about · email me · subscribe
Spurious correlation #5,334 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Democratic Presidential candidate in Rhode Island and the second variable is Kerosene used in Ethiopia.  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

Apparently, whenever Democrats gain popularity in Rhode Island, it sends such a wave of excitement across the country that it inadvertently leads to impromptu dance parties. These rhythmic movements somehow resonate with the molecules in kerosene, causing an unexplainable surge in its usage in far-off Ethiopia. It's a political dance-off with combustible consequences!

Model: dalle-3
Prompt: [ Cute 2D animation ] An image of the scene in Rhode Island shows a colorful crowd of people with big smiles on their faces, waving blue flags and holding up signs with "Democratic Candidate" written on them. The characters are illustrated in a happy and upbeat manner, with exaggerated expressions of joy as they cast their votes at polling stations. In the depiction of Ethiopia, a group of villagers is animated gathering around a flickering kerosene lamp, their bodies swaying to the beat of spontaneous music. The animation captures the energy and joy as their movements somehow sync with the sudden increase in kerosene usage. The characters are depicted in a warm and lively manner, exuding a sense of community and celebration. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Democratic Presidential candidate in Rhode Island and Kerosene used in Ethiopia. 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: Art nouveau Cutsy graphics Cyberpunk inspired by bauhaus Cute 2D animation
ChatGPT: Cute 2D animation

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for the Democratic Presidential candidate in Rhode Island and Kerosene used in Ethiopia, in the following situation: Apparently, whenever Democrats gain popularity in Rhode Island, it sends such a wave of excitement across the country that it inadvertently leads to impromptu dance parties. These rhythmic movements somehow resonate with the molecules in kerosene, causing an unexplainable surge in its usage in far-off Ethiopia. It's a political dance-off with combustible consequences!. Keep the description simple.
ChatGPT: In Rhode Island, a crowd of people joyously waves blue flags and holds up signs with "Democratic Candidate" written on them, as they cast their votes at polling stations. Meanwhile, in Ethiopia, a group of villagers surrounds a flickering kerosene lamp, their bodies swaying to the beat of spontaneous music, their movements somehow syncing with the sudden increase in kerosene usage.

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: [ Cute 2D animation ] and depicting this scene: In Rhode Island, a crowd of people joyously waves blue flags and holds up signs with "Democratic Candidate" written on them, as they cast their votes at polling stations. Meanwhile, in Ethiopia, a group of villagers surrounds a flickering kerosene lamp, their bodies swaying to the beat of spontaneous music, their movements somehow syncing with the sudden increase in kerosene usage. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Cute 2D animation ] An image of the scene in Rhode Island shows a colorful crowd of people with big smiles on their faces, waving blue flags and holding up signs with "Democratic Candidate" written on them. The characters are illustrated in a happy and upbeat manner, with exaggerated expressions of joy as they cast their votes at polling stations. In the depiction of Ethiopia, a group of villagers is animated gathering around a flickering kerosene lamp, their bodies swaying to the beat of spontaneous music. The animation captures the energy and joy as their movements somehow sync with the sudden increase in kerosene usage. The characters are depicted in a warm and lively manner, exuding a sense of community and celebration.

*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 Democrat Presidential candidate in Rhode Island caused Kerosene used in Ethiopia to increase.

AI academic paper

(Because p < 0.01)
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

The Journal of Global Interconnectedness and Unlikely Correlations

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. 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, make it sound serious.

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 0.8699899 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]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

In the realm of statistical analysis, one often encounters intriguing correlations that surprise even the most seasoned researchers. Our current study delves into an unusual pairing: the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. While the initial juxtaposition of these variables may appear as disparate as an electron and a proton, our investigation has brought to light a connection that is as striking as a sudden surge of voltage.

We embarked on this statistical journey armed with data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, ready to uncover insights that might shed light on this curious link. Our approach was as meticulous as a scientist analyzing the molecular structure of a complex compound, and our scrutiny of the data was as thorough as a seasoned detective interrogating a suspect.

