about · email me · subscribe
Spurious correlation #5,275 · 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 Republican Presidential candidate in Illinois and the second variable is Kerosene used in Eritrea.  The chart goes from 1994 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Some voters in Illinois were so fired up about the election that they decided to celebrate by hosting elaborate backyard barbecues. This led to a sudden surge in the demand for outdoor cooking equipment, including old-fashioned kerosene stoves. Unable to resist the temptation of grilled goodies, the people of Eritrea also embraced the barbecue trend, causing a run on kerosene supplies in their local markets. It seems like political preferences weren't the only thing sparking heated debates across continents! But in reality, these two events are likely completely unrelated, just a funny coincidence.

Model: dalle-3
Prompt: Generate an image of a bustling town square with a twist - on the left side, vibrant red, white, and blue decorations adorn buildings and people eagerly cast their ballots for the Republican Presidential candidate, while on the right side, a lively market scene unfolds with Eritrean locals happily using kerosene stoves for outdoor barbecues. The scene is filled with a cyber folk aesthetic, blending traditional elements with futuristic touches, such as holographic banners and digitally enhanced barbecue grills. 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 Republican Presidential candidate in Illinois and Kerosene used in Eritrea. 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: Concept art An image that looks like it is a scene from 'Star Wars' Symbolism Cyber folk Cute 2D animation
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 Republican Presidential candidate in Illinois and Kerosene used in Eritrea, in the following situation: Some voters in Illinois were so fired up about the election that they decided to celebrate by hosting elaborate backyard barbecues. This led to a sudden surge in the demand for outdoor cooking equipment, including old-fashioned kerosene stoves. Unable to resist the temptation of grilled goodies, the people of Eritrea also embraced the barbecue trend, causing a run on kerosene supplies in their local markets. It seems like political preferences weren't the only thing sparking heated debates across continents! But in reality, these two events are likely completely unrelated, just a funny coincidence.. Keep the description simple.
ChatGPT: In Illinois, voters enthusiastically cast their ballots for the Republican Presidential candidate, while in Eritrea, people eagerly utilized kerosene for their outdoor barbecues. The demand for kerosene stoves soared in both places, as the aroma of grilling food wafted through the air, sparking lively debates and discussions.

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 Illinois, voters enthusiastically cast their ballots for the Republican Presidential candidate, while in Eritrea, people eagerly utilized kerosene for their outdoor barbecues. The demand for kerosene stoves soared in both places, as the aroma of grilling food wafted through the air, sparking lively debates and discussions. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling town square with a twist - on the left side, vibrant red, white, and blue decorations adorn buildings and people eagerly cast their ballots for the Republican Presidential candidate, while on the right side, a lively market scene unfolds with Eritrean locals happily using kerosene stoves for outdoor barbecues. The scene is filled with a cyber folk aesthetic, blending traditional elements with futuristic touches, such as holographic banners and digitally enhanced barbecue grills.

*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 Republican Presidential candidate in Illinois caused Kerosene used in Eritrea to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea

The Journal of Eclectic Political Analysis

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Include a pun 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 0.9245507 and p < 0.01 for 1994 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]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior 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 Votes for the Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
**[[INTRODUCTION]]**

The intertwining of political forces and energy dynamics has long piqued the curiosity of researchers seeking to shed light on the complex relationships that underpin our global sociopolitical landscape. In this study, we embark on a peculiar journey that ties together votes for the Republican presidential candidate in Illinois with the enigmatic kerosene consumption in Eritrea. This unexpected coupling raises eyebrows, prompting us to delve into the intricacies of these seemingly unrelated phenomena.

As scholars in our respective fields, we are well aware of the myriad factors that shape political preferences and energy usage. However, the entanglement of these specific variables is as surprising as finding a light switch in a dark room; it illuminates the need to reevaluate our traditional understanding of the interplay between disparate domains. To address this curiosity, we have meticulously analyzed data spanning nearly three decades, employing robust statistical methodologies to unravel the enigma that lies at the nexus of Republican support and kerosene consumption.

Our investigation takes us down unexpected paths, akin to stumbling upon a hidden trail in a dense forest. The emergence of a remarkable correlation coefficient of 0.9245507 and a statistically significant p-value of less than 0.01 reveals a connection that is as bright and unmistakable as a beacon in the darkness. As we meander through the complexities of our findings, we remain poised to steer clear of premature causational assumptions, recognizing that correlation does not necessarily imply causation, in the same way that a lit match does not cause the sun to rise.

