about · email me · subscribe
Spurious correlation #4,408 · 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 Libertarian Presidential candidate in Indiana and the second variable is Petroluem consumption in Mozambique.  The chart goes from 1980 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As more people in Indiana showed support for the Libertarian candidate, it sparked a wave of interest in individual freedom and self-reliance. This unconventional enthusiasm sent ripples of independence across the globe, reaching all the way to Mozambique. Inspired by the idea of self-governing and non-intervention, the people of Mozambique decided to express their own personal liberty by taking spontaneous road trips, leading to a surge in petroleum consumption. Who knew that the road to political change could also be the one paved with...well, more road trips!

Model: dalle-3
Prompt: Prompt: Generate an image of a vibrant cyber folk festival in Indiana, with people voting for the Libertarian Presidential candidate, while in the background, individuals from Mozambique are shown embracing self-governing ideas and embarking on spontaneous road trips, resulting in increased petroleum consumption. The scene should convey a sense of personal freedom, self-reliance, and cultural exchange between the two communities. 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 Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. 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: Photorealism Cyber folk Vaporwave Brutalism Hyper-realistic
ChatGPT: Cyber folk

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 Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique, in the following situation: As more people in Indiana showed support for the Libertarian candidate, it sparked a wave of interest in individual freedom and self-reliance. This unconventional enthusiasm sent ripples of independence across the globe, reaching all the way to Mozambique. Inspired by the idea of self-governing and non-intervention, the people of Mozambique decided to express their own personal liberty by taking spontaneous road trips, leading to a surge in petroleum consumption. Who knew that the road to political change could also be the one paved with...well, more road trips!. Keep the description simple.
ChatGPT: In Indiana, more people than ever cast their votes for the Libertarian Presidential candidate. This sparked a surge of interest in individual freedom and self-reliance. As a result, the people of Mozambique became inspired by this idea of self-governing and non-intervention. Promptly, they decided to express their own personal freedom by embarking on spontaneous road trips, resulting in a noticeable surge in petroleum consumption.

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: [ Cyber folk ] and depicting this scene: In Indiana, more people than ever cast their votes for the Libertarian Presidential candidate. This sparked a surge of interest in individual freedom and self-reliance. As a result, the people of Mozambique became inspired by this idea of self-governing and non-intervention. Promptly, they decided to express their own personal freedom by embarking on spontaneous road trips, resulting in a noticeable surge in petroleum consumption. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image of a vibrant cyber folk festival in Indiana, with people voting for the Libertarian Presidential candidate, while in the background, individuals from Mozambique are shown embracing self-governing ideas and embarking on spontaneous road trips, resulting in increased petroleum consumption. The scene should convey a sense of personal freedom, self-reliance, and cultural exchange between the two communities.

*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 Votes for the Libertarian Presidential candidate in Indiana caused Petroluem consumption in Mozambique to increase.

AI academic paper

(Because p < 0.01)
Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique

The Journal of Zany Cross-Cultural Studies

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

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 0.9566517 and p < 0.01 for 1980 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]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Political preferences and energy consumption are not typically associated with one another, yet in the world of data analysis, surprising connections often emerge. Our research sets out to uncover the perplexing link between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, spanning the years 1980 to 2020. Despite the geographical and cultural chasm between these two entities, the data led us down a convoluted path that traversed continents and ideologies, ultimately bringing us to a compelling revelation.

While the initial premise of this investigation may seem whimsical, our journey into the depths of data proved to be anything but a jolly romp. Armed with datasets from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, we embarked on an intellectual odyssey that tested the limits of statistical analysis and our own resolve. The correlation coefficient, a steadfast guide in our pursuit, waltzed its way to a seemingly remarkable 0.9566517, leaving us in a state of stupefaction. Furthermore, the p-value, that elusive measure of significance, whispered to us in insignificance at <0.01, bringing with it a sense of wonder usually reserved for quantum mechanics and exceptionally fluffy kittens.

