it seemed. Yet, armed with our trusty statistical tools and an arsenal of puns, we delved into this quixotic quest with the hope of unearthing a connection that would make even the most stoic researcher gasp with disbelief.
As we navigated through the labyrinth of environmental and energy data, we couldn't help but revel in the irony of our endeavor. Here we were, analyzing the air, while also adding a touch of levity with our statistical analyses and correlations. It was as if we had stumbled upon a cosmic joke – one that left us simultaneously scratching our heads and gasping for fresh air.
The initial findings of our study left us feeling breathless as we uncovered a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. Yes, you read that correctly – a gas-ily high correlation that left our statistical senses tingling with both excitement and disbelief. It was a moment that called for a quick gasp, followed by a round of nerdy science puns to lighten the mood.
But, beyond the puns and the gas-related humor, there lies a serious and compelling correlation that begs for further scrutiny. So, join us in embracing the unexpected and the gas-tounding as we unravel the mysterious connection between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. It's a breath of fresh air, laced with statistical intrigue and a dash of absurdity – and we wouldn't have it any other way. Let's dive in and prepare to be gas-lighted by the curious correlation that awaits.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles revealed a gas-ily high correlation coefficient of 0.8792277, an r-squared of 0.7730414, and p < 0.01 for the period spanning 1981 to 2018. The statistical air was thick with significance, prompting us to take a deep breath and dive into the implications of this unexpected connection.

In Figure 1, we present a scatterplot that visually encapsulates the gas-tly relationship between the two variables. Behold the beauty of statistical serendipity, where the data points waltz across the graph in harmonious synchronization, almost as if they're performing an intricate ballet of correlation.

Our findings not only left us gasping for air at the unlikely link between these geographically distant entities but also pondering the intricate web of factors that might underpin this intriguing correlation. It's as if the statistical universe decided to play an unexpected prank on us, leaving us both baffled and amused by the cosmic comedy of correlation.

As we catch our breath and marvel at the statistical spectacle before us, it becomes clear that this correlation opens a Pandora's box of questions. What unseen forces drive this unexpected connection? Is there a hidden dance of environmental variables that orchestrates this unlikely harmony between distant locales?

The statistical stage is set, the audience of curious researchers awaits, and the show must go on. It's time to exhale, embrace the gas-tounding correlation, and let our findings ignite a fervor of further exploration into the enigmatic dance between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. So, dear readers, take a deep breath and join us as we venture into the whimsical world of statistical surprise and scientific puns.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

[[LITERATURE REVIEW]]
The investigation into the seemingly whimsical correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles led us to a myriad of scholarly and not-so-scholarly sources. At the outset, our pursuit for academic rigor led us to scholarly works such as "The Paradox of Polluted Air" by Smith, which delves into the complexities of air pollution and its unforeseen connections, and "The Gas Chronicles" by Doe, which offers a historical perspective on the evolution of liquefied petroleum gas usage across the world.
However, while trawling through the pool of academic literature, we could not help but stumble upon sources that added an unexpected layer of whimsy to our research. "Gassy Tales: A Collection of Gas-Related Anecdotes" by Jones, although not directly related to environmental research, provided a much-needed laugh amidst the sea of scholarly seriousness. Additionally, "The Unbearable Lightness of Being...Powered by LPG" by Kundera, though a work of fiction, offered a peculiar insight into the potential metaphysical connections between air quality and the use of liquefied petroleum gas.
As if that wasn't enough, our journey through the scholarly landscape took an even more unexpected turn when we encountered social media posts that seemed to uncannily touch upon our research topic. Tweets like "Just watched my LPG-powered stove produce more smoke than an 18th-century locomotive #airpollutionwoes" and "Gadsden's air quality has me considering wearing a gas mask as a fashion statement #justbreathe" provided a quirky, yet oddly relevant, perspective on the intersection between air pollution in Gadsden, Alabama, and LPG use in the Netherlands Antilles.
In essence, our foray into the literature – both serious and whimsical – has provided an eclectic mix of perspectives that mirror the unexpected and gas-tly nature of our research. As we embark on this gas-ifying journey, it becomes abundantly clear that while the pursuit of knowledge is undoubtedly serious, a touch of humor and absurdity can illuminate even the most unexpected correlations. So, with a dash of scholarly seriousness and a sprinkle of whimsy, we venture forth to unravel the enigmatic ties between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

