about · email me · subscribe
Spurious correlation #5,446 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Libertarian Senators in Wisconsin and the second variable is Liquefied petroleum gas used in United Arab Emirates.  The chart goes from 1980 to 2016, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As Libertarian votes for Senators in Wisconsin increased, it led to a spike in demand for cheese. This surge in cheese demand prompted Wisconsin dairy farmers to embrace the principles of self-sufficiency, including producing their own energy. Consequently, there was a significant uptick in the production of Liquefied petroleum gas as these dairy farmers attempted to milk every possible energy resource, ultimately leading to an increase in the supply of Liquefied petroleum gas, which found its whey to the United Arab Emirates, where it was welcomed with open arms. Thus, the surprising connection between Libertarian votes in Wisconsin and the Liquefied petroleum gas usage in the United Arab Emirates was utterly gouda!

Model: dalle-3
Prompt: Prompt: Generate an image showing a TIME magazine cover featuring a lush Wisconsin dairy farm with rolling green fields, grazing cows, and a barn in the background. Against the backdrop, depict the process of Liquefied petroleum gas production, illustrating how the increase in Libertarian votes for Senators led to the thriving of dairy farms and subsequently a rise in LPG production. Show the LPG surplus being transported and embraced in the United Arab Emirates, possibly through visual cues such as a map route or cultural elements. 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: Votes for Libertarian Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. 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 Pop art Realistic a funny image you would see on reddit A TIME magazine cover image
ChatGPT: A TIME magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for Libertarian Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates, in the following situation: As Libertarian votes for Senators in Wisconsin increased, it led to a spike in demand for cheese. This surge in cheese demand prompted Wisconsin dairy farmers to embrace the principles of self-sufficiency, including producing their own energy. Consequently, there was a significant uptick in the production of Liquefied petroleum gas as these dairy farmers attempted to milk every possible energy resource, ultimately leading to an increase in the supply of Liquefied petroleum gas, which found its whey to the United Arab Emirates, where it was welcomed with open arms. Thus, the surprising connection between Libertarian votes in Wisconsin and the Liquefied petroleum gas usage in the United Arab Emirates was utterly gouda!. Keep the description simple.
ChatGPT: In Wisconsin, as Libertarian votes for Senators increased, dairy farms thrived, leading to a rise in Liquefied petroleum gas production. This surplus then made its way to the United Arab Emirates, where it was embraced with open arms.

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 TIME magazine cover image ] and depicting this scene: In Wisconsin, as Libertarian votes for Senators increased, dairy farms thrived, leading to a rise in Liquefied petroleum gas production. This surplus then made its way to the United Arab Emirates, where it was embraced with open arms. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image showing a TIME magazine cover featuring a lush Wisconsin dairy farm with rolling green fields, grazing cows, and a barn in the background. Against the backdrop, depict the process of Liquefied petroleum gas production, illustrating how the increase in Libertarian votes for Senators led to the thriving of dairy farms and subsequently a rise in LPG production. Show the LPG surplus being transported and embraced in the United Arab Emirates, possibly through visual cues such as a map route or cultural elements.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Libertarian votes for Senators in Wisconsin caused Liquefied petroleum gas used in United Arab Emirates to increase.

AI academic paper

(Because p < 0.01)
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

The Journal of Political Puns and Pandemonium

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 silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9742614 and p < 0.01 for 1980 to 2016.

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]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Ladies and gentlemen, esteemed colleagues, and fellow aficionados of the absurd, welcome to a journey that will leave you scratching your head, shaking with laughter, and possibly reconsidering your career choices. In this research paper, we delve into the bizarre and bewildering world of electoral behavior and energy consumption, as we endeavor to unravel the tangled web between Libertarian votes in Wisconsin and the enthusiastic embrace of liquefied petroleum gas in the United Arab Emirates.

The plot thickens as we confront a correlation coefficient that would make even the most seasoned statistician do a double take. Yes, folks, we are talking about a staggering 0.9742614 - a number that defies the laws of political gravity and energy thermodynamics! And if that's not enough to make you do a spit-take with your morning coffee, consider the fact that the p-value is less than 0.01.

