about · email me · subscribe
Spurious correlation #4,446 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Democrat Presidential candidate in Montana and the second variable is Gasoline pumped in Togo.  The chart goes from 1980 to 2020, and the two variables track closely in value over that time. Small Image

AI explanation

As the support for the Democratic candidate in Montana surged, it sparked a wave of economic optimism. This led to an unexpected ripple effect in Togo, where the demand for gasoline mysteriously skyrocketed. It seems like even in the world of fuel, it's all about finding the right candidate to 'ignite' progress!

Model: dalle-3
Prompt: Generate an image of a surreal setting featuring a bustling polling station in Montana with long queues of voters proudly displaying "I Voted" stickers. Blend this scene with a lively gas station in Togo crowded with people waiting to pump gasoline into their vehicles. The juxtaposition of the political fervor and economic activity should convey a sense of energy and hope, symbolizing the unexpected connection between political support and economic activity. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. 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: a funny image macro A scene from Skyrim Celtic art Cute 2D animation Cute cartoon
ChatGPT: A scene from Skyrim

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo, in the following situation: As the support for the Democratic candidate in Montana surged, it sparked a wave of economic optimism. This led to an unexpected ripple effect in Togo, where the demand for gasoline mysteriously skyrocketed. It seems like even in the world of fuel, it's all about finding the right candidate to 'ignite' progress!. Keep the description simple.
ChatGPT: In Montana, a line of voters stretches around a polling station, with many people proudly displaying "I Voted" stickers for the Democratic Presidential candidate. Nearby, a gas station in Togo is bustling with activity as people queue up to pump gasoline into their vehicles, creating a sudden surge in demand. Both scenes are filled with a sense of energy and hope, symbolizing the unexpected connection between political support and economic activity.

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: [ A scene from Skyrim ] and depicting this scene: In Montana, a line of voters stretches around a polling station, with many people proudly displaying "I Voted" stickers for the Democratic Presidential candidate. Nearby, a gas station in Togo is bustling with activity as people queue up to pump gasoline into their vehicles, creating a sudden surge in demand. Both scenes are filled with a sense of energy and hope, symbolizing the unexpected connection between political support and economic activity. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a surreal setting featuring a bustling polling station in Montana with long queues of voters proudly displaying "I Voted" stickers. Blend this scene with a lively gas station in Togo crowded with people waiting to pump gasoline into their vehicles. The juxtaposition of the political fervor and economic activity should convey a sense of energy and hope, symbolizing the unexpected connection between political support and economic activity.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Votes for the Democrat Presidential candidate in Montana caused Gasoline pumped in Togo to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

The Journal of Comedic Comparative Politics

Jan 2024
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9166098 and p < 0.01 for 1980 to 2020.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of politics and petroleum, metaphoric mayhem or numerical nonsense? The enchanting enigma of the relationship between votes for the Democratic presidential candidate in the sprawling landscapes of Montana and the volumetric vagaries of gasoline consumption in the West African nation of Togo has captured the attention of scholars, skeptics, and stand-up comedians alike. What might appear to be a whimsical pairing at first blush has engendered scintillating speculation and downright delightful debates in the hallowed halls of academia.

The haphazard hypothesis that democratic votes in the wilds of the American West could hold any sway over the pumping of petrol in the tropical climes of Togo may seem frivolous, to say the least. However, statistics, much like a good joke, have a tendency to surprise and beguile. As we embark upon this jovial journey of empirical investigation, we must approach the apparently absurd with boundless curiosity and the occasional chuckle.

Ever since the inception of this improbable inquiry, the academic community has been ablaze with curiosity, conjuring comical conjectures and eccentric explanations. The perky correlation of 0.9166098 and a p-value less than 0.01, spanning from 1980 to 2020, has left many an eyebrow raised and elicited no small number of wry quips. Is this purely a prank of statistical shenanigans, or could there be a whimsical Wu Xing governing the alignment of these seemingly arbitrary phenomena?

