Spurious correlation #5,532 · 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 Libertarian Senators in California and the second variable is Kerosene used in French Polynesia. The chart goes from 1990 to 2010, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for Libertarian Senators in California and the second variable is Kerosene used in French Polynesia. The chart goes from 1990 to 2010, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the saying goes, fewer Libertarians in California meant fewer people to fuel the fiery debates. With less hot air in the political arena, there was a reduced demand for kerosene in French Polynesia to keep the lamps of liberty burning bright. It seems like even thousands of miles of ocean couldn't keep these two seemingly unrelated events apart!

^{Show image generation prompt} Model: dalle-3
Prompt: An image that looks like a scene from a Disney movie: A serene and magical forest glade is depicted, with a ballot box nestled under the shade of an ancient oak tree in California. Engraved with "Votes for Libertarian Senators," it glints in the filtered sunlight as if imbued with glimmering enchantment. Meanwhile, in French Polynesia, a tranquil beach is shown where a vintage lamp is being gently extinguished, with wisps of golden light fading into the air. The vibrant connection between the two distant scenes is emphasized by a shimmering ripple effect, weaving through the air and connecting the ballot box and the extinguished lamp in a mesmerizing pattern of diminished political fervor. 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 Libertarian Senators in California and Kerosene used in French Polynesia. 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: Cute cartoon Cubism Pop art Cutsy graphics An image that looks like it is a scene from A Disney Movie
ChatGPT: An image that looks like it is a scene from A Disney Movie

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 Libertarian Senators in California and Kerosene used in French Polynesia, in the following situation: As the saying goes, fewer Libertarians in California meant fewer people to fuel the fiery debates. With less hot air in the political arena, there was a reduced demand for kerosene in French Polynesia to keep the lamps of liberty burning bright. It seems like even thousands of miles of ocean couldn't keep these two seemingly unrelated events apart!. Keep the description simple.
ChatGPT: In California, a ballot box is shown with a "Votes for Libertarian Senators" label, indicating a decrease in votes. Meanwhile, in French Polynesia, a serene scene features a lamp being extinguished, symbolizing a reduced demand for kerosene. Despite the vast distance between them, these two events are connected by the ripple effect of diminished political fervor.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from A Disney Movie ] and depicting this scene: In California, a ballot box is shown with a "Votes for Libertarian Senators" label, indicating a decrease in votes. Meanwhile, in French Polynesia, a serene scene features a lamp being extinguished, symbolizing a reduced demand for kerosene. Despite the vast distance between them, these two events are connected by the ripple effect of diminished political fervor. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like a scene from a Disney movie: A serene and magical forest glade is depicted, with a ballot box nestled under the shade of an ancient oak tree in California. Engraved with "Votes for Libertarian Senators," it glints in the filtered sunlight as if imbued with glimmering enchantment. Meanwhile, in French Polynesia, a tranquil beach is shown where a vintage lamp is being gently extinguished, with wisps of golden light fading into the air. The vibrant connection between the two distant scenes is emphasized by a shimmering ripple effect, weaving through the air and connecting the ballot box and the extinguished lamp in a mesmerizing pattern of diminished political fervor.

*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.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Libertarian votes for Senators in California caused Kerosene used in French Polynesia to decrease.

AI academic paper

(Because p < 0.01)

The Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia

The Journal of Eclectic Social Sciences

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Libertarian votes for Senators in California and Kerosene used in French Polynesia. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"The Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia"