Now, before you dismiss this as mere statistical tomfoolery or an overactive imagination, let us assure you that our data is as solid as a Wisconsin cheese curd and as reliable as a camel in the desert. Our sources include the illustrious MIT Election Data and Science Lab, the invaluable Harvard Dataverse, and the Energy Information Administration, leaving no room for doubt or suspicion.

So, grab your favorite beverage, settle into your favorite armchair, and prepare to be entertained, enlightened, and perhaps, thoroughly perplexed. Our findings promise to shatter preconceived notions about the interconnectedness of disparate phenomena, prompting you to raise an eyebrow, scratch your chin, and maybe even let out a hearty chuckle.

As we navigate through the cornfields of electoral politics and the shimmering sands of energy consumption, we invite you to join us in this delightful dance of discovery. It's a waltz between the land of cheese and the land of oil, where the steps may be unconventional, but the music is undeniably catchy. So, without further ado, let us dive into the quagmire of correlations and contradictions, where the only certainty is the unpredictability of human behavior and the whims of statistical anomalies.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. 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 name some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Ladies and gentlemen, esteemed colleagues, and fellow aficionados of the absurd, welcome to a journey that will leave you scratching your head, shaking with laughter, and possibly reconsidering your career choices. In this research paper, we delve into the bizarre and bewildering world of electoral behavior and energy consumption, as we endeavor to unravel the tangled web between Libertarian votes in Wisconsin and the enthusiastic embrace of liquefied petroleum gas in the United Arab Emirates.
The plot thickens as we confront a correlation coefficient that would make even the most seasoned statistician do a double take. Yes, folks, we are talking about a staggering 0.9742614 - a number that defies the laws of political gravity and energy thermodynamics! And if that's not enough to make you do a spit-take with your morning coffee, consider the fact that the p-value is less than 0.01.
Now, before you dismiss this as mere statistical tomfoolery or an overactive imagination, let us assure you that our data is as solid as a Wisconsin cheese curd and as reliable as a camel in the desert. Our sources include the illustrious MIT Election Data and Science Lab, the invaluable Harvard Dataverse, and the Energy Information Administration, leaving no room for doubt or suspicion.
So, grab your favorite beverage, settle into your favorite armchair, and prepare to be entertained, enlightened, and perhaps, thoroughly perplexed. Our findings promise to shatter preconceived notions about the interconnectedness of disparate phenomena, prompting you to raise an eyebrow, scratch your chin, and maybe even let out a hearty chuckle.
As we navigate through the cornfields of electoral politics and the shimmering sands of energy consumption, we invite you to join us in this delightful dance of discovery. It's a waltz between the land of cheese and the land of oil, where the steps may be unconventional, but the music is undeniably catchy. So, without further ado, let us dive into the quagmire of correlations and contradictions, where the only certainty is the unpredictability of human behavior and the whims of statistical anomalies.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The literature on the subject of unusual correlations between political behavior and energy consumption is as sparse as a desert oasis, but we have managed to excavate a few intriguing studies that laid the groundwork for our offbeat investigation. Smith, in "The Unlikely Affinities: A Statistical Exploration," first hinted at the possibility of perplexing connections between seemingly unrelated variables, setting the stage for our own venture into uncharted statistical territory. Doe, in "Politics and Petroleum: A Surprising Tango," waltzed through the complexities of political preferences and oil consumption, leading us to ponder the potential parallels between libertarian voting patterns and liquefied petroleum gas usage.

However, as we ventured deeper into the annals of scholarly inquiry, we stumbled upon a series of studies that took an unexpected turn, much like a rodeo clown at a rocket launch. Jones, in "The Curious Case of Political Proclivities and Propane," noted a tantalizing hint of correlation between political ideology and gas-based energy sources, leaving us teetering on the edge of statistical revelation. This breadcrumb trail of empirical investigations raised our hopes and tickled our curiosity, but it was time to delve into more unconventional sources of inspiration.

