about · email me · subscribe
Spurious correlation #5,804 · 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 the Democratic Presidential candidate in Missouri and the second variable is Kerosene used in Eswatini.  The chart goes from 1989 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the political tension in Missouri heated up, more hot air was generated, leading to an unexpected surplus of kerosene in Eswatini. Remember, when it comes to politics and energy, things can really start burning up!

Model: dalle-3
Prompt: Generate an image that resembles a scene from 'Star Wars,' featuring a bustling market in Eswatini. Colorful jerry cans of kerosene are stacked high under a bright blue sky. In the midst of this vibrant market, people are busy voting at a polling station in Missouri, with lines of voters snaking out of the building. The tension in the air creates a palpable wave of heat that shimmers across the scene, causing the kerosene cans to appear even brighter. 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 the Democratic Presidential candidate in Missouri and Kerosene used in Eswatini. 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: Surrealism Cubism Futuristic An image that looks like it is a scene from 'Star Wars' Pop art
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 the Democratic Presidential candidate in Missouri and Kerosene used in Eswatini, in the following situation: As the political tension in Missouri heated up, more hot air was generated, leading to an unexpected surplus of kerosene in Eswatini. Remember, when it comes to politics and energy, things can really start burning up!. Keep the description simple.
ChatGPT: In a bustling market in Eswatini, colorful jerry cans of kerosene are stacked high under a bright blue sky. People are busy voting at a polling station in Missouri, with lines of voters snaking out of the building. The tension in the air seems to create a wave of heat that shimmers across the scene, causing the kerosene cans to appear even brighter.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a bustling market in Eswatini, colorful jerry cans of kerosene are stacked high under a bright blue sky. People are busy voting at a polling station in Missouri, with lines of voters snaking out of the building. The tension in the air seems to create a wave of heat that shimmers across the scene, causing the kerosene cans to appear even brighter. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that resembles a scene from 'Star Wars,' featuring a bustling market in Eswatini. Colorful jerry cans of kerosene are stacked high under a bright blue sky. In the midst of this vibrant market, people are busy voting at a polling station in Missouri, with lines of voters snaking out of the building. The tension in the air creates a palpable wave of heat that shimmers across the scene, causing the kerosene cans to appear even brighter.

*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 Votes for the Democrat Presidential candidate in Missouri caused Kerosene used in Eswatini to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

The Journal of Quirky Sociopolitical Correlations

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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. Make lots of jokes, goofy observations, and puns.

Rhyme words in the title.

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 0.8622439 and p < 0.01 for 1989 to 2020.

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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As researchers, we often seek to uncover correlations and connections between variables that seem to be as unrelated as guacamole and math textbooks. In this study, we set out to explore the intriguing relationship between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. At first glance, one might assume that these two variables have as much in common as a toaster and a bicycle, but our rigorous statistical analysis has revealed a surprising correlation that is enough to make anyone do a double take.

The title of this paper, "Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents," is not just a catchy play on words; it accurately encapsulates the curious connection we have unraveled through our research. While most people may be more accustomed to thinking about political preferences and energy consumption as unrelated as a kangaroo and a cup of coffee, our findings suggest that there may be more to the story than meets the eye.

The decision to embark on this investigation was not made lightly, but rather sparked by a serendipitous encounter with preliminary data that left us scratching our heads in delightful confusion. Who would have thought that the electoral preferences of Missourians and the kerosene habits of Eswatini citizens could be intertwined like a pair of mating slinkies? As fervent aficionados of statistical puzzles, we simply could not resist the allure of this quirky connection.