The correlations we uncovered are as surprising as finding a labrador retriever in a physics lab: a correlation coefficient of 0.8699899 with a significance level of p < 0.01. It's safe to say that this finding has sparked more curiosity than a cat encountering a metronome for the first time. And like a good mystery novel, this discovery has left us eager to delve deeper into the underlying factors that may account for this seemingly improbable association.

Despite the initial absurdity of it all, our study points to the potential for a convergence of disciplines that is as unexpected as a chemist crafting an avant-garde culinary creation. Indeed, the intersection of political behavior and energy usage has given rise to questions that are as complex as quantum physics and as weighty as an anvil in Wile E. Coyote's hands.

As we delve into the depths of this quirky correlation, we are reminded of a whimsical quote often attributed to Albert Einstein: "The only source of knowledge is experience." And our experience with this peculiar connection has filled us with a sense of wonder, akin to that of a child encountering a magnifying glass for the first time. We hope that our findings will ignite a curiosity in others that is as relentless as the gravitational pull of a black hole.

In the following sections, we will unravel the threads of this statistical enigma and ponder the implications of this unexpected relationship. Just as the observant astronomer gazes at the night sky, searching for patterns and anomalies, we invite our readers to join us in exploring this uncharted territory of statistical serendipity. After all, as the saying goes, "In statistics, as in life, expect the unexpected."


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. 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 name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
In the realm of statistical analysis, one often encounters intriguing correlations that surprise even the most seasoned researchers. Our current study delves into an unusual pairing: the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. While the initial juxtaposition of these variables may appear as disparate as an electron and a proton, our investigation has brought to light a connection that is as striking as a sudden surge of voltage.
We embarked on this statistical journey armed with data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, ready to uncover insights that might shed light on this curious link. Our approach was as meticulous as a scientist analyzing the molecular structure of a complex compound, and our scrutiny of the data was as thorough as a seasoned detective interrogating a suspect.
The correlations we uncovered are as surprising as finding a labrador retriever in a physics lab: a correlation coefficient of 0.8699899 with a significance level of p < 0.01. It's safe to say that this finding has sparked more curiosity than a cat encountering a metronome for the first time. And like a good mystery novel, this discovery has left us eager to delve deeper into the underlying factors that may account for this seemingly improbable association.
Despite the initial absurdity of it all, our study points to the potential for a convergence of disciplines that is as unexpected as a chemist crafting an avant-garde culinary creation. Indeed, the intersection of political behavior and energy usage has given rise to questions that are as complex as quantum physics and as weighty as an anvil in Wile E. Coyote's hands.
As we delve into the depths of this quirky correlation, we are reminded of a whimsical quote often attributed to Albert Einstein: "The only source of knowledge is experience." And our experience with this peculiar connection has filled us with a sense of wonder, akin to that of a child encountering a magnifying glass for the first time. We hope that our findings will ignite a curiosity in others that is as relentless as the gravitational pull of a black hole.
In the following sections, we will unravel the threads of this statistical enigma and ponder the implications of this unexpected relationship. Just as the observant astronomer gazes at the night sky, searching for patterns and anomalies, we invite our readers to join us in exploring this uncharted territory of statistical serendipity. After all, as the saying goes, "In statistics, as in life, expect the unexpected."

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia has baffled and bemused researchers for decades. Despite the seeming absurdity of this unlikely association, our study aims to provide a comprehensive overview of the literature surrounding this enigmatic correlation.

Smith et al. (2010) conducted a seminal study on political voting patterns in Rhode Island, examining the demographic, socioeconomic, and historical factors influencing electoral preferences. The authors' rigorous analysis, akin to a Sherlock Holmes investigation, revealed intriguing insights into the shifting dynamics of political allegiances within the state.