Turning our attention to relevant non-fiction literature, we encountered "The Libertarian Manifesto of Petroleum Politics" and "Wisconsin's Whimsical Gas Grin: A Political Paradox," both of which offered tantalizing hints at the potential interplay between libertarian sentiments and the consumption of liquefied petroleum gas. While these works provided valuable insights into the theoretical underpinnings of our study, it was the unexpected encounters in the realm of fiction that truly piqued our interest.

Enter "The Sandcastle Senator: A Tale of Libertarian Locomotion" and "Desert Dreams and Dairy Dilemmas: A Fantasy of Fuel and Freedom," two fictitious narratives that, while seemingly unrelated to our research objectives, sparked our imagination and infused our investigation with a dose of whimsy. As we navigated through these literary labyrinths, we couldn't help but draw parallels between the fantastical landscapes of fiction and the perplexing terrain of our empirical inquiry.

In a bold departure from conventional academic sources, we also turned our gaze towards the whimsical world of cartoons and children's shows. From the kinetic energy of "The Flintstones" to the enigmatic allure of "Scooby-Doo," these cultural artifacts, while ostensibly unrelated to our research, reminded us of the unpredictable twists and turns that often accompany scholarly pursuits. After all, who can resist a chuckle at the thought of Fred Flintstone's libertarian leanings or Shaggy's secret stash of liquefied petroleum gas?

In conclusion, the literature review journey has been nothing short of a rollercoaster ride through the hallways of academia, the landscapes of fiction, and the playgrounds of popular culture. While our quest for scholarly enlightenment may have taken us through unorthodox paths, it has imbued our research with a sense of levity and irreverence that complements the gravity of our statistical findings. As we prepare to unveil the mysterious maneuvers of libertarian votes in Wisconsin and the spirited consumption of liquefied petroleum gas in the United Arab Emirates, we invite our readers to join us in this idiosyncratic exploration of the absurd and the astonishing.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1980 to 2016

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]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

[[INTRODUCTION]]
Ladies and gentlemen, esteemed colleagues, and fellow aficionados of the absurd, welcome to a journey that will leave you scratching your head, shaking with laughter, and possibly reconsidering your career choices. In this research paper, we delve into the bizarre and bewildering world of electoral behavior and energy consumption, as we endeavor to unravel the tangled web between Libertarian votes in Wisconsin and the enthusiastic embrace of liquefied petroleum gas in the United Arab Emirates.
The plot thickens as we confront a correlation coefficient that would make even the most seasoned statistician do a double take. Yes, folks, we are talking about a staggering 0.9742614 - a number that defies the laws of political gravity and energy thermodynamics! And if that's not enough to make you do a spit-take with your morning coffee, consider the fact that the p-value is less than 0.01.
Now, before you dismiss this as mere statistical tomfoolery or an overactive imagination, let us assure you that our data is as solid as a Wisconsin cheese curd and as reliable as a camel in the desert. Our sources include the illustrious MIT Election Data and Science Lab, the invaluable Harvard Dataverse, and the Energy Information Administration, leaving no room for doubt or suspicion.
So, grab your favorite beverage, settle into your favorite armchair, and prepare to be entertained, enlightened, and perhaps, thoroughly perplexed. Our findings promise to shatter preconceived notions about the interconnectedness of disparate phenomena, prompting you to raise an eyebrow, scratch your chin, and maybe even let out a hearty chuckle.
As we navigate through the cornfields of electoral politics and the shimmering sands of energy consumption, we invite you to join us in this delightful dance of discovery. It's a waltz between the land of cheese and the land of oil, where the steps may be unconventional, but the music is undeniably catchy. So, without further ado, let us dive into the quagmire of correlations and contradictions, where the only certainty is the unpredictability of human behavior and the whims of statistical anomalies.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The methodology adopted for this unorthodox investigation involved a blend of traditional statistical analyses and a sprinkle of whimsical creativity. Our research team embarked on a quest reminiscent of Indiana Jones, traversing the treacherous terrain of data collection, wrangling spreadsheets, and decoding cryptic patterns in electoral and energy consumption records.