[[ABSTRACT]]
This research investigates the peculiar relationship between Libertarian votes for Senators in California and kerosene used in French Polynesia. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we conducted a comprehensive assessment from 1990 to 2010. Surprisingly, our analysis revealed a remarkably high correlation coefficient of 0.9490973 and p < 0.01, suggesting a strong statistical connection between these seemingly disparate phenomena. Despite the absurdity of the association, our findings indicate a surprisingly robust link between senatorial preferences in California and kerosene consumption in French Polynesia. Further research is warranted to explore the mechanisms underlying this unexpected correlation.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of research is often filled with unexpected discoveries and bizarre correlations that leave even the most astute scholars scratching their heads. In the realm of politics and energy consumption, one might not anticipate any meaningful intersection between the votes for Libertarian Senators in California and the kerosene usage patterns in the paradisiacal French Polynesia. However, as the saying goes, truth is often stranger than fiction. In this study, we delve into the peculiar relationship between these seemingly unrelated variables.
While it may initially seem like pairing a pineapple with a pepperoni pizza, our analysis of the data reveals an astonishingly high correlation coefficient, violating the conventional wisdom that these two phenomena could not possibly be connected. Our investigation serves as a reminder that in the intricate tapestry of social, political, and economic dynamics, there are often unexpected threads intertwining disparate elements.
One might question our decision to explore such an esoteric and whimsical topic. However, as thinkers and researchers, it is our duty to shine a light on even the most convoluted and confounding relationships, for it is in these unconventional findings that we may uncover new insights and push the boundaries of knowledge. So, join us on this scholarly escapade as we unravel the enigmatic connection between Libertarian votes in the Golden State and the aromatic allure of kerosene in the South Pacific.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "The Political Landscape of California," Smith et al. find extensive data on senatorial voting patterns encompassing multiple ideologies, including Libertarian preferences, in the state of California. Additionally, Doe and Jones explore the patterns of energy consumption in various Pacific island nations in "Island Energy Trends." These serious scholarly endeavors lay the groundwork for our investigation into the unlikely correlation between Libertarian votes for Senators in California and kerosene usage in French Polynesia.

While the topic of political preferences and energy consumption may seem weighty and formidable, it is essential to acknowledge the light-hearted and even whimsical nature of our investigation. As we tread the tenuous bridge between political ideology and fuel usage, we must also recognize the presence of some literary works that, although not directly related to our scholarly pursuit, possess titles that could easily be mistaken for studies on political and energy dynamics. For instance, "Libertarianism and the Search for Paradise" and "Kerosene Dreams: A Tale of Fuel and Fiction" are not real academic works, but their names evoke the precise amalgamation of politics and energy that we seek to explore.

A particularly unconventional source that has contributed to our understanding of this peculiar connection is a social media post by a self-proclaimed political pundit, who, in a moment of unanticipated insight, tweeted: "The Libertarian vote in California is as unpredictable as the kerosene consumption in French Polynesia – both defy conventional logic!" While this post may have been intended as a jest, little did the author realize that it would serve as the catalyst for sparking our curiosity in this intriguing relationship.

In light of our unorthodox pursuits, we invite readers to approach our investigation with a sense of openness and levity, for it is in the most unexpected places that we often unearth valuable insights. As we delve into this unusual linkage, let us not lose sight of the potential for elucidating new perspectives and shedding light on the enigmatic crossroads of seemingly unconnected phenomena.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Libertarian votes for Senators in California and Kerosene used in French Polynesia. Make lots of 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 1990 to 2010

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 Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia"

[[ABSTRACT]]
This research investigates the peculiar relationship between Libertarian votes for Senators in California and kerosene used in French Polynesia. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we conducted a comprehensive assessment from 1990 to 2010. Surprisingly, our analysis revealed a remarkably high correlation coefficient of 0.9490973 and p < 0.01, suggesting a strong statistical connection between these seemingly disparate phenomena. Despite the absurdity of the association, our findings indicate a surprisingly robust link between senatorial preferences in California and kerosene consumption in French Polynesia. Further research is warranted to explore the mechanisms underlying this unexpected correlation.

[[INTRODUCTION]]
The world of research is often filled with unexpected discoveries and bizarre correlations that leave even the most astute scholars scratching their heads. In the realm of politics and energy consumption, one might not anticipate any meaningful intersection between the votes for Libertarian Senators in California and the kerosene usage patterns in the paradisiacal French Polynesia. However, as the saying goes, truth is often stranger than fiction. In this study, we delve into the peculiar relationship between these seemingly unrelated variables.
While it may initially seem like pairing a pineapple with a pepperoni pizza, our analysis of the data reveals an astonishingly high correlation coefficient, violating the conventional wisdom that these two phenomena could not possibly be connected. Our investigation serves as a reminder that in the intricate tapestry of social, political, and economic dynamics, there are often unexpected threads intertwining disparate elements.
One might question our decision to explore such an esoteric and whimsical topic. However, as thinkers and researchers, it is our duty to shine a light on even the most convoluted and confounding relationships, for it is in these unconventional findings that we may uncover new insights and push the boundaries of knowledge. So, join us on this scholarly escapade as we unravel the enigmatic connection between Libertarian votes in the Golden State and the aromatic allure of kerosene in the South Pacific.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To explore the inexplicably entangled realms of politics and energy, our research team embarked on a voyage through the vast seas of data, navigating the treacherous waters of statistical analysis and computational models. Our inquiries began with an extensive search across the internet, charting a course to plunder the bounty of information from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration.

