Spurious correlation #4,625 · 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 New York and the second variable is Gasoline pumped in Netherlands Antilles. The chart goes from 1980 to 2016, 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 New York and the second variable is Gasoline pumped in Netherlands Antilles. The chart goes from 1980 to 2016, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more Libertarian-friendly Senators were elected in New York, there was a push for deregulation, leading to a boom in the gasoline industry. This unexpected demand for gasoline pumped in Netherlands Antilles created a supply chain frenzy, causing prices to soar. Who knew that New York politics could have such a fuelish impact on the Caribbean gas market!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a surreal, colorful cityscape with skyscrapers representing New York in a retro-futuristic vaporwave-style aesthetic. In the foreground, depict workers busy pumping gasoline into containers against a backdrop of palm trees and tropical scenery to represent the Netherlands Antilles. Include visual cues to convey the surge in gasoline demand, such as stylized price charts, gas pumps, or fuel gauges. The scene should capture the chaotic yet vibrant energy of a rapidly shifting global market. 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: Libertarian votes for Senators in New York and Gasoline pumped in Netherlands Antilles. 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: Cyber folk An image that looks like it is a scene from a Pixar movie Vaporwave Macabre Charcoal
ChatGPT: Vaporwave

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 Libertarian votes for Senators in New York and Gasoline pumped in Netherlands Antilles, in the following situation: As more Libertarian-friendly Senators were elected in New York, there was a push for deregulation, leading to a boom in the gasoline industry. This unexpected demand for gasoline pumped in Netherlands Antilles created a supply chain frenzy, causing prices to soar. Who knew that New York politics could have such a fuelish impact on the Caribbean gas market!. Keep the description simple.
ChatGPT: In New York, more people voted for Libertarian senators, leading to a push for deregulation. This resulted in a sudden increase in the demand for gasoline. All the way in the Netherlands Antilles, workers hustled to pump more gasoline to meet this new demand. As the supply chain frenzy ensued, gasoline prices soared, creating a ripple effect in the Caribbean gas market.

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: [ Vaporwave ] and depicting this scene: In New York, more people voted for Libertarian senators, leading to a push for deregulation. This resulted in a sudden increase in the demand for gasoline. All the way in the Netherlands Antilles, workers hustled to pump more gasoline to meet this new demand. As the supply chain frenzy ensued, gasoline prices soared, creating a ripple effect in the Caribbean gas market. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a surreal, colorful cityscape with skyscrapers representing New York in a retro-futuristic vaporwave-style aesthetic. In the foreground, depict workers busy pumping gasoline into containers against a backdrop of palm trees and tropical scenery to represent the Netherlands Antilles. Include visual cues to convey the surge in gasoline demand, such as stylized price charts, gas pumps, or fuel gauges. The scene should capture the chaotic yet vibrant energy of a rapidly shifting global market.

*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 an increase in Libertarian votes for Senators in New York caused Gasoline pumped in Netherlands Antilles to increase.

AI academic paper

(Because p < 0.01)

Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity

The Journal of Political Petroleum Studies

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 New York and Gasoline pumped in Netherlands Antilles. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity

[[ABSTRACT]]
This study giddily gambols through the puzzling relationship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. The researchers traversed the trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to teasingly tackle this titillating topic. Astoundingly, a correlation coefficient of 0.9294978 and p < 0.01 was unearthed for the years 1980 to 2016. These fascinating findings raise questions that tickle the intellect and spark a sense of wonder in the most stoic of researchers. Digging deeper into the connections between political leanings and fuel consumption, this study aims to infuse a bit of levity into the often staid world of academic research.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of political leanings and socioeconomic indicators has long been a subject of scholarly inquiry, yielding insights into the complex interplay of human behavior and societal trends. However, amidst this landscape of typical research pursuits, the curious correlation between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles stands out like a hippopotamus in a ballet class.
The allure of this unlikely pairing has led us to embark on this whimsical journey, where we aim to shed light on the enigmatic connection that has eluded the keen scholarly gaze for far too long. One cannot help but approach this investigation with a wry smile, pondering the possibility of a clandestine love affair between political ideologies and vehicular propulsion fluids.
As we delve into the labyrinth of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we do so with a sense of adventure and a dash of humor, fully embracing the unexpected twists and comedic potential of our research endeavor. After all, what is academia if not a playground for inquisitive minds to frolic and froth over the most unconventional of correlations?
Armed with statistical rigor and a playful spirit, we invite our fellow scholars to join us on this capricious odyssey, where the pursuit of knowledge mingles with the joy of uncovering the delightfully absurd. As we unravel the intricacies of this tantalizing tale, we hope to infuse a touch of levity into the often solemn halls of academic inquiry and, perhaps, ignite a few chuckles along the way.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The burgeoning field of interdisciplinary research has seen a vast array of peculiar correlations and unexpected connections, ranging from the relationship between economic growth and the consumption of chocolate (Smith, 2015) to the link between political affiliations and one’s preference for spicy foods (Doe, 2017). However, none quite tickles the fancy like the curious kinship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. As we brace ourselves for the bewitching journey ahead, let us first wade through the serious literature before we succumb to the siren call of jest and whimsy.

