about · email me · subscribe
Spurious correlation #5,528 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Average views of Numberphile YouTube videos and the second variable is Google searches for 'how to cure a hangover'.  The chart goes from 2011 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Apparently, as people learned more about complex mathematical concepts, they realized that the best solution to a hangover was simply not to drink in the first place. Who knew the real 'number phile' cure for a hangover was just subtraction – as in, subtracting the cocktails! It's a case of math nerds leading the way to sober mornings for everyone. And if you think about it, the whole situation is a sin wave of events – as the views of Numberphile videos go down, the Google searches for hangover cures also hit a new low. It's just proof that sometimes the best solutions are the ones you don't 'count' on!

Model: dalle-3
Prompt: [An image that looks like it is a scene from a Pixar movie] Description: Create an image that depicts a whimsical laboratory-like setting. In the center of the image, there are two graphs, one showing a decline in the average views of Numberphile YouTube videos with a line sloping downwards and the other displaying a decrease in Google searches for 'how to cure a hangover' with another line sloping downwards. The graphs intersect at the bottom, indicating the correlation between the two. Above the graphs, a glowing lightbulb shines brightly, signifying a realization. Between the graphs, depict a simple equation symbol "subtracting the cocktails," implying the solution to a hangover. The entire scene is warm and inviting, with soft lighting and an atmosphere of discovery. 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: Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. 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: Surrealism Cute 2D animation An image that looks like it is a scene from a Pixar movie Whimsical illustration Oragami
ChatGPT: An image that looks like it is a scene from a Pixar movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover', in the following situation: Apparently, as people learned more about complex mathematical concepts, they realized that the best solution to a hangover was simply not to drink in the first place. Who knew the real 'number phile' cure for a hangover was just subtraction – as in, subtracting the cocktails! It's a case of math nerds leading the way to sober mornings for everyone. And if you think about it, the whole situation is a sin wave of events – as the views of Numberphile videos go down, the Google searches for hangover cures also hit a new low. It's just proof that sometimes the best solutions are the ones you don't 'count' on!. Keep the description simple.
ChatGPT: In the scene, a graph shows a decline in the average views of Numberphile YouTube videos, represented by a line sloping downwards. Beside it, a separate graph depicts a decrease in Google searches for 'how to cure a hangover', also represented by a line sloping downwards. The two lines intersect at the bottom of the graphs, symbolizing the correlation between the decrease in mathematical video views and hangover cure searches. A lightbulb shines above the graphs, indicating the realization that the solution to a hangover lies in avoiding alcohol, as expressed by the equation symbol "subtracting the cocktails" written between the two graphs.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In the scene, a graph shows a decline in the average views of Numberphile YouTube videos, represented by a line sloping downwards. Beside it, a separate graph depicts a decrease in Google searches for 'how to cure a hangover', also represented by a line sloping downwards. The two lines intersect at the bottom of the graphs, symbolizing the correlation between the decrease in mathematical video views and hangover cure searches. A lightbulb shines above the graphs, indicating the realization that the solution to a hangover lies in avoiding alcohol, as expressed by the equation symbol "subtracting the cocktails" written between the two graphs. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [An image that looks like it is a scene from a Pixar movie] Description: Create an image that depicts a whimsical laboratory-like setting. In the center of the image, there are two graphs, one showing a decline in the average views of Numberphile YouTube videos with a line sloping downwards and the other displaying a decrease in Google searches for 'how to cure a hangover' with another line sloping downwards. The graphs intersect at the bottom, indicating the correlation between the two. Above the graphs, a glowing lightbulb shines brightly, signifying a realization. Between the graphs, depict a simple equation symbol "subtracting the cocktails," implying the solution to a hangover. The entire scene is warm and inviting, with soft lighting and an atmosphere of discovery.

*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 a decrease in Average views of Numberphile YouTube videos caused how to cure a hangover (Google searches for 'how to cure a hangover') to decrease.

AI academic paper

(Because p < 0.01)
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

The Journal of Inebriation Studies

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. 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 YouTube and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9346466 and p < 0.01 for 2011 to 2023.

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

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The pursuit of knowledge knows no bounds, and in the age of digital enlightenment, it has transcended mere academic studies to permeate the very fabric of our online interactions. Through the lens of internet data, we aim to explore the uncharted territories where mathematical musings intersect with the groans of hangover-induced woes. As the old adage goes, "In vino veritas," but what of the truths we seek in the whispers of searches for remedies to the consequences of revelry?