The first stage of our odyssey involved collecting historical voting data from California senatorial elections, specifically focusing on the share of votes garnered by Libertarian candidates. Likewise, we charted the consumption of kerosene in the tropical haven of French Polynesia, extracting figures from the Energy Information Administration to illuminate the patterns of this peculiar fuel's usage from 1990 to 2010.

With our datasets in hand, we set sail for the uncharted territories of statistical analysis, employing the venerable tools of linear regression and correlation analysis to navigate the turbulent seas of mathematical relationships. Our computations sought to uncover any semblance of coherence between the votes for Libertarian Senators in California and the consumption of kerosene in French Polynesia.

Amidst our analytical endeavors, we also explored the potential influence of external factors such as economic indicators, climate patterns, and cultural trends on the apparent connection between political leanings and energy preferences.

The voyage of discovery culminated in the revelation of a strikingly high correlation coefficient of 0.9490973, accompanied by a p-value of less than 0.01, signaling a remarkably robust statistical relationship between these seemingly incongruous variables.

Upon unearthing this perplexing association, we were reminded of the age-old adage that truth is often stranger than fiction. As we hoisted our sails and navigated the choppy waters of unconventional data relationships, we were propelled by the winds of curiosity and driven by the desire to shed light on the enigmatic threads woven into the fabric of societal phenomena.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Libertarian votes for Senators in California and Kerosene used in French Polynesia. Make lots of 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]]
"The Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia"

[[ABSTRACT]]
This research investigates the peculiar relationship between Libertarian votes for Senators in California and kerosene used in French Polynesia. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we conducted a comprehensive assessment from 1990 to 2010. Surprisingly, our analysis revealed a remarkably high correlation coefficient of 0.9490973 and p < 0.01, suggesting a strong statistical connection between these seemingly disparate phenomena. Despite the absurdity of the association, our findings indicate a surprisingly robust link between senatorial preferences in California and kerosene consumption in French Polynesia. Further research is warranted to explore the mechanisms underlying this unexpected correlation.

[[LITERATURE REVIEW]]
In "The Political Landscape of California," Smith et al. find extensive data on senatorial voting patterns encompassing multiple ideologies, including Libertarian preferences, in the state of California. Additionally, Doe and Jones explore the patterns of energy consumption in various Pacific island nations in "Island Energy Trends." These serious scholarly endeavors lay the groundwork for our investigation into the unlikely correlation between Libertarian votes for Senators in California and kerosene usage in French Polynesia.
While the topic of political preferences and energy consumption may seem weighty and formidable, it is essential to acknowledge the light-hearted and even whimsical nature of our investigation. As we tread the tenuous bridge between political ideology and fuel usage, we must also recognize the presence of some literary works that, although not directly related to our scholarly pursuit, possess titles that could easily be mistaken for studies on political and energy dynamics. For instance, "Libertarianism and the Search for Paradise" and "Kerosene Dreams: A Tale of Fuel and Fiction" are not real academic works, but their names evoke the precise amalgamation of politics and energy that we seek to explore.
A particularly unconventional source that has contributed to our understanding of this peculiar connection is a social media post by a self-proclaimed political pundit, who, in a moment of unanticipated insight, tweeted: "The Libertarian vote in California is as unpredictable as the kerosene consumption in French Polynesia – both defy conventional logic!" While this post may have been intended as a jest, little did the author realize that it would serve as the catalyst for sparking our curiosity in this intriguing relationship.
In light of our unorthodox pursuits, we invite readers to approach our investigation with a sense of openness and levity, for it is in the most unexpected places that we often unearth valuable insights. As we delve into this unusual linkage, let us not lose sight of the potential for elucidating new perspectives and shedding light on the enigmatic crossroads of seemingly unconnected phenomena.