Smith and colleagues (2010) have expounded upon the enigmatic interplay of political leanings and economic behaviors, shedding light on the intricate dance between ideological stances and consumer preferences. Moreover, Doe et al. (2013) have probed the fascinating fusion of cultural inclinations and energy consumption, unraveling the curious tapestry that links societal beliefs with the demand for fuel. Jones (2016) eloquently extends this line of inquiry by examining the ripple effects of political ideologies on global market dynamics, offering a panoramic view of the nuanced interdependencies that underpin human decision-making processes. Despite these scholarly forays into the realms of politics and petroleum, the specific link between Libertarian votes in New York and gasoline usage in the Netherlands Antilles has eluded their discerning gazes.

Turning to the world of non-fiction, a smorgasbord of literature awaits the intrepid explorer seeking to unearth the uncanny connections that lay veiled beneath the surface. In "Freakonomics" (Levitt & Dubner, 2005), the authors cunningly dissect the bizarre associations that animate human behavior, preparing the soil for unexpected revelations that verily leap off the pages. In a similar vein, "The Tipping Point" (Gladwell, 2000) offers a tantalizing glimpse into the undercurrents of societal trends, hinting at the unseen forces that might subtly nudge individuals towards certain political proclivities and fuel-related habits.

Adding a touch of literary whimsy to our expedition, we turn to the world of fiction where the improbable often becomes the plausible, and the logical defies reason. In "The Hitchhiker's Guide to the Galaxy" (Adams, 1979), the eponymous guide presents a veritable cornucopia of oddities and curiosities, mirroring our own pursuit of the confounding correlation between political preferences and petrol promenades. Drawing inspiration from the wry humor of "Catch-22" (Heller, 1961), we revel in the absurdity of our own quest, recognizing the farcical nature of our scholarly endeavors.

In the realm of cinema, "The Big Lebowski" (Coen & Coen, 1998) offers a comical perspective on the ripples of political ideologies in everyday life, though the connection to gasoline in the Netherlands Antilles may be tenuous at best. "Fear and Loathing in Las Vegas" (Gilliam, 1998) provides a zany, if not entirely relevant, exploration of countercultural movements and the ethos of rebellion that could be tangentially related to our investigation.

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 New York and Gasoline pumped in Netherlands Antilles. 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]]
Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity

[[ABSTRACT]]
This study giddily gambols through the puzzling relationship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. The researchers traversed the trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to teasingly tackle this titillating topic. Astoundingly, a correlation coefficient of 0.9294978 and p < 0.01 was unearthed for the years 1980 to 2016. These fascinating findings raise questions that tickle the intellect and spark a sense of wonder in the most stoic of researchers. Digging deeper into the connections between political leanings and fuel consumption, this study aims to infuse a bit of levity into the often staid world of academic research.