The implications of our discoveries extend beyond mere statistical fascination, much like an unexpected bonfire illuminating a midnight gathering. They prompt us to delve deeper into the intricate dance of political allegiance and energy utilization, inviting us to explore the interplay of geopolitical preferences and resource consumption with a renewed sense of curiosity. Our journey also underscores the importance of remaining open to unconventional connections, much like stumbling upon a surprising quirk in an ancient map that leads to uncharted territories.

In the pages that follow, we offer a luminescent account of our analytical journey, hoping to spark not only further research but also the imagination of our readers as we venture into the illuminating, albeit unexpected, intersection of political behavior 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 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 Republican Presidential candidate in Illinois and Kerosene used in Eritrea. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intertwining of political forces and energy dynamics has long piqued the curiosity of researchers seeking to shed light on the complex relationships that underpin our global sociopolitical landscape. In this study, we embark on a peculiar journey that ties together votes for the Republican presidential candidate in Illinois with the enigmatic kerosene consumption in Eritrea. This unexpected coupling raises eyebrows, prompting us to delve into the intricacies of these seemingly unrelated phenomena.
As scholars in our respective fields, we are well aware of the myriad factors that shape political preferences and energy usage. However, the entanglement of these specific variables is as surprising as finding a light switch in a dark room; it illuminates the need to reevaluate our traditional understanding of the interplay between disparate domains. To address this curiosity, we have meticulously analyzed data spanning nearly three decades, employing robust statistical methodologies to unravel the enigma that lies at the nexus of Republican support and kerosene consumption.
Our investigation takes us down unexpected paths, akin to stumbling upon a hidden trail in a dense forest. The emergence of a remarkable correlation coefficient of 0.9245507 and a statistically significant p-value of less than 0.01 reveals a connection that is as bright and unmistakable as a beacon in the darkness. As we meander through the complexities of our findings, we remain poised to steer clear of premature causational assumptions, recognizing that correlation does not necessarily imply causation, in the same way that a lit match does not cause the sun to rise.
The implications of our discoveries extend beyond mere statistical fascination, much like an unexpected bonfire illuminating a midnight gathering. They prompt us to delve deeper into the intricate dance of political allegiance and energy utilization, inviting us to explore the interplay of geopolitical preferences and resource consumption with a renewed sense of curiosity. Our journey also underscores the importance of remaining open to unconventional connections, much like stumbling upon a surprising quirk in an ancient map that leads to uncharted territories.
In the pages that follow, we offer a luminescent account of our analytical journey, hoping to spark not only further research but also the imagination of our readers as we venture into the illuminating, albeit unexpected, intersection of political behavior and energy dynamics.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The authors begin this literature review by examining the work of reputable scholars who have delved into the fascinating world of political behavior and energy consumption at the intersection of geopolitics. Smith (2015) presents a comprehensive analysis of voting patterns in the Midwest, shedding light on the underlying factors that drive support for Republican candidates in Illinois. In a similarly enlightening vein, Doe (2018) dissects the complex socio-economic dynamics of resource utilization in developing nations, offering a nuanced exploration of kerosene consumption in Eritrea. Building upon these foundations, Jones (2020) synthesizes the disparate strands of political allegiance and energy utilization, setting the stage for our own foray into this captivating territory.

Turning to non-fiction books, "Energy and Politics" by Green (2017) provides a thought-provoking examination of the intertwining forces of political decision-making and energy policies, offering valuable insights that resonate with the central themes of our research. Furthermore, "Global Trends in Kerosene Market" by Blue (2019) sheds light on the intricate dynamics of kerosene consumption across regions, laying a groundwork for the unexpected linkage we are unraveling.

Expanding our literary scope to the realm of fiction, the evocative work of A. Lightbringer's "The Illuminated Vote" captures the existential struggle of a political campaign manager grappling with the enigmatic allure of a kerosene lantern in a distant land, symbolizing the illumination of his candidate's prospects on the eve of an election. Similarly, the enigmatic tales of E. Flicker's "Kerosene Chronicles" transport readers to a world where the flickering flame of a kerosene lamp becomes a metaphor for the political intrigue and power struggles in a small Illinois town.

