about · email me · subscribe
Spurious correlation #4,412 · 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 Republican Senators in Utah and the second variable is Fossil fuel use in Suriname.  The chart goes from 1980 to 2018, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of Republican votes for Senators in Utah rises, so does the demand for balloons to celebrate. Suriname, feeling the festive vibes, decides to host the world's first Fossil Fuel Fueled Balloon Festival, leading to a significant uptick in fossil fuel use. It's a gas-guzzling, politically-charged party in the skies over Suriname!

Model: dalle-3
Prompt: An image that looks like it is a scene from 'Star Wars': [ In Utah, as Republican votes for Senators increase, the demand for celebratory balloons skyrockets. Meanwhile, in Suriname, the world's first Fossil Fuel Fueled Balloon Festival is taking place, causing a surge in fossil fuel use. The skies are filled with colorful balloons, creating a festive but environmentally impactful scene. ] When generating this image, make sure to include a desert landscape with red rock formations in the background. Show various sizes and shapes of colorful balloons filling the sky over the desert, alongside an unusual sight of futuristic balloons powered by fossil fuels adding to the spectacle. The scene should have an otherworldly, epic feel, akin to the grandeur of a 'Star Wars' setting. 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: Republican votes for Senators in Utah and Fossil fuel use in Suriname. 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: Cutsy graphics An image that looks like it is a scene from a Pixar movie Cute cartoon Cubism An image that looks like it is a scene from 'Star Wars'
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 Republican votes for Senators in Utah and Fossil fuel use in Suriname, in the following situation: As the number of Republican votes for Senators in Utah rises, so does the demand for balloons to celebrate. Suriname, feeling the festive vibes, decides to host the world's first Fossil Fuel Fueled Balloon Festival, leading to a significant uptick in fossil fuel use. It's a gas-guzzling, politically-charged party in the skies over Suriname!. Keep the description simple.
ChatGPT: In Utah, as Republican votes for Senators increase, the demand for celebratory balloons skyrockets. Meanwhile, in Suriname, the world's first Fossil Fuel Fueled Balloon Festival is taking place, causing a surge in fossil fuel use. The skies are filled with colorful balloons, creating a festive but environmentally impactful scene.

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 Utah, as Republican votes for Senators increase, the demand for celebratory balloons skyrockets. Meanwhile, in Suriname, the world's first Fossil Fuel Fueled Balloon Festival is taking place, causing a surge in fossil fuel use. The skies are filled with colorful balloons, creating a festive but environmentally impactful scene. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from 'Star Wars': [ In Utah, as Republican votes for Senators increase, the demand for celebratory balloons skyrockets. Meanwhile, in Suriname, the world's first Fossil Fuel Fueled Balloon Festival is taking place, causing a surge in fossil fuel use. The skies are filled with colorful balloons, creating a festive but environmentally impactful scene. ] When generating this image, make sure to include a desert landscape with red rock formations in the background. Show various sizes and shapes of colorful balloons filling the sky over the desert, alongside an unusual sight of futuristic balloons powered by fossil fuels adding to the spectacle. The scene should have an otherworldly, epic feel, akin to the grandeur of a 'Star Wars' setting.

*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 Republican votes for Senators in Utah caused Fossil fuel use in Suriname to increase.

AI academic paper

(Because p < 0.01)
Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation

The Journal of Unusual 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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 0.8725118 and p < 0.01 for 1980 to 2018.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
Introduction

Politics and energy usage have always been two areas of great fascination for researchers seeking to unravel the enigmatic and often inscrutable patterns underlying human behavior and societal dynamics. The confluence of Utah's conservative political landscape and Suriname's fossil fuel consumption presents an alluring paradox, akin to a statistical riddle wrapped in a tantalizing mystery inside a data-driven enigma. As researchers, we have long been accustomed to delving into the depths of correlation matrices and regression analyses, akin to intrepid explorers venturing into uncharted statistical territory. The quirks and idiosyncrasies of our findings, akin to unexpected pops of color in a grayscale dataset, have left us both bemused and intrigued, akin to stumbling upon a gaggle of penguins in the desert.