In a separate endeavor, Doe and Jones (2015) investigated energy usage trends in developing countries, with a particular focus on kerosene consumption in Ethiopian households. Their meticulous examination unearthed the complex interplay of cultural, economic, and infrastructural factors shaping the reliance on kerosene as a primary source of lighting and cooking fuel.

Building on these foundational studies, our research team sought to explore the unexpected nexus of these divergent datasets. As we traversed the academic landscape, we encountered an eclectic array of literary works that shed light on tangentially related themes.

From "Energy Policy in the Developing World" by Chang (2005) to "Politics in Small States" by Westergaard (2012), the literature on energy dynamics and political dynamics proved to be as expansive as the night sky and as illuminating as a lighthouse on a stormy night.

In a departure from the conventional, we drew inspiration from fiction texts that, although not directly related to our research topic, provided intriguing perspectives on the curious nature of unexpected connections. Titles such as "The Unlikely Pilgrimage of Harold Fry" by Rachel Joyce and "Election" by Tom Perrotta offered captivating narratives that mirrored the improbable linkage we seek to unravel.

Furthermore, our team embraced the visual medium, immersing ourselves in relevant television shows such as "The X-Files," which epitomizes the pursuit of inexplicable phenomena, and "Stranger Things," a delightfully mysterious series that embodies the spirit of unearthing hidden connections.

With each literary and visual encounter, we found ourselves captivated by the uncanny parallels and unexpected concatenations, much like stumbling upon a treasure map in a spaceship manual. As we waded through this eclectic amalgamation of sources, one thing became abundantly clear: the interplay between political choices in one corner of the world and energy consumption in another is as intriguing as a riddle wrapped in a mystery inside an enigma.

In the subsequent sections, we will navigate the empirical findings, theoretical frameworks, and methodological considerations that underpin our investigation, all the while embracing the delightful quirkiness of this scholarly pursuit. As we venture forth, buoyed by a sense of curiosity that rivals that of a feline encountering a fresh ball of yarn, we invite our readers to join us on this whimsical academic escapade. After all, in the delightful words of Roald Dahl, "A little nonsense now and then, is relished by the wisest men."


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1980 to 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]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

[[INTRODUCTION]]
INTRODUCTION
In the realm of statistical analysis, one often encounters intriguing correlations that surprise even the most seasoned researchers. Our current study delves into an unusual pairing: the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. While the initial juxtaposition of these variables may appear as disparate as an electron and a proton, our investigation has brought to light a connection that is as striking as a sudden surge of voltage.
We embarked on this statistical journey armed with data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, ready to uncover insights that might shed light on this curious link. Our approach was as meticulous as a scientist analyzing the molecular structure of a complex compound, and our scrutiny of the data was as thorough as a seasoned detective interrogating a suspect.
The correlations we uncovered are as surprising as finding a labrador retriever in a physics lab: a correlation coefficient of 0.8699899 with a significance level of p < 0.01. It's safe to say that this finding has sparked more curiosity than a cat encountering a metronome for the first time. And like a good mystery novel, this discovery has left us eager to delve deeper into the underlying factors that may account for this seemingly improbable association.
Despite the initial absurdity of it all, our study points to the potential for a convergence of disciplines that is as unexpected as a chemist crafting an avant-garde culinary creation. Indeed, the intersection of political behavior and energy usage has given rise to questions that are as complex as quantum physics and as weighty as an anvil in Wile E. Coyote's hands.
As we delve into the depths of this quirky correlation, we are reminded of a whimsical quote often attributed to Albert Einstein: "The only source of knowledge is experience." And our experience with this peculiar connection has filled us with a sense of wonder, akin to that of a child encountering a magnifying glass for the first time. We hope that our findings will ignite a curiosity in others that is as relentless as the gravitational pull of a black hole.
In the following sections, we will unravel the threads of this statistical enigma and ponder the implications of this unexpected relationship. Just as the observant astronomer gazes at the night sky, searching for patterns and anomalies, we invite our readers to join us in exploring this uncharted territory of statistical serendipity. After all, as the saying goes, "In statistics, as in life, expect the unexpected."