Venturing into the realm of social media, a tweet by @VoteLightGiver draws a captivating parallel between the fervent support for a political candidate and the burning desire for a reliable kerosene supply in rural communities, suggesting a deeply ingrained connection that extends beyond mere statistical correlations.

As we journey through this literature review, we are reminded of the captivating dance of illumination that shapes the intricate tapestry of human behavior, and we are poised to uncover the unexpected revelations that lie at the juncture of political allegiance 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 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 Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 1994 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]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

[[INTRODUCTION]]
The intertwining of political forces and energy dynamics has long piqued the curiosity of researchers seeking to shed light on the complex relationships that underpin our global sociopolitical landscape. In this study, we embark on a peculiar journey that ties together votes for the Republican presidential candidate in Illinois with the enigmatic kerosene consumption in Eritrea. This unexpected coupling raises eyebrows, prompting us to delve into the intricacies of these seemingly unrelated phenomena.
As scholars in our respective fields, we are well aware of the myriad factors that shape political preferences and energy usage. However, the entanglement of these specific variables is as surprising as finding a light switch in a dark room; it illuminates the need to reevaluate our traditional understanding of the interplay between disparate domains. To address this curiosity, we have meticulously analyzed data spanning nearly three decades, employing robust statistical methodologies to unravel the enigma that lies at the nexus of Republican support and kerosene consumption.
Our investigation takes us down unexpected paths, akin to stumbling upon a hidden trail in a dense forest. The emergence of a remarkable correlation coefficient of 0.9245507 and a statistically significant p-value of less than 0.01 reveals a connection that is as bright and unmistakable as a beacon in the darkness. As we meander through the complexities of our findings, we remain poised to steer clear of premature causational assumptions, recognizing that correlation does not necessarily imply causation, in the same way that a lit match does not cause the sun to rise.
The implications of our discoveries extend beyond mere statistical fascination, much like an unexpected bonfire illuminating a midnight gathering. They prompt us to delve deeper into the intricate dance of political allegiance and energy utilization, inviting us to explore the interplay of geopolitical preferences and resource consumption with a renewed sense of curiosity. Our journey also underscores the importance of remaining open to unconventional connections, much like stumbling upon a surprising quirk in an ancient map that leads to uncharted territories.
In the pages that follow, we offer a luminescent account of our analytical journey, hoping to spark not only further research but also the imagination of our readers as we venture into the illuminating, albeit unexpected, intersection of political behavior and energy dynamics.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the mysterious entanglement between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea, our research team embarked on a journey that was as convoluted as finding a needle in a haystack and as illuminating as a fireworks display on a starry night. We harnessed data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, diligently scouring the internet for relevant information like archeologists unearthing ancient treasures.

Our analysis spanned the years from 1994 to 2020, a time frame that witnessed the ever-changing tides of political fervor and the ebb and flow of energy usage patterns. Using a mix of statistical methods ranging from straightforward regression analyses to more complex time series modeling, we teased out insights from the data with the precision of a detective solving a perplexing case.

The relationship between Republican votes in Illinois and kerosene consumption in Eritrea was quantified using rigorous statistical tools, akin to measuring the brightness of distant stars with sophisticated telescopes. The resulting correlation coefficient of 0.9245507 and a p-value less than 0.01 emerged like a shining beacon in the fog, revealing a remarkably tight connection that defied traditional expectations, much like discovering a bustling city in the midst of a desert.

In order to further navigate through the intricacies of our findings, we implemented sensitivity analyses to ensure the robustness of our results, much like double-checking the accuracy of a treasure map before setting off on an expedition to uncover buried riches. This meticulous approach allowed us to navigate the complex terrain of causality, acknowledging that correlation does not necessarily imply causation, in the same way that finding a lost sock under the bed doesn't mean it caused the laundry machine to malfunction.

Moreover, to account for potential confounding variables and spurious relationships that could cloud our insights, we conducted supplementary analyses akin to untangling a knot of wires, ensuring that our conclusions remained as clear as day. As we journeyed through this uncharted territory, our methodology served as a trusty compass, guiding us through the unexpected connections that emerged from our investigation and shedding light on the enigmatic intersection of political behavior and energy dynamics.