Embracing this puzzling partnership between distant domains, and refraining from succumbing to the siren song of mischievous mirth, we proceed with gravitas and measured merriment. Dare we to dream that our whimsical exploration will yield insight into the cheeky charm of this merry mismatch? The ensuing analysis is an invitation to join us on a merry dance of incongruity, in the hope of mining the golden nuggets of knowledge hidden within this serendipitous synchrony.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of politics and petroleum, metaphoric mayhem or numerical nonsense? The enchanting enigma of the relationship between votes for the Democratic presidential candidate in the sprawling landscapes of Montana and the volumetric vagaries of gasoline consumption in the West African nation of Togo has captured the attention of scholars, skeptics, and stand-up comedians alike. What might appear to be a whimsical pairing at first blush has engendered scintillating speculation and downright delightful debates in the hallowed halls of academia.
The haphazard hypothesis that democratic votes in the wilds of the American West could hold any sway over the pumping of petrol in the tropical climes of Togo may seem frivolous, to say the least. However, statistics, much like a good joke, have a tendency to surprise and beguile. As we embark upon this jovial journey of empirical investigation, we must approach the apparently absurd with boundless curiosity and the occasional chuckle.
Ever since the inception of this improbable inquiry, the academic community has been ablaze with curiosity, conjuring comical conjectures and eccentric explanations. The perky correlation of 0.9166098 and a p-value less than 0.01, spanning from 1980 to 2020, has left many an eyebrow raised and elicited no small number of wry quips. Is this purely a prank of statistical shenanigans, or could there be a whimsical Wu Xing governing the alignment of these seemingly arbitrary phenomena?
Embracing this puzzling partnership between distant domains, and refraining from succumbing to the siren song of mischievous mirth, we proceed with gravitas and measured merriment. Dare we to dream that our whimsical exploration will yield insight into the cheeky charm of this merry mismatch? The ensuing analysis is an invitation to join us on a merry dance of incongruity, in the hope of mining the golden nuggets of knowledge hidden within this serendipitous synchrony.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, "Democracy and Petroleum: A Global Analysis" by Smith et al., the authors find a complex and multifaceted relationship between political ideologies and the consumption of fossil fuels. However, little did they expect this relationship to extend to the highly specific correlation between votes for the Democratic presidential candidate in the state of Montana and the amount of gasoline pumped in the faraway land of Togo. The improbable connection between these two seemingly disparate variables has sent shockwaves through the scholarly community, inspiring a flurry of inquiries and raising more than a few eyebrows.

Building on this scholarly foundation, Doe and Jones delve into the intricacies of cross-continental data analysis in "Fueling the Political Fire: A Comparative Study of Democratic Votes and Gasoline Consumption." The authors unearth a surprising pattern that challenges traditional notions of causality and geographic influence. These serious and scholastically sound studies set the stage for our own investigation into this perplexing paradox.

Turning to the wider array of literature, we encounter "Fueling the Flame: Petro-Politics in the Modern Era" by renowned energy economist Dr. Laura Black, shedding light on the complex interplay between political ideologies and energy consumption. Meanwhile, "Montana Dreams, Togo Tales" by sociologist Dr. Ivan Green takes a more narrative approach, exploring the cultural and social dimensions of the electoral process and gasoline consumption in the two distinct locations.

Venturing further into the realm of speculative fiction, we encounter "Gasoline Galore: A Togolese Odyssey" by the acclaimed novelist Lily Winters, a colorful tale woven with themes of political intrigue and petroleum passions. Additionally, "The Democratic Dilemma: A Montana Mystery" by renowned mystery writer Agatha Sleuth offers a tantalizing blend of electoral enigmas and the allure of the unknown.

In expanding our search for relevant and potentially elucidating sources, we must acknowledge the unorthodox methods that were undertaken in the pursuit of this academic inquiry. This included perusing the labyrinthine lengths of CVS receipts, an unconventional yet surprisingly fruitful source of hidden wisdom and whimsy. Through diligent examination of these otherwise overlooked artifacts, we intend to further enrich the discourse surrounding this merry mismatch of electoral and energy eccentricities.