First and foremost, the data on Libertarian votes in Wisconsin senatorial elections was sourced from the MIT Election Data and Science Lab. This treasure trove of electoral information provided us with a comprehensive overview of political leanings in the heartland of America. Armed with this knowledge, we ventured into the labyrinth of statistics, employing the arcane arts of correlation analysis and regression modeling to tease out any potential connections.

Simultaneously, our team cast its gaze toward the golden deserts of the United Arab Emirates, where the consumption of liquefied petroleum gas (LPG) was monitored and documented by the Energy Information Administration. Armed with this dataset, we set sail on the choppy seas of energy economics, navigating through the waves of supply, demand, and consumption patterns with a compass calibrated for curiosity and a sextant of skepticism.

The thorny task of aligning these disparate datasets fell upon the shoulders of our intrepid data wranglers, who deftly maneuvered through the tangled forests of spreadsheets and databases with the finesse of a tightrope walker in a hurricane. After painstakingly aligning the temporal dimensions and adapting the units of measurement, we finally arrived at a dataset that could be subjected to the unblinking eye of statistical scrutiny.

With our data primed and prepped like a contestant on a culinary competition show, we set about unleashing an army of statistical tests, dancing between Pearson's correlation coefficient, Spearman's rank correlation, and the formidable p-value. Like a chef meticulously calibrating the flavors in a gourmet dish, we sought to uncover the subtle nuances and overtones lurking beneath the surface of our datasets.

The interpretation of our findings resembled a carefully choreographed ballet, where the tiniest of nuances could reveal a grand symphony. P-values were scrutinized like precious gems under the light of a jeweler's lamp, and correlation coefficients were examined with the precision of a watchmaker assembling a delicate timepiece.

The ultimate result of our statistical pas de deux was a remarkable correlation coefficient of 0.9742614, accompanied by a p-value that prompted a collective gasp from our team. The implications of these findings were as clear as a mirage in the desert, tantalizing yet enigmatic, leaving us at the precipice of revelation and amusement.

In summary, the methodology employed in this study combined the rigor of traditional statistical analyses with the audacity of exploring uncharted connections. Our journey was fraught with challenges, surprises, and the occasional quirk of fate, but through it all, we remained steadfast in our quest to shed light on the improbable relationship between libertarian votes in Wisconsin and the consumption of liquefied petroleum gas in the United Arab Emirates.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration .

For the time period 1980 to 2016, you found a correlation 0.9742614, r-squared of 0.9491853, 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]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Ladies and gentlemen, esteemed colleagues, and fellow aficionados of the absurd, welcome to a journey that will leave you scratching your head, shaking with laughter, and possibly reconsidering your career choices. In this research paper, we delve into the bizarre and bewildering world of electoral behavior and energy consumption, as we endeavor to unravel the tangled web between Libertarian votes in Wisconsin and the enthusiastic embrace of liquefied petroleum gas in the United Arab Emirates.
The plot thickens as we confront a correlation coefficient that would make even the most seasoned statistician do a double take. Yes, folks, we are talking about a staggering 0.9742614 - a number that defies the laws of political gravity and energy thermodynamics! And if that's not enough to make you do a spit-take with your morning coffee, consider the fact that the p-value is less than 0.01.
Now, before you dismiss this as mere statistical tomfoolery or an overactive imagination, let us assure you that our data is as solid as a Wisconsin cheese curd and as reliable as a camel in the desert. Our sources include the illustrious MIT Election Data and Science Lab, the invaluable Harvard Dataverse, and the Energy Information Administration, leaving no room for doubt or suspicion.
So, grab your favorite beverage, settle into your favorite armchair, and prepare to be entertained, enlightened, and perhaps, thoroughly perplexed. Our findings promise to shatter preconceived notions about the interconnectedness of disparate phenomena, prompting you to raise an eyebrow, scratch your chin, and maybe even let out a hearty chuckle.
As we navigate through the cornfields of electoral politics and the shimmering sands of energy consumption, we invite you to join us in this delightful dance of discovery. It's a waltz between the land of cheese and the land of oil, where the steps may be unconventional, but the music is undeniably catchy. So, without further ado, let us dive into the quagmire of correlations and contradictions, where the only certainty is the unpredictability of human behavior and the whims of statistical anomalies.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation revealed a striking correlation between Libertarian votes in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. The correlation coefficient of 0.9742614 indicated an incredibly strong positive relationship between these seemingly unrelated variables. This finding defies conventional logic, much like finding a palm tree in a Wisconsin blizzard or a cheesehead at a camel race!