In the pages that follow, we offer a detailed account of our methodological odyssey, paving the way for future explorations into the intriguing nexus of Republican support and kerosene consumption, much like a trail of breadcrumbs leading to new realms of inquiry.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 1994 to 2020, you found a correlation 0.9245507, r-squared of 0.8547941, 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]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intertwining of political forces and energy dynamics has long piqued the curiosity of researchers seeking to shed light on the complex relationships that underpin our global sociopolitical landscape. In this study, we embark on a peculiar journey that ties together votes for the Republican presidential candidate in Illinois with the enigmatic kerosene consumption in Eritrea. This unexpected coupling raises eyebrows, prompting us to delve into the intricacies of these seemingly unrelated phenomena.
As scholars in our respective fields, we are well aware of the myriad factors that shape political preferences and energy usage. However, the entanglement of these specific variables is as surprising as finding a light switch in a dark room; it illuminates the need to reevaluate our traditional understanding of the interplay between disparate domains. To address this curiosity, we have meticulously analyzed data spanning nearly three decades, employing robust statistical methodologies to unravel the enigma that lies at the nexus of Republican support and kerosene consumption.
Our investigation takes us down unexpected paths, akin to stumbling upon a hidden trail in a dense forest. The emergence of a remarkable correlation coefficient of 0.9245507 and a statistically significant p-value of less than 0.01 reveals a connection that is as bright and unmistakable as a beacon in the darkness. As we meander through the complexities of our findings, we remain poised to steer clear of premature causational assumptions, recognizing that correlation does not necessarily imply causation, in the same way that a lit match does not cause the sun to rise.
The implications of our discoveries extend beyond mere statistical fascination, much like an unexpected bonfire illuminating a midnight gathering. They prompt us to delve deeper into the intricate dance of political allegiance and energy utilization, inviting us to explore the interplay of geopolitical preferences and resource consumption with a renewed sense of curiosity. Our journey also underscores the importance of remaining open to unconventional connections, much like stumbling upon a surprising quirk in an ancient map that leads to uncharted territories.
In the pages that follow, we offer a luminescent account of our analytical journey, hoping to spark not only further research but also the imagination of our readers as we venture into the illuminating, albeit unexpected, intersection of political behavior and energy dynamics.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the relationship between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea revealed a startling correlation coefficient of 0.9245507, with an r-squared value of 0.8547941 and a p-value less than 0.01. This luminous correlation suggests a remarkably tight relationship between the two variables, defying conventional expectations and leaving us more illuminated than a lighthouse on a dark night.

The scatterplot (Fig. 1) showcases this luminous association, painting a vivid picture of the unexpectedly strong link between these seemingly unrelated variables. It is as if a spotlight has been cast upon a stage, revealing a surprising performance in the theater of statistical relationships. The data points dance in tandem, as if performing a meticulously choreographed routine, leaving us not only bewildered but also in awe of this unexpected synchronization.

Our findings shed light on the intricate union of political preferences and energy consumption, sparking a renewed interest in unraveling the underlying mechanisms at play. While we exercise caution against prematurely assuming causation, the strength of this correlation beckons us to delve deeper into the enigmatic connection, much like a captivating mystery novel that compels its readers to turn page after page in anticipation of the next revelation.

This unexpected convergence, akin to discovering a rainbow in the midst of a storm, underscores the importance of remaining vigilant for unanticipated relationships in the vast landscape of data analysis. Our research not only uncovers this unlikely correlation but also ignites a flame of curiosity, urging further exploration into the intersection of political behavior and energy dynamics. Just as a single spark can kindle a grand bonfire, our findings have the potential to illuminate a path towards a deeper understanding of the interplay between geopolitical inclinations and resource utilization.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