As we waded through the sea of numbers, charts, and regression analyses, we couldn't help but marvel at the enigmatic nature of statistics; as if peering into the intricacies of human behavior and global forces. Amidst the cold, hard numbers, we found ourselves entertained by the dance of causality and correlation, a spectacle that left us feeling much like spectators at a particularly perplexing ballet performance – unsure of the steps, but enthralled by the graceful movements unfolding before us.

Join us as we unravel this curious entanglement of political proclivities and energy appetites, where the ballot box and the gas pump converge in a dance of statistical significance that challenges our preconceptions and leaves us with a sense of awe at the mysteries that data often uncovers.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. 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 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]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Political preferences and energy consumption are not typically associated with one another, yet in the world of data analysis, surprising connections often emerge. Our research sets out to uncover the perplexing link between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, spanning the years 1980 to 2020. Despite the geographical and cultural chasm between these two entities, the data led us down a convoluted path that traversed continents and ideologies, ultimately bringing us to a compelling revelation.
While the initial premise of this investigation may seem whimsical, our journey into the depths of data proved to be anything but a jolly romp. Armed with datasets from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, we embarked on an intellectual odyssey that tested the limits of statistical analysis and our own resolve. The correlation coefficient, a steadfast guide in our pursuit, waltzed its way to a seemingly remarkable 0.9566517, leaving us in a state of stupefaction. Furthermore, the p-value, that elusive measure of significance, whispered to us in insignificance at <0.01, bringing with it a sense of wonder usually reserved for quantum mechanics and exceptionally fluffy kittens.
As we waded through the sea of numbers, charts, and regression analyses, we couldn't help but marvel at the enigmatic nature of statistics; as if peering into the intricacies of human behavior and global forces. Amidst the cold, hard numbers, we found ourselves entertained by the dance of causality and correlation, a spectacle that left us feeling much like spectators at a particularly perplexing ballet performance – unsure of the steps, but enthralled by the graceful movements unfolding before us.
Join us as we unravel this curious entanglement of political proclivities and energy appetites, where the ballot box and the gas pump converge in a dance of statistical significance that challenges our preconceptions and leaves us with a sense of awe at the mysteries that data often uncovers.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Our investigation into the fascinating nexus of political inclinations and energy utilization takes us on a whimsical jaunt through an array of scholarly works, each offering unique perspectives on seemingly unrelated domains. Smith et al. (2015) delve into the intricacies of electoral behavior, providing insights into the labyrinthine world of voting trends, while Doe (2017) grapples with the multifaceted nature of energy consumption in emerging economies. It is amidst this serious discourse that we stumble upon unexpected bedfellows in the form of non-fiction tomes such as "The Energy Transition" by Jones (2019) and "Political Polarization in America" by Patel (2018).

As we venture further into the literary cosmos, we encounter an array of engaging and marginally relevant works that tickle our scholarly fancies. Titles like "Oil, Politics, and Power: The World's Petroleum Industry" by Green (2005) and "The Libertarian Manifesto" by Gold (2008) draw our attention with promises of elucidating the complexities of petroleum and political ideologies. However, it is the whimsical world of fiction that truly captures our hearts and occasionally leads us astray. The pages of "Petrolhead Chronicles" by White (2016) and "Election Escapades" by Black (2012) offer literary diversions that, while ostensibly unrelated to our scholarly pursuits, never fail to infuse our days with doses of levity.

In our quest for understanding the unexpected connection between American electoral choices and Mozambican energy patterns, we are compelled to peek into more unconventional sources. Cartoons such as "The Adventures of Captain Petrol" and children's shows like "The Petrol Pals" make their way into our research toolkit, offering unexpected insights into the delightful yet confounding intersection of transcontinental voting proclivities and petroleum predilections.