The scatterplot in Fig. 1 portrays this eyebrow-raising relationship, showcasing the tight clustering of data points that almost seems too good to be true. It's as if the cheeseheads in Wisconsin are waving to the folks enjoying their shawarma in the UAE, all while sipping from the same fuel tank!

With an r-squared value of 0.9491853, our model explains a whopping 94.92% of the variability in liquefied petroleum gas consumption in the UAE based on Libertarian votes in Wisconsin. This level of predictability is as surprising as a desert oasis in the heart of Milwaukee!

Furthermore, the p-value of less than 0.01 offers solid evidence that this correlation is not a mere statistical fluke but a genuine relationship that demands attention. It's like finding a needle in a haystack, only in this case, the needle is dressed in a cheese wedge costume and exuding an aroma of petroleum fumes!

In conclusion, our findings highlight a connection that is as perplexing as it is intriguing. This unexpected correlation beckons for further exploration and prompts more questions than it answers, leaving us marveling at the mystifying dance between Midwestern political preferences and desert fuel consumption. It's a conundrum that may have you scratching your head, rubbing your eyes, and ultimately appreciating the sheer audacity of the statistical universe.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. 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]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

[[LITERATURE REVIEW]]
The literature on the subject of unusual correlations between political behavior and energy consumption is as sparse as a desert oasis, but we have managed to excavate a few intriguing studies that laid the groundwork for our offbeat investigation. Smith, in "The Unlikely Affinities: A Statistical Exploration," first hinted at the possibility of perplexing connections between seemingly unrelated variables, setting the stage for our own venture into uncharted statistical territory. Doe, in "Politics and Petroleum: A Surprising Tango," waltzed through the complexities of political preferences and oil consumption, leading us to ponder the potential parallels between libertarian voting patterns and liquefied petroleum gas usage.
However, as we ventured deeper into the annals of scholarly inquiry, we stumbled upon a series of studies that took an unexpected turn, much like a rodeo clown at a rocket launch. Jones, in "The Curious Case of Political Proclivities and Propane," noted a tantalizing hint of correlation between political ideology and gas-based energy sources, leaving us teetering on the edge of statistical revelation. This breadcrumb trail of empirical investigations raised our hopes and tickled our curiosity, but it was time to delve into more unconventional sources of inspiration.
Turning our attention to relevant non-fiction literature, we encountered "The Libertarian Manifesto of Petroleum Politics" and "Wisconsin's Whimsical Gas Grin: A Political Paradox," both of which offered tantalizing hints at the potential interplay between libertarian sentiments and the consumption of liquefied petroleum gas. While these works provided valuable insights into the theoretical underpinnings of our study, it was the unexpected encounters in the realm of fiction that truly piqued our interest.
Enter "The Sandcastle Senator: A Tale of Libertarian Locomotion" and "Desert Dreams and Dairy Dilemmas: A Fantasy of Fuel and Freedom," two fictitious narratives that, while seemingly unrelated to our research objectives, sparked our imagination and infused our investigation with a dose of whimsy. As we navigated through these literary labyrinths, we couldn't help but draw parallels between the fantastical landscapes of fiction and the perplexing terrain of our empirical inquiry.
In a bold departure from conventional academic sources, we also turned our gaze towards the whimsical world of cartoons and children's shows. From the kinetic energy of "The Flintstones" to the enigmatic allure of "Scooby-Doo," these cultural artifacts, while ostensibly unrelated to our research, reminded us of the unpredictable twists and turns that often accompany scholarly pursuits. After all, who can resist a chuckle at the thought of Fred Flintstone's libertarian leanings or Shaggy's secret stash of liquefied petroleum gas?
In conclusion, the literature review journey has been nothing short of a rollercoaster ride through the hallways of academia, the landscapes of fiction, and the playgrounds of popular culture. While our quest for scholarly enlightenment may have taken us through unorthodox paths, it has imbued our research with a sense of levity and irreverence that complements the gravity of our statistical findings. As we prepare to unveil the mysterious maneuvers of libertarian votes in Wisconsin and the spirited consumption of liquefied petroleum gas in the United Arab Emirates, we invite our readers to join us in this idiosyncratic exploration of the absurd and the astonishing.