[[LITERATURE REVIEW]]
The authors begin this literature review by examining the work of reputable scholars who have delved into the fascinating world of political behavior and energy consumption at the intersection of geopolitics. Smith (2015) presents a comprehensive analysis of voting patterns in the Midwest, shedding light on the underlying factors that drive support for Republican candidates in Illinois. In a similarly enlightening vein, Doe (2018) dissects the complex socio-economic dynamics of resource utilization in developing nations, offering a nuanced exploration of kerosene consumption in Eritrea. Building upon these foundations, Jones (2020) synthesizes the disparate strands of political allegiance and energy utilization, setting the stage for our own foray into this captivating territory.
Turning to non-fiction books, "Energy and Politics" by Green (2017) provides a thought-provoking examination of the intertwining forces of political decision-making and energy policies, offering valuable insights that resonate with the central themes of our research. Furthermore, "Global Trends in Kerosene Market" by Blue (2019) sheds light on the intricate dynamics of kerosene consumption across regions, laying a groundwork for the unexpected linkage we are unraveling.
Expanding our literary scope to the realm of fiction, the evocative work of A. Lightbringer's "The Illuminated Vote" captures the existential struggle of a political campaign manager grappling with the enigmatic allure of a kerosene lantern in a distant land, symbolizing the illumination of his candidate's prospects on the eve of an election. Similarly, the enigmatic tales of E. Flicker's "Kerosene Chronicles" transport readers to a world where the flickering flame of a kerosene lamp becomes a metaphor for the political intrigue and power struggles in a small Illinois town.
Venturing into the realm of social media, a tweet by @VoteLightGiver draws a captivating parallel between the fervent support for a political candidate and the burning desire for a reliable kerosene supply in rural communities, suggesting a deeply ingrained connection that extends beyond mere statistical correlations.
As we journey through this literature review, we are reminded of the captivating dance of illumination that shapes the intricate tapestry of human behavior, and we are poised to uncover the unexpected revelations that lie at the juncture of political allegiance and energy dynamics.

[[RESULTS]]
The analysis of the relationship between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea revealed a startling correlation coefficient of 0.9245507, with an r-squared value of 0.8547941 and a p-value less than 0.01. This luminous correlation suggests a remarkably tight relationship between the two variables, defying conventional expectations and leaving us more illuminated than a lighthouse on a dark night.
The scatterplot (Fig. 1) showcases this luminous association, painting a vivid picture of the unexpectedly strong link between these seemingly unrelated variables. It is as if a spotlight has been cast upon a stage, revealing a surprising performance in the theater of statistical relationships. The data points dance in tandem, as if performing a meticulously choreographed routine, leaving us not only bewildered but also in awe of this unexpected synchronization.
Our findings shed light on the intricate union of political preferences and energy consumption, sparking a renewed interest in unraveling the underlying mechanisms at play. While we exercise caution against prematurely assuming causation, the strength of this correlation beckons us to delve deeper into the enigmatic connection, much like a captivating mystery novel that compels its readers to turn page after page in anticipation of the next revelation.
This unexpected convergence, akin to discovering a rainbow in the midst of a storm, underscores the importance of remaining vigilant for unanticipated relationships in the vast landscape of data analysis. Our research not only uncovers this unlikely correlation but also ignites a flame of curiosity, urging further exploration into the intersection of political behavior and energy dynamics. Just as a single spark can kindle a grand bonfire, our findings have the potential to illuminate a path towards a deeper understanding of the interplay between geopolitical inclinations and resource utilization.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The unearthed correlation between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea has illuminated a path towards a deeper understanding of the interplay between geopolitical inclinations and resource utilization, much like a kerosene lamp piercing through the darkness. Our findings not only shed light on this unlikely correlation but also ignite curiosity, urging further exploration into this unexpected relationship.

Revisiting the literature review, it is intriguing to note the incorporation of seemingly whimsical works such as "The Illuminated Vote" and "Kerosene Chronicles." The existential struggle of a political campaign manager grappling with the enigmatic allure of a kerosene lantern in a distant land resonates with our findings, metaphorically capturing the illuminating bond between political support and kerosene consumption. Furthermore, the captivating parallel drawn in a tweet between the fervent support for a political candidate and the burning desire for a reliable kerosene supply in rural communities takes on a more substantial meaning in light of our statistically significant results.

Our findings align with previous research by Smith and Doe, who separately delved into the enthralling worlds of voting patterns in the Midwest and resource utilization in developing nations. The unexpectedly strong correlation coefficient of 0.9245507, accompanied by the r-squared value of 0.8547941 and a p-value less than 0.01, fortifies the intriguing hypothesis that there is, indeed, a remarkably tight relationship between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. Similarly, the teasing mention of "The Illuminated Vote" and "Kerosene Chronicles" in the literature review finds a tangible parallel in our findings, underscoring the profundity of this connection that transcends geographical boundaries and socio-political contexts.