As we navigate this maze of scholarly contributions and imaginative narratives, it becomes clear that the confluence of democratic votes in Montana and gasoline pumped in Togo is a subject that demands both rigorous analysis and the occasional lighthearted chuckle. This literature review serves as a stepping stone for our own earnest exploration of this whimsical conjunction and allows for a lighthearted reprieve amidst the scholarly solemnity.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Energy Information Administration . You used data from 1980 to 2020

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

[[INTRODUCTION]]
The intersection of politics and petroleum, metaphoric mayhem or numerical nonsense? The enchanting enigma of the relationship between votes for the Democratic presidential candidate in the sprawling landscapes of Montana and the volumetric vagaries of gasoline consumption in the West African nation of Togo has captured the attention of scholars, skeptics, and stand-up comedians alike. What might appear to be a whimsical pairing at first blush has engendered scintillating speculation and downright delightful debates in the hallowed halls of academia.
The haphazard hypothesis that democratic votes in the wilds of the American West could hold any sway over the pumping of petrol in the tropical climes of Togo may seem frivolous, to say the least. However, statistics, much like a good joke, have a tendency to surprise and beguile. As we embark upon this jovial journey of empirical investigation, we must approach the apparently absurd with boundless curiosity and the occasional chuckle.
Ever since the inception of this improbable inquiry, the academic community has been ablaze with curiosity, conjuring comical conjectures and eccentric explanations. The perky correlation of 0.9166098 and a p-value less than 0.01, spanning from 1980 to 2020, has left many an eyebrow raised and elicited no small number of wry quips. Is this purely a prank of statistical shenanigans, or could there be a whimsical Wu Xing governing the alignment of these seemingly arbitrary phenomena?
Embracing this puzzling partnership between distant domains, and refraining from succumbing to the siren song of mischievous mirth, we proceed with gravitas and measured merriment. Dare we to dream that our whimsical exploration will yield insight into the cheeky charm of this merry mismatch? The ensuing analysis is an invitation to join us on a merry dance of incongruity, in the hope of mining the golden nuggets of knowledge hidden within this serendipitous synchrony.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the perplexing correlation between votes for the Democratic presidential candidate in Montana and the gasoline pumped in Togo, our intrepid research team embarked on an odyssey through the labyrinthine labyrinths of data gathering and analysis. The first step in this quirky quest involved harnessing the vast expanse of the internet, with our valiant researchers gallivanting across the digital landscape in a trained frenzy akin to cybernetic cowboys herding bytes rather than bovines.

Drawing upon the digital derring-do of esteemed repositories such as the MIT Election Data and Science Lab, the Harvard Dataverse, and the Energy Information Administration, the data haul was conducted with the meticulousness of a Great Dane attending a tea party. This veritable cornucopia of information from the years 1980 to 2020 was then subjected to an array of statistical chicanery that would make a prankster blush.

The enigmatic algorithmic alchemy then ensued, seeking to unravel the riddles and jests hidden within the numbers. Employing a skillfully crafted concatenation of regression analysis, time-series models, and more mathematical mayhem, our team endeavored to tease out any semblance of sense from this merry mismatch. Our robust, yet whimsically whimsical, statistical methodology aimed to bring forth the empirical evidence that would either unravel this enigmatic enigma or add another layer of playful perplexity to the annals of academic research.

In our delightfully detailed expedition, spanning a tumultuous tapestry of time and space, we entrusted the data to reveal its secrets in a manner resembling an eager spelunker exploring the mysterious recesses of a digital cave. Our methodology, though rigorous and peppered with statistical solemnity, could not help but imbue the entire process with a dash of academic absurdity in the hope of uncovering the hidden punchline to this cosmic comedy of disparate data points.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 1980 to 2020, you found a correlation 0.9166098, r-squared of 0.8401736, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of politics and petroleum, metaphoric mayhem or numerical nonsense? The enchanting enigma of the relationship between votes for the Democratic presidential candidate in the sprawling landscapes of Montana and the volumetric vagaries of gasoline consumption in the West African nation of Togo has captured the attention of scholars, skeptics, and stand-up comedians alike. What might appear to be a whimsical pairing at first blush has engendered scintillating speculation and downright delightful debates in the hallowed halls of academia.
The haphazard hypothesis that democratic votes in the wilds of the American West could hold any sway over the pumping of petrol in the tropical climes of Togo may seem frivolous, to say the least. However, statistics, much like a good joke, have a tendency to surprise and beguile. As we embark upon this jovial journey of empirical investigation, we must approach the apparently absurd with boundless curiosity and the occasional chuckle.
Ever since the inception of this improbable inquiry, the academic community has been ablaze with curiosity, conjuring comical conjectures and eccentric explanations. The perky correlation of 0.9166098 and a p-value less than 0.01, spanning from 1980 to 2020, has left many an eyebrow raised and elicited no small number of wry quips. Is this purely a prank of statistical shenanigans, or could there be a whimsical Wu Xing governing the alignment of these seemingly arbitrary phenomena?
Embracing this puzzling partnership between distant domains, and refraining from succumbing to the siren song of mischievous mirth, we proceed with gravitas and measured merriment. Dare we to dream that our whimsical exploration will yield insight into the cheeky charm of this merry mismatch? The ensuing analysis is an invitation to join us on a merry dance of incongruity, in the hope of mining the golden nuggets of knowledge hidden within this serendipitous synchrony.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our empirical investigation into the unlikely liaison between votes for the Democratic presidential candidate in Montana and the volume of gasoline pumped in Togo are nothing short of astonishing. Our statistical analysis unveiled a remarkably strong correlation coefficient of 0.9166098, indicating a substantial association between these seemingly disconnected variables. The R-squared value of 0.8401736 further cements the robustness of this correlation, implying that approximately 84% of the variation in Togo's gasoline consumption can be explained by the votes for the Democrat presidential candidate in Montana. Moreover, the p-value of less than 0.01 signifies the statistical significance of this relationship, shunning the notion of mere fortuitousness.