The abstract teases the revelation of a correlation coefficient of 0.8622439 and a p-value of less than 0.01, but fear not, dear reader, as the wild ride of statistical shenanigans has only just begun. Buckle up as we delve into the depths of our data analysis, shedding light on the convoluted dance of these two seemingly unrelated variables. Get ready to have your assumptions upended, your preconceptions challenged, and your funny bone tickled by the unexpected capers of statistics. It's time to uncover the mystery behind the sizzling link between blue votes and kerosene totes!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As researchers, we often seek to uncover correlations and connections between variables that seem to be as unrelated as guacamole and math textbooks. In this study, we set out to explore the intriguing relationship between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. At first glance, one might assume that these two variables have as much in common as a toaster and a bicycle, but our rigorous statistical analysis has revealed a surprising correlation that is enough to make anyone do a double take.
The title of this paper, "Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents," is not just a catchy play on words; it accurately encapsulates the curious connection we have unraveled through our research. While most people may be more accustomed to thinking about political preferences and energy consumption as unrelated as a kangaroo and a cup of coffee, our findings suggest that there may be more to the story than meets the eye.
The decision to embark on this investigation was not made lightly, but rather sparked by a serendipitous encounter with preliminary data that left us scratching our heads in delightful confusion. Who would have thought that the electoral preferences of Missourians and the kerosene habits of Eswatini citizens could be intertwined like a pair of mating slinkies? As fervent aficionados of statistical puzzles, we simply could not resist the allure of this quirky connection.
The abstract teases the revelation of a correlation coefficient of 0.8622439 and a p-value of less than 0.01, but fear not, dear reader, as the wild ride of statistical shenanigans has only just begun. Buckle up as we delve into the depths of our data analysis, shedding light on the convoluted dance of these two seemingly unrelated variables. Get ready to have your assumptions upended, your preconceptions challenged, and your funny bone tickled by the unexpected capers of statistics. It's time to uncover the mystery behind the sizzling link between blue votes and kerosene totes!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al." and "Doe and Jones," the authors find evidence of correlations between voting patterns and energy consumption, echoing the age-old adage that politics and energy make strange bedfellows. While these seminal works pique our interest, our research takes us down a path that is eerily similar to the plot of an absurd sci-fi novel. We find ourselves traversing the uncharted terrain of statistical analysis, where the unexpected becomes the expected, and the mundane transforms into the miraculous.

Turning to non-fiction works, "Energy Economics" by Peter Davis and "Political Analysis and Rational Choice" by Peter C. Ordeshook offer valuable insights on the dynamics of resource consumption and electoral behavior. As our investigation delves deeper, we encounter a literary landscape that resembles the mind-bending narratives of fiction. "Election Inferno" by Dan Brown and "The Statistical Mysteries of Eswatini" by Agatha Christie beckon us into a realm where the ordinary becomes extraordinary, and the improbable emerges as the inevitable.

Pushing the boundaries of scholarly research, we draw inspiration from unconventional sources, including the whimsical world of children's entertainment. Through the lens of "The Magic School Bus" and "Scooby-Doo," we embrace the spirit of curiosity and embark on a quest for knowledge that rivals the most preposterous plotlines. As our journey unfolds, we find ourselves navigating the labyrinth of data with all the enthusiasm of a cartoon character chasing after a mythical treasure.

Like a puzzle that demands to be solved or a riddle that begs to be unravelled, the connection between blue votes in Missouri and kerosene consumption in Eswatini emerges as a phenomenon that defies conventional wisdom. We invite our fellow researchers to join us in this whimsical expedition as we unravel the enigmatic correlation that transcends borders and challenges the very fabric of statistical expectations.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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 MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1989 to 2020

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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

[[INTRODUCTION]]
As researchers, we often seek to uncover correlations and connections between variables that seem to be as unrelated as guacamole and math textbooks. In this study, we set out to explore the intriguing relationship between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. At first glance, one might assume that these two variables have as much in common as a toaster and a bicycle, but our rigorous statistical analysis has revealed a surprising correlation that is enough to make anyone do a double take.
The title of this paper, "Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents," is not just a catchy play on words; it accurately encapsulates the curious connection we have unraveled through our research. While most people may be more accustomed to thinking about political preferences and energy consumption as unrelated as a kangaroo and a cup of coffee, our findings suggest that there may be more to the story than meets the eye.
The decision to embark on this investigation was not made lightly, but rather sparked by a serendipitous encounter with preliminary data that left us scratching our heads in delightful confusion. Who would have thought that the electoral preferences of Missourians and the kerosene habits of Eswatini citizens could be intertwined like a pair of mating slinkies? As fervent aficionados of statistical puzzles, we simply could not resist the allure of this quirky connection.
The abstract teases the revelation of a correlation coefficient of 0.8622439 and a p-value of less than 0.01, but fear not, dear reader, as the wild ride of statistical shenanigans has only just begun. Buckle up as we delve into the depths of our data analysis, shedding light on the convoluted dance of these two seemingly unrelated variables. Get ready to have your assumptions upended, your preconceptions challenged, and your funny bone tickled by the unexpected capers of statistics. It's time to uncover the mystery behind the sizzling link between blue votes and kerosene totes!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the enigmatic relationship between Democratic votes in Missouri and kerosene consumption in Eswatini, we embarked on a whirlwind statistical adventure that would make even the most intrepid explorer of data break out in a cold sweat. Our journey began with the procurement of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, where we traversed the digital landscape like Indiana Jones in search of hidden treasures.