In this study, we set out to examine the peculiar connection between Republican votes for Senators in Utah and fossil fuel use in Suriname, seeking to unearth the hidden threads spun by the statistical loom that weave together these seemingly disparate variables. Drawing upon the expanse of political data from the esteemed MIT Election Data and Science Lab, along with the troves of energy statistics housed within the Harvard Dataverse and the Energy Information Administration, our research endeavors endeavored to unpack the underlying concatenation of factors that bind together the electoral leanings of a US state and the energy proclivities of a South American nation.

The allure of this research lies not only in the statistical acrobatics undertaken to establish a robust empirical relationship but also in the whimsical nature of the relationship itself. As we waded through seas of data, traversing the tenebrous realm of statistical significance, we stumbled upon a correlation coefficient of 0.8725118, which loomed over us like an unexpected apparition in the halls of academe. With a p-value that shimmered seductively below the acclaimed threshold of 0.01, our findings beckoned to us like a siren's call, tempting us to unravel the mysteries that lay within the labyrinthine corridors of statistical inference.

While our pursuit may appear far-fetched to the uninitiated, our statistical foray into these seemingly incongruous domains of political preference and energy consumption has yielded findings that not only confound conventional wisdom but also infuse an element of levity into the oftentimes solemn realm of academic inquiry. As we unveil the whimsical tendrils that bind these divergent variables, we invite our readers to join us in this mirthful jaunt through the juncture where Republican votes and fossil fuel usage converge, offering a respite from the rigors of conventional scholarship and a peek into the serendipitous caprices of empirical inquiry.

In the subsequent sections of this paper, we shall embark upon a detailed exegesis of the methodology employed, the intricacies of the data analyzed, the robustness of the statistical models constructed, and the implications of our findings. Thus, armed with a hearty dose of statistical fortitude and a penchant for reveling in the unexpected, we invite our readers to delve into this curiously charming nexus of Utah's quirks, Republican proclivities, and Surinamese energy whims.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
Politics and energy usage have always been two areas of great fascination for researchers seeking to unravel the enigmatic and often inscrutable patterns underlying human behavior and societal dynamics. The confluence of Utah's conservative political landscape and Suriname's fossil fuel consumption presents an alluring paradox, akin to a statistical riddle wrapped in a tantalizing mystery inside a data-driven enigma. As researchers, we have long been accustomed to delving into the depths of correlation matrices and regression analyses, akin to intrepid explorers venturing into uncharted statistical territory. The quirks and idiosyncrasies of our findings, akin to unexpected pops of color in a grayscale dataset, have left us both bemused and intrigued, akin to stumbling upon a gaggle of penguins in the desert.
In this study, we set out to examine the peculiar connection between Republican votes for Senators in Utah and fossil fuel use in Suriname, seeking to unearth the hidden threads spun by the statistical loom that weave together these seemingly disparate variables. Drawing upon the expanse of political data from the esteemed MIT Election Data and Science Lab, along with the troves of energy statistics housed within the Harvard Dataverse and the Energy Information Administration, our research endeavors endeavored to unpack the underlying concatenation of factors that bind together the electoral leanings of a US state and the energy proclivities of a South American nation.
The allure of this research lies not only in the statistical acrobatics undertaken to establish a robust empirical relationship but also in the whimsical nature of the relationship itself. As we waded through seas of data, traversing the tenebrous realm of statistical significance, we stumbled upon a correlation coefficient of 0.8725118, which loomed over us like an unexpected apparition in the halls of academe. With a p-value that shimmered seductively below the acclaimed threshold of 0.01, our findings beckoned to us like a siren's call, tempting us to unravel the mysteries that lay within the labyrinthine corridors of statistical inference.
While our pursuit may appear far-fetched to the uninitiated, our statistical foray into these seemingly incongruous domains of political preference and energy consumption has yielded findings that not only confound conventional wisdom but also infuse an element of levity into the oftentimes solemn realm of academic inquiry. As we unveil the whimsical tendrils that bind these divergent variables, we invite our readers to join us in this mirthful jaunt through the juncture where Republican votes and fossil fuel usage converge, offering a respite from the rigors of conventional scholarship and a peek into the serendipitous caprices of empirical inquiry.
In the subsequent sections of this paper, we shall embark upon a detailed exegesis of the methodology employed, the intricacies of the data analyzed, the robustness of the statistical models constructed, and the implications of our findings. Thus, armed with a hearty dose of statistical fortitude and a penchant for reveling in the unexpected, we invite our readers to delve into this curiously charming nexus of Utah's quirks, Republican proclivities, and Surinamese energy whims.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between Republican votes for Senators in Utah and fossil fuel use in Suriname has garnered limited attention in prior research. However, the few existing studies provide valuable insights into this quirky correlation. Smith et al. (2015) offer a comprehensive analysis of political voting patterns in Utah, shedding light on the historic dominance of Republican candidates in statewide elections. Meanwhile, Doe and Jones (2017) delve into the intricate web of fossil fuel consumption trends in Suriname, providing a nuanced understanding of the country's energy dynamics.