One figure illustrates the striking correlation between votes for the Democrat presidential candidate in Montana and gasoline pumped in Togo over the period of 1980 to 2020 (see Fig. 1). This scatterplot graphically portrays the alignment of these incongruous phenomena, serving as a visual testament to the improbable synchrony we have uncovered.

In what might seem akin to finding ripples in a desert mirage, this unanticipated linkage between the political landscape of Montana and the fuel dynamics of Togo has left many a tongue wagging in bemusement. The inexplicable nature of this correlation begs for further inquiry into the whimsical workings of the universe, provoking wonder and amusement in equal measure.

Nevertheless, our findings invite both playful speculation and serious contemplation. While the whim of statistical serendipity may be an enticing concept, we tread cautiously in avoiding hasty conclusions on the matter. The mystery persists, beckoning us to delve further into the delightful dance of unexpected connections that transcend borders and ideologies.

In the vernacular of academia, the unexpected correlations illuminated in this study are akin to discovering the comedic punchline at the end of a seemingly unrelated narrative, reminding us that humor and insight often share the same stage, albeit in a statistically significant manner.

The results of this study engender much skepticism and wit, but as we navigate this unlikely union of Montanan votes and Togolese gasoline, our aim is to exploit the humor and curiosity it evokes to propel further exploration and scholarship in this delightfully incongruous domain.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Montana and Gasoline pumped in Togo. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

[[LITERATURE REVIEW]]
In their seminal work, "Democracy and Petroleum: A Global Analysis" by Smith et al., the authors find a complex and multifaceted relationship between political ideologies and the consumption of fossil fuels. However, little did they expect this relationship to extend to the highly specific correlation between votes for the Democratic presidential candidate in the state of Montana and the amount of gasoline pumped in the faraway land of Togo. The improbable connection between these two seemingly disparate variables has sent shockwaves through the scholarly community, inspiring a flurry of inquiries and raising more than a few eyebrows.
Building on this scholarly foundation, Doe and Jones delve into the intricacies of cross-continental data analysis in "Fueling the Political Fire: A Comparative Study of Democratic Votes and Gasoline Consumption." The authors unearth a surprising pattern that challenges traditional notions of causality and geographic influence. These serious and scholastically sound studies set the stage for our own investigation into this perplexing paradox.
Turning to the wider array of literature, we encounter "Fueling the Flame: Petro-Politics in the Modern Era" by renowned energy economist Dr. Laura Black, shedding light on the complex interplay between political ideologies and energy consumption. Meanwhile, "Montana Dreams, Togo Tales" by sociologist Dr. Ivan Green takes a more narrative approach, exploring the cultural and social dimensions of the electoral process and gasoline consumption in the two distinct locations.
Venturing further into the realm of speculative fiction, we encounter "Gasoline Galore: A Togolese Odyssey" by the acclaimed novelist Lily Winters, a colorful tale woven with themes of political intrigue and petroleum passions. Additionally, "The Democratic Dilemma: A Montana Mystery" by renowned mystery writer Agatha Sleuth offers a tantalizing blend of electoral enigmas and the allure of the unknown.
In expanding our search for relevant and potentially elucidating sources, we must acknowledge the unorthodox methods that were undertaken in the pursuit of this academic inquiry. This included perusing the labyrinthine lengths of CVS receipts, an unconventional yet surprisingly fruitful source of hidden wisdom and whimsy. Through diligent examination of these otherwise overlooked artifacts, we intend to further enrich the discourse surrounding this merry mismatch of electoral and energy eccentricities.
As we navigate this maze of scholarly contributions and imaginative narratives, it becomes clear that the confluence of democratic votes in Montana and gasoline pumped in Togo is a subject that demands both rigorous analysis and the occasional lighthearted chuckle. This literature review serves as a stepping stone for our own earnest exploration of this whimsical conjunction and allows for a lighthearted reprieve amidst the scholarly solemnity.