Our first step involved wrangling the vast quantities of data, a process that resembled untangling a ball of yarn in a room full of playful kittens. We meticulously combed through the decades from 1989 to 2020, examining each data point with the precision of a neurosurgeon performing delicate maneuvers.

Next, we employed a diversified array of statistical methods that would make even the most seasoned mathematician raise an eyebrow. We utilized linear regression analysis, time series modeling, and even dabbled in some multivariate techniques, all the while navigating this statistical maze like a contestant on a game show aiming for the grand prize.

The model building process was as intricate as assembling a 1,000-piece jigsaw puzzle. We carefully selected covariates that we believed could shed light on the unlikely marriage of Democratic votes and kerosene consumption, and we tuned our models with the diligence of a master musician tuning a grand piano before a symphony.

The resulting analysis revealed a correlation coefficient of 0.8622439, a value that made our hearts skip a beat and the p-value of less than 0.01 had us doing a victory dance reminiscent of a medalist at the Olympic Games. Our findings not only spark lively discussions but also illuminate the unexpected relationship between these two seemingly disparate variables, leaving us marveling at the capricious nature of statistical fate.

In conclusion, our methodology was not just a rigorous application of statistical techniques; it was a wild rollercoaster ride through the realms of data analysis that left us exhilarated and slightly dizzy. Like a magician pulling a rabbit out of a hat, we hope our methodology will charm and delight our readers while shedding light on the peculiar link between blue votes and kerosene totes.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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 MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration .

For the time period 1989 to 2020, you found a correlation 0.8622439, r-squared of 0.7434646, 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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As researchers, we often seek to uncover correlations and connections between variables that seem to be as unrelated as guacamole and math textbooks. In this study, we set out to explore the intriguing relationship between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. At first glance, one might assume that these two variables have as much in common as a toaster and a bicycle, but our rigorous statistical analysis has revealed a surprising correlation that is enough to make anyone do a double take.
The title of this paper, "Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents," is not just a catchy play on words; it accurately encapsulates the curious connection we have unraveled through our research. While most people may be more accustomed to thinking about political preferences and energy consumption as unrelated as a kangaroo and a cup of coffee, our findings suggest that there may be more to the story than meets the eye.
The decision to embark on this investigation was not made lightly, but rather sparked by a serendipitous encounter with preliminary data that left us scratching our heads in delightful confusion. Who would have thought that the electoral preferences of Missourians and the kerosene habits of Eswatini citizens could be intertwined like a pair of mating slinkies? As fervent aficionados of statistical puzzles, we simply could not resist the allure of this quirky connection.
The abstract teases the revelation of a correlation coefficient of 0.8622439 and a p-value of less than 0.01, but fear not, dear reader, as the wild ride of statistical shenanigans has only just begun. Buckle up as we delve into the depths of our data analysis, shedding light on the convoluted dance of these two seemingly unrelated variables. Get ready to have your assumptions upended, your preconceptions challenged, and your funny bone tickled by the unexpected capers of statistics. It's time to uncover the mystery behind the sizzling link between blue votes and kerosene totes!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis unveil a remarkable correlation between the percentage of votes cast for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. Our findings reveal a correlation coefficient of 0.8622439, indicating a strong positive relationship between these seemingly unrelated variables. This correlation coefficient is nothing short of astounding, leaving us scratching our heads like perplexed penguins in a statistical snowstorm.

Additionally, the coefficient of determination (r-squared) of 0.7434646 suggests that approximately 74.35% of the variation in kerosene usage in Eswatini can be explained by the variation in Democratic vote share in Missouri. This is a statistically significant amount of explanation, leaving us feeling as triumphant as chemists who finally synthesized the perfect pun.

Furthermore, the p-value of less than 0.01 provides compelling evidence that the observed correlation is not due to random chance. This statistical significance is as rare and delightful as finding a four-leaf clover in a field of standard deviations.

In visualizing the relationship, our scatterplot (Fig. 1) depicts a striking pattern that confirms the strength of the correlation. The data points form a tight cluster resembling a synchronized group of statistical dancers, demonstrating the coherence of the relationship. This visual depiction of the correlation is as clear as a freshly cleaned beaker in a chemistry lab.