It has been a matter of perennial curiosity whether the esoteric realms of number theory and the pragmatic pursuit of morning-after solace are connected in unforeseen ways. In this study, we undertake the ambitious task of unearthing the correlation, nay, the intertwined dance between the average views of Numberphile YouTube videos and the desperate digital inquiries for "how to cure a hangover."

While the uninitiated may raise a quizzical brow at the seemingly incongruous pairing of these two phenomena, our in-depth analysis aims to illuminate the cryptic connections that underlie these seemingly unrelated realms. A harmony, if you will, between the esoteric and the existential, emerges from the digital ether, hinting at a correlation that transcends mere chance.

Through an audacious excavation of data spanning a decade, we have unraveled a noteworthy correlation coefficient of 0.9346466 and p < 0.01, presenting a compelling argument for the entwined relationship between the pursuit of numerical concepts and the fervent hunt for a panacea to quell the consequences of unbridled revelry. As we dive deeper into this digital odyssey, the question emerges: Are the digits of mathematical ponderings and the throbbing aftereffects of merrymaking truly bound in an intangible, interconnected embrace, or is this but a whimsical dance on the stage of internet eccentricities?


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. 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]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The pursuit of knowledge knows no bounds, and in the age of digital enlightenment, it has transcended mere academic studies to permeate the very fabric of our online interactions. Through the lens of internet data, we aim to explore the uncharted territories where mathematical musings intersect with the groans of hangover-induced woes. As the old adage goes, "In vino veritas," but what of the truths we seek in the whispers of searches for remedies to the consequences of revelry?
It has been a matter of perennial curiosity whether the esoteric realms of number theory and the pragmatic pursuit of morning-after solace are connected in unforeseen ways. In this study, we undertake the ambitious task of unearthing the correlation, nay, the intertwined dance between the average views of Numberphile YouTube videos and the desperate digital inquiries for "how to cure a hangover."
While the uninitiated may raise a quizzical brow at the seemingly incongruous pairing of these two phenomena, our in-depth analysis aims to illuminate the cryptic connections that underlie these seemingly unrelated realms. A harmony, if you will, between the esoteric and the existential, emerges from the digital ether, hinting at a correlation that transcends mere chance.
Through an audacious excavation of data spanning a decade, we have unraveled a noteworthy correlation coefficient of 0.9346466 and p < 0.01, presenting a compelling argument for the entwined relationship between the pursuit of numerical concepts and the fervent hunt for a panacea to quell the consequences of unbridled revelry. As we dive deeper into this digital odyssey, the question emerges: Are the digits of mathematical ponderings and the throbbing aftereffects of merrymaking truly bound in an intangible, interconnected embrace, or is this but a whimsical dance on the stage of internet eccentricities?

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In their comprehensive study, Smith et al. (2017) examined the digital behavior of individuals in their pursuit of remedies for the reverberating repercussions of revelry. The authors found a substantial uptick in Google searches for "how to cure a hangover" following weekends and public holidays, aligning with the anecdotal beliefs of many, presumably nursing their well-deserved revelry. Similarly, Doe (2019) conducted a study on the behavioral patterns of individuals engaging with mathematical content on YouTube, noting an intriguing surge in the average views of Numberphile videos during the late hours of weekends, coinciding with the traditional time of indulgence.

Further adding credence to this peculiar association, Jones (2020) explored the underlying motivations driving online engagement with hangover remedies, identifying a penchant for seeking comfort in communal online spaces. Conversely, the digital musings on mathematical concepts, as elucidated by Adams and Brown's "Mathematics in the Modern World," delve into the convergence of ideas and the dissemination of knowledge through digital platforms, setting the stage for the serendipitous encounter of numerical musings and morning-after quests.

The seamless intersection of esoteric mathematical musings and the pragmatic pursuit of hangover cures finds an echo in the fictional realms as well. The characters in Douglas Adams' "The Hitchhiker's Guide to the Galaxy" grapple with the mysteries of the universe while navigating the perils of intergalactic revelry, presenting a whimsically parallel narrative to the digital dance of internet activities. On a more subtly related note, the escapades of wizards in J.K. Rowling's "Harry Potter and the Sorcerer's Stone" offer enchanting parallels to the interwoven realms of mathematical musings and the pursuit of remedies, as the characters navigate the magical undercurrents of numerical incantations and the throes of hangover elixirs.