Moving beyond strictly academic sources, "Energy Politics" by Williams (2018) explores the sociopolitical ramifications of fossil fuel utilization in developing nations. In a similar vein, "The Grand Old Party" by Thompson (2019) offers a compelling narrative of the Republican Party's influence in American politics. These works, while not directly addressing the specific correlation of interest, contribute to a broader contextual understanding of the intersecting domains of political affiliations and energy utilization.

Expanding into the realm of fiction, the works of J.K. Rowling, particularly the "Harry Potter" series, may seem distant from the focal point of this study. However, the themes of power struggles and allegiances present in these novels bear a curious resemblance to the dynamics of political voting. Similarly, "Oil and Water" by Robinson (2016) weaves a tale of unexpected connections, much like the improbable correlation under investigation.

Venturing into more unconventional sources, it is worth noting that the back covers of shampoo bottles, though not typically recognized as scholarly literature, provide a surprising trove of information. Suspiciously smooth prose and grandiose claims adorn these containers, often promising transformative effects akin to the monumental shifts in senatorial voting and fossil fuel use. Although not rigorously peer-reviewed, these sources warrant acknowledgment for their strangely captivating narratives and unanticipated correlations.

Through this eclectic review, the authors find a blend of insightful scholarship, whimsical fiction, and unexpected sources that collectively inform the foundation of this study. As we delve deeper into our own analysis, we aim to build upon this diverse array of influences and unravel the enigmatic connection between Republican votes and fossil fuel use, guided by a spirit of scholarly inquiry and a dash of irreverent curiosity.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 1980 to 2018

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

[[INTRODUCTION]]
Introduction
Politics and energy usage have always been two areas of great fascination for researchers seeking to unravel the enigmatic and often inscrutable patterns underlying human behavior and societal dynamics. The confluence of Utah's conservative political landscape and Suriname's fossil fuel consumption presents an alluring paradox, akin to a statistical riddle wrapped in a tantalizing mystery inside a data-driven enigma. As researchers, we have long been accustomed to delving into the depths of correlation matrices and regression analyses, akin to intrepid explorers venturing into uncharted statistical territory. The quirks and idiosyncrasies of our findings, akin to unexpected pops of color in a grayscale dataset, have left us both bemused and intrigued, akin to stumbling upon a gaggle of penguins in the desert.
In this study, we set out to examine the peculiar connection between Republican votes for Senators in Utah and fossil fuel use in Suriname, seeking to unearth the hidden threads spun by the statistical loom that weave together these seemingly disparate variables. Drawing upon the expanse of political data from the esteemed MIT Election Data and Science Lab, along with the troves of energy statistics housed within the Harvard Dataverse and the Energy Information Administration, our research endeavors endeavored to unpack the underlying concatenation of factors that bind together the electoral leanings of a US state and the energy proclivities of a South American nation.
The allure of this research lies not only in the statistical acrobatics undertaken to establish a robust empirical relationship but also in the whimsical nature of the relationship itself. As we waded through seas of data, traversing the tenebrous realm of statistical significance, we stumbled upon a correlation coefficient of 0.8725118, which loomed over us like an unexpected apparition in the halls of academe. With a p-value that shimmered seductively below the acclaimed threshold of 0.01, our findings beckoned to us like a siren's call, tempting us to unravel the mysteries that lay within the labyrinthine corridors of statistical inference.
While our pursuit may appear far-fetched to the uninitiated, our statistical foray into these seemingly incongruous domains of political preference and energy consumption has yielded findings that not only confound conventional wisdom but also infuse an element of levity into the oftentimes solemn realm of academic inquiry. As we unveil the whimsical tendrils that bind these divergent variables, we invite our readers to join us in this mirthful jaunt through the juncture where Republican votes and fossil fuel usage converge, offering a respite from the rigors of conventional scholarship and a peek into the serendipitous caprices of empirical inquiry.
In the subsequent sections of this paper, we shall embark upon a detailed exegesis of the methodology employed, the intricacies of the data analyzed, the robustness of the statistical models constructed, and the implications of our findings. Thus, armed with a hearty dose of statistical fortitude and a penchant for reveling in the unexpected, we invite our readers to delve into this curiously charming nexus of Utah's quirks, Republican proclivities, and Surinamese energy whims.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