As we navigate this charmingly zany voyage through the annals of literature, we find ourselves embracing the unconventional and relishing the playful detours that our scholarly pursuits unveil. Join us on this academic escapade, where serious inquiry and scholarly whimsy collide in a dance as enigmatic and entertaining as the correlation we seek to unravel.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1980 to 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]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

[[INTRODUCTION]]
Political preferences and energy consumption are not typically associated with one another, yet in the world of data analysis, surprising connections often emerge. Our research sets out to uncover the perplexing link between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, spanning the years 1980 to 2020. Despite the geographical and cultural chasm between these two entities, the data led us down a convoluted path that traversed continents and ideologies, ultimately bringing us to a compelling revelation.
While the initial premise of this investigation may seem whimsical, our journey into the depths of data proved to be anything but a jolly romp. Armed with datasets from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, we embarked on an intellectual odyssey that tested the limits of statistical analysis and our own resolve. The correlation coefficient, a steadfast guide in our pursuit, waltzed its way to a seemingly remarkable 0.9566517, leaving us in a state of stupefaction. Furthermore, the p-value, that elusive measure of significance, whispered to us in insignificance at <0.01, bringing with it a sense of wonder usually reserved for quantum mechanics and exceptionally fluffy kittens.
As we waded through the sea of numbers, charts, and regression analyses, we couldn't help but marvel at the enigmatic nature of statistics; as if peering into the intricacies of human behavior and global forces. Amidst the cold, hard numbers, we found ourselves entertained by the dance of causality and correlation, a spectacle that left us feeling much like spectators at a particularly perplexing ballet performance – unsure of the steps, but enthralled by the graceful movements unfolding before us.
Join us as we unravel this curious entanglement of political proclivities and energy appetites, where the ballot box and the gas pump converge in a dance of statistical significance that challenges our preconceptions and leaves us with a sense of awe at the mysteries that data often uncovers.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To untangle the confounding web of factors that connect votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, our research team delved into a meticulous and at times convoluted methodology that involved a wide array of data collection and analysis techniques.

Data Collection:
We sourced our data from various reputable sources, including the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration. The Indiana election data was meticulously scoured from the MIT Election Data and Science Lab, providing a rich and comprehensive dataset of presidential voting trends from 1980 to 2020. To complement this, we accessed petroleum consumption data from Mozambique through the Energy Information Administration, ensuring that we had a detailed and expansive representation of energy usage over the same time period.

Normalization and Standardization:
Given the disparate nature of the data sources and the divergent scales of measurement, our team employed a series of normalization and standardization techniques to ensure that the variables were harmonized for meaningful analysis. This involved converting the voting percentages to z-scores and manipulating the petroleum consumption data to align with the distribution of votes for the Libertarian candidate.

Statistical Analysis:
The heart of our methodology lay in the application of advanced statistical techniques to decipher the relationship between these seemingly unrelated variables. We conducted a series of regression analyses, including simple linear regression and multiple regression models, to assess the strength and direction of the association between votes for the Libertarian candidate in Indiana and petroleum consumption in Mozambique. Additionally, we calculated correlation coefficients and p-values to gauge the significance and consistency of the observed relationship.

Robustness Checks:
To ensure the robustness of our findings, we subjected the data to various sensitivity analyses, exploring different time intervals and controlling for potential confounding variables such as geopolitical events and economic trends. This rigorous process allowed us to gauge the stability and reliability of the observed patterns, safeguarding against spurious correlations and misleading inferences.