In conclusion, our research has illuminated an unexpected and thought-provoking correlation between political voting patterns and energy consumption. These findings challenge conventional wisdom and invite further investigation into the humorous and surprising complexities of statistical relationships. As we ponder the implications of our results, we cannot help but marvel at the quirky and captivating nature of statistical analysis.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

[[LITERATURE REVIEW]]
In "Smith et al." and "Doe and Jones," the authors find evidence of correlations between voting patterns and energy consumption, echoing the age-old adage that politics and energy make strange bedfellows. While these seminal works pique our interest, our research takes us down a path that is eerily similar to the plot of an absurd sci-fi novel. We find ourselves traversing the uncharted terrain of statistical analysis, where the unexpected becomes the expected, and the mundane transforms into the miraculous.
Turning to non-fiction works, "Energy Economics" by Peter Davis and "Political Analysis and Rational Choice" by Peter C. Ordeshook offer valuable insights on the dynamics of resource consumption and electoral behavior. As our investigation delves deeper, we encounter a literary landscape that resembles the mind-bending narratives of fiction. "Election Inferno" by Dan Brown and "The Statistical Mysteries of Eswatini" by Agatha Christie beckon us into a realm where the ordinary becomes extraordinary, and the improbable emerges as the inevitable.
Pushing the boundaries of scholarly research, we draw inspiration from unconventional sources, including the whimsical world of children's entertainment. Through the lens of "The Magic School Bus" and "Scooby-Doo," we embrace the spirit of curiosity and embark on a quest for knowledge that rivals the most preposterous plotlines. As our journey unfolds, we find ourselves navigating the labyrinth of data with all the enthusiasm of a cartoon character chasing after a mythical treasure.
Like a puzzle that demands to be solved or a riddle that begs to be unravelled, the connection between blue votes in Missouri and kerosene consumption in Eswatini emerges as a phenomenon that defies conventional wisdom. We invite our fellow researchers to join us in this whimsical expedition as we unravel the enigmatic correlation that transcends borders and challenges the very fabric of statistical expectations.

[[RESULTS]]
The results of our analysis unveil a remarkable correlation between the percentage of votes cast for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. Our findings reveal a correlation coefficient of 0.8622439, indicating a strong positive relationship between these seemingly unrelated variables. This correlation coefficient is nothing short of astounding, leaving us scratching our heads like perplexed penguins in a statistical snowstorm.
Additionally, the coefficient of determination (r-squared) of 0.7434646 suggests that approximately 74.35% of the variation in kerosene usage in Eswatini can be explained by the variation in Democratic vote share in Missouri. This is a statistically significant amount of explanation, leaving us feeling as triumphant as chemists who finally synthesized the perfect pun.
Furthermore, the p-value of less than 0.01 provides compelling evidence that the observed correlation is not due to random chance. This statistical significance is as rare and delightful as finding a four-leaf clover in a field of standard deviations.
In visualizing the relationship, our scatterplot (Fig. 1) depicts a striking pattern that confirms the strength of the correlation. The data points form a tight cluster resembling a synchronized group of statistical dancers, demonstrating the coherence of the relationship. This visual depiction of the correlation is as clear as a freshly cleaned beaker in a chemistry lab.
In conclusion, our research has illuminated an unexpected and thought-provoking correlation between political voting patterns and energy consumption. These findings challenge conventional wisdom and invite further investigation into the humorous and surprising complexities of statistical relationships. As we ponder the implications of our results, we cannot help but marvel at the quirky and captivating nature of statistical analysis.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The correlation between the share of Democratic votes in Missouri and kerosene consumption in Eswatini is as unexpected as finding a statistical unicorn in the realm of data analysis. Our findings not only support the prior research but also add an entertaining twist to the age-old adage that "correlation does not imply causation" – perhaps, in this case, it implies connection across continents!

Our results align with the works of "Smith et al." and "Doe and Jones," shedding light on the peculiar interplay between political choices and energy usage. It appears that the connection between blue votes and kerosene totes is not just a statistical anomaly but a real, tangible phenomenon that leaves us pondering the whimsical intricacies of the universe. These findings add a comedic dimension to the scholarly pursuit of knowledge, making the dry world of statistics as lively as a stand-up comedy show.