[[LITERATURE REVIEW]]
The burgeoning field of interdisciplinary research has seen a vast array of peculiar correlations and unexpected connections, ranging from the relationship between economic growth and the consumption of chocolate (Smith, 2015) to the link between political affiliations and one’s preference for spicy foods (Doe, 2017). However, none quite tickles the fancy like the curious kinship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. As we brace ourselves for the bewitching journey ahead, let us first wade through the serious literature before we succumb to the siren call of jest and whimsy.
Smith and colleagues (2010) have expounded upon the enigmatic interplay of political leanings and economic behaviors, shedding light on the intricate dance between ideological stances and consumer preferences. Moreover, Doe et al. (2013) have probed the fascinating fusion of cultural inclinations and energy consumption, unraveling the curious tapestry that links societal beliefs with the demand for fuel. Jones (2016) eloquently extends this line of inquiry by examining the ripple effects of political ideologies on global market dynamics, offering a panoramic view of the nuanced interdependencies that underpin human decision-making processes. Despite these scholarly forays into the realms of politics and petroleum, the specific link between Libertarian votes in New York and gasoline usage in the Netherlands Antilles has eluded their discerning gazes.
Turning to the world of non-fiction, a smorgasbord of literature awaits the intrepid explorer seeking to unearth the uncanny connections that lay veiled beneath the surface. In "Freakonomics" (Levitt & Dubner, 2005), the authors cunningly dissect the bizarre associations that animate human behavior, preparing the soil for unexpected revelations that verily leap off the pages. In a similar vein, "The Tipping Point" (Gladwell, 2000) offers a tantalizing glimpse into the undercurrents of societal trends, hinting at the unseen forces that might subtly nudge individuals towards certain political proclivities and fuel-related habits.
Adding a touch of literary whimsy to our expedition, we turn to the world of fiction where the improbable often becomes the plausible, and the logical defies reason. In "The Hitchhiker's Guide to the Galaxy" (Adams, 1979), the eponymous guide presents a veritable cornucopia of oddities and curiosities, mirroring our own pursuit of the confounding correlation between political preferences and petrol promenades. Drawing inspiration from the wry humor of "Catch-22" (Heller, 1961), we revel in the absurdity of our own quest, recognizing the farcical nature of our scholarly endeavors.
In the realm of cinema, "The Big Lebowski" (Coen & Coen, 1998) offers a comical perspective on the ripples of political ideologies in everyday life, though the connection to gasoline in the Netherlands Antilles may be tenuous at best. "Fear and Loathing in Las Vegas" (Gilliam, 1998) provides a zany, if not entirely relevant, exploration of countercultural movements and the ethos of rebellion that could be tangentially related to our investigation.

[[RESULTS]]
The bountiful data collected and analyzed have yielded some remarkably intriguing results. A robust correlation coefficient of 0.9294978 and an r-squared value of 0.8639661 were uncovered, indicating a strikingly strong relationship between Libertarian votes for Senators in New York and gasoline pumped in the Netherlands Antilles for the years 1980 to 2016. With the p-value falling below 0.01, these findings are anything but run-of-the-mill; they practically pirouette into the realm of statistical significance, winking mischievously at the traditional bounds of academic inquiry.
The scatterplot (Fig. 1) showcases this connection in all its whimsical glory, illustrating the dance of data points that waltz along the axis with an undeniable synchronicity. It's as if political ideologies and gasoline consumption have choreographed a dazzling tango, leaving onlookers both bemused and bewitched by the unexpected elegance of their partnership.
This enigmatic correlation evokes a sense of wonder, inviting us to ponder the surreal symphony of human behavior and societal dynamics. While some may be tempted to dismiss these results as a statistical fluke, the robustness of the findings cannot be ignored. It's as if the numbers themselves are nudging us with a playful wink, urging us to embrace the whimsy and delve deeper into the mysteries of this captivating conundrum.
The richness of these findings paves the way for future research to embrace the unconventional, the eccentric, and the outright zany in the pursuit of knowledge. By infusing a touch of levity into the often serious discourse of academia, we can open new doors of inquiry and invite a sense of delight into the scholarly domain. As we reflect on these results, let us not forget to approach our research endeavors with a twinkle in our eyes and a readiness to uncover the unexpected.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The serendipitous synergy between Libertarian votes for Senators in New York and gasoline pumped in the Netherlands Antilles has left both researchers and readers in a state of bemused disbelief. The robust correlation coefficient and r-squared value, coupled with a p-value below 0.01, all point towards a compelling connection that demands further exploration, much like a mysterious carnival ride beckoning the adventurous.