While the path we traversed in this methodology may have been arduous and at times labyrinthine, the fruits of our labor culminated in a comprehensive understanding of the enigmatic connection between political votes in the heartland of America and the energy appetite of a nation across the Atlantic. We emerged from this methodological journey with a newfound appreciation for the complexities of data analysis and a profound sense of intrigue at the peculiar connections that statistical exploration often unveils.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1980 to 2020, you found a correlation 0.9566517, r-squared of 0.9151825, 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]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Political preferences and energy consumption are not typically associated with one another, yet in the world of data analysis, surprising connections often emerge. Our research sets out to uncover the perplexing link between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, spanning the years 1980 to 2020. Despite the geographical and cultural chasm between these two entities, the data led us down a convoluted path that traversed continents and ideologies, ultimately bringing us to a compelling revelation.
While the initial premise of this investigation may seem whimsical, our journey into the depths of data proved to be anything but a jolly romp. Armed with datasets from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, we embarked on an intellectual odyssey that tested the limits of statistical analysis and our own resolve. The correlation coefficient, a steadfast guide in our pursuit, waltzed its way to a seemingly remarkable 0.9566517, leaving us in a state of stupefaction. Furthermore, the p-value, that elusive measure of significance, whispered to us in insignificance at <0.01, bringing with it a sense of wonder usually reserved for quantum mechanics and exceptionally fluffy kittens.
As we waded through the sea of numbers, charts, and regression analyses, we couldn't help but marvel at the enigmatic nature of statistics; as if peering into the intricacies of human behavior and global forces. Amidst the cold, hard numbers, we found ourselves entertained by the dance of causality and correlation, a spectacle that left us feeling much like spectators at a particularly perplexing ballet performance – unsure of the steps, but enthralled by the graceful movements unfolding before us.
Join us as we unravel this curious entanglement of political proclivities and energy appetites, where the ballot box and the gas pump converge in a dance of statistical significance that challenges our preconceptions and leaves us with a sense of awe at the mysteries that data often uncovers.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The primary focus of our investigation was to discern the perplexing correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique from 1980 to 2020. After an arduous but intellectually invigorating analysis, our research team unearthed a correlation coefficient of 0.9566517, with an r-squared value of 0.9151825 and a p-value that prompted exclamations of statistical significance at < 0.01. The correlation observed is visually represented in Figure 1, which displays a scatterplot showcasing the resolute relationship between these seemingly unrelated variables.

The robust correlation between these two disparate entities leaves us in a state of scholarly bewilderment, akin to stumbling upon a treasure trove of statistical intrigue. The statistical significance of our findings is not lost on us, and we are left pondering the profound implications of a relationship so unexpected it rivals the plot twists of a mystery novel.

As with any groundbreaking discovery, our findings invite further examination and discussion, piquing the curiosity of both data aficionados and skeptics alike. The connection between votes cast in a landlocked state of the United States and the energy consumption patterns of a nation on the southeastern coast of Africa is an intellectual enigma that demands attention.

In conclusion, our research has unearthed a correlation so compelling, it's almost as if the ballot box and the gas pump are engaged in a dance of statistical importance that challenges conventional wisdom and beckons us to delve deeper into the mysteries that data often unravels. Join us as we venture into the whimsical world of statistical significance, where the seemingly unrelated realms of American politics and Mozambican energy preferences converge in an unlikely pas de deux that defies easy explanation but yields a newfound appreciation for the intricate dance of causality and correlation.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

[[LITERATURE REVIEW]]
Our investigation into the fascinating nexus of political inclinations and energy utilization takes us on a whimsical jaunt through an array of scholarly works, each offering unique perspectives on seemingly unrelated domains. Smith et al. (2015) delve into the intricacies of electoral behavior, providing insights into the labyrinthine world of voting trends, while Doe (2017) grapples with the multifaceted nature of energy consumption in emerging economies. It is amidst this serious discourse that we stumble upon unexpected bedfellows in the form of non-fiction tomes such as "The Energy Transition" by Jones (2019) and "Political Polarization in America" by Patel (2018).
As we venture further into the literary cosmos, we encounter an array of engaging and marginally relevant works that tickle our scholarly fancies. Titles like "Oil, Politics, and Power: The World's Petroleum Industry" by Green (2005) and "The Libertarian Manifesto" by Gold (2008) draw our attention with promises of elucidating the complexities of petroleum and political ideologies. However, it is the whimsical world of fiction that truly captures our hearts and occasionally leads us astray. The pages of "Petrolhead Chronicles" by White (2016) and "Election Escapades" by Black (2012) offer literary diversions that, while ostensibly unrelated to our scholarly pursuits, never fail to infuse our days with doses of levity.
In our quest for understanding the unexpected connection between American electoral choices and Mozambican energy patterns, we are compelled to peek into more unconventional sources. Cartoons such as "The Adventures of Captain Petrol" and children's shows like "The Petrol Pals" make their way into our research toolkit, offering unexpected insights into the delightful yet confounding intersection of transcontinental voting proclivities and petroleum predilections.
As we navigate this charmingly zany voyage through the annals of literature, we find ourselves embracing the unconventional and relishing the playful detours that our scholarly pursuits unveil. Join us on this academic escapade, where serious inquiry and scholarly whimsy collide in a dance as enigmatic and entertaining as the correlation we seek to unravel.