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
To investigate the perplexing connection between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in Ethiopia, our research team embarked on a virtual journey akin to traversing a labyrinth of data. We scoured the archives of the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, navigating the digital landscape as deftly as a cat seeking a sunbeam on a lazy afternoon. Our intrepid quest led us to a trove of data spanning the years from 1980 to 2020, providing a panoramic view of these diametrically distant variables.

Statistical Analysis:
As we grappled with the data, we turned to statistical methods that were as robust as a sturdy oak tree in a storm, aiming to uncover patterns that might be as elusive as a chameleon in a kaleidoscope. Employing the venerable Pearson correlation coefficient, we sought to quantify the strength and direction of the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. Our statistical tools were honed with precision, much like a chef preparing a delicate soufflé, as we meticulously calculated the correlation coefficient and the associated p-value, ensuring that our findings would stand up to scrutiny like a stoic oak in the face of a tempest.

Validity Checks:
To fortify the credibility of our findings, we implemented rigorous checks that were as thorough as a security screening at an international airport. We scrutinized the data for outliers, anomalies, and potential confounding variables, guarding against misleading conclusions like a vigilant watchdog protecting its territory. Our commitment to data integrity and methodological rigor was unwavering, much like a scientist dedicated to upholding the laws of thermodynamics.

Ethical Considerations:
As custodians of data, we are bound by the principles of research ethics as firmly as a ship tethered to its moorings, ensuring the confidentiality and privacy of individuals represented in our datasets. Our ethical compass guided our conduct, emphasizing the paramount importance of safeguarding the rights and welfare of those whose information formed the bedrock of our investigation.

Limitations:
It is paramount to acknowledge the limitations inherent in our methodology, much like a ship captain acknowledging the constraints of navigating through uncharted waters. Our reliance on publicly available data sources may introduce biases and constraints, and the observational nature of our study precludes causal inferences. Moreover, the multifaceted nature of political dynamics and energy usage posits a complex landscape that may elude complete capture in our statistical model, much like trying to corral a wilful herd of cats into a neatly arranged formation.

In the grand tapestry of statistical inquiry, our methodology constitutes a thread in the rich fabric of scientific exploration, contributing to the perennial endeavor of unraveling the intricate patterns of the world around us.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1980 to 2020, you found a correlation 0.8699899, r-squared of 0.7568825, 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]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
In the realm of statistical analysis, one often encounters intriguing correlations that surprise even the most seasoned researchers. Our current study delves into an unusual pairing: the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. While the initial juxtaposition of these variables may appear as disparate as an electron and a proton, our investigation has brought to light a connection that is as striking as a sudden surge of voltage.
We embarked on this statistical journey armed with data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, ready to uncover insights that might shed light on this curious link. Our approach was as meticulous as a scientist analyzing the molecular structure of a complex compound, and our scrutiny of the data was as thorough as a seasoned detective interrogating a suspect.
The correlations we uncovered are as surprising as finding a labrador retriever in a physics lab: a correlation coefficient of 0.8699899 with a significance level of p < 0.01. It's safe to say that this finding has sparked more curiosity than a cat encountering a metronome for the first time. And like a good mystery novel, this discovery has left us eager to delve deeper into the underlying factors that may account for this seemingly improbable association.
Despite the initial absurdity of it all, our study points to the potential for a convergence of disciplines that is as unexpected as a chemist crafting an avant-garde culinary creation. Indeed, the intersection of political behavior and energy usage has given rise to questions that are as complex as quantum physics and as weighty as an anvil in Wile E. Coyote's hands.
As we delve into the depths of this quirky correlation, we are reminded of a whimsical quote often attributed to Albert Einstein: "The only source of knowledge is experience." And our experience with this peculiar connection has filled us with a sense of wonder, akin to that of a child encountering a magnifying glass for the first time. We hope that our findings will ignite a curiosity in others that is as relentless as the gravitational pull of a black hole.
In the following sections, we will unravel the threads of this statistical enigma and ponder the implications of this unexpected relationship. Just as the observant astronomer gazes at the night sky, searching for patterns and anomalies, we invite our readers to join us in exploring this uncharted territory of statistical serendipity. After all, as the saying goes, "In statistics, as in life, expect the unexpected."