This study's findings seem to affirm the earlier work by Smith and colleagues (2010), who probed the intricate dance between political leanings and consumer preferences. The surreptitious embrace of Libertarian ideals in New York appears to reverberate across the seas, persuading the denizens of the Netherlands Antilles to fuel their vehicles with a discernible gusto. The levels of gasoline pumped in these tropical islands could be seen as a manifestation of the Libertarian spirit wafting over from the United States, a phenomenon akin to an ideological trade wind.

Doe et al. (2013) also alluded to the captivating fusion of cultural inclinations and energy consumption, hinting at the possibility of ideological undercurrents shaping patterns of fuel usage. Our findings seem to mirror this perspective, portraying a whimsical symbiosis between political leanings and the fervor with which gasoline is drawn from the bowels of the earth. It's as if the act of refueling becomes an unwitting paean to one's political affiliations, carried out with a fervor that transcends the mundane task of topping up the tank.

Through these findings, we have uncovered a portal to a realm where the rational and the ludicrous waltz hand in hand. The scatterplot (Fig. 1) paints a picture of data points twirling and spinning with an exuberant synchronicity, reminiscent of a splendid ballroom dance where statistical significance and whimsy engage in a lively tango.

These findings invite a mirthful reconsideration of the influences that nudge human behaviors and societal trends. As we move forward, it is imperative to approach our research with an open mind and an appetite for the unexpected, for who knows what other enigmatic connections await the discerning gaze of intrepid scholars.

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 New York and Gasoline pumped in Netherlands Antilles. 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]]
Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity

[[ABSTRACT]]
This study giddily gambols through the puzzling relationship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. The researchers traversed the trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to teasingly tackle this titillating topic. Astoundingly, a correlation coefficient of 0.9294978 and p < 0.01 was unearthed for the years 1980 to 2016. These fascinating findings raise questions that tickle the intellect and spark a sense of wonder in the most stoic of researchers. Digging deeper into the connections between political leanings and fuel consumption, this study aims to infuse a bit of levity into the often staid world of academic research.

[[INTRDUCTION]]
The intersection of political leanings and socioeconomic indicators has long been a subject of scholarly inquiry, yielding insights into the complex interplay of human behavior and societal trends. However, amidst this landscape of typical research pursuits, the curious correlation between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles stands out like a hippopotamus in a ballet class.
The allure of this unlikely pairing has led us to embark on this whimsical journey, where we aim to shed light on the enigmatic connection that has eluded the keen scholarly gaze for far too long. One cannot help but approach this investigation with a wry smile, pondering the possibility of a clandestine love affair between political ideologies and vehicular propulsion fluids.
As we delve into the labyrinth of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we do so with a sense of adventure and a dash of humor, fully embracing the unexpected twists and comedic potential of our research endeavor. After all, what is academia if not a playground for inquisitive minds to frolic and froth over the most unconventional of correlations?
Armed with statistical rigor and a playful spirit, we invite our fellow scholars to join us on this capricious odyssey, where the pursuit of knowledge mingles with the joy of uncovering the delightfully absurd. As we unravel the intricacies of this tantalizing tale, we hope to infuse a touch of levity into the often solemn halls of academic inquiry and, perhaps, ignite a few chuckles along the way.

[[RESULTS]]
The bountiful data collected and analyzed have yielded some remarkably intriguing results. A robust correlation coefficient of 0.9294978 and an r-squared value of 0.8639661 were uncovered, indicating a strikingly strong relationship between Libertarian votes for Senators in New York and gasoline pumped in the Netherlands Antilles for the years 1980 to 2016. With the p-value falling below 0.01, these findings are anything but run-of-the-mill; they practically pirouette into the realm of statistical significance, winking mischievously at the traditional bounds of academic inquiry.
The scatterplot (Fig. 1) showcases this connection in all its whimsical glory, illustrating the dance of data points that waltz along the axis with an undeniable synchronicity. It's as if political ideologies and gasoline consumption have choreographed a dazzling tango, leaving onlookers both bemused and bewitched by the unexpected elegance of their partnership.
This enigmatic correlation evokes a sense of wonder, inviting us to ponder the surreal symphony of human behavior and societal dynamics. While some may be tempted to dismiss these results as a statistical fluke, the robustness of the findings cannot be ignored. It's as if the numbers themselves are nudging us with a playful wink, urging us to embrace the whimsy and delve deeper into the mysteries of this captivating conundrum.
The richness of these findings paves the way for future research to embrace the unconventional, the eccentric, and the outright zany in the pursuit of knowledge. By infusing a touch of levity into the often serious discourse of academia, we can open new doors of inquiry and invite a sense of delight into the scholarly domain. As we reflect on these results, let us not forget to approach our research endeavors with a twinkle in our eyes and a readiness to uncover the unexpected.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the findings of this study whimsically waltz into the realm of statistical significance, twirling together the worlds of political leanings and gasoline consumption in a delightful dance. The palpable correlation between Libertarian votes for Senators in New York and the amount of gasoline pumped in the Netherlands Antilles from 1980 to 2016 raises eyebrows and elicits the kind of bemused chuckles usually reserved for a particularly clever pun.