METHODOLOGY

Data Collection and Variables
In this study, we meticulously assembled an eclectic assortment of variables from diverse sources, akin to a connoisseur curating a gourmet feast of statistical delicacies. Our team harnessed the rich repositories of the MIT Election Data and Science Lab, where political data flourishes like a well-tended garden of electoral intrigue. Nestled within this cornucopia of information, we plucked the variable representing Republican votes for Senators in Utah, eager to scrutinize the nuanced oscillations of political allegiance across the years.

For our energy-related counterpart, we ventured into the Harvard Dataverse and the Energy Information Administration's treasure trove, akin to intrepid explorers foraging for sustenance in the wilds of statistical abundance. From this bounty, we extracted the fossil fuel consumption data for the enigmatic nation of Suriname, its energy proclivities akin to a dance of statistical electrons pirouetting within our analytical framework.

Variables were selected with the discernment of an art connoisseur admiring the brushstrokes of a master painter, bearing in mind an array of considerations such as temporal coverage, reliability, and a hint of serendipity to enliven our statistical narrative.

Statistical Analysis
To unravel the enigmatic tapestry of correlations that seemed to interlace Republican votes in a US state and fossil fuel use in a South American nation, we employed a medley of statistical techniques akin to a symphony conductor orchestrating a harmonious ensemble of empirical inquiry. Our journey through the labyrinth of statistical inference commenced with the calculation of the correlation coefficient, which emerged from the data like a genial apparition beckoning us towards deeper analytical waters.

Having nudged this correlation coefficient into the limelight, we then scrutinized it for statistical significance, akin to a discerning critic appraising the merits of an avant-garde piece of empirical art. The p-value, an elusive yet pivotal statistic in the grand opera of hypothesis testing, enraptured us with its seductive allure as it shimmered tantalizingly below the revered threshold of 0.01, beckoning to us like a celestial dance of statistical significance.

Moreover, we performed robustness checks, akin to stress-testing the infrastructure of our statistical edifice, to ascertain the durability of our findings under varying analytical conditions. Sensitivity analyses were conducted with the meticulousness of a jeweler examining the facets of a rare gem, ensuring that our results stood firm against the caprices of alternative specifications and modeling choices.

Through the symphonic interplay of statistical analyses, our aim was not only to establish a robust empirical relationship but also to infuse an element of levity into the often staid proceedings of scholarly inquiry, akin to a whimsical clown cavorting in the hallowed halls of statistical academia.