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon analyzing the data collected from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, a striking correlation was observed between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia. The correlation coefficient of 0.8699899 revealed a remarkably strong relationship between these seemingly unrelated variables, akin to the unexpected fusion of two chemical elements resulting in a surprising compound.

The correlation was found to be positively significant with an r-squared value of 0.7568825 and a p-value less than 0.01, indicating a high level of confidence in the association. This statistical revelation is as astonishing as a conductor harnessing the power of lightning to illuminate a concert hall.

For a visual representation of the correlation, please refer to Figure 1, which illustrates the robust and unmistakable relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. The scatterplot in Figure 1 vividly captures the coherence between the two variables in a manner as clear as a freshly polished microscope slide.

These findings challenge conventional wisdom and stimulate the imagination, much like a sudden insight during a game of Scrabble that unearths an unforeseen connection between the letters on the board. The implications of this unexpected correlation warrant further investigation and spark curiosity akin to a physicist pondering the mysteries of the universe.

Our results invite researchers to delve into the why and the how behind this curious link, compelling them to examine this statistical convergence with the same fervor as an archaeologist uncovering a hidden tomb. The fusion of political behavior and energy usage in this unanticipated association presents a puzzle as intricate as a Rubik's Cube and as thought-provoking as a paradox in quantum mechanics.

In conclusion, our analysis has uncovered a captivating correlation between votes for the Democratic presidential candidate in Rhode Island and kerosene consumption in Ethiopia, igniting intrigue and stimulating further exploration into the interconnectedness of seemingly unrelated phenomena.

This concludes the results section.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

[[LITERATURE REVIEW]]
The connection between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia has baffled and bemused researchers for decades. Despite the seeming absurdity of this unlikely association, our study aims to provide a comprehensive overview of the literature surrounding this enigmatic correlation.
Smith et al. (2010) conducted a seminal study on political voting patterns in Rhode Island, examining the demographic, socioeconomic, and historical factors influencing electoral preferences. The authors' rigorous analysis, akin to a Sherlock Holmes investigation, revealed intriguing insights into the shifting dynamics of political allegiances within the state.
In a separate endeavor, Doe and Jones (2015) investigated energy usage trends in developing countries, with a particular focus on kerosene consumption in Ethiopian households. Their meticulous examination unearthed the complex interplay of cultural, economic, and infrastructural factors shaping the reliance on kerosene as a primary source of lighting and cooking fuel.
Building on these foundational studies, our research team sought to explore the unexpected nexus of these divergent datasets. As we traversed the academic landscape, we encountered an eclectic array of literary works that shed light on tangentially related themes.

From "Energy Policy in the Developing World" by Chang (2005) to "Politics in Small States" by Westergaard (2012), the literature on energy dynamics and political dynamics proved to be as expansive as the night sky and as illuminating as a lighthouse on a stormy night.
In a departure from the conventional, we drew inspiration from fiction texts that, although not directly related to our research topic, provided intriguing perspectives on the curious nature of unexpected connections. Titles such as "The Unlikely Pilgrimage of Harold Fry" by Rachel Joyce and "Election" by Tom Perrotta offered captivating narratives that mirrored the improbable linkage we seek to unravel.
Furthermore, our team embraced the visual medium, immersing ourselves in relevant television shows such as "The X-Files," which epitomizes the pursuit of inexplicable phenomena, and "Stranger Things," a delightfully mysterious series that embodies the spirit of unearthing hidden connections.
With each literary and visual encounter, we found ourselves captivated by the uncanny parallels and unexpected concatenations, much like stumbling upon a treasure map in a spaceship manual. As we waded through this eclectic amalgamation of sources, one thing became abundantly clear: the interplay between political choices in one corner of the world and energy consumption in another is as intriguing as a riddle wrapped in a mystery inside an enigma.
In the subsequent sections, we will navigate the empirical findings, theoretical frameworks, and methodological considerations that underpin our investigation, all the while embracing the delightful quirkiness of this scholarly pursuit. As we venture forth, buoyed by a sense of curiosity that rivals that of a feline encountering a fresh ball of yarn, we invite our readers to join us on this whimsical academic escapade. After all, in the delightful words of Roald Dahl, "A little nonsense now and then, is relished by the wisest men."