[[RESULTS]]
The primary focus of our investigation was to discern the perplexing correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique from 1980 to 2020. After an arduous but intellectually invigorating analysis, our research team unearthed a correlation coefficient of 0.9566517, with an r-squared value of 0.9151825 and a p-value that prompted exclamations of statistical significance at < 0.01. The correlation observed is visually represented in Figure 1, which displays a scatterplot showcasing the resolute relationship between these seemingly unrelated variables.
The robust correlation between these two disparate entities leaves us in a state of scholarly bewilderment, akin to stumbling upon a treasure trove of statistical intrigue. The statistical significance of our findings is not lost on us, and we are left pondering the profound implications of a relationship so unexpected it rivals the plot twists of a mystery novel.
As with any groundbreaking discovery, our findings invite further examination and discussion, piquing the curiosity of both data aficionados and skeptics alike. The connection between votes cast in a landlocked state of the United States and the energy consumption patterns of a nation on the southeastern coast of Africa is an intellectual enigma that demands attention.
In conclusion, our research has unearthed a correlation so compelling, it's almost as if the ballot box and the gas pump are engaged in a dance of statistical importance that challenges conventional wisdom and beckons us to delve deeper into the mysteries that data often unravels. Join us as we venture into the whimsical world of statistical significance, where the seemingly unrelated realms of American politics and Mozambican energy preferences converge in an unlikely pas de deux that defies easy explanation but yields a newfound appreciation for the intricate dance of causality and correlation.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

In this discussion, we aim to delve into the captivating correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, a relationship that defies conventional boundaries and challenges our preconceived notions of causality. Our findings not only substantiate the prior research but also add a layer of statistical significance to the whimsical observations made in the literature review.

When reflecting on the lighthearted literature that opened unexpected doors to our scholarly pursuits, we find ourselves marveling at how seemingly tangential sources have inadvertently paved the way for our groundbreaking discovery. The whimsical detours into non-fiction works on energy transition and political polarization serve as intriguing backing for our findings. The offbeat allure of fiction and entertainment, such as "Petrolhead Chronicles" and "The Petrol Pals," unexpectedly add depth to our scholarly odyssey. These diversions eventually reinforce our appreciation for the unanticipated and prod us to explore the seemingly absurd with a newfound curiosity.

Our results, with a correlation coefficient bordering on the astonishing at 0.9566517, resonate with the narrative woven by previous discussions on the topic. The robustness of this correlation, underscored by an r-squared value of 0.9151825, amplifies the significance of the connection between American electoral proclivities and Mozambican energy consumption. As the empirical evidence triumphantly aligns with the playful inspirations drawn from the literature review, we are left with no choice but to acknowledge the unexpected and, dare I say, delightfully ludicrous nature of this correlation.

Like uncovering the final plot twist in a captivating mystery novel, our research has led us to a revelatory juncture. The correlation between votes cast in Indiana and the energy preferences of Mozambique, while initially whimsical in its proposal, has led us to the solemn realization that even the most unexpected connections can be grounded in statistical import. It's almost as if the statistical dance of these seemingly unrelated variables transverses continents and defies conventional boundaries with an irreverent and enigmatic flair.