In the subsequent section, we shall expound upon the prodigious findings of our statistical odyssey, revealing the unexpected kinship between Utah's political predilections and Suriname's energy whims, thereby shedding light on the quirky correlation that animates this transcontinental statistical ballet.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 1980 to 2018, you found a correlation 0.8725118, r-squared of 0.7612769, 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]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
Politics and energy usage have always been two areas of great fascination for researchers seeking to unravel the enigmatic and often inscrutable patterns underlying human behavior and societal dynamics. The confluence of Utah's conservative political landscape and Suriname's fossil fuel consumption presents an alluring paradox, akin to a statistical riddle wrapped in a tantalizing mystery inside a data-driven enigma. As researchers, we have long been accustomed to delving into the depths of correlation matrices and regression analyses, akin to intrepid explorers venturing into uncharted statistical territory. The quirks and idiosyncrasies of our findings, akin to unexpected pops of color in a grayscale dataset, have left us both bemused and intrigued, akin to stumbling upon a gaggle of penguins in the desert.
In this study, we set out to examine the peculiar connection between Republican votes for Senators in Utah and fossil fuel use in Suriname, seeking to unearth the hidden threads spun by the statistical loom that weave together these seemingly disparate variables. Drawing upon the expanse of political data from the esteemed MIT Election Data and Science Lab, along with the troves of energy statistics housed within the Harvard Dataverse and the Energy Information Administration, our research endeavors endeavored to unpack the underlying concatenation of factors that bind together the electoral leanings of a US state and the energy proclivities of a South American nation.
The allure of this research lies not only in the statistical acrobatics undertaken to establish a robust empirical relationship but also in the whimsical nature of the relationship itself. As we waded through seas of data, traversing the tenebrous realm of statistical significance, we stumbled upon a correlation coefficient of 0.8725118, which loomed over us like an unexpected apparition in the halls of academe. With a p-value that shimmered seductively below the acclaimed threshold of 0.01, our findings beckoned to us like a siren's call, tempting us to unravel the mysteries that lay within the labyrinthine corridors of statistical inference.
While our pursuit may appear far-fetched to the uninitiated, our statistical foray into these seemingly incongruous domains of political preference and energy consumption has yielded findings that not only confound conventional wisdom but also infuse an element of levity into the oftentimes solemn realm of academic inquiry. As we unveil the whimsical tendrils that bind these divergent variables, we invite our readers to join us in this mirthful jaunt through the juncture where Republican votes and fossil fuel usage converge, offering a respite from the rigors of conventional scholarship and a peek into the serendipitous caprices of empirical inquiry.
In the subsequent sections of this paper, we shall embark upon a detailed exegesis of the methodology employed, the intricacies of the data analyzed, the robustness of the statistical models constructed, and the implications of our findings. Thus, armed with a hearty dose of statistical fortitude and a penchant for reveling in the unexpected, we invite our readers to delve into this curiously charming nexus of Utah's quirks, Republican proclivities, and Surinamese energy whims.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a noteworthy correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. For the time period spanning 1980 to 2018, the correlation coefficient was found to be 0.8725118, indicating a strong positive relationship between these seemingly unrelated variables. The r-squared value of 0.7612769 further substantiates this robust association, explaining approximately 76.13% of the variance in fossil fuel use in Suriname based on Republican votes in Utah.

The p-value, an esteemed guest in the realm of statistical significance, gracefully danced below the conventional threshold of 0.01, affirming the legitimacy of the observed relationship. Our findings exude a delightful whimsy, akin to discovering a hidden Easter egg in a labyrinthine statistical landscape, and beckon further exploration to unravel the delightful intricacies of these peculiar associations.

Directing attention to Figure 1, we proudly present a scatterplot that graphically illustrates the marked correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. This depiction encapsulates the essence of our research endeavors, encapsulating the unexpected fusion of these variables in a visually compelling manner.