Notably, our statistical analysis has unveiled a correlation coefficient of 0.8622439, which is as strong as the magnetism between two resonating statistical poles. This robust coefficient indicates a compelling positive relationship between the variables, akin to the harmonious melody of statistical instruments playing in unison. The coefficient of determination (r-squared) of 0.7434646 further reinforces the substantial explanatory power of the relationship, leaving us feeling as accomplished as scientists who have cracked the code to a daunting statistical puzzle.

Moreover, the p-value of less than 0.01 adds a touch of statistical glamour to our findings, as rare and captivating as discovering a statistical diamond in the rough of data analysis. This validation of statistical significance strengthens the credibility of our results and cements the quirky connection between blue votes and kerosene totes as a fascinating avenue for future exploration.

The visual representation of the relationship in our scatterplot offers a charming portrayal of the correlation, resembling a synchronized dance of statistical elegance. This visual depiction not only bolsters the strength of the correlation but also brings a dynamic flair to the typically rigid world of statistical visualization, akin to a colorful fireworks display amidst the grayscale landscape of data analysis.

In essence, our research has unearthed an unlikely yet captivating correlation that challenges the conventional boundaries of statistical expectations. It invites researchers to embark on a quest for knowledge as thrilling as a treasure hunt and as amusing as a whimsical tale from the world of fiction. As we delve deeper into this enigmatic nexus of blue votes and kerosene totes, we are reminded of the delightful unpredictability that accompanies the relentless pursuit of statistical understanding.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Missouri and Kerosene used in Eswatini. 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]]
Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents

[[ABSTRACT]]
This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

[[INTRDUCTION]]
As researchers, we often seek to uncover correlations and connections between variables that seem to be as unrelated as guacamole and math textbooks. In this study, we set out to explore the intriguing relationship between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. At first glance, one might assume that these two variables have as much in common as a toaster and a bicycle, but our rigorous statistical analysis has revealed a surprising correlation that is enough to make anyone do a double take.
The title of this paper, "Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents," is not just a catchy play on words; it accurately encapsulates the curious connection we have unraveled through our research. While most people may be more accustomed to thinking about political preferences and energy consumption as unrelated as a kangaroo and a cup of coffee, our findings suggest that there may be more to the story than meets the eye.
The decision to embark on this investigation was not made lightly, but rather sparked by a serendipitous encounter with preliminary data that left us scratching our heads in delightful confusion. Who would have thought that the electoral preferences of Missourians and the kerosene habits of Eswatini citizens could be intertwined like a pair of mating slinkies? As fervent aficionados of statistical puzzles, we simply could not resist the allure of this quirky connection.
The abstract teases the revelation of a correlation coefficient of 0.8622439 and a p-value of less than 0.01, but fear not, dear reader, as the wild ride of statistical shenanigans has only just begun. Buckle up as we delve into the depths of our data analysis, shedding light on the convoluted dance of these two seemingly unrelated variables. Get ready to have your assumptions upended, your preconceptions challenged, and your funny bone tickled by the unexpected capers of statistics. It's time to uncover the mystery behind the sizzling link between blue votes and kerosene totes!

[[RESULTS]]
The results of our analysis unveil a remarkable correlation between the percentage of votes cast for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini. Our findings reveal a correlation coefficient of 0.8622439, indicating a strong positive relationship between these seemingly unrelated variables. This correlation coefficient is nothing short of astounding, leaving us scratching our heads like perplexed penguins in a statistical snowstorm.
Additionally, the coefficient of determination (r-squared) of 0.7434646 suggests that approximately 74.35% of the variation in kerosene usage in Eswatini can be explained by the variation in Democratic vote share in Missouri. This is a statistically significant amount of explanation, leaving us feeling as triumphant as chemists who finally synthesized the perfect pun.
Furthermore, the p-value of less than 0.01 provides compelling evidence that the observed correlation is not due to random chance. This statistical significance is as rare and delightful as finding a four-leaf clover in a field of standard deviations.
In visualizing the relationship, our scatterplot (Fig. 1) depicts a striking pattern that confirms the strength of the correlation. The data points form a tight cluster resembling a synchronized group of statistical dancers, demonstrating the coherence of the relationship. This visual depiction of the correlation is as clear as a freshly cleaned beaker in a chemistry lab.
In conclusion, our research has illuminated an unexpected and thought-provoking correlation between political voting patterns and energy consumption. These findings challenge conventional wisdom and invite further investigation into the humorous and surprising complexities of statistical relationships. As we ponder the implications of our results, we cannot help but marvel at the quirky and captivating nature of statistical analysis.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the seemingly incongruous connection between votes for the Democratic presidential candidate in Missouri and the consumption of kerosene in the Kingdom of Eswatini has ignited a statistical firework display of insight and amusement. The correlation coefficient of 0.8622439 emerged as the star of the show, showcasing a bond tighter than the grip of a statistics professor on a beloved calculator.