The unexpectedly strong link between these seemingly unrelated variables, as depicted in the vivid scatterplot, beckons us to delve deeper into the underlying mechanisms at play. While causality remains shrouded in mystery, our results prompt a reevaluation of the intersection between geopolitical inclinations and resource utilization. As we navigate through this enigmatic territory, akin to deciphering an ancient manuscript, our findings propel us to shine a torchlight into the depths of this unusual relationship. There is an uncanny beauty in the dance of statistical relationships that leaves us not only bewildered but also in awe of this unexpected synchronization, much like stumbling upon a captivating mystery novel that compels its readers to turn page after page in anticipation of the next revelation.

In light of our research, we spark a new conversation and illuminate a path towards a deeper understanding of the intricate union of political preferences and energy consumption. This study not only uncovers an unlikely correlation but also ignites a flame of curiosity, urging further exploration into the intersection of political behavior and energy dynamics. Much like a single spark kindling a grand bonfire, our findings have the potential to illuminate a path towards a more nuanced appreciation of the interplay between geopolitical inclinations and resource utilization.




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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in Illinois and Kerosene used in Eritrea. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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]]
"Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea"

[[ABSTRACT]]
This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

[[INTRDUCTION]]
The intertwining of political forces and energy dynamics has long piqued the curiosity of researchers seeking to shed light on the complex relationships that underpin our global sociopolitical landscape. In this study, we embark on a peculiar journey that ties together votes for the Republican presidential candidate in Illinois with the enigmatic kerosene consumption in Eritrea. This unexpected coupling raises eyebrows, prompting us to delve into the intricacies of these seemingly unrelated phenomena.
As scholars in our respective fields, we are well aware of the myriad factors that shape political preferences and energy usage. However, the entanglement of these specific variables is as surprising as finding a light switch in a dark room; it illuminates the need to reevaluate our traditional understanding of the interplay between disparate domains. To address this curiosity, we have meticulously analyzed data spanning nearly three decades, employing robust statistical methodologies to unravel the enigma that lies at the nexus of Republican support and kerosene consumption.
Our investigation takes us down unexpected paths, akin to stumbling upon a hidden trail in a dense forest. The emergence of a remarkable correlation coefficient of 0.9245507 and a statistically significant p-value of less than 0.01 reveals a connection that is as bright and unmistakable as a beacon in the darkness. As we meander through the complexities of our findings, we remain poised to steer clear of premature causational assumptions, recognizing that correlation does not necessarily imply causation, in the same way that a lit match does not cause the sun to rise.
The implications of our discoveries extend beyond mere statistical fascination, much like an unexpected bonfire illuminating a midnight gathering. They prompt us to delve deeper into the intricate dance of political allegiance and energy utilization, inviting us to explore the interplay of geopolitical preferences and resource consumption with a renewed sense of curiosity. Our journey also underscores the importance of remaining open to unconventional connections, much like stumbling upon a surprising quirk in an ancient map that leads to uncharted territories.
In the pages that follow, we offer a luminescent account of our analytical journey, hoping to spark not only further research but also the imagination of our readers as we venture into the illuminating, albeit unexpected, intersection of political behavior and energy dynamics.

[[RESULTS]]
The analysis of the relationship between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea revealed a startling correlation coefficient of 0.9245507, with an r-squared value of 0.8547941 and a p-value less than 0.01. This luminous correlation suggests a remarkably tight relationship between the two variables, defying conventional expectations and leaving us more illuminated than a lighthouse on a dark night.
The scatterplot (Fig. 1) showcases this luminous association, painting a vivid picture of the unexpectedly strong link between these seemingly unrelated variables. It is as if a spotlight has been cast upon a stage, revealing a surprising performance in the theater of statistical relationships. The data points dance in tandem, as if performing a meticulously choreographed routine, leaving us not only bewildered but also in awe of this unexpected synchronization.
Our findings shed light on the intricate union of political preferences and energy consumption, sparking a renewed interest in unraveling the underlying mechanisms at play. While we exercise caution against prematurely assuming causation, the strength of this correlation beckons us to delve deeper into the enigmatic connection, much like a captivating mystery novel that compels its readers to turn page after page in anticipation of the next revelation.
This unexpected convergence, akin to discovering a rainbow in the midst of a storm, underscores the importance of remaining vigilant for unanticipated relationships in the vast landscape of data analysis. Our research not only uncovers this unlikely correlation but also ignites a flame of curiosity, urging further exploration into the intersection of political behavior and energy dynamics. Just as a single spark can kindle a grand bonfire, our findings have the potential to illuminate a path towards a deeper understanding of the interplay between geopolitical inclinations and resource utilization.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has brought to light an unexpected and thoroughly illuminating connection between votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. The remarkably tight correlation coefficient of 0.9245507, coupled with a p-value of less than 0.01, casts a radiance that rivals a supernova, captivating our attention and igniting an unparalleled sense of curiosity. This unexpected relationship challenges conventional wisdom, much like a magician who defies the laws of nature with a remarkable sleight of hand.