In summary, our findings not only unravel the enigmatic connection between these seemingly incongruent factors but also underscore the capricious nature of empirical inquiry, infusing an element of levity into the conventional milieu of statistical exploration.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

[[LITERATURE REVIEW]]
The connection between Republican votes for Senators in Utah and fossil fuel use in Suriname has garnered limited attention in prior research. However, the few existing studies provide valuable insights into this quirky correlation. Smith et al. (2015) offer a comprehensive analysis of political voting patterns in Utah, shedding light on the historic dominance of Republican candidates in statewide elections. Meanwhile, Doe and Jones (2017) delve into the intricate web of fossil fuel consumption trends in Suriname, providing a nuanced understanding of the country's energy dynamics.
Moving beyond strictly academic sources, "Energy Politics" by Williams (2018) explores the sociopolitical ramifications of fossil fuel utilization in developing nations. In a similar vein, "The Grand Old Party" by Thompson (2019) offers a compelling narrative of the Republican Party's influence in American politics. These works, while not directly addressing the specific correlation of interest, contribute to a broader contextual understanding of the intersecting domains of political affiliations and energy utilization.
Expanding into the realm of fiction, the works of J.K. Rowling, particularly the "Harry Potter" series, may seem distant from the focal point of this study. However, the themes of power struggles and allegiances present in these novels bear a curious resemblance to the dynamics of political voting. Similarly, "Oil and Water" by Robinson (2016) weaves a tale of unexpected connections, much like the improbable correlation under investigation.
Venturing into more unconventional sources, it is worth noting that the back covers of shampoo bottles, though not typically recognized as scholarly literature, provide a surprising trove of information. Suspiciously smooth prose and grandiose claims adorn these containers, often promising transformative effects akin to the monumental shifts in senatorial voting and fossil fuel use. Although not rigorously peer-reviewed, these sources warrant acknowledgment for their strangely captivating narratives and unanticipated correlations.
Through this eclectic review, the authors find a blend of insightful scholarship, whimsical fiction, and unexpected sources that collectively inform the foundation of this study. As we delve deeper into our own analysis, we aim to build upon this diverse array of influences and unravel the enigmatic connection between Republican votes and fossil fuel use, guided by a spirit of scholarly inquiry and a dash of irreverent curiosity.

[[RESULTS]]
The statistical analysis revealed a noteworthy correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. For the time period spanning 1980 to 2018, the correlation coefficient was found to be 0.8725118, indicating a strong positive relationship between these seemingly unrelated variables. The r-squared value of 0.7612769 further substantiates this robust association, explaining approximately 76.13% of the variance in fossil fuel use in Suriname based on Republican votes in Utah.
The p-value, an esteemed guest in the realm of statistical significance, gracefully danced below the conventional threshold of 0.01, affirming the legitimacy of the observed relationship. Our findings exude a delightful whimsy, akin to discovering a hidden Easter egg in a labyrinthine statistical landscape, and beckon further exploration to unravel the delightful intricacies of these peculiar associations.
Directing attention to Figure 1, we proudly present a scatterplot that graphically illustrates the marked correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. This depiction encapsulates the essence of our research endeavors, encapsulating the unexpected fusion of these variables in a visually compelling manner.
In summary, our findings not only unravel the enigmatic connection between these seemingly incongruent factors but also underscore the capricious nature of empirical inquiry, infusing an element of levity into the conventional milieu of statistical exploration.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study extraordinarily corroborate the insights gleaned from prior research, affirming the unlikely yet captivating relationship between Republican votes for Senators in Utah and fossil fuel use in Suriname. Our results, with a correlation coefficient of 0.8725118 and a p-value of less than 0.01, provide compelling evidence that this quirky correlation is not just a statistical fluke but a substantial and robust phenomenon.

Drawing on the literature review's whimsical sources, our study aligns with the concept of unexpected connections in "Oil and Water" by Robinson. Additionally, the power struggles and allegiances portrayed in J.K. Rowling's "Harry Potter" series echo the intricate dynamics evident in our findings, showcasing the enchanting resemblance between magical narratives and statistical analyses.

The scatterplot in Figure 1 is a visual delight, akin to discovering a rare Pokémon in the wilderness of data visualization. This graphical representation not only captures the essence of our findings but also serves as a testament to the unexpected fusion of variables, reminiscent of a serendipitous encounter in a statistical safari.

Our study emphasizes the capricious nature of empirical inquiry, akin to embarking on a delightful scavenger hunt through the vast expanse of statistical landscapes. Just as the back covers of shampoo bottles offer surprising narratives, our research unravels an enigmatic connection that transcends the boundaries of conventional statistical relationships, embodying the spirit of irreverent curiosity.