The coefficient of determination (r-squared) of 0.7434646 further solidifies the substantial relationship between these variables, leaving us feeling as satisfied as researchers who have finally cracked the code to the perennial question of why the chicken crossed the road.

The p-value of less than 0.01 acts as an exclamation mark at the end of a statistically significant sentence, boldly asserting that this correlation is as real and improbable as a unicorn sighting in a data center.

Our scatterplot (Fig. 1) serves as a visual testament to the striking correlation, with data points aligning more closely than peas in a pod at a statistical family reunion. This compelling visualization leaves us as dazzled as astronomers discovering a new constellation in the statistical sky.

As we wrap up this lighthearted statistical romp, we are left with a data-driven punchline that challenges conventional assumptions and tickles the intellectual senses. Our journey has underscored the delightful unpredictability of statistical relationships, reminding us that even the most unrelated variables can tango in the intricate dance of correlation.

Having unearthed this captivating correlation, we assert with confidence that no further research is needed in this area. We have extracted all the statistical humor and insight possible from this unexpected connection, leaving no correlation coefficient unturned and no p-value unscrutinized. It's time to bid adieu to the enthralling saga of blue votes and kerosene totes, as we turn our statistical gaze toward the next unlikely pair of variables awaiting illumination.


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 Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Sociopolitical Correlations


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 Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents. Respond only with the name of a fictional organization.

ChatGPT:

The Society for International Petrochemical and Political Analysis


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 Blue Votes and Kerosene Totes: A Surprising Correlation Across Continents with an abstract of This paper delves into the unexpected connections between the presidential vote share for the Democratic candidate in the state of Missouri and the consumption of kerosene in the Kingdom of Eswatini. With data sourced from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we employed rigorous statistical analysis to unveil a correlation coefficient of 0.8622439 and, lo and behold, a p-value of less than 0.01 for the period from 1989 to 2020. Our findings reveal a trove of humorous insights and ignite some fiery discussions on the interplay between seemingly disparate variables. Get ready to be illuminated by the sparks flying in this research–it's not just the kerosene!

ChatGPT:

Blue vote share, Democratic candidate, Missouri, kerosene consumption, Eswatini, correlation coefficient, statistical analysis, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, presidential vote share, surprising correlation, humorous insights

*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 the Democratic Presidential candidate in Missouri
Detailed data title: Percentage of all votes cast for the Democrat Presidential candidate in Missouri
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Democratic Presidential candidate in Missouri

Kerosene used in Eswatini
Detailed data title: Volume of kerosene used consumed in Eswatini in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Eswatini

Correlation r = 0.8622439 (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 = 0.7434646 (Coefficient of determination)
This means 74.3% of the change in the one variable (i.e., Kerosene used in Eswatini) is predictable based on the change in the other (i.e., Votes for the Democratic Presidential candidate in Missouri) over the 8 years from 1989 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0059. 0.0058787859249276100000000000
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 0.86 in 0.59% of random cases. Said differently, if you correlated 170 random variables Which I absolutely did.
with the same 7 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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.

[ 0.4, 0.97 ] 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.
19921996200020042008201220162020
Votes for the Democratic Presidential candidate in Missouri (Percentage of votes)44.071747.539647.084346.100449.292644.383538.135241.4088
Kerosene used in Eswatini (Million Barrels/Day)0.10.20.2443910.2052890.2096390.1689620.0847120.087082




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.
  5. 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([44.0717,47.5396,47.0843,46.1004,49.2926,44.3835,38.1352,41.4088,])
array_2 = np.array([0.1,0.2,0.244391,0.205289,0.209639,0.168962,0.084712,0.087082,])
array_1_name = "Votes for the Democratic Presidential candidate in Missouri"
array_2_name = "Kerosene used in Eswatini"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!


Correlation ID: 5804 · Black Variable ID: 26123 · Red Variable ID: 24399
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0