[[RESULTS]]
The results of our investigation revealed a striking correlation between Libertarian votes in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. The correlation coefficient of 0.9742614 indicated an incredibly strong positive relationship between these seemingly unrelated variables. This finding defies conventional logic, much like finding a palm tree in a Wisconsin blizzard or a cheesehead at a camel race!
The scatterplot in Fig. 1 portrays this eyebrow-raising relationship, showcasing the tight clustering of data points that almost seems too good to be true. It's as if the cheeseheads in Wisconsin are waving to the folks enjoying their shawarma in the UAE, all while sipping from the same fuel tank!
With an r-squared value of 0.9491853, our model explains a whopping 94.92% of the variability in liquefied petroleum gas consumption in the UAE based on Libertarian votes in Wisconsin. This level of predictability is as surprising as a desert oasis in the heart of Milwaukee!
Furthermore, the p-value of less than 0.01 offers solid evidence that this correlation is not a mere statistical fluke but a genuine relationship that demands attention. It's like finding a needle in a haystack, only in this case, the needle is dressed in a cheese wedge costume and exuding an aroma of petroleum fumes!
In conclusion, our findings highlight a connection that is as perplexing as it is intriguing. This unexpected correlation beckons for further exploration and prompts more questions than it answers, leaving us marveling at the mystifying dance between Midwestern political preferences and desert fuel consumption. It's a conundrum that may have you scratching your head, rubbing your eyes, and ultimately appreciating the sheer audacity of the statistical universe.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

In this delightfully unexpected and somewhat befuddling section of our research, we joyously delve into the implications of our eyebrow-raising findings. The correlation between Libertarian votes in Wisconsin and the consumption of liquefied petroleum gas in the United Arab Emirates has left us grappling with a conundrum as confounding as finding a frozen custard stand in the desert or discovering a cheese wheel floating in an oil rig.

Our results not only confirmed the improbable link posited by Smith, Doe, Jones, and the whimsical narratives of "The Sandcastle Senator" and "Desert Dreams and Dairy Dilemmas," but also transcended the boundaries of statistical predictability. The tight clustering of data points in our scatterplot echoes the surreal image of a cheesehead ambassador communicating with a shawarma connoisseur through the shared medium of liquefied petroleum gas. It's as if the spirit of political libertarianism has embarked on an international journey that defies geographical and cultural divides, much like a cheese-toting astronaut orbiting the Earth.

The r-squared value of 0.9491853 reflects a level of predictability that is as remarkable as discovering a libertarian-themed oasis in the Wisconsin countryside. Furthermore, the p-value of less than 0.01 unequivocally establishes the credibility of this correlation, leaving no room for skepticism as to the validity of this unexpected alliance. It's akin to stumbling upon a treasure chest buried beneath a dairy farm, only to find it filled with liquefied petroleum gas canisters adorned with libertarian bumper stickers.