[[RESULTS]]
Our analysis of the correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles revealed a gas-ily high correlation coefficient of 0.8792277, an r-squared of 0.7730414, and p < 0.01 for the period spanning 1981 to 2018. The statistical air was thick with significance, prompting us to take a deep breath and dive into the implications of this unexpected connection.
In Figure 1, we present a scatterplot that visually encapsulates the gas-tly relationship between the two variables. Behold the beauty of statistical serendipity, where the data points waltz across the graph in harmonious synchronization, almost as if they're performing an intricate ballet of correlation.
Our findings not only left us gasping for air at the unlikely link between these geographically distant entities but also pondering the intricate web of factors that might underpin this intriguing correlation. It's as if the statistical universe decided to play an unexpected prank on us, leaving us both baffled and amused by the cosmic comedy of correlation.
As we catch our breath and marvel at the statistical spectacle before us, it becomes clear that this correlation opens a Pandora's box of questions. What unseen forces drive this unexpected connection? Is there a hidden dance of environmental variables that orchestrates this unlikely harmony between distant locales?
The statistical stage is set, the audience of curious researchers awaits, and the show must go on. It's time to exhale, embrace the gas-tounding correlation, and let our findings ignite a fervor of further exploration into the enigmatic dance between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. So, dear readers, take a deep breath and join us as we venture into the whimsical world of statistical surprise and scientific puns.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the gas-tly correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles has left us gasping for air, much like Gadsden's residents on a smoggy day. We set out with a whimsical curiosity, but as it turns out, the correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018 revealed a gas-tounding connection that demands our scientific seriousness.

It is both astonishing and comical how our findings support the prior research. We are reminded of "The Paradox of Polluted Air" by Smith, which delved into the complexities of air pollution and its unforeseen connections. The correlation we've uncovered in our study adds another layer to this paradox, perhaps making it a gas-ier paradox than previously thought! Moreover, "The Gas Chronicles" by Doe takes on a whole new meaning in light of our findings, highlighting the global interconnectedness of LPG usage and air quality.

Turning to the unexpectedly whimsical sources, "Gassy Tales: A Collection of Gas-Related Anecdotes" by Jones and "The Unbearable Lightness of Being...Powered by LPG" by Kundera, we find ourselves chuckling at the fortuitousness of how jokes about gas and air quality now seem eerily relevant.

In fact, it's almost as if the quirky social media posts we stumbled upon while trawling through the scholarly landscape were onto something. Tweets like "Just watched my LPG-powered stove produce more smoke than an 18th-century locomotive #airpollutionwoes" and "Gadsden's air quality has me considering wearing a gas mask as a fashion statement #justbreathe" now seem to offer an unwitting glimpse into the very correlation we have uncovered.

In that sense, our study has rendered the unexpected laughable and the bewildering quite insightful. As researchers, we are gasping at the veracity of these findings, juxtaposed with the jest and whimsy encountered along the way. The scientific universe is nothing if not full of surprises, and it appears to have orchestrated a grand comedy of correlation for us to unravel.

As we marvel at the statistical spectacle before us, we are left pondering the intricate dance of variables that have led to this unlikely harmony. It's as if the data points on our scatterplot have decided to perform a tango of correlation, leading us to question the unseen forces driving this unexpected connection. Could there be a series of comedic and cosmic coincidences at play, or are there deeper underlying factors awaiting our scientific scrutiny?

Thus, we conclude our discussion with a deep breath and a gaze into the gas-tly dance between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. The curtain rises on a scientific stage set for a comedic yet curious exploration, leaving us as researchers to embrace the gas-tounding correlation and let our findings ignite further exploration into this enigmatic statistical ballet. So, dear readers, we invite you to join us in taking a deep breath and diving headfirst into the whimsical world of scientific surprise and statistical splendor.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Gadsden, Alabama and Liquefied petroleum gas used in Netherlands Antilles. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"A Breath of Fresh Air: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles"

[[ABSTRACT]]
In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.

Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.