The robust correlation coefficient and r-squared value, coupled with the tantalizingly low p-value, prance about like a pair of jesters, gleefully defying the expectations of traditional academic inquiry. The scatterplot, akin to a surrealist painting, captures the whimsical romance between political ideologies and fuel consumption, leaving us to wonder if they are secret lovers in the grand masquerade of global socio-political dynamics.

As we bid adieu to this captivating conundrum, it is clear that the results of this study beckon us to embrace the eccentric, to tango with the unconventional, and to revel in the sheer audacity of academic inquiry. With a nod to the levity and mirth that have enlivened this research endeavor, it is with utter certainty that no further research is needed in this curious domain of scholarly pursuit.

After all, why venture further into the unknown when we have already unearthed a treasure trove of amusement and intellectual titillation? Let this be a whimsical waypoint in the annals of academic discovery, where the unexpected confluence of Libertarian leanings and gasoline galore has charmed and amused in equal measure.

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 Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Petroleum Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Applied Energy Economics and Freedom Studies

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 Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity with an abstract of This study giddily gambols through the puzzling relationship between Libertarian votes for Senators in New York and the levels of gasoline pumped in the Netherlands Antilles. The researchers traversed the trove of data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration to teasingly tackle this titillating topic. Astoundingly, a correlation coefficient of 0.9294978 and p < 0.01 was unearthed for the years 1980 to 2016. These fascinating findings raise questions that tickle the intellect and spark a sense of wonder in the most stoic of researchers. Digging deeper into the connections between political leanings and fuel consumption, this study aims to infuse a bit of levity into the often staid world of academic research.

ChatGPT:

Libertarian, gasoline consumption, Senator voting, New York, Netherlands Antilles, correlation coefficient, political leanings, fuel consumption, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, academic research

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

Gasoline pumped in Netherlands Antilles
Detailed data title: Volume of gasoline pumped consumed in Netherlands Antilles in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Gasoline pumped in Netherlands Antilles

Correlation r = 0.9294978 (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 = 0.8639661 (Coefficient of determination)
This means 86.4% of the change in the one variable (i.e., Gasoline pumped in Netherlands Antilles) is predictable based on the change in the other (i.e., Votes for Libertarian Senators in New York) over the 10 years from 1980 through 2016.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.9E-5.^Show 0.0000992120297873208100000000
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 0.93 in 0.0099% of random cases. Said differently, if you correlated 10,079 random variables^Note Which I absolutely did.
with the same 9 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.72, 0.98 ] 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.

	1988	1992	1994	1998	2000	2004	2006	2010	2012	2016
Votes for Libertarian Senators in New York (Total votes)	12064	108530	17991	8223	4734	19073	20996	43285	31894	48121
Gasoline pumped in Netherlands Antilles (Million Barrels/Day)	2	3.5	2	2	1.91109	2.00432	2.12666	2.22014	2.02149	2.066

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
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.
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([12064,108530,17991,8223,4734,19073,20996,43285,31894,48121,])
array_2 = np.array([2,3.5,2,2,1.91109,2.00432,2.12666,2.22014,2.02149,2.066,])
array_1_name = "Votes for Libertarian Senators in New York"
array_2_name = "Gasoline pumped in Netherlands Antilles"

# 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 New York
Line chart for only Gasoline pumped in Netherlands Antilles
AI-generated correlation image
The spurious research paper: Libertarian Leanings and Gasoline Galore: Analyzing the Alluring Affinity

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 4625 · Black Variable ID: 26288 · Red Variable ID: 24741


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