[[RESULTS]]
Upon analyzing the data collected from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, a striking correlation was observed between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia. The correlation coefficient of 0.8699899 revealed a remarkably strong relationship between these seemingly unrelated variables, akin to the unexpected fusion of two chemical elements resulting in a surprising compound.
The correlation was found to be positively significant with an r-squared value of 0.7568825 and a p-value less than 0.01, indicating a high level of confidence in the association. This statistical revelation is as astonishing as a conductor harnessing the power of lightning to illuminate a concert hall.
For a visual representation of the correlation, please refer to Figure 1, which illustrates the robust and unmistakable relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. The scatterplot in Figure 1 vividly captures the coherence between the two variables in a manner as clear as a freshly polished microscope slide.
These findings challenge conventional wisdom and stimulate the imagination, much like a sudden insight during a game of Scrabble that unearths an unforeseen connection between the letters on the board. The implications of this unexpected correlation warrant further investigation and spark curiosity akin to a physicist pondering the mysteries of the universe.
Our results invite researchers to delve into the why and the how behind this curious link, compelling them to examine this statistical convergence with the same fervor as an archaeologist uncovering a hidden tomb. The fusion of political behavior and energy usage in this unanticipated association presents a puzzle as intricate as a Rubik's Cube and as thought-provoking as a paradox in quantum mechanics.
In conclusion, our analysis has uncovered a captivating correlation between votes for the Democratic presidential candidate in Rhode Island and kerosene consumption in Ethiopia, igniting intrigue and stimulating further exploration into the interconnectedness of seemingly unrelated phenomena.
This concludes the results section.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our analysis raise more questions than they answer, much like a magician pulling a rabbit out of a hat only to reveal another hat with yet another rabbit. The remarkable correlation between votes for the Democratic presidential candidate in Rhode Island and kerosene consumption in Ethiopian households suggests a connection as enigmatic as the elusive Higgs boson or the perplexing puzzles of quantum entanglement.

Our study aimed to shed light on this obscure association, much like a searchlight piercing through the darkness of an unexplored cave. The remarkably strong correlation coefficient, akin to a sturdy bridge connecting two distant lands, echoes and reaffirms the prior research by Smith et al. (2010) and Doe and Jones (2015), and other investigators who ventured into the mysteries of political voting patterns and energy usage trends. These seemingly whimsical intersections are akin to uncovering a treasure trove amidst a field of theoretical rubble, emphasizing the intricate interconnectedness of diverse phenomena in our complex world.

The statistically significant relationship we observed, as surprising as finding Bigfoot in a soda factory, merits further scrutiny and exploration from a multidisciplinary perspective. The potential influences and mechanisms driving this unanticipated linkage are as intriguing as the plot twists in a mystery novel, beckoning researchers to unravel the layers of causality and implication laced within this statistical anomaly.

Our investigation paves the way for future inquiry, akin to a playful game of leapfrog, where each finding acts as a stepping stone to propel the field forward. The unanticipated convergence of political preferences and energy consumption hints at an interwoven tapestry of global dynamics, enveloping the socio-political realm in the same mysterious allure as a black hole in outer space.

As we continue to peel back the layers of this metaphorical onion, we urge fellow scholars to approach this improbable connection with the same blend of rigorous inquiry and good-natured wonderment that fuels scientific discovery and advances human understanding. After all, as the great physicist Richard Feynman once said, "Nature is peculiar, very peculiar indeed."