[[RESULTS]]
The results of our research unearthed a striking correlation between Libertarian votes for Senators in California and kerosene usage in the idyllic French Polynesia. We found a correlation coefficient of 0.9490973, indicating a remarkably strong relationship between these seemingly disparate variables. Further bolstering our findings, the coefficient of determination (r-squared) was calculated to be 0.9007856, signifying that an impressive 90.08% of the variation in kerosene usage can be explained by the Libertarian votes for Senators in California. Moreover, the p-value was found to be less than 0.01, providing compelling evidence that this relationship is not the product of mere coincidence or random chance.
To visually capture the robust association we uncovered, we present a scatterplot (Fig. 1) that vividly illustrates the remarkably tight clustering of data points. The scatterplot itself is a testament to the unanticipated harmony between these two seemingly incongruous variables.
These findings underscore the remarkable and confounding nature of statistical relationships in the social and political realm, where unexpected connections can emerge from the most unpredictable sources. Clearly, the world of data analysis continues to defy conventional wisdom and challenge our preconceived notions, reminding us that truth can indeed be stranger than fiction.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation reveal a remarkable and robust correlation between Libertarian votes for Senators in California and kerosene usage in French Polynesia, supporting the prior research that hinted at the existence of an unlikely connection. While the association may seem as improbable as finding a palm tree in the Arctic, our findings emphasize the significance of exploring uncharted territories in behavioral and energy economics.

Our data substantiates the seminal works of Smith et al. and Doe and Jones, who laid the groundwork for our unconventional pursuit. The marriage of political preferences in California and kerosene consumption in French Polynesia may appear as mismatched as a hula dancer in a snowstorm, yet our statistical analysis aligns with the essence of these scholarly foundations.

Acknowledging the whimsical nature of this investigation, it is imperative to highlight the inadvertent insights extracted from seemingly amusing sources. An off-hand tweet in the vast sea of social media, akin to a pearl in an oyster, serendipitously inspired our examination of this perplexing linkage. The serendipitous mélange of political livelihood and energy expenditure that compelled our curiosity is a testimony to the value of acknowledging unorthodox sources of inspiration.

Our findings present a scatterplot illustrative of the remarkably tight clustering of data points, akin to finding a paradisiacal lagoon amidst the tempestuous political and energy landscapes. The scatterplot serves as an apt visual testament to the unforeseen harmony between these seemingly incongruous variables, mirroring the enigmatic consonance of seemingly unrelated phenomena.

In conclusion, the remarkable correlation uncovered in this study challenges the conventional wisdom and beckons researchers to ponder the serendipitous interplay of seemingly unrelated variables. While the investigation may have commenced with a measure of whimsy, the empirical evidence astutely highlights the uncanny interconnectedness of political preferences and energy usage, evincing the potential for novel insights from the most extraordinary of places. This improbable correlation serves as a poignant reminder that the world of empirical research and data analysis is replete with revelations that transcend the bounds of conventional comprehension.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics 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 Libertarian votes for Senators in California and Kerosene used in French Polynesia. Make lots of 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]]
"The Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia"

[[ABSTRACT]]
This research investigates the peculiar relationship between Libertarian votes for Senators in California and kerosene used in French Polynesia. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we conducted a comprehensive assessment from 1990 to 2010. Surprisingly, our analysis revealed a remarkably high correlation coefficient of 0.9490973 and p < 0.01, suggesting a strong statistical connection between these seemingly disparate phenomena. Despite the absurdity of the association, our findings indicate a surprisingly robust link between senatorial preferences in California and kerosene consumption in French Polynesia. Further research is warranted to explore the mechanisms underlying this unexpected correlation.

[[INTRDUCTION]]
The world of research is often filled with unexpected discoveries and bizarre correlations that leave even the most astute scholars scratching their heads. In the realm of politics and energy consumption, one might not anticipate any meaningful intersection between the votes for Libertarian Senators in California and the kerosene usage patterns in the paradisiacal French Polynesia. However, as the saying goes, truth is often stranger than fiction. In this study, we delve into the peculiar relationship between these seemingly unrelated variables.
While it may initially seem like pairing a pineapple with a pepperoni pizza, our analysis of the data reveals an astonishingly high correlation coefficient, violating the conventional wisdom that these two phenomena could not possibly be connected. Our investigation serves as a reminder that in the intricate tapestry of social, political, and economic dynamics, there are often unexpected threads intertwining disparate elements.
One might question our decision to explore such an esoteric and whimsical topic. However, as thinkers and researchers, it is our duty to shine a light on even the most convoluted and confounding relationships, for it is in these unconventional findings that we may uncover new insights and push the boundaries of knowledge. So, join us on this scholarly escapade as we unravel the enigmatic connection between Libertarian votes in the Golden State and the aromatic allure of kerosene in the South Pacific.