With our findings, we tacitly dare future scholars to embrace the unconventional and relish in the serendipitous discoveries that await in the scholarly cosmos. The improbable union of American politics and Mozambican energy choices, far from being an anomaly, serves as a whimsical reminder that the correlation coefficient is, in fact, mightier than the sword, and can, quite unexpectedly, unite the seemingly unconnected in a dance of statistical enchantment.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Libertarian Presidential candidate in Indiana and Petroluem consumption in Mozambique. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique"

[[ABSTRACT]]
This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

[[INTRDUCTION]]
Political preferences and energy consumption are not typically associated with one another, yet in the world of data analysis, surprising connections often emerge. Our research sets out to uncover the perplexing link between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique, spanning the years 1980 to 2020. Despite the geographical and cultural chasm between these two entities, the data led us down a convoluted path that traversed continents and ideologies, ultimately bringing us to a compelling revelation.
While the initial premise of this investigation may seem whimsical, our journey into the depths of data proved to be anything but a jolly romp. Armed with datasets from the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, we embarked on an intellectual odyssey that tested the limits of statistical analysis and our own resolve. The correlation coefficient, a steadfast guide in our pursuit, waltzed its way to a seemingly remarkable 0.9566517, leaving us in a state of stupefaction. Furthermore, the p-value, that elusive measure of significance, whispered to us in insignificance at <0.01, bringing with it a sense of wonder usually reserved for quantum mechanics and exceptionally fluffy kittens.
As we waded through the sea of numbers, charts, and regression analyses, we couldn't help but marvel at the enigmatic nature of statistics; as if peering into the intricacies of human behavior and global forces. Amidst the cold, hard numbers, we found ourselves entertained by the dance of causality and correlation, a spectacle that left us feeling much like spectators at a particularly perplexing ballet performance – unsure of the steps, but enthralled by the graceful movements unfolding before us.
Join us as we unravel this curious entanglement of political proclivities and energy appetites, where the ballot box and the gas pump converge in a dance of statistical significance that challenges our preconceptions and leaves us with a sense of awe at the mysteries that data often uncovers.

[[RESULTS]]
The primary focus of our investigation was to discern the perplexing correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique from 1980 to 2020. After an arduous but intellectually invigorating analysis, our research team unearthed a correlation coefficient of 0.9566517, with an r-squared value of 0.9151825 and a p-value that prompted exclamations of statistical significance at < 0.01. The correlation observed is visually represented in Figure 1, which displays a scatterplot showcasing the resolute relationship between these seemingly unrelated variables.
The robust correlation between these two disparate entities leaves us in a state of scholarly bewilderment, akin to stumbling upon a treasure trove of statistical intrigue. The statistical significance of our findings is not lost on us, and we are left pondering the profound implications of a relationship so unexpected it rivals the plot twists of a mystery novel.
As with any groundbreaking discovery, our findings invite further examination and discussion, piquing the curiosity of both data aficionados and skeptics alike. The connection between votes cast in a landlocked state of the United States and the energy consumption patterns of a nation on the southeastern coast of Africa is an intellectual enigma that demands attention.
In conclusion, our research has unearthed a correlation so compelling, it's almost as if the ballot box and the gas pump are engaged in a dance of statistical importance that challenges conventional wisdom and beckons us to delve deeper into the mysteries that data often unravels. Join us as we venture into the whimsical world of statistical significance, where the seemingly unrelated realms of American politics and Mozambican energy preferences converge in an unlikely pas de deux that defies easy explanation but yields a newfound appreciation for the intricate dance of causality and correlation.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In traversing the labyrinth of data and statistical analysis, our study has unearthed a correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique that verges on the surreal. The robust correlation coefficient and p-value evoke a sense of wonder akin to stumbling upon a particularly elusive Easter egg in a digital maze. The interconnectedness between heartland politics and southeastern African energy preferences serves as a reminder that in the world of data, unexpected connections abound. As we bid adieu to this whirlwind exploration, we are left with a lingering sense of intrigue that rivals the allure of a cryptic crossword puzzle or a magician’s sleight of hand.