Our discussion lays the groundwork for further interdisciplinary exploration, and we eagerly anticipate the contributions of future researchers who embark on this captivating academic escapade. Just as Michelangelo once chiseled away at marble to unveil the timeless beauty within, so too must we chip away at the veneer of the unusual to uncover the underlying truths within this unlikely correlation.



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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Rhode Island and Kerosene used in Ethiopia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia

[[ABSTRACT]]
This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

[[INTRDUCTION]]
INTRODUCTION
In the realm of statistical analysis, one often encounters intriguing correlations that surprise even the most seasoned researchers. Our current study delves into an unusual pairing: the relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. While the initial juxtaposition of these variables may appear as disparate as an electron and a proton, our investigation has brought to light a connection that is as striking as a sudden surge of voltage.
We embarked on this statistical journey armed with data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, ready to uncover insights that might shed light on this curious link. Our approach was as meticulous as a scientist analyzing the molecular structure of a complex compound, and our scrutiny of the data was as thorough as a seasoned detective interrogating a suspect.
The correlations we uncovered are as surprising as finding a labrador retriever in a physics lab: a correlation coefficient of 0.8699899 with a significance level of p < 0.01. It's safe to say that this finding has sparked more curiosity than a cat encountering a metronome for the first time. And like a good mystery novel, this discovery has left us eager to delve deeper into the underlying factors that may account for this seemingly improbable association.
Despite the initial absurdity of it all, our study points to the potential for a convergence of disciplines that is as unexpected as a chemist crafting an avant-garde culinary creation. Indeed, the intersection of political behavior and energy usage has given rise to questions that are as complex as quantum physics and as weighty as an anvil in Wile E. Coyote's hands.
As we delve into the depths of this quirky correlation, we are reminded of a whimsical quote often attributed to Albert Einstein: "The only source of knowledge is experience." And our experience with this peculiar connection has filled us with a sense of wonder, akin to that of a child encountering a magnifying glass for the first time. We hope that our findings will ignite a curiosity in others that is as relentless as the gravitational pull of a black hole.
In the following sections, we will unravel the threads of this statistical enigma and ponder the implications of this unexpected relationship. Just as the observant astronomer gazes at the night sky, searching for patterns and anomalies, we invite our readers to join us in exploring this uncharted territory of statistical serendipity. After all, as the saying goes, "In statistics, as in life, expect the unexpected."

[[RESULTS]]
Upon analyzing the data collected from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, a striking correlation was observed between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia. The correlation coefficient of 0.8699899 revealed a remarkably strong relationship between these seemingly unrelated variables, akin to the unexpected fusion of two chemical elements resulting in a surprising compound.
The correlation was found to be positively significant with an r-squared value of 0.7568825 and a p-value less than 0.01, indicating a high level of confidence in the association. This statistical revelation is as astonishing as a conductor harnessing the power of lightning to illuminate a concert hall.
For a visual representation of the correlation, please refer to Figure 1, which illustrates the robust and unmistakable relationship between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia. The scatterplot in Figure 1 vividly captures the coherence between the two variables in a manner as clear as a freshly polished microscope slide.
These findings challenge conventional wisdom and stimulate the imagination, much like a sudden insight during a game of Scrabble that unearths an unforeseen connection between the letters on the board. The implications of this unexpected correlation warrant further investigation and spark curiosity akin to a physicist pondering the mysteries of the universe.
Our results invite researchers to delve into the why and the how behind this curious link, compelling them to examine this statistical convergence with the same fervor as an archaeologist uncovering a hidden tomb. The fusion of political behavior and energy usage in this unanticipated association presents a puzzle as intricate as a Rubik's Cube and as thought-provoking as a paradox in quantum mechanics.
In conclusion, our analysis has uncovered a captivating correlation between votes for the Democratic presidential candidate in Rhode Island and kerosene consumption in Ethiopia, igniting intrigue and stimulating further exploration into the interconnectedness of seemingly unrelated phenomena.
This concludes the results section.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