As we approach the enigmatic nexus of digital phenomena, it is imperative to acknowledge the unorthodox wellspring of insights that have shaped this study. Notably, the haphazard collection of incidental observations from the annals of seemingly incongruous sources, including but not limited to whimsical interpretations of ancient tomes, the cryptic whispers of overheard conversations, and the surprisingly enlightening wisdom gleaned from perusing arcane CVS receipts, has contributed to the composite understanding of the intertwined dance between mathematical theorizing and the quest for hangover remedies.


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from YouTube and Google Trends . You used data from 2011 to 2023

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

[[INTRODUCTION]]
The pursuit of knowledge knows no bounds, and in the age of digital enlightenment, it has transcended mere academic studies to permeate the very fabric of our online interactions. Through the lens of internet data, we aim to explore the uncharted territories where mathematical musings intersect with the groans of hangover-induced woes. As the old adage goes, "In vino veritas," but what of the truths we seek in the whispers of searches for remedies to the consequences of revelry?
It has been a matter of perennial curiosity whether the esoteric realms of number theory and the pragmatic pursuit of morning-after solace are connected in unforeseen ways. In this study, we undertake the ambitious task of unearthing the correlation, nay, the intertwined dance between the average views of Numberphile YouTube videos and the desperate digital inquiries for "how to cure a hangover."
While the uninitiated may raise a quizzical brow at the seemingly incongruous pairing of these two phenomena, our in-depth analysis aims to illuminate the cryptic connections that underlie these seemingly unrelated realms. A harmony, if you will, between the esoteric and the existential, emerges from the digital ether, hinting at a correlation that transcends mere chance.
Through an audacious excavation of data spanning a decade, we have unraveled a noteworthy correlation coefficient of 0.9346466 and p < 0.01, presenting a compelling argument for the entwined relationship between the pursuit of numerical concepts and the fervent hunt for a panacea to quell the consequences of unbridled revelry. As we dive deeper into this digital odyssey, the question emerges: Are the digits of mathematical ponderings and the throbbing aftereffects of merrymaking truly bound in an intangible, interconnected embrace, or is this but a whimsical dance on the stage of internet eccentricities?

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on this whimsical digital odyssey, we turned to the vast expanses of the internet, seeking to capture the elusive dance between mathematical ponderings and the throbbing aftermath of jovial revelry. Our data collection process began with the retrieval of average views for Numberphile YouTube videos, a treasure trove of mathematical musings, spanning the time frame from 2011 to 2023. The allure of these video lectures on number theory and related mathematical phenomena was undeniable, drawing in audiences with a gravitational force comparable to that of a particularly captivating conundrum.

With fervent enthusiasm, we delved into the realm of Google Trends, where the echoes of hangover-induced woes reverberated through the digital corridors. We meticulously documented the aggregated search interest for the perennially pertinent query, "how to cure a hangover," within the same temporal bounds as our exploration of Numberphile's numerical enigmas. The quest for this remedy, a beacon of hope amidst the head-throbbing tribulations, provided a tantalizing juxtaposition to the abstruse conundrums presented in the mathematical depths of YouTube.

Having gathered these digital artifacts, we painstakingly curated and cleansed the datasets, endeavoring to separate the signal from the noise, much like the introspective rumination following a particularly indulgent evening. The quantitative analysis that followed sought to untangle the clandestine ties between these seemingly divergent realms, employing statistical measures of association to discern the degree of correlation.

Our arsenal of statistical tools included the calculation of Pearson's correlation coefficient, a stalwart companion in our quest to measure the strength and direction of the relationship between the two domains of interest. Additionally, the determination of the p-value served as a litmus test for the significance of the observed correlation, separating the mere caprices of chance from the resolute bonds we sought to unveil.

Upon subjecting our data to the crucible of statistical scrutiny, the emergence of a formidable correlation coefficient of 0.9346466 and a p-value less than 0.01 heralded a moment of revelatory triumph. This robust measure of association indicated a compelling entwined relationship between the average views of Numberphile YouTube videos and the fervent digital pursuit of hangover cures, accentuating the unexpected synchrony between these seemingly disparate domains.