This research beckons us to consider the myriad influences that transcend geographical and cultural boundaries, reminding us that statistical dance partners can emerge from the unlikeliest of pairings. As we close this chapter, we are inclined to embrace the enchanting quirkiness of statistical analyses and cherish the pursuit of uncovering hidden links, even if they seem as unexpected as a penguin at a desert oasis.

In light of the resounding significance of our findings, we posit that further pursuit of this whimsical correlation may be akin to chasing a statistical unicorn. While the allure of unraveling such curiosities is undeniable, we dare to assert that the dance of causality and correlation between American political proclivities and Mozambican energy appetites has been unearthed with a conviction that further excavation may lead to the diminishment of enchanting mysteries. Thus, we advocate for accepting these findings with an amused nod to the capricious nature of statistical entanglements and assert that no more research is needed in this area.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Zany Cross-Cultural Studies


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 Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Global Energy Politics and Voter Behavior


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 Fuel the Vote: Exploring the Connection Between Votes for the Libertarian Presidential Candidate in Indiana and Petroleum Consumption in Mozambique with an abstract of This paper delves into the unlikely yet compelling relationship between political preferences in the American heartland and energy consumption in a distant African nation. Drawing upon comprehensive data sets from the prestigious MIT Election Data and Science Lab and Harvard Dataverse, along with the Energy Information Administration, our research team embarked on an intellectually exhilarating journey to disentangle the web of factors that underpin the correlation between votes for the Libertarian presidential candidate in Indiana and petroleum consumption in Mozambique. Our findings unveil a relationship so striking, it's almost as if the votes cast in the heartland carry the power to influence the energy preferences of a nation located halfway across the globe. With a correlation coefficient that practically screamed significance at 0.9566517 and a p-value so minuscule it left us in awe at < 0.01 over the period from 1980 to 2020, the evidence is nothing short of astonishing. As we navigate through the charts and regression analyses, we emerge with a newfound appreciation for the intricate dance of causality and correlation, and a sneaking suspicion that even in the world of data, mysteries often elude our understanding. So come, join us on this whimsical, scholarly journey, where the seemingly disparate domains of American politics and Mozambican petroleum consumption converge in a dance of statistical importance.

ChatGPT:

votes, Libertarian presidential candidate, Indiana, petroleum consumption, Mozambique, correlation, energy consumption, American politics, Mozambican petroleum, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, regression analysis, causality, statistical significance

*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 Libertarian Presidential candidate in Indiana
Detailed data title: Total votes cast for the Libertarian Presidential candidate in Indiana
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Libertarian Presidential candidate in Indiana

Petroluem consumption in Mozambique
Detailed data title: Volume of petroluem consumption consumed in Mozambique in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Petroluem consumption in Mozambique

Correlation r = 0.9566517 (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 = 0.9151825 (Coefficient of determination)
This means 91.5% of the change in the one variable (i.e., Petroluem consumption in Mozambique) is predictable based on the change in the other (i.e., Votes for the Libertarian Presidential candidate in Indiana) over the 10 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-5. 0.0000146586542194505950000000
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 0.96 in 0.0015% of random cases. Said differently, if you correlated 68,219 random variables You don't actually need 68 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 9 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 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.

[ 0.82, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
1980198419921996200020042008201220162020
Votes for the Libertarian Presidential candidate in Indiana (Total votes)1962767417936156321553018058292575011113399359232
Petroluem consumption in Mozambique (Million Barrels/Day)13126.884487.0844810.646510.96813.31117.513342.299130.2179




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([19627,6741,7936,15632,15530,18058,29257,50111,133993,59232,])
array_2 = np.array([13,12,6.88448,7.08448,10.6465,10.968,13.311,17.5133,42.2991,30.2179,])
array_1_name = "Votes for the Libertarian Presidential candidate in Indiana"
array_2_name = "Petroluem consumption in Mozambique"

# 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: 4408 · Black Variable ID: 25976 · Red Variable ID: 24717
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0