While our study may have appeared whimsical at first glance, the gravity of our findings demands a level of consideration that is as earnest as it is amusing. The mysterious maneuvers of libertarian votes in Wisconsin and the spirited consumption of liquefied petroleum gas in the United Arab Emirates beckon for further scrutiny, as improbable as it may seem. It's a statistical puzzle that tugs at the corners of our academic curiosity, inviting us to embrace the enigma with open minds and appreciative chuckles.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 Libertarian votes for Senators in Wisconsin and Liquefied petroleum gas used in United Arab Emirates. 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]]
Libertarian Votes in Wisconsin: A Liquefied Laughter Link

[[ABSTRACT]]
In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

[[INTRDUCTION]]
Ladies and gentlemen, esteemed colleagues, and fellow aficionados of the absurd, welcome to a journey that will leave you scratching your head, shaking with laughter, and possibly reconsidering your career choices. In this research paper, we delve into the bizarre and bewildering world of electoral behavior and energy consumption, as we endeavor to unravel the tangled web between Libertarian votes in Wisconsin and the enthusiastic embrace of liquefied petroleum gas in the United Arab Emirates.
The plot thickens as we confront a correlation coefficient that would make even the most seasoned statistician do a double take. Yes, folks, we are talking about a staggering 0.9742614 - a number that defies the laws of political gravity and energy thermodynamics! And if that's not enough to make you do a spit-take with your morning coffee, consider the fact that the p-value is less than 0.01.
Now, before you dismiss this as mere statistical tomfoolery or an overactive imagination, let us assure you that our data is as solid as a Wisconsin cheese curd and as reliable as a camel in the desert. Our sources include the illustrious MIT Election Data and Science Lab, the invaluable Harvard Dataverse, and the Energy Information Administration, leaving no room for doubt or suspicion.
So, grab your favorite beverage, settle into your favorite armchair, and prepare to be entertained, enlightened, and perhaps, thoroughly perplexed. Our findings promise to shatter preconceived notions about the interconnectedness of disparate phenomena, prompting you to raise an eyebrow, scratch your chin, and maybe even let out a hearty chuckle.
As we navigate through the cornfields of electoral politics and the shimmering sands of energy consumption, we invite you to join us in this delightful dance of discovery. It's a waltz between the land of cheese and the land of oil, where the steps may be unconventional, but the music is undeniably catchy. So, without further ado, let us dive into the quagmire of correlations and contradictions, where the only certainty is the unpredictability of human behavior and the whims of statistical anomalies.

[[RESULTS]]
The results of our investigation revealed a striking correlation between Libertarian votes in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. The correlation coefficient of 0.9742614 indicated an incredibly strong positive relationship between these seemingly unrelated variables. This finding defies conventional logic, much like finding a palm tree in a Wisconsin blizzard or a cheesehead at a camel race!
The scatterplot in Fig. 1 portrays this eyebrow-raising relationship, showcasing the tight clustering of data points that almost seems too good to be true. It's as if the cheeseheads in Wisconsin are waving to the folks enjoying their shawarma in the UAE, all while sipping from the same fuel tank!
With an r-squared value of 0.9491853, our model explains a whopping 94.92% of the variability in liquefied petroleum gas consumption in the UAE based on Libertarian votes in Wisconsin. This level of predictability is as surprising as a desert oasis in the heart of Milwaukee!
Furthermore, the p-value of less than 0.01 offers solid evidence that this correlation is not a mere statistical fluke but a genuine relationship that demands attention. It's like finding a needle in a haystack, only in this case, the needle is dressed in a cheese wedge costume and exuding an aroma of petroleum fumes!
In conclusion, our findings highlight a connection that is as perplexing as it is intriguing. This unexpected correlation beckons for further exploration and prompts more questions than it answers, leaving us marveling at the mystifying dance between Midwestern political preferences and desert fuel consumption. It's a conundrum that may have you scratching your head, rubbing your eyes, and ultimately appreciating the sheer audacity of the statistical universe.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In the grand tapestry of statistical anomalies, our research has unveiled a correlation between Libertarian votes in Wisconsin and the consumption of liquefied petroleum gas in the United Arab Emirates that is as confounding as a camel trying to navigate a dairy farm. The strength of this correlation, with a coefficient of 0.9742614, defies conventional wisdom much like trying to herd cheese wheels across a desert. The predictability of 94.92% in the variability of gas consumption based on Wisconsin votes is as astonishing as stumbling upon a cheese festival in an Abu Dhabi marketplace.

While we can't ignore the evidence pointing to this unexpected relationship, we must also acknowledge the sheer absurdity of the findings. The p-value of less than 0.01, like a mirage in the desert, lures us into a world where political inclinations and fuel preferences perform an unlikely tango, leaving us bewildered and amused.

In light of these revelatory but rib-tickling results, we assert, with great confidence and a touch of whimsy, that further research in this area would be akin to searching for a sandwich in the Sahara – unnecessary and possibly fraught with humorous missteps. We leave this peculiar puzzle in the hands of future scholars who may endeavor to unravel the enigmatic connection between the heartland of America and the desert kingdom, armed with a hearty dose of skepticism and, of course, a keen sense of humor. For now, let us bid adieu to this tale of political caprice, statistical intrigue, and unexpected correlations, leaving it to be pondered with a chuckle and a raised eyebrow.


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 Libertarian Votes in Wisconsin: A Liquefied Laughter Link. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Puns and Pandemonium


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 Libertarian Votes in Wisconsin: A Liquefied Laughter Link. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Zany Political Analysis and Research


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Libertarian Votes in Wisconsin: A Liquefied Laughter Link with an abstract of In this study, we set out to examine the peculiar relationship between the votes cast for Libertarian candidates in Wisconsin senatorial elections and the consumption of liquefied petroleum gas in the United Arab Emirates. This eyebrow-raising investigation delves into the intersection of political preferences in the heartland of America and the fiery fuel consumption in a desert kingdom.
Utilizing data extracted from MIT Election Data and Science Lab, Harvard Dataverse, and Energy Information Administration, we embarked on an intellectual rollercoaster to uncover any potential ties between these seemingly unrelated phenomena. To our bewilderment, we stumbled upon a correlation coefficient of 0.9742614, with a p-value of less than 0.01, for the time span from 1980 to 2016.
Our findings raise more questions than answers, giving rise to intriguing possibilities and provoking chuckles of disbelief. From the dairy farms of Wisconsin to the sand dunes of the United Arab Emirates, our research sheds light on an unexpected correlation that warrants further investigation and perhaps a good-natured laugh or two.

ChatGPT:

Libertarian candidates, Wisconsin senatorial elections, liquefied petroleum gas consumption, United Arab Emirates, political preferences, correlation coefficient, p-value, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, 1980-2016, political correlations

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Votes for Libertarian Senators in Wisconsin
Detailed data title: Percentage of votes cast for Federal Libertarian Senate candidates in Wisconsin
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Libertarian Senators in Wisconsin

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

Correlation r = 0.9742614 (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 = 0.9491853 (Coefficient of determination)
This means 94.9% of the change in the one variable (i.e., Liquefied petroleum gas used in United Arab Emirates) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in Wisconsin) over the 9 years from 1980 through 2016.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.8E-6. 0.0000087834599110284810000000
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 0.97 in 0.00088% of random cases. Said differently, if you correlated 113,850 random variables You don't actually need 113 thousand 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 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 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.

[ 0.88, 0.99 ] 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.
198019821992199419982000200420122016
Votes for Libertarian Senators in Wisconsin (Percentage of votes)0.4391160.5144080.3725680.9861220.317520.8404450.2836522.068182.96842
Liquefied petroleum gas used in United Arab Emirates (Million Barrels/Day)0.5055370.9975934.6183.24.504522.5799740.120549.017




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




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([0.439116,0.514408,0.372568,0.986122,0.31752,0.840445,0.283652,2.06818,2.96842,])
array_2 = np.array([0.505537,0.997593,4.6,18,3.2,4.50452,2.57997,40.1205,49.017,])
array_1_name = "Votes for Libertarian Senators in Wisconsin"
array_2_name = "Liquefied petroleum gas used in United Arab Emirates"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!


Correlation ID: 5446 · Black Variable ID: 26484 · Red Variable ID: 25044
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0