In conclusion, the peculiar correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname not only adds a touch of whimsy to the world of statistical exploration but also underscores the delightful intricacies and unexpected correlations that infuse scholarly inquiry with a dash of unanticipated charm.


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 Republican votes for Senators in Utah and Fossil fuel use in Suriname. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation"

[[ABSTRACT]]
This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

[[INTRDUCTION]]
Introduction
Politics and energy usage have always been two areas of great fascination for researchers seeking to unravel the enigmatic and often inscrutable patterns underlying human behavior and societal dynamics. The confluence of Utah's conservative political landscape and Suriname's fossil fuel consumption presents an alluring paradox, akin to a statistical riddle wrapped in a tantalizing mystery inside a data-driven enigma. As researchers, we have long been accustomed to delving into the depths of correlation matrices and regression analyses, akin to intrepid explorers venturing into uncharted statistical territory. The quirks and idiosyncrasies of our findings, akin to unexpected pops of color in a grayscale dataset, have left us both bemused and intrigued, akin to stumbling upon a gaggle of penguins in the desert.
In this study, we set out to examine the peculiar connection between Republican votes for Senators in Utah and fossil fuel use in Suriname, seeking to unearth the hidden threads spun by the statistical loom that weave together these seemingly disparate variables. Drawing upon the expanse of political data from the esteemed MIT Election Data and Science Lab, along with the troves of energy statistics housed within the Harvard Dataverse and the Energy Information Administration, our research endeavors endeavored to unpack the underlying concatenation of factors that bind together the electoral leanings of a US state and the energy proclivities of a South American nation.
The allure of this research lies not only in the statistical acrobatics undertaken to establish a robust empirical relationship but also in the whimsical nature of the relationship itself. As we waded through seas of data, traversing the tenebrous realm of statistical significance, we stumbled upon a correlation coefficient of 0.8725118, which loomed over us like an unexpected apparition in the halls of academe. With a p-value that shimmered seductively below the acclaimed threshold of 0.01, our findings beckoned to us like a siren's call, tempting us to unravel the mysteries that lay within the labyrinthine corridors of statistical inference.
While our pursuit may appear far-fetched to the uninitiated, our statistical foray into these seemingly incongruous domains of political preference and energy consumption has yielded findings that not only confound conventional wisdom but also infuse an element of levity into the oftentimes solemn realm of academic inquiry. As we unveil the whimsical tendrils that bind these divergent variables, we invite our readers to join us in this mirthful jaunt through the juncture where Republican votes and fossil fuel usage converge, offering a respite from the rigors of conventional scholarship and a peek into the serendipitous caprices of empirical inquiry.
In the subsequent sections of this paper, we shall embark upon a detailed exegesis of the methodology employed, the intricacies of the data analyzed, the robustness of the statistical models constructed, and the implications of our findings. Thus, armed with a hearty dose of statistical fortitude and a penchant for reveling in the unexpected, we invite our readers to delve into this curiously charming nexus of Utah's quirks, Republican proclivities, and Surinamese energy whims.

[[RESULTS]]
The statistical analysis revealed a noteworthy correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. For the time period spanning 1980 to 2018, the correlation coefficient was found to be 0.8725118, indicating a strong positive relationship between these seemingly unrelated variables. The r-squared value of 0.7612769 further substantiates this robust association, explaining approximately 76.13% of the variance in fossil fuel use in Suriname based on Republican votes in Utah.
The p-value, an esteemed guest in the realm of statistical significance, gracefully danced below the conventional threshold of 0.01, affirming the legitimacy of the observed relationship. Our findings exude a delightful whimsy, akin to discovering a hidden Easter egg in a labyrinthine statistical landscape, and beckon further exploration to unravel the delightful intricacies of these peculiar associations.
Directing attention to Figure 1, we proudly present a scatterplot that graphically illustrates the marked correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. This depiction encapsulates the essence of our research endeavors, encapsulating the unexpected fusion of these variables in a visually compelling manner.
In summary, our findings not only unravel the enigmatic connection between these seemingly incongruent factors but also underscore the capricious nature of empirical inquiry, infusing an element of levity into the conventional milieu of statistical exploration.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research unearths a whimsical correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname, akin to discovering a lively conga line at a solemn academic soirée. The robust correlation coefficient of 0.8725118, with a p-value reminiscent of a well-behaved specter lingering below the revered threshold of 0.01, beckons to us like a well-executed punchline in the comedy of statistical analysis. The r-squared value of 0.7612769 adds an exclamation point to this unlikely union, much like an unexpected pun punctuating a droll discourse.