While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

[[INTRDUCTION]]
As researchers, we often find ourselves diving into the depths of data, hoping to uncover unexpected connections and correlations. In the case of our study, we ventured into the curious realm of air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Little did we know that this investigation would lead us down a windy path filled with twists, turns, and a surprising amount of gas-related puns.
Now, we understand if you initially raised an eyebrow or even let out a chuckle upon reading our research topic. Air pollution in Gadsden and LPG in the Netherlands Antilles – a match made in statistical heaven, or so it seemed. Yet, armed with our trusty statistical tools and an arsenal of puns, we delved into this quixotic quest with the hope of unearthing a connection that would make even the most stoic researcher gasp with disbelief.
As we navigated through the labyrinth of environmental and energy data, we couldn't help but revel in the irony of our endeavor. Here we were, analyzing the air, while also adding a touch of levity with our statistical analyses and correlations. It was as if we had stumbled upon a cosmic joke – one that left us simultaneously scratching our heads and gasping for fresh air.
The initial findings of our study left us feeling breathless as we uncovered a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. Yes, you read that correctly – a gas-ily high correlation that left our statistical senses tingling with both excitement and disbelief. It was a moment that called for a quick gasp, followed by a round of nerdy science puns to lighten the mood.
But, beyond the puns and the gas-related humor, there lies a serious and compelling correlation that begs for further scrutiny. So, join us in embracing the unexpected and the gas-tounding as we unravel the mysterious connection between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. It's a breath of fresh air, laced with statistical intrigue and a dash of absurdity – and we wouldn't have it any other way. Let's dive in and prepare to be gas-lighted by the curious correlation that awaits.

[[RESULTS]]
Our analysis of the correlation between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles revealed a gas-ily high correlation coefficient of 0.8792277, an r-squared of 0.7730414, and p < 0.01 for the period spanning 1981 to 2018. The statistical air was thick with significance, prompting us to take a deep breath and dive into the implications of this unexpected connection.
In Figure 1, we present a scatterplot that visually encapsulates the gas-tly relationship between the two variables. Behold the beauty of statistical serendipity, where the data points waltz across the graph in harmonious synchronization, almost as if they're performing an intricate ballet of correlation.
Our findings not only left us gasping for air at the unlikely link between these geographically distant entities but also pondering the intricate web of factors that might underpin this intriguing correlation. It's as if the statistical universe decided to play an unexpected prank on us, leaving us both baffled and amused by the cosmic comedy of correlation.
As we catch our breath and marvel at the statistical spectacle before us, it becomes clear that this correlation opens a Pandora's box of questions. What unseen forces drive this unexpected connection? Is there a hidden dance of environmental variables that orchestrates this unlikely harmony between distant locales?
The statistical stage is set, the audience of curious researchers awaits, and the show must go on. It's time to exhale, embrace the gas-tounding correlation, and let our findings ignite a fervor of further exploration into the enigmatic dance between air pollution in Gadsden and the use of LPG in the Netherlands Antilles. So, dear readers, take a deep breath and join us as we venture into the whimsical world of statistical surprise and scientific puns.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

As we wrap up this gas-tacular journey through the unlikely connection between air pollution in Gadsden, Alabama, and the use of LPG in the Netherlands Antilles, one thing is clear – the statistical universe has a sense of humor that is as quirky as our puns. Our findings gas-ily revealed a correlation coefficient of 0.8792277 and p < 0.01, leaving us both flabbergasted and doubled over with statistical amusement.

But fear not, fellow researchers, for our quest has not been in vain. We've cracked the statistical case wide open, unveiling a correlation that's as surprising as a scientist's reaction to a well-timed science joke. It's clear that the statistical forces at play in this correlation are nothing short of gas-tounding.

So, as we exhale a breath of statistical awe and bid adieu to this gas-guzzling endeavor, we do so with a wink and a nod to the absurdity and intrigue that lurks within our data. Our findings not only leave us breathless but also gasp-ing for a respite from the gas-related shenanigans that have accompanied our statistical adventures.

In conclusion, let's raise our beakers, toast to the gas-tly correlation we've uncovered, and declare with utmost confidence that no further research is needed in this peculiar and pun-filled arena of statistical exploration. It's been a gas, but it's time to let this correlation bask in the limelight of statistical wonderment. Cheers to a correlation that is as unexpected as a lab experiment gone awry, and may our statistical paths cross again in similarly delightfully absurd ways. Let's leave this gas-laden section of research in the realms of statistical legend, shall we?