[[RESULTS]]
The results of our empirical investigation into the unlikely liaison between votes for the Democratic presidential candidate in Montana and the volume of gasoline pumped in Togo are nothing short of astonishing. Our statistical analysis unveiled a remarkably strong correlation coefficient of 0.9166098, indicating a substantial association between these seemingly disconnected variables. The R-squared value of 0.8401736 further cements the robustness of this correlation, implying that approximately 84% of the variation in Togo's gasoline consumption can be explained by the votes for the Democrat presidential candidate in Montana. Moreover, the p-value of less than 0.01 signifies the statistical significance of this relationship, shunning the notion of mere fortuitousness.
One figure illustrates the striking correlation between votes for the Democrat presidential candidate in Montana and gasoline pumped in Togo over the period of 1980 to 2020 (see Fig. 1). This scatterplot graphically portrays the alignment of these incongruous phenomena, serving as a visual testament to the improbable synchrony we have uncovered.
In what might seem akin to finding ripples in a desert mirage, this unanticipated linkage between the political landscape of Montana and the fuel dynamics of Togo has left many a tongue wagging in bemusement. The inexplicable nature of this correlation begs for further inquiry into the whimsical workings of the universe, provoking wonder and amusement in equal measure.
Nevertheless, our findings invite both playful speculation and serious contemplation. While the whim of statistical serendipity may be an enticing concept, we tread cautiously in avoiding hasty conclusions on the matter. The mystery persists, beckoning us to delve further into the delightful dance of unexpected connections that transcend borders and ideologies.
In the vernacular of academia, the unexpected correlations illuminated in this study are akin to discovering the comedic punchline at the end of a seemingly unrelated narrative, reminding us that humor and insight often share the same stage, albeit in a statistically significant manner.
The results of this study engender much skepticism and wit, but as we navigate this unlikely union of Montanan votes and Togolese gasoline, our aim is to exploit the humor and curiosity it evokes to propel further exploration and scholarship in this delightfully incongruous domain.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study have illuminated an unexpected and unusually robust correlation between votes for the Democrat presidential candidate in Montana and the consumption of gasoline in Togo. The extent to which these seemingly disparate variables are intertwined mirrors the whimsical nature of our previous literature review, where incongruous sources and unconventional methods led us to this anomalously coherent discovery. Indeed, this discovery serves as a delightful testament to the unpredictability of the academic pursuit and the often-overlooked propensity for serendipitous synchrony.

Building on the foundations laid by previous scholarly works, our findings corroborate and even amplify the improbable yet undeniably present connection between political preferences in one region and the energy dynamics of another. The significant correlation coefficient, coupled with the robust R-squared value and the statistically significant p-value, defies the traditional notions of causality and geographical influence, echoing the astonishment generated by the scholarly community and the general public alike.

The whimsical nature of this discovery invites a playful yet earnest exploration of the underlying mechanisms that could plausibly explain this unexpected liaison. Amidst the typically sober hues of academic discourse, this discovery introduces a spark of merriment and mirth, giving pause to contemplate the wondrous and inexplicable tapestry of interconnectedness that shrouds our world.

Venturing beyond the lighthearted quips and scholarly astonishment, the unexpected correlation between Montanan votes and Togolese gasoline beckons further investigation into the profound and potentially transformative implications. The potential ramifications of such interconnections, both humorous and consequential, present an invitation to reassess the seemingly disparate aspects of our world and embrace the unexpected juxtapositions that drive the engines of discovery and insight, much like the fuel that propels Togo and the democratic fervor that enlivens Montana.