CONCLUSION
In conclusion, our exploration of the unexpected correlation between votes for the Democrat presidential candidate in Rhode Island and kerosene consumption in Ethiopia has shed light on an intriguing statistical enigma. The robust relationship we uncovered is as surprising as a chemist discovering a new element in the periodic table.
As the data revealed a remarkably strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, we were left pondering the connection between these seemingly disparate variables, much like a detective piecing together clues in a gripping mystery novel.
The implications of this peculiar association are as thought-provoking as a philosophical paradox, urging further investigation into the underlying mechanisms driving this unlikely convergence. The interplay between political preferences in Rhode Island and energy usage in Ethiopian households presents a conundrum as intricate as a game of chess, sparking curiosity and prompting interdisciplinary inquiry at the crossroads of politics and energy consumption.
Although the reasons behind this correlation may seem as elusive as a rare subatomic particle, we can confidently assert that no further research is needed to explore this hilariously unexpected connection. As the saying goes, "Some things are better left unexplained."


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 The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Global Interconnectedness and Unlikely Correlations


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Irreverent and Unlikely Statistical Analyses


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 The Blue State and the Burning Question: A Statistical Analysis of the Connection between Votes for the Democrat Presidential Candidate in Rhode Island and Kerosene Consumption in Ethiopia with an abstract of This paper explores the curious link between political preferences in the smallest state of the United States and the utilization of kerosene, a widely-used fuel in Ethiopia. Drawing on data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, our research team delves into the quantitative relationship between the percentage of votes for the Democratic presidential candidate in Rhode Island and the consumption of kerosene in households across Ethiopia from 1980 to 2020. Our analysis reveals a surprisingly strong correlation coefficient of 0.8699899 with a significance level of p < 0.01, prompting a thorough investigation into the underlying factors that may contribute to this association. While the alignment of these seemingly disparate variables may initially appear whimsical, our findings uncover potential avenues for further interdisciplinary inquiry at the intersection of political behavior and energy usage. Additional studies are warranted to illuminate the mechanisms driving this unexpected connection and its implications for global socio-political dynamics.

ChatGPT:

Democrat presidential candidate votes, Rhode Island, kerosene consumption, Ethiopia, statistical analysis, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, political behavior, energy usage, interdisciplinary inquiry, global socio-political 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 Democratic Presidential candidate in Rhode Island
Detailed data title: Percentage of all votes cast for the Democrat Presidential candidate in Rhode Island
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Democratic Presidential candidate in Rhode Island

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

Correlation r = 0.8699899 (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 = 0.7568825 (Coefficient of determination)
This means 75.7% of the change in the one variable (i.e., Kerosene used in Ethiopia) is predictable based on the change in the other (i.e., Votes for the Democratic Presidential candidate in Rhode Island) over the 9 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0023. 0.0022921651098805950000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.87 in 0.23% of random cases. Said differently, if you correlated 436 random variables Which I absolutely did.
with the same 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.49, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
198019841992200020042008201220162020
Votes for the Democratic Presidential candidate in Rhode Island (Percentage of votes)47.682148.017447.04860.987759.423462.86462.70154.406659.4762
Kerosene used in Ethiopia (Million Barrels/Day)0.6279070.7848840.33.421484.266285.343425.7392631.41068




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  5. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([47.6821,48.0174,47.048,60.9877,59.4234,62.864,62.701,54.4066,59.4762,])
array_2 = np.array([0.627907,0.784884,0.3,3.42148,4.26628,5.34342,5.73926,3,1.41068,])
array_1_name = "Votes for the Democratic Presidential candidate in Rhode Island"
array_2_name = "Kerosene used in Ethiopia"

# 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?

Cheers to you for rating this correlation!


Correlation ID: 5334 · Black Variable ID: 26161 · Red Variable ID: 24404
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0