As we bask in the glow of our findings, we must exercise caution against leaping to causal conclusions, for correlation, as we are keenly aware, does not imply causation. It is akin to mistaking the flicker of a firefly for the radiance of the sun. Nevertheless, the sheer luminosity of this correlation beckons for further exploration, as if a treasure map has been unfurled, revealing uncharted territories ripe for scholarly investigation.

Our journey into this unexpected convergence serves as a testament to the unfathomable intricacies of statistical relationships. It compels us to embrace the unexpected, much as one would welcome an unforeseen rainbow on an overcast day.

In light of these findings, we assert that no further research is needed in this area. The glow of knowledge we have illuminated in this paper stands as a beacon, guiding fellow researchers away from this path and toward other unexplored frontiers. Just as a lantern shines brightly to guide travelers through the darkest of nights, our research stands as a testament to the limitless possibilities that await those who dare to unravel the enigmatic connections that lie within the vast expanse of data analysis.


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 Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Political Analysis


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 Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea. Respond only with the name of a fictional organization.

ChatGPT:

Society for Global Energy and Political Analysis


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Lighting Up the Political Landscape: An Illuminating Connection Between Votes for the Republican Presidential Candidate in Illinois and Kerosene Consumption in Eritrea with an abstract of This paper elucidates an unexpected and enigmatic relationship between seemingly disparate variables: the votes for the Republican presidential candidate in Illinois and kerosene consumption in Eritrea. By harnessing data from reputable sources including MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we unpack this perplexing association with statistical rigor. Our analysis yields a staggering correlation coefficient of 0.9245507 and p < 0.01 for the years spanning from 1994 to 2020, illuminating a remarkably tight relationship that defies conventional wisdom. While causality remains shrouded in ambiguity, our findings prompt a reevaluation of the intersection between geopolitical preferences and energy utilization, shedding light on the unexpected dance of political allegiance and kerosene consumption. With this research, we spark a new conversation, igniting intrigue as we venture into uncharted territory at the intersection of political behavior and energy dynamics.

ChatGPT:

Republican presidential candidate, Illinois, kerosene consumption, Eritrea, correlation, statistical analysis, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, political allegiance, energy utilization, geopolitical preferences, causality, political behavior, 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 the Republican Presidential candidate in Illinois
Detailed data title: Percentage of all votes cast for the Republican Presidential candidate in Illinois
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Republican Presidential candidate in Illinois

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

Correlation r = 0.9245507 (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 = 0.8547941 (Coefficient of determination)
This means 85.5% of the change in the one variable (i.e., Kerosene used in Eritrea) is predictable based on the change in the other (i.e., Votes for the Republican Presidential candidate in Illinois) over the 7 years from 1994 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0029. 0.0028827538226096030000000000
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 0.92 in 0.29% of random cases. Said differently, if you correlated 347 random variables Which I absolutely did.
with the same 6 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 6 because we have two variables measured over a period of 7 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.

[ 0.56, 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.
1996200020042008201220162020
Votes for the Republican Presidential candidate in Illinois (Percentage of votes)36.8142.584944.478636.780940.732738.761840.5535
Kerosene used in Eritrea (Million Barrels/Day)0.20.4435250.5280050.2745630.2964930.2956830.311185




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  5. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([36.81,42.5849,44.4786,36.7809,40.7327,38.7618,40.5535,])
array_2 = np.array([0.2,0.443525,0.528005,0.274563,0.296493,0.295683,0.311185,])
array_1_name = "Votes for the Republican Presidential candidate in Illinois"
array_2_name = "Kerosene used in Eritrea"

# 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 rating is much appreciated!


Correlation ID: 5275 · Black Variable ID: 26090 · Red Variable ID: 24390
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0