In our relentless pursuit of digital whimsy, the confluence of mathematical revelations and the search for solace amidst morning-after tribulations has illuminated an unexpected parallel, offering a symphony of insight into the idiosyncratic behaviors that permeate the digital ether. As we gaze upon the duality of human curiosity manifested in numerical reveries and remedial quests, our quest for understanding remains steadfast as we, in the immortal words of the Bard, "pluck the fruit of knowledge from the tree of data," peering into the uncharted harmonies between mathematical abstractions and the tangible yearnings for respite.


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from YouTube and Google Trends .

For the time period 2011 to 2023, you found a correlation 0.9346466, r-squared of 0.8735643, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The pursuit of knowledge knows no bounds, and in the age of digital enlightenment, it has transcended mere academic studies to permeate the very fabric of our online interactions. Through the lens of internet data, we aim to explore the uncharted territories where mathematical musings intersect with the groans of hangover-induced woes. As the old adage goes, "In vino veritas," but what of the truths we seek in the whispers of searches for remedies to the consequences of revelry?
It has been a matter of perennial curiosity whether the esoteric realms of number theory and the pragmatic pursuit of morning-after solace are connected in unforeseen ways. In this study, we undertake the ambitious task of unearthing the correlation, nay, the intertwined dance between the average views of Numberphile YouTube videos and the desperate digital inquiries for "how to cure a hangover."
While the uninitiated may raise a quizzical brow at the seemingly incongruous pairing of these two phenomena, our in-depth analysis aims to illuminate the cryptic connections that underlie these seemingly unrelated realms. A harmony, if you will, between the esoteric and the existential, emerges from the digital ether, hinting at a correlation that transcends mere chance.
Through an audacious excavation of data spanning a decade, we have unraveled a noteworthy correlation coefficient of 0.9346466 and p < 0.01, presenting a compelling argument for the entwined relationship between the pursuit of numerical concepts and the fervent hunt for a panacea to quell the consequences of unbridled revelry. As we dive deeper into this digital odyssey, the question emerges: Are the digits of mathematical ponderings and the throbbing aftereffects of merrymaking truly bound in an intangible, interconnected embrace, or is this but a whimsical dance on the stage of internet eccentricities?

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The correlation analysis between the average views of Numberphile YouTube videos and Google searches for "how to cure a hangover" revealed a striking relationship, with a correlation coefficient of 0.9346466 and an r-squared value of 0.8735643, both of which were statistically significant at p < 0.01. This robust correlation suggests a compelling connection between these seemingly disparate domains of internet activity.

Figure 1 illustrates the undeniable correlation between the two variables, portraying a scatterplot that vividly depicts their intertwined digital dance. The plot is a visual testament to the harmonious relationship between mathematical musings and the pursuit of morning-after solace, serving as an ode to the unexpected connections that underlie the enigmatic behaviors of online denizens.

The degree of correlation unearthed in this study not only invites contemplation on the quirky harmonies of internet activity but also prompts a lighthearted reflection on the whimsical juxtaposition of numerical ponderings and the sobering pursuit of alleviating the effects of imbibed indulgences. The uncovering of such a compelling correlation paints a vivid portrait of the symbiotic relationship between intellectual exploration and the pragmatic quests that define the human experience, bridging the digital chasm between the cerebral and the corporeal.

These findings not only shed light on the enduring quest for remedies to the aftermath of revelry but also evoke a playful curiosity about the interconnected symphony of internet pursuits. As we confront the unexpected entanglement of these unlikely bedfellows, the study beckons forth a whimsical reimagining of the digital landscape, where the pursuit of knowledge and the pursuit of relief converge in an unexpected pas de deux of online activity.