In conclusion, our study adds a dash of whimsy to the serious discussions on political ideologies and energy consumption, reminding us that beneath the layers of statistical analyses and scholarly rigidity lies a realm of unexpected laughter and insight. This delightful discovery brings forth a confluence of curiosity and contemplation, inspiring both convivial discourse and profound scholarly inquiry as we navigate the intellectually rebellious waters of Montanan democracy and Togolese fuel.

And in the grand tradition of whimsical academia, we find ourselves recalling the words of renowned humorist Mark Twain: "The rule is perfect: in all matters of opinion our adversaries are insane."

Let the mirthful mismatch of Montanan Democrat votes and Togolese gasoline continue to amuse, baffle, and enlighten us as we forge ahead in the delightful dance of academic exploration.


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

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

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?

[[ABSTRACT]]
The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.

Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.

Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

[[INTRDUCTION]]
The intersection of politics and petroleum, metaphoric mayhem or numerical nonsense? The enchanting enigma of the relationship between votes for the Democratic presidential candidate in the sprawling landscapes of Montana and the volumetric vagaries of gasoline consumption in the West African nation of Togo has captured the attention of scholars, skeptics, and stand-up comedians alike. What might appear to be a whimsical pairing at first blush has engendered scintillating speculation and downright delightful debates in the hallowed halls of academia.
The haphazard hypothesis that democratic votes in the wilds of the American West could hold any sway over the pumping of petrol in the tropical climes of Togo may seem frivolous, to say the least. However, statistics, much like a good joke, have a tendency to surprise and beguile. As we embark upon this jovial journey of empirical investigation, we must approach the apparently absurd with boundless curiosity and the occasional chuckle.
Ever since the inception of this improbable inquiry, the academic community has been ablaze with curiosity, conjuring comical conjectures and eccentric explanations. The perky correlation of 0.9166098 and a p-value less than 0.01, spanning from 1980 to 2020, has left many an eyebrow raised and elicited no small number of wry quips. Is this purely a prank of statistical shenanigans, or could there be a whimsical Wu Xing governing the alignment of these seemingly arbitrary phenomena?
Embracing this puzzling partnership between distant domains, and refraining from succumbing to the siren song of mischievous mirth, we proceed with gravitas and measured merriment. Dare we to dream that our whimsical exploration will yield insight into the cheeky charm of this merry mismatch? The ensuing analysis is an invitation to join us on a merry dance of incongruity, in the hope of mining the golden nuggets of knowledge hidden within this serendipitous synchrony.

[[RESULTS]]
The results of our empirical investigation into the unlikely liaison between votes for the Democratic presidential candidate in Montana and the volume of gasoline pumped in Togo are nothing short of astonishing. Our statistical analysis unveiled a remarkably strong correlation coefficient of 0.9166098, indicating a substantial association between these seemingly disconnected variables. The R-squared value of 0.8401736 further cements the robustness of this correlation, implying that approximately 84% of the variation in Togo's gasoline consumption can be explained by the votes for the Democrat presidential candidate in Montana. Moreover, the p-value of less than 0.01 signifies the statistical significance of this relationship, shunning the notion of mere fortuitousness.
One figure illustrates the striking correlation between votes for the Democrat presidential candidate in Montana and gasoline pumped in Togo over the period of 1980 to 2020 (see Fig. 1). This scatterplot graphically portrays the alignment of these incongruous phenomena, serving as a visual testament to the improbable synchrony we have uncovered.
In what might seem akin to finding ripples in a desert mirage, this unanticipated linkage between the political landscape of Montana and the fuel dynamics of Togo has left many a tongue wagging in bemusement. The inexplicable nature of this correlation begs for further inquiry into the whimsical workings of the universe, provoking wonder and amusement in equal measure.
Nevertheless, our findings invite both playful speculation and serious contemplation. While the whim of statistical serendipity may be an enticing concept, we tread cautiously in avoiding hasty conclusions on the matter. The mystery persists, beckoning us to delve further into the delightful dance of unexpected connections that transcend borders and ideologies.
In the vernacular of academia, the unexpected correlations illuminated in this study are akin to discovering the comedic punchline at the end of a seemingly unrelated narrative, reminding us that humor and insight often share the same stage, albeit in a statistically significant manner.
The results of this study engender much skepticism and wit, but as we navigate this unlikely union of Montanan votes and Togolese gasoline, our aim is to exploit the humor and curiosity it evokes to propel further exploration and scholarship in this delightfully incongruous domain.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the improbable yet prolific relationship between votes for the Democratic presidential candidate in Montana and the volumetric vagaries of gasoline consumption in Togo has uncovered a correlation that is as surprising as it is statistically significant. The spectacle of this mismatched duo harmonizing so snugly in the realm of statistical analysis is a testament to the whimsical dance of unexpected connections that befuddles and beguiles.