As we reflect on these findings, we cannot help but marvel at the curious caprices of empirical inquiry, reminiscent of a jester's jest amid the stately court of statistical exploration. Our study not only sheds light on this quixotic relationship but also brings a touch of levity to the staid corridors of academic scholarship.

In light of our findings, we assert with a wink and a nod that further research in this area is akin to beating a dead horse in a statistical stable—unnecessary and potentially hazardous to one's academic reputation. Our endeavor stands as a beacon of mirthful inquiry, urging fellow researchers to embrace the delightful quirks and serendipitous associations that enliven the often sober landscape of empirical investigation.

No further statistical acrobatics are warranted to substantiate this whimsical connection, for the evidence is as clear as the nose on a principal component's face—much to the chagrin of the uninitiated. With a metaphorical tip of our academic hats, we bid adieu to this unlikely yet charming dalliance between Republican votes and Surinamese energy proclivities, leaving it as a testament to the unpredictable and jovial nature of empirical scholarship.


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 Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unusual 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 Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Data 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 Republican Votes, Fossil Fuels, and Utah's Quirks: A Quirky Correlation with an abstract of This study sought to uncover the quirky correlation between Republican votes for Senators in Utah and fossil fuel use in Suriname. Leveraging data from MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delved into this unlikely connection. The findings revealed a correlation coefficient of 0.8725118 and p < 0.01 for the years 1980 to 2018. Our work not only sheds light on this surprising relationship but also highlights the whimsical aspects of electoral and energy dynamics.

ChatGPT:

Republican votes, Utah Senators, fossil fuel usage, Suriname, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, electoral dynamics, energy dynamics.

*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 Republican Senators in Utah
Detailed data title: Total number of votes cast for Federal Republican Senate candidates in Utah
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Republican Senators in Utah

Fossil fuel use in Suriname
Detailed data title: Total fossil fuel use in Suriname in billion kWh
Source: Energy Information Administration
See what else correlates with Fossil fuel use in Suriname

Correlation r = 0.8725118 (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 = 0.7612769 (Coefficient of determination)
This means 76.1% of the change in the one variable (i.e., Fossil fuel use in Suriname) is predictable based on the change in the other (i.e., Votes for Republican Senators in Utah) over the 14 years from 1980 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.7E-5. 0.0000468390326697442200000000
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 0.87 in 0.0047% of random cases. Said differently, if you correlated 21,350 random variables You don't actually need 21 thousand variables to find a correlation like this one. 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.

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 13 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.64, 0.96 ] 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.
19801982198619881992199419982000200420062010201220162018
Votes for Republican Senators in Utah (Total votes)437675309332314608430089420069357297316652504803626640356238360403657608760220665215
Fossil fuel use in Suriname (Billion kWh)0.6410.2530.4110.4020.2890.3070.1270.6870.6930.7010.483161.070661.117660.88266




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




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([437675,309332,314608,430089,420069,357297,316652,504803,626640,356238,360403,657608,760220,665215,])
array_2 = np.array([0.641,0.253,0.411,0.402,0.289,0.307,0.127,0.687,0.693,0.701,0.48316,1.07066,1.11766,0.88266,])
array_1_name = "Votes for Republican Senators in Utah"
array_2_name = "Fossil fuel use in Suriname"

# 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?

Your correlation inspection deserves a standing ovation!


Correlation ID: 4412 · Black Variable ID: 26323 · Red Variable ID: 24004
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0