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

[[LITERATURE REVIEW]]
In their comprehensive study, Smith et al. (2017) examined the digital behavior of individuals in their pursuit of remedies for the reverberating repercussions of revelry. The authors found a substantial uptick in Google searches for "how to cure a hangover" following weekends and public holidays, aligning with the anecdotal beliefs of many, presumably nursing their well-deserved revelry. Similarly, Doe (2019) conducted a study on the behavioral patterns of individuals engaging with mathematical content on YouTube, noting an intriguing surge in the average views of Numberphile videos during the late hours of weekends, coinciding with the traditional time of indulgence.
Further adding credence to this peculiar association, Jones (2020) explored the underlying motivations driving online engagement with hangover remedies, identifying a penchant for seeking comfort in communal online spaces. Conversely, the digital musings on mathematical concepts, as elucidated by Adams and Brown's "Mathematics in the Modern World," delve into the convergence of ideas and the dissemination of knowledge through digital platforms, setting the stage for the serendipitous encounter of numerical musings and morning-after quests.
The seamless intersection of esoteric mathematical musings and the pragmatic pursuit of hangover cures finds an echo in the fictional realms as well. The characters in Douglas Adams' "The Hitchhiker's Guide to the Galaxy" grapple with the mysteries of the universe while navigating the perils of intergalactic revelry, presenting a whimsically parallel narrative to the digital dance of internet activities. On a more subtly related note, the escapades of wizards in J.K. Rowling's "Harry Potter and the Sorcerer's Stone" offer enchanting parallels to the interwoven realms of mathematical musings and the pursuit of remedies, as the characters navigate the magical undercurrents of numerical incantations and the throes of hangover elixirs.
As we approach the enigmatic nexus of digital phenomena, it is imperative to acknowledge the unorthodox wellspring of insights that have shaped this study. Notably, the haphazard collection of incidental observations from the annals of seemingly incongruous sources, including but not limited to whimsical interpretations of ancient tomes, the cryptic whispers of overheard conversations, and the surprisingly enlightening wisdom gleaned from perusing arcane CVS receipts, has contributed to the composite understanding of the intertwined dance between mathematical theorizing and the quest for hangover remedies.

[[RESULTS]]
The correlation analysis between the average views of Numberphile YouTube videos and Google searches for "how to cure a hangover" revealed a striking relationship, with a correlation coefficient of 0.9346466 and an r-squared value of 0.8735643, both of which were statistically significant at p < 0.01. This robust correlation suggests a compelling connection between these seemingly disparate domains of internet activity.
Figure 1 illustrates the undeniable correlation between the two variables, portraying a scatterplot that vividly depicts their intertwined digital dance. The plot is a visual testament to the harmonious relationship between mathematical musings and the pursuit of morning-after solace, serving as an ode to the unexpected connections that underlie the enigmatic behaviors of online denizens.
The degree of correlation unearthed in this study not only invites contemplation on the quirky harmonies of internet activity but also prompts a lighthearted reflection on the whimsical juxtaposition of numerical ponderings and the sobering pursuit of alleviating the effects of imbibed indulgences. The uncovering of such a compelling correlation paints a vivid portrait of the symbiotic relationship between intellectual exploration and the pragmatic quests that define the human experience, bridging the digital chasm between the cerebral and the corporeal.
These findings not only shed light on the enduring quest for remedies to the aftermath of revelry but also evoke a playful curiosity about the interconnected symphony of internet pursuits. As we confront the unexpected entanglement of these unlikely bedfellows, the study beckons forth a whimsical reimagining of the digital landscape, where the pursuit of knowledge and the pursuit of relief converge in an unexpected pas de deux of online activity.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of this study robustly support the findings of Smith et al. (2017) and Doe (2019), who observed an uptick in Google searches for hangover cures following weekends and public holidays, aligning with the patterns of indulgence commonly associated with these periods. The surge in average views of Numberphile videos during late weekend hours, as noted by Doe (2019), resonates with our revelation of a substantial correlation between such views and hangover cure searches. This interconnectedness illuminates the lingering effects of weekend revelry, spurring individuals to seek solace in both mathematical escapades and pursuits of morning-after remedies.

The parallel narrative drawn from literary realms, such as in Douglas Adams' "The Hitchhiker's Guide to the Galaxy" and J.K. Rowling's "Harry Potter and the Sorcerer's Stone," although seemingly whimsical, resonates deeply with the digital dance observed in our study. The seemingly incongruous sources mentioned in our literature review have imparted a rich tapestry of insights, leading us to appreciate the unexpected coherence between pure numerical musings and corporeal pursuits, mirroring the nuanced interplay between mathematical deliberations and the real-world repercussions of imbibed indulgences.

Our findings, in keeping with the playful spirit of this endeavor, not only corroborate the hitherto unexpected corollary between mathematically inclined online activities and the quest for hangover cures but also prompt a lighthearted contemplation of the serendipitous symphony of digital behavior. The tangible illustration of the correlation in Figure 1 offers a visual testament to the whimsical interplay between seemingly disparate pursuits, inviting a reimagining of the digital landscape as a stage for the unexpected pas de deux of intellectual inquiry and corporeal comfort-seeking.

As we unravel the hidden connections between potential remedies for revelry's aftermath and the captivating world of mathematical musings, the study evokes a sense of wonder at the quirkiness of digital behavior, inviting further explorations into the whimsical intermingling of unlikely bedfellows in the online sphere.

And just like a potent hangover cure, this study, too, invites us to savor the unexpected unity in its findings, serving as a delightful reminder that even amidst the rigorous pursuit of knowledge, there is always room for a light-hearted reflection on the delightful absurdities of the human experience.


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 Average views of Numberphile YouTube videos and Google searches for 'how to cure a hangover'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures

[[ABSTRACT]]
The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."

Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.

As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

[[INTRDUCTION]]
The pursuit of knowledge knows no bounds, and in the age of digital enlightenment, it has transcended mere academic studies to permeate the very fabric of our online interactions. Through the lens of internet data, we aim to explore the uncharted territories where mathematical musings intersect with the groans of hangover-induced woes. As the old adage goes, "In vino veritas," but what of the truths we seek in the whispers of searches for remedies to the consequences of revelry?
It has been a matter of perennial curiosity whether the esoteric realms of number theory and the pragmatic pursuit of morning-after solace are connected in unforeseen ways. In this study, we undertake the ambitious task of unearthing the correlation, nay, the intertwined dance between the average views of Numberphile YouTube videos and the desperate digital inquiries for "how to cure a hangover."
While the uninitiated may raise a quizzical brow at the seemingly incongruous pairing of these two phenomena, our in-depth analysis aims to illuminate the cryptic connections that underlie these seemingly unrelated realms. A harmony, if you will, between the esoteric and the existential, emerges from the digital ether, hinting at a correlation that transcends mere chance.
Through an audacious excavation of data spanning a decade, we have unraveled a noteworthy correlation coefficient of 0.9346466 and p < 0.01, presenting a compelling argument for the entwined relationship between the pursuit of numerical concepts and the fervent hunt for a panacea to quell the consequences of unbridled revelry. As we dive deeper into this digital odyssey, the question emerges: Are the digits of mathematical ponderings and the throbbing aftereffects of merrymaking truly bound in an intangible, interconnected embrace, or is this but a whimsical dance on the stage of internet eccentricities?

[[RESULTS]]
The correlation analysis between the average views of Numberphile YouTube videos and Google searches for "how to cure a hangover" revealed a striking relationship, with a correlation coefficient of 0.9346466 and an r-squared value of 0.8735643, both of which were statistically significant at p < 0.01. This robust correlation suggests a compelling connection between these seemingly disparate domains of internet activity.
Figure 1 illustrates the undeniable correlation between the two variables, portraying a scatterplot that vividly depicts their intertwined digital dance. The plot is a visual testament to the harmonious relationship between mathematical musings and the pursuit of morning-after solace, serving as an ode to the unexpected connections that underlie the enigmatic behaviors of online denizens.
The degree of correlation unearthed in this study not only invites contemplation on the quirky harmonies of internet activity but also prompts a lighthearted reflection on the whimsical juxtaposition of numerical ponderings and the sobering pursuit of alleviating the effects of imbibed indulgences. The uncovering of such a compelling correlation paints a vivid portrait of the symbiotic relationship between intellectual exploration and the pragmatic quests that define the human experience, bridging the digital chasm between the cerebral and the corporeal.
These findings not only shed light on the enduring quest for remedies to the aftermath of revelry but also evoke a playful curiosity about the interconnected symphony of internet pursuits. As we confront the unexpected entanglement of these unlikely bedfellows, the study beckons forth a whimsical reimagining of the digital landscape, where the pursuit of knowledge and the pursuit of relief converge in an unexpected pas de deux of online activity.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has ferreted out a surprisingly robust correlation between the average views of Numberphile YouTube videos and Google searches for "how to cure a hangover." The notable correlation coefficient of 0.9346466 and the statistically significant p-value of < 0.01 signal a compelling connection between these seemingly unrelated corners of internet activity. The salient visual representation in Figure 1 not only serves to underscore this unanticipated relationship but also prompts whimsical contemplation on the mysterious interplay between numerical ponderings and the search for solace after spirited indulgence.

The implications of these findings stretch past the digital frontier, offering a lighthearted lens through which to view the human pursuit of knowledge and relief. As we contemplate the blurry line between scholarly pursuits and the groans of morning-after reverie, a new chapter in the whimsical symphony of internet activities unfolds before us. It seems the digits of mathematical musings and the throbbing aftereffects of merrymaking are intertwined in an intangible embrace, beckoning forth a chuckle at the unexpected waltz of internet eccentricities.

In light of these resounding findings, we assert with confidence that no further research in this peculiar intersection is warranted. The quirky correlation between number ponderings and hangover remedies beckons us to raise a metaphorical toast to the colorful chaos of digital behavior and the unexpected harmonies that emerge from its midst. With this, we bid adieu to this most whimsical of academic pursuits, consigning it to the annals of delightfully eccentric correlations. Cheers to the enigmatic dance of digitized curiosity and convalescent contemplations!


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Inebriation 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 The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Inebriation 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 The Tipsy Tutorials: Tracking the Ties between Numberphile Views and Hangover Cures with an abstract of The staggering effects of overindulgence in libations have long plagued humanity, leading individuals to seek solace in the search for remedies to alleviate the thumping consequences of a night well-celebrated. In this study, we delved into the digitized depths of internet data to uncover the entwined relationship between the average views of Numberphile YouTube videos and the Google searches for "how to cure a hangover."
Through an exhaustive analysis of data spanning from 2011 to 2023, a noteworthy correlation coefficient of 0.9346466 and p < 0.01 emerged, suggesting a robust connection between the two seemingly disparate realms. Our findings not only shed light on the perpetually pertinent topic of hangover cures but also offer a whimsical insight into the digital behavior of individuals amidst their recuperative musings.
As we embark on this quest to unravel the enigmatic ties between mathematical musings and morning-after remedies, the line between numerical gymnastics and the groans of hangover-induced woes seems to blur, beckoning forth a new chapter in the unlikely symphony of internet activities.

ChatGPT:

"Numberphile YouTube views," "hangover cures," "correlation coefficient of views and hangover searches," "Google search data analysis," "digital behavior analysis," "internet activities research," "mathematical musings and remedies correlation," "YouTube video analytics," "hangover remedies search trends."

*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

Average views of Numberphile YouTube videos
Detailed data title: Average views of Numberphile YouTube videos.
Source: Numberphile YouTube
Additional Info: Current total views of videos released that year.

See what else correlates with Average views of Numberphile YouTube videos

Google searches for 'how to cure a hangover'
Detailed data title: Relative volume of Google searches for 'how to cure a hangover' (Worldwide, without quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'how to cure a hangover'

Correlation r = 0.9346466 (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 = 0.8735643 (Coefficient of determination)
This means 87.4% of the change in the one variable (i.e., Google searches for 'how to cure a hangover') is predictable based on the change in the other (i.e., Average views of Numberphile YouTube videos) over the 13 years from 2011 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.9E-6. 0.0000028595449074182130000000
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 0.93 in 0.00029% of random cases. Said differently, if you correlated 349,706 random variables You don't actually need 349 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 12 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 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.

[ 0.79, 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.
2011201220132014201520162017201820192020202120222023
Average views of Numberphile YouTube videos (Average views)220647011147401332760136911011440101032870916583645020666162490306396157334124228877
Google searches for 'how to cure a hangover' (Rel. search volume)74.7563.833360.666756.7549.833346.083349.545.7543.66673843.2535.166730




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




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([2206470,1114740,1332760,1369110,1144010,1032870,916583,645020,666162,490306,396157,334124,228877,])
array_2 = np.array([74.75,63.8333,60.6667,56.75,49.8333,46.0833,49.5,45.75,43.6667,38,43.25,35.1667,30,])
array_1_name = "Average views of Numberphile YouTube videos"
array_2_name = "Google searches for 'how to cure a hangover'"

# 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?

Big thanks for reviewing!


Correlation ID: 5528 · Black Variable ID: 25471 · Red Variable ID: 1347
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0