The findings of this study prompt both a wry smile and a thoughtful furrow of the brow. The conspicuous correlation coefficient of 0.9166098, coupled with a p-value of less than 0.01, leaves us no choice but to acknowledge the undeniable synchrony between these seemingly disparate variables. We cannot help but marvel at the curious interconnectedness that underpins the world of statistical relationships, much like finding a punchline that somehow fits into an unrelated quip.

While the enchanting allure of this serendipitous synchrony incites mirth and merriment, we must proceed with measured merriment and cautious curiosity. Perhaps there is no need to unravel the mystery behind this unlikely pairing any further, as it stands as a hilarious testament to the capricious nature of statistical correlations. This whimsical musing may simply be a delightful anomaly, a statistical joke if you will, challenging us to contemplate the universe's sense of humor.

Therefore, we assert with a chuckle and a flourish that no more research is needed in this area. The whimsy of this unlikely correlation has left us pondering the cosmic joke that underlies the statistical universe, inviting us to revel in the statistician's version of a well-timed punchline.

That’s all, folks!


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 Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Comedic Comparative Politics


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 Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony?. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Mismatched Metrics Analysis


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Montana's Democrat Votes and Togo's Gasoline: A Mirthful Mismatch or a Serendipitous Synchrony? with an abstract of The curious correlation between votes for the Democratic presidential candidate in Montana and the amount of gasoline pumped in Togo has been a topic of mirth and merriment among academia and the general public alike. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and the Energy Information Administration, we delved into this whimsical conjunction to illuminate the underlying dynamics.
Our rigorous statistical analysis revealed a surprising correlation coefficient of 0.9166098 and a statistically significant p-value of less than 0.01 for the period spanning from 1980 to 2020. While these findings may bewilder the casual observer, prompting many a quizzical quip, we must resist the urge to leap to whimsical conclusions.
Although these results may appear preposterous at first glance, there is an indubitable need for profound contemplation and careful consideration before dismissing this serendipitous synchrony as mere flimflam. Our work calls for further whimsical exploration into the underlying factors that may interlink these seemingly incongruous phenomena, instigating delightful discourse and laughter in the hallowed halls of academia.

ChatGPT:

Montana, Democrat, votes, gasoline, Togo, correlation, statistical analysis, MIT Election Data and Science Lab, Harvard Dataverse, Energy Information Administration, correlation coefficient, p-value, whimsical, serendipitous synchrony, mirthful mismatch absurd, incongruous phenomena

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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

Correlation r = 0.9166098 (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 = 0.8401736 (Coefficient of determination)
This means 84% of the change in the one variable (i.e., Gasoline pumped in Togo) is predictable based on the change in the other (i.e., Votes for the Democrat Presidential candidate in Montana) over the 11 years from 1980 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.2E-5. 0.0000724023839007968700000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.92 in 0.0072% of random cases. Said differently, if you correlated 13,812 random variables Which I absolutely did.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.7, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19801984198819921996200020042008201220162020
Votes for the Democrat Presidential candidate in Montana (Total votes)118032146742168936154507167922137126173710231667201839177709244786
Gasoline pumped in Togo (Million Barrels/Day)1.252781.4361121.61.51.211912.540364.125163.379372.921233.45871




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([118032,146742,168936,154507,167922,137126,173710,231667,201839,177709,244786,])
array_2 = np.array([1.25278,1.43611,2,1.6,1.5,1.21191,2.54036,4.12516,3.37937,2.92123,3.45871,])
array_1_name = "Votes for the Democrat Presidential candidate in Montana"
array_2_name = "Gasoline pumped in Togo"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!


Correlation ID: 4446 · Black Variable ID: 26000 · Red Variable ID: 24994
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0