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: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles. 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: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles. Respond only with the name of a fictional organization.

ChatGPT:

The Alliance for Atmospheric Advancements


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: Uncovering the Gas-tly Connection Between Air Pollution in Gadsden, Alabama, and Liquefied Petroleum Gas in the Netherlands Antilles with an abstract of In this study, we delve into the seemingly far-fetched relationship between air pollution in Gadsden, Alabama, and the use of liquefied petroleum gas (LPG) in the Netherlands Antilles. Our research team, armed with puns and peculiar analytical skills, focused on data from the Environmental Protection Agency and the Energy Information Administration to shed light on this unexpected correlation.
Our findings, which are nothing short of gas-ifying, revealed a correlation coefficient of 0.8792277 and p < 0.01 for the period spanning 1981 to 2018. We took a deep breath and dug into the labyrinth of environmental data to find this intriguing connection, which left us both gasping for air and laughing at the unexpected link between these seemingly unrelated geographies.
While we gasped, chuckled, and maybe even groaned at the occasional dad joke, our serious investigation uncovered a relationship that demands further investigation. So, let's take a breather and ponder this gas-tounding correlation between air pollution in Gadsden and the use of LPG in the Netherlands Antilles.

ChatGPT:

air pollution, Gadsden Alabama, liquefied petroleum gas, LPG, Netherlands Antilles, correlation coefficient, Environmental Protection Agency, Energy Information Administration, data analysis, pollution correlation, geographical 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 Gadsden, Alabama
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Gadsden, AL
Source: Environmental Protection Agency
See what else correlates with Air pollution in Gadsden, Alabama

Liquefied petroleum gas used in Netherlands Antilles
Detailed data title: Volume of liquefied petroleum gas used consumed in Netherlands Antilles in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Liquefied petroleum gas used in Netherlands Antilles

Correlation r = 0.8792277 (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 = 0.7730414 (Coefficient of determination)
This means 77.3% of the change in the one variable (i.e., Liquefied petroleum gas used in Netherlands Antilles) is predictable based on the change in the other (i.e., Air pollution in Gadsden, Alabama) over the 38 years from 1981 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.81E-13. 0.0000000000003805519975734693
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 0.88 in 3.81E-11% of random cases. Said differently, if you correlated 2,627,761,794,384 random variables You don't actually need 2 trillion 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 37 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 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.

[ 0.78, 0.94 ] 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.
19811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018
Air pollution in Gadsden, Alabama (Bad air quality days)0.2234040.1827410.176190.1660230.08865250.14909100000000000000.069306900.08677690.03521130.01408450.02857140.02127660.06811150.0029411800.0027548200000.01917810.01704550.005555560.00308642
Liquefied petroleum gas used in Netherlands Antilles (Million Barrels/Day)5.47555.201734.87324.654183.887613.82.422.42.52.31.71.82.31.91.92.12.12.22.341422.416442.356082.334722.403292.459273.230033.562993.406573.549032.507792.78572.143132.161181.989062.36262.3792.40232.4023




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([0.223404,0.182741,0.17619,0.166023,0.0886525,0.149091,0,0,0,0,0,0,0,0,0,0,0,0,0,0.0693069,0,0.0867769,0.0352113,0.0140845,0.0285714,0.0212766,0.0681115,0.00294118,0,0.00275482,0,0,0,0,0.0191781,0.0170455,0.00555556,0.00308642,])
array_2 = np.array([5.4755,5.20173,4.8732,4.65418,3.88761,3.8,2.4,2,2.4,2.5,2.3,1.7,1.8,2.3,1.9,1.9,2.1,2.1,2.2,2.34142,2.41644,2.35608,2.33472,2.40329,2.45927,3.23003,3.56299,3.40657,3.54903,2.50779,2.7857,2.14313,2.16118,1.98906,2.3626,2.379,2.4023,2.4023,])
array_1_name = "Air pollution in Gadsden, Alabama"
array_2_name = "Liquefied petroleum gas used in Netherlands Antilles"

# 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?

Cheers to you for rating this correlation!


Correlation ID: 1740 · Black Variable ID: 21526 · Red Variable ID: 24743
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0