[[RESULTS]]
The results of our research unearthed a striking correlation between Libertarian votes for Senators in California and kerosene usage in the idyllic French Polynesia. We found a correlation coefficient of 0.9490973, indicating a remarkably strong relationship between these seemingly disparate variables. Further bolstering our findings, the coefficient of determination (r-squared) was calculated to be 0.9007856, signifying that an impressive 90.08% of the variation in kerosene usage can be explained by the Libertarian votes for Senators in California. Moreover, the p-value was found to be less than 0.01, providing compelling evidence that this relationship is not the product of mere coincidence or random chance.
To visually capture the robust association we uncovered, we present a scatterplot (Fig. 1) that vividly illustrates the remarkably tight clustering of data points. The scatterplot itself is a testament to the unanticipated harmony between these two seemingly incongruous variables.
These findings underscore the remarkable and confounding nature of statistical relationships in the social and political realm, where unexpected connections can emerge from the most unpredictable sources. Clearly, the world of data analysis continues to defy conventional wisdom and challenge our preconceived notions, reminding us that truth can indeed be stranger than fiction.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the inexplicable correlation between Libertarian votes for Senators in California and kerosene consumption in French Polynesia has yielded some rather illuminating and combustible findings. While the swirling mists of mystery still enshroud the exact mechanisms driving this perplexing connection, our research has unequivocally demonstrated the existence of a statistically robust relationship between these seemingly unrelated variables.

The unexpectedly high correlation coefficient of 0.9490973 and the infinitesimally small p-value have raised more than a few eyebrows among our colleagues, as well as prompting a fair share of perplexed chuckles. It seems that the tides of statistical fate have conspired to link the libertarian spirit of California with the aromatic allure of kerosene in the tranquil waters of French Polynesia.

While some may dismiss our findings as mere statistical tomfoolery, the undeniable strength of our correlation demands serious consideration. Our research serves as a quirky reminder that the world of data analysis is rife with surprises, and that truth can indeed spring from the most unlikely bedfellows.

In light of these findings, we cannot help but feel a tantalizing sense of curiosity about the intricate web of cause and effect that binds these two disparate realms. However, we must vehemently assert that no further investigation is warranted in this peculiar realm of inquiry. The time has come to extinguish the flame of curiosity and let this kerosene-drenched mystery rest.

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 Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Social Sciences

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 Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Transnational Energy and Political Dynamics (CTEPD)

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 Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia with an abstract of This research investigates the peculiar relationship between Libertarian votes for Senators in California and kerosene used in French Polynesia. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we conducted a comprehensive assessment from 1990 to 2010. Surprisingly, our analysis revealed a remarkably high correlation coefficient of 0.9490973 and p < 0.01, suggesting a strong statistical connection between these seemingly disparate phenomena. Despite the absurdity of the association, our findings indicate a surprisingly robust link between senatorial preferences in California and kerosene consumption in French Polynesia. Further research is warranted to explore the mechanisms underlying this unexpected correlation.

ChatGPT:

libertarian votes, senators, California, kerosene consumption, French Polynesia, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, statistical analysis, research, mechanisms, unexpected correlation

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

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

Correlation r = 0.9490973 (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 = 0.9007856 (Coefficient of determination)
This means 90.1% of the change in the one variable (i.e., Kerosene used in French Polynesia) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in California) over the 7 years from 1990 through 2010.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00109.^Show 0.0010923443274678640000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.95 in 0.109% of random cases. Said differently, if you correlated 915 random variables^Note Which I absolutely did.
with the same 6 degrees of freedom, ^Note 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.

[ 0.69, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1992	1994	1998	2000	2004	2006	2010
Votes for Libertarian Senators in California (Total votes)	483718	179100	93926	187718	216522	133851	175242
Kerosene used in French Polynesia (Million Barrels/Day)	0.04224	0.02117	0.02117	0.0211202	0.0211202	0.0211781	0.0211781

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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.
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.
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. ^Note 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. ^{Show the steps to do this.} 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([483718,179100,93926,187718,216522,133851,175242,])
array_2 = np.array([0.04224,0.02117,0.02117,0.0211202,0.0211202,0.0211781,0.0211781,])
array_1_name = "Votes for Libertarian Senators in California"
array_2_name = "Kerosene used in French Polynesia"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Votes for Libertarian Senators in California
Line chart for only Kerosene used in French Polynesia
AI-generated correlation image
The spurious research paper: The Libertarian Leverage: A Burning Connection Between Senatorial Preferences in California and Kerosene Consumption in French Polynesia

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 5532 · Black Variable ID: 26208 · Red Variable ID: 24432


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: