Spurious correlation #4,673 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of Breweries in the United States and the second variable is Average number of comments on Mark Rober YouTube videos. The chart goes from 2011 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of Breweries in the United States and the second variable is Average number of comments on Mark Rober YouTube videos. The chart goes from 2011 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of breweries in the United States increases, there is a corresponding increase in the production of hoppy, bubbly, and effervescent beverages. These beverages, when consumed, lead to a surge in cognitive stimulation and creative ideation among the populace. This surge inadvertently prompts viewers to engage more with the mind-blowing content of Mark Rober, thereby leading to a higher average number of comments on his YouTube videos. So, in a way, the more breweries there are, the hoppier and comment-happier the Mark Rober fan base becomes.

^{Show image generation prompt} Model: dalle-3
Prompt: Generative prompt for DALL·E-3: Generate an image in the style of a vibrant and dynamic magazine cover, reminiscent of TIME magazine. The scene depicts a bustling street in the United States, with colorful breweries lining the sidewalk. The air is rich with the aroma of freshly made hoppy and fizzy drinks. People are immersed in conversation, their faces animated with enthusiasm as they savor their beverages. In the background, a large screen displays Mark Rober's engaging YouTube videos, and a constant stream of comments reflects the heightened engagement from the creatively stimulated viewers. Create a visually compelling representation of this lively and bustling atmosphere, while keeping the depiction simple and without any text or speech bubbles. 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: The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. 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: Steampunk Whimsical illustration Minimalism A TIME magazine cover image An image that looks like it is a scene from 'Star Wars'
ChatGPT: A TIME magazine cover image

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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos, in the following situation: As the number of breweries in the United States increases, there is a corresponding increase in the production of hoppy, bubbly, and effervescent beverages. These beverages, when consumed, lead to a surge in cognitive stimulation and creative ideation among the populace. This surge inadvertently prompts viewers to engage more with the mind-blowing content of Mark Rober, thereby leading to a higher average number of comments on his YouTube videos. So, in a way, the more breweries there are, the hoppier and comment-happier the Mark Rober fan base becomes.. Keep the description simple.
ChatGPT: Imagine a bustling street in the United States, lined with vibrant breweries. The air is filled with the delightful aroma of hoppy and fizzy drinks being created. People are chatting excitedly as they enjoy their beverages, their eyes alight with inspiration. In the backdrop, a screen shows Mark Rober's YouTube videos, and a constant stream of comments appears, reflecting the heightened engagement from the creatively stimulated viewers.

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 TIME magazine cover image ] and depicting this scene: Imagine a bustling street in the United States, lined with vibrant breweries. The air is filled with the delightful aroma of hoppy and fizzy drinks being created. People are chatting excitedly as they enjoy their beverages, their eyes alight with inspiration. In the backdrop, a screen shows Mark Rober's YouTube videos, and a constant stream of comments appears, reflecting the heightened engagement from the creatively stimulated viewers. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generative prompt for DALL·E-3: Generate an image in the style of a vibrant and dynamic magazine cover, reminiscent of TIME magazine. The scene depicts a bustling street in the United States, with colorful breweries lining the sidewalk. The air is rich with the aroma of freshly made hoppy and fizzy drinks. People are immersed in conversation, their faces animated with enthusiasm as they savor their beverages. In the background, a large screen displays Mark Rober's engaging YouTube videos, and a constant stream of comments reflects the heightened engagement from the creatively stimulated viewers. Create a visually compelling representation of this lively and bustling atmosphere, while keeping the depiction simple and without any text or speech bubbles.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in The number of Breweries in the United States caused Average number of comments on Mark Rober YouTube videos to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement

The Sudsy Scholar

Jan 2024

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

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement"

[[ABSTRACT]]
In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.

Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.

While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
With a wry smile and a raised eyebrow, we embark on a scholarly exploration of an unlikely duo that has captivated our collective curiosity: breweries and YouTube engagement. In this boisterous foray into the world of statistical analysis, we endeavor to unravel the enigmatic connection between the proliferation of craft beer establishments and the voluminous outpouring of commentary on the digital domain of Mark Rober's YouTube videos.
The suds of curiosity have bubbled over in the realm of public discourse, prompting us to delve into the effervescent domains of data, numbers, and the pleasantly intoxicating world of online engagement. As astute observers of society's quirks and conundrums, we couldn't resist the opportunity to uncork the statistical potential hidden beneath the frothy surface of our research subjects.
Pouring over the comprehensive dataset provided by the Brewers Association and immersing ourselves in the rich tapestry of YouTube comments, we endeavored to distill the essence of this peculiar relationship. Our analysis sought to ferment a deeper understanding of whether the rise in craft breweries across the United States indeed has an inextricable link to the digital cacophony surrounding the scintillating scientific escapades crafted by Mark Rober.
A foamy correlation coefficient of 0.9347448 emerged from our rigorous analytical process, accompanied by a p-value that glimmered with statistical significance, standing resolutely beneath the 0.01 threshold. These compelling numbers beckon us to raise a frosted glass to the robustness of our findings, as they hint at a significant, albeit unexpected, kinship between two seemingly disparate cultural phenomena.
As we navigate the intoxicating waters of statistical analysis and sociocultural trends, we invite our esteemed readers to join us in toasting to the unexpected whimsy that we unearth in our scholarly pursuits. After all, who could have predicted that a statistical study would lead us down the meandering paths of digital engagement and the foamy concoctions of craft brews?

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The burgeoning field of brewerics, pardon, economics has seen a frothy surge in scholarly inquiries into the relationship between fermenting business endeavors and the digital realms of social engagement. Our investigation into the connection between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos is both novel and, dare I say, hop-timistic. Although the intersection of craft brewing and online discourse may seem ale-ien to some, its implications are not to be brushed aside. We earnestly set out to navigate the boisterous currents of scholarship and frivolity (or rather, froth-olity?) in our exploration of this quirk-ridden landscape.

Smith and Doe (2018) paint a lager-than-life picture of the economic impact of breweries in the United States, delving into the nuances of supply chain dynamics and consumer behavior. Meanwhile, Jones (2019) carves a path through the mists of online engagement, dissecting the intricacies of digital interactions and the fleeting nature of internet fame. As we imbibe the findings of these reputable scholars, we also turn to more tangentially related literary quaffs for inspiration.

In "The Oxford Companion to Beer" by Garrett Oliver (2011), the author guides us through the labyrinthine history of brewing, from ancient Mesopotamia to the foamy craft beer renaissance of the modern era. Oliver's work reminds us that the effervescence of brewing culture is indeed a tapestry woven through the fabric of human civilization - an ale-storical journey, if you will.

Turning to fictional works that seemingly tread the ale-dged territory of our research, "A Brew to a Kill" by Cleo Coyle (2015) and "The Brewer's Tale" by Karen Brooks (2014) beckon us with their frothy titles. While these books may not provide scholarly insights, they certainly whet our appetite for the playful punnage surrounding brewing and the pec-hops-uliar nature of the beer business.

And as we frolic through the nebulous realms of popular culture, we draw inspiration from movies that, in their own idiosyncratic ways, mirror the whimsical tides of our research. "Beerfest" (2006) and "Strange Brew" (1983) may be more comedic whimsies than scholarly tomes, yet their playful take on the world of brewing adds a dash of levity to our academic pursuits. After all, who of a scholarly disposition can resist the allure of a well-crafted, hop-soaked jest?

Thus, armed with the quills of humor and the steins of curiosity, we wade into the literature surrounding our peculiar brew-tiful research inquiry, ready to tap into the deliciously nuanced narrative of breweries and YouTube engagement.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. 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 Brewers Association and YouTube . You used data from 2011 to 2022

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]]
"Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement"

[[ABSTRACT]]
In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.

Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.

While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

[[INTRODUCTION]]
With a wry smile and a raised eyebrow, we embark on a scholarly exploration of an unlikely duo that has captivated our collective curiosity: breweries and YouTube engagement. In this boisterous foray into the world of statistical analysis, we endeavor to unravel the enigmatic connection between the proliferation of craft beer establishments and the voluminous outpouring of commentary on the digital domain of Mark Rober's YouTube videos.
The suds of curiosity have bubbled over in the realm of public discourse, prompting us to delve into the effervescent domains of data, numbers, and the pleasantly intoxicating world of online engagement. As astute observers of society's quirks and conundrums, we couldn't resist the opportunity to uncork the statistical potential hidden beneath the frothy surface of our research subjects.
Pouring over the comprehensive dataset provided by the Brewers Association and immersing ourselves in the rich tapestry of YouTube comments, we endeavored to distill the essence of this peculiar relationship. Our analysis sought to ferment a deeper understanding of whether the rise in craft breweries across the United States indeed has an inextricable link to the digital cacophony surrounding the scintillating scientific escapades crafted by Mark Rober.
A foamy correlation coefficient of 0.9347448 emerged from our rigorous analytical process, accompanied by a p-value that glimmered with statistical significance, standing resolutely beneath the 0.01 threshold. These compelling numbers beckon us to raise a frosted glass to the robustness of our findings, as they hint at a significant, albeit unexpected, kinship between two seemingly disparate cultural phenomena.
As we navigate the intoxicating waters of statistical analysis and sociocultural trends, we invite our esteemed readers to join us in toasting to the unexpected whimsy that we unearth in our scholarly pursuits. After all, who could have predicted that a statistical study would lead us down the meandering paths of digital engagement and the foamy concoctions of craft brews?

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Clearly, as any dedicated academic researcher would do, we approached our investigation with a seriousness befitting the weighty topics of craft brewing and YouTube engagement. Our crack team of researchers embarked on a data-gathering journey that spanned the digital realms of Brewers Association reports, YouTube engagement metrics, and perhaps a few too many taste tests of local ale varieties (strictly for the sake of scientific rigor, of course).

First, we diligently plundered the Brewers Association for comprehensive data on the number of breweries in the United States. As any aficionado of statistical analysis will agree, the frothy landscape of craft brewing demands a methodical approach. We meticulously sifted through years of data, from the heady days of 2011 to the more recent brew-ha-has of 2022, to capture the effervescent essence of the industry’s growth.

Next, we turned our attention to the digital domain, foraging for insights amid the bubbling cauldron of YouTube engagement surrounding the scientifically captivating content of Mark Rober. Armed with computational tools fit for a digital brewmaster, we collected and analyzed the average number of comments on Rober’s YouTube videos from the same time period. With each keystroke, we delved into the robust data, aiming to distill the essence of digital discourse in the era of burgeoning brews.

The connection between these seemingly dissimilar domains called for a statistical embrace that could encompass the foamy complexities of cultural phenomena. Employing the venerable tools of correlation analysis, we stirred the numbers until they yielded a correlation coefficient that would make even the most discerning beer aficionado nod in approval. With the accompanying p-value serving as our trusty co-pilot, we navigated the statistical rapids and emerged with a result that left us feeling as buoyant as a freshly poured pint.

While some may view our methodology as a quirky concoction of digital sleuthing and statistical sorcery, we assure our esteemed readers that every step was taken with the utmost gravity – well, as much gravity as one can muster when immersed in the frothy depths of beer and YouTube analytics. With a twinkle in our eye and a steadfast dedication to scholarly pursuits, we charted a course through the ebullient waves of data, ultimately coming ashore with a trove of insights to share with the academic community.

In the hallowed tradition of academic research, we tip our hats to the methodological rigors that underpin our investigation while also toasting to the unexpected whimsy that colored every step of our scholarly journey.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. 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 Brewers Association and YouTube .

For the time period 2011 to 2022, you found a correlation 0.9347448, r-squared of 0.8737479, 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]]
"Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement"

[[ABSTRACT]]
In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.

Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.

While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
With a wry smile and a raised eyebrow, we embark on a scholarly exploration of an unlikely duo that has captivated our collective curiosity: breweries and YouTube engagement. In this boisterous foray into the world of statistical analysis, we endeavor to unravel the enigmatic connection between the proliferation of craft beer establishments and the voluminous outpouring of commentary on the digital domain of Mark Rober's YouTube videos.
The suds of curiosity have bubbled over in the realm of public discourse, prompting us to delve into the effervescent domains of data, numbers, and the pleasantly intoxicating world of online engagement. As astute observers of society's quirks and conundrums, we couldn't resist the opportunity to uncork the statistical potential hidden beneath the frothy surface of our research subjects.
Pouring over the comprehensive dataset provided by the Brewers Association and immersing ourselves in the rich tapestry of YouTube comments, we endeavored to distill the essence of this peculiar relationship. Our analysis sought to ferment a deeper understanding of whether the rise in craft breweries across the United States indeed has an inextricable link to the digital cacophony surrounding the scintillating scientific escapades crafted by Mark Rober.
A foamy correlation coefficient of 0.9347448 emerged from our rigorous analytical process, accompanied by a p-value that glimmered with statistical significance, standing resolutely beneath the 0.01 threshold. These compelling numbers beckon us to raise a frosted glass to the robustness of our findings, as they hint at a significant, albeit unexpected, kinship between two seemingly disparate cultural phenomena.
As we navigate the intoxicating waters of statistical analysis and sociocultural trends, we invite our esteemed readers to join us in toasting to the unexpected whimsy that we unearth in our scholarly pursuits. After all, who could have predicted that a statistical study would lead us down the meandering paths of digital engagement and the foamy concoctions of craft brews?

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The correlation analysis conducted on the data collected from the Brewers Association and YouTube comments yielded intriguing results that can only be described as a "hoppy accident." The correlation coefficient of 0.9347448, with an r-squared value of 0.8737479, painted a picture as vivid as a pint of craft ale and as clear as a filtered lager. The p-value of less than 0.01 stood as a testament to the robustness of the relationship between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022.

The robust correlation coefficient of 0.93 suggests a strong positive relationship between these seemingly unrelated variables, leaving us with the unmistakable impression of a well-poured pint - refreshingly delightful and full of complexity. If there's one thing we've learned from this merry statistical expedition, it's that when it comes to unearthing unexpected connections, the proof is in the malt-infused pudding.

The scatterplot (Fig. 1) visually encapsulates the staggering correlation between the number of breweries and average YouTube comments, offering a compelling visualization of the frothy relationship that has captivated both our statistical analysis and our imagination. Indeed, the visual representation of these findings is akin to the head on a meticulously crafted beer - captivating in its presentation and indicative of the effervescence beneath the surface.

The robust nature of these statistical measures underscores the intriguing interplay between the rise of craft breweries and the digital discourse that permeates the realm of Mark Rober's scientific spectacles. As we eagerly raise our metaphorical glasses to these compelling findings, it becomes clear that there is more brewing beneath the surface of this unexpected correlation than meets the statistical eye.

Our findings prompt contemplation of the interconnected nature of cultural phenomena, digital engagement, and the multifaceted landscape of American craft brewing. The unmistakable presence of this correlation, like the lingering aroma of a well-crafted beer, invites exploration into the quirky intricacies of societal dynamics and the uncharted territories where hops, humor, and hot takes collide.

In summary, our statistical findings have unveiled a significant correlation between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos, shining a spotlight on the unexpectedly intertwined nature of these phenomena. We raise a figurative toast to the whimsical, the unexpected, and the statistical musings that bring forth a refreshing wave of insight in the academically inclined mind.

That brings the results section to a close, leaving us with the satisfying aftertaste of statistical discovery and the lingering thrill of uncovering correlations in unexpected places.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. 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]]
"Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement"

[[ABSTRACT]]
In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.

Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.

While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

[[LITERATURE REVIEW]]
The burgeoning field of brewerics, pardon, economics has seen a frothy surge in scholarly inquiries into the relationship between fermenting business endeavors and the digital realms of social engagement. Our investigation into the connection between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos is both novel and, dare I say, hop-timistic. Although the intersection of craft brewing and online discourse may seem ale-ien to some, its implications are not to be brushed aside. We earnestly set out to navigate the boisterous currents of scholarship and frivolity (or rather, froth-olity?) in our exploration of this quirk-ridden landscape.
Smith and Doe (2018) paint a lager-than-life picture of the economic impact of breweries in the United States, delving into the nuances of supply chain dynamics and consumer behavior. Meanwhile, Jones (2019) carves a path through the mists of online engagement, dissecting the intricacies of digital interactions and the fleeting nature of internet fame. As we imbibe the findings of these reputable scholars, we also turn to more tangentially related literary quaffs for inspiration.
In "The Oxford Companion to Beer" by Garrett Oliver (2011), the author guides us through the labyrinthine history of brewing, from ancient Mesopotamia to the foamy craft beer renaissance of the modern era. Oliver's work reminds us that the effervescence of brewing culture is indeed a tapestry woven through the fabric of human civilization - an ale-storical journey, if you will.
Turning to fictional works that seemingly tread the ale-dged territory of our research, "A Brew to a Kill" by Cleo Coyle (2015) and "The Brewer's Tale" by Karen Brooks (2014) beckon us with their frothy titles. While these books may not provide scholarly insights, they certainly whet our appetite for the playful punnage surrounding brewing and the pec-hops-uliar nature of the beer business.
And as we frolic through the nebulous realms of popular culture, we draw inspiration from movies that, in their own idiosyncratic ways, mirror the whimsical tides of our research. "Beerfest" (2006) and "Strange Brew" (1983) may be more comedic whimsies than scholarly tomes, yet their playful take on the world of brewing adds a dash of levity to our academic pursuits. After all, who of a scholarly disposition can resist the allure of a well-crafted, hop-soaked jest?
Thus, armed with the quills of humor and the steins of curiosity, we wade into the literature surrounding our peculiar brew-tiful research inquiry, ready to tap into the deliciously nuanced narrative of breweries and YouTube engagement.

[[RESULTS]]
The correlation analysis conducted on the data collected from the Brewers Association and YouTube comments yielded intriguing results that can only be described as a "hoppy accident." The correlation coefficient of 0.9347448, with an r-squared value of 0.8737479, painted a picture as vivid as a pint of craft ale and as clear as a filtered lager. The p-value of less than 0.01 stood as a testament to the robustness of the relationship between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022.
The robust correlation coefficient of 0.93 suggests a strong positive relationship between these seemingly unrelated variables, leaving us with the unmistakable impression of a well-poured pint - refreshingly delightful and full of complexity. If there's one thing we've learned from this merry statistical expedition, it's that when it comes to unearthing unexpected connections, the proof is in the malt-infused pudding.
The scatterplot (Fig. 1) visually encapsulates the staggering correlation between the number of breweries and average YouTube comments, offering a compelling visualization of the frothy relationship that has captivated both our statistical analysis and our imagination. Indeed, the visual representation of these findings is akin to the head on a meticulously crafted beer - captivating in its presentation and indicative of the effervescence beneath the surface.
The robust nature of these statistical measures underscores the intriguing interplay between the rise of craft breweries and the digital discourse that permeates the realm of Mark Rober's scientific spectacles. As we eagerly raise our metaphorical glasses to these compelling findings, it becomes clear that there is more brewing beneath the surface of this unexpected correlation than meets the statistical eye.
Our findings prompt contemplation of the interconnected nature of cultural phenomena, digital engagement, and the multifaceted landscape of American craft brewing. The unmistakable presence of this correlation, like the lingering aroma of a well-crafted beer, invites exploration into the quirky intricacies of societal dynamics and the uncharted territories where hops, humor, and hot takes collide.
In summary, our statistical findings have unveiled a significant correlation between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos, shining a spotlight on the unexpectedly intertwined nature of these phenomena. We raise a figurative toast to the whimsical, the unexpected, and the statistical musings that bring forth a refreshing wave of insight in the academically inclined mind.
That brings the results section to a close, leaving us with the satisfying aftertaste of statistical discovery and the lingering thrill of uncovering correlations in unexpected places.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have enriched the academic discussion on the interconnected realms of craft brewing and online engagement, shedding light on an unexpected correlation that froths with intriguing implications. The robust correlation coefficient of 0.9347448, coupled with a p-value less than 0.01, fortifies the notion that there is indeed a palpable connection between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos.

Drawing from the bubbling cauldron of literature in the field of "brewerics," our findings stand as a testament to the ale-luring interplay between the emergence of craft breweries and the digital dialogue surrounding captivating scientific content. The robustness of our statistical evidence aligns with the hop-timistic insights put forth by Smith and Doe (2018) in their examination of the economic impact of breweries, as well as the ferment of online engagement discerned by Jones (2019). It's clear that our study's findings give a frothy nod to these prior works and bolster the understanding of the intricate dance between craft brewing and digital discourse.

Our results also harken back to the tangentially related literary quaffs we encountered in our literary ale-ventures. The figurative frothiness of "A Brew to a Kill" and "The Brewer's Tale" seems to have seeped into the statistical fabric of our findings, echoing the playful punnage that infuses the world of brewing and its interconnectedness with other facets of our cultural tapestry.

Even as we revel in the scholarly integrity of our work, we acknowledge the playful spirit of levity that imbues our field of inquiry. For, after all, it is the unexpected twist in the statistical tale, the hop-soaked jest, that adds an effervescent charm to our academic pursuits.

In essence, our findings act as a foamy beacon, illuminating the uncharted territories where hops and hot takes intertwine in the digital landscape. With our scholarly goblets raised, we toast to the frothy nature of statistical inquiry and its ability to unearth unforeseen correlations.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 The number of Breweries in the United States and Average number of comments on Mark Rober YouTube videos. 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]]
"Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement"

[[ABSTRACT]]
In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.

Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.

While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

[[INTRDUCTION]]
With a wry smile and a raised eyebrow, we embark on a scholarly exploration of an unlikely duo that has captivated our collective curiosity: breweries and YouTube engagement. In this boisterous foray into the world of statistical analysis, we endeavor to unravel the enigmatic connection between the proliferation of craft beer establishments and the voluminous outpouring of commentary on the digital domain of Mark Rober's YouTube videos.
The suds of curiosity have bubbled over in the realm of public discourse, prompting us to delve into the effervescent domains of data, numbers, and the pleasantly intoxicating world of online engagement. As astute observers of society's quirks and conundrums, we couldn't resist the opportunity to uncork the statistical potential hidden beneath the frothy surface of our research subjects.
Pouring over the comprehensive dataset provided by the Brewers Association and immersing ourselves in the rich tapestry of YouTube comments, we endeavored to distill the essence of this peculiar relationship. Our analysis sought to ferment a deeper understanding of whether the rise in craft breweries across the United States indeed has an inextricable link to the digital cacophony surrounding the scintillating scientific escapades crafted by Mark Rober.
A foamy correlation coefficient of 0.9347448 emerged from our rigorous analytical process, accompanied by a p-value that glimmered with statistical significance, standing resolutely beneath the 0.01 threshold. These compelling numbers beckon us to raise a frosted glass to the robustness of our findings, as they hint at a significant, albeit unexpected, kinship between two seemingly disparate cultural phenomena.
As we navigate the intoxicating waters of statistical analysis and sociocultural trends, we invite our esteemed readers to join us in toasting to the unexpected whimsy that we unearth in our scholarly pursuits. After all, who could have predicted that a statistical study would lead us down the meandering paths of digital engagement and the foamy concoctions of craft brews?

[[RESULTS]]
The correlation analysis conducted on the data collected from the Brewers Association and YouTube comments yielded intriguing results that can only be described as a "hoppy accident." The correlation coefficient of 0.9347448, with an r-squared value of 0.8737479, painted a picture as vivid as a pint of craft ale and as clear as a filtered lager. The p-value of less than 0.01 stood as a testament to the robustness of the relationship between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022.
The robust correlation coefficient of 0.93 suggests a strong positive relationship between these seemingly unrelated variables, leaving us with the unmistakable impression of a well-poured pint - refreshingly delightful and full of complexity. If there's one thing we've learned from this merry statistical expedition, it's that when it comes to unearthing unexpected connections, the proof is in the malt-infused pudding.
The scatterplot (Fig. 1) visually encapsulates the staggering correlation between the number of breweries and average YouTube comments, offering a compelling visualization of the frothy relationship that has captivated both our statistical analysis and our imagination. Indeed, the visual representation of these findings is akin to the head on a meticulously crafted beer - captivating in its presentation and indicative of the effervescence beneath the surface.
The robust nature of these statistical measures underscores the intriguing interplay between the rise of craft breweries and the digital discourse that permeates the realm of Mark Rober's scientific spectacles. As we eagerly raise our metaphorical glasses to these compelling findings, it becomes clear that there is more brewing beneath the surface of this unexpected correlation than meets the statistical eye.
Our findings prompt contemplation of the interconnected nature of cultural phenomena, digital engagement, and the multifaceted landscape of American craft brewing. The unmistakable presence of this correlation, like the lingering aroma of a well-crafted beer, invites exploration into the quirky intricacies of societal dynamics and the uncharted territories where hops, humor, and hot takes collide.
In summary, our statistical findings have unveiled a significant correlation between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos, shining a spotlight on the unexpectedly intertwined nature of these phenomena. We raise a figurative toast to the whimsical, the unexpected, and the statistical musings that bring forth a refreshing wave of insight in the academically inclined mind.
That brings the results section to a close, leaving us with the satisfying aftertaste of statistical discovery and the lingering thrill of uncovering correlations in unexpected places.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our scholarly expedition into the frothy realms of statistical analysis has wielded a robust finding that leaves us buzzing with intellectual excitement. The staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01, provides a strong foundation for the assertion that there exists an unexpectedly bubbly link between the burgeoning brewery scene in the United States and the spirited digital discourse surrounding Mark Rober's YouTube escapades.

While our study has shed light on this sudsy correlation, we must acknowledge that correlation does not imply causation - much like enjoying a cold brew at a picnic doesn't guarantee sunshine, despite the presence of anecdotal evidence. Nevertheless, the sheer strength of the correlation prompts us to consider the potential interplay between the cultural phenomenon of craft brewing and the digital engagement surrounding scientific content on the internet. It's like a rich, malty stout that leaves us pondering the depths of its flavor profile long after the pint is empty.

As we take the last sip of our findings, we cannot help but wonder about the intriguing dynamics at play. Could it be that the heady enthusiasm for craft beer and the lively discussions on Mark Rober's YouTube channel mutually feed into a broader zeitgeist of intellectual curiosity and community interaction? It's a head-scratcher, much like trying to figure out the optimal foam-to-beer ratio in a pour.

Ultimately, our findings beckon us to revel in the quirky interconnectedness of cultural phenomena and digital engagement, like a whimsical dance between the bubbles in a freshly poured glass of champagne. Like any good discussion over a pint, our conclusion may inspire more queries than answers, but as we savor the flavors of statistical discovery, we raise our glasses to the revelatory delight of this unexpected correlation.

With the clinking of glasses and the satisfied hum of curious minds, we assert that no further research is needed in this area. After all, we've likely reached the peak of "beer-illiant" discoveries with this study, leaving no room for more excitement to brew in the academic world.

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 Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement. Respond only with the name of a fictional academic journal.

ChatGPT:

The Sudsy Scholar

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 Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Ale-Linked Analytical 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 Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement with an abstract of In this scholarly investigation, we set out to quench the thirst for knowledge by probing the intriguing relationship between the burgeoning brewery scene in the United States and the buzz surrounding Mark Rober's YouTube channel. Employing data sourced from the Brewers Association and the depths of YouTube's comment sections, our team delved into the numbers, aiming to pour over the statistics and ferment meaningful insights.
Our findings revealed a staggeringly high correlation coefficient of 0.9347448, coupled with a p-value less than 0.01. This robust statistical evidence suggests that there is indeed a frothy link between the number of breweries in the United States and the average number of comments on Mark Rober's YouTube videos from 2011 to 2022. As the craft beer community bubbled with enthusiasm, so too did the digital discourse around the ingenious scientific content served up by Rober.
While the etiology of this connection warrants further investigation, this brew-tiful correlation invites contemplation on the interconnected nature of pop culture, digital engagement, and the foamy landscape of American craft brewing. As we raise a scholarly glass to these findings, we raise the question: Are YouTube comments the new brews of the digital age, fermenting in the bubbling vat of online discourse? With a stout statistical backing, this correlation taps into the quirky intricacies of our ever-evolving societal tapestry and hints at the unexplored realms where hops meet hot takes.

ChatGPT:

breweries, YouTube engagement, correlation, Mark Rober, digital engagement, craft brewing, statistical evidence, Brewers Association, YouTube comments, United States breweries, online discourse

*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

The number of Breweries in the United States
Detailed data title: Number of Breweries in the United States
Source: Brewers Association
See what else correlates with The number of Breweries in the United States

Average number of comments on Mark Rober YouTube videos
Detailed data title: Average number of comments on Mark Rober YouTube videos.
Source: YouTube
See what else correlates with Average number of comments on Mark Rober YouTube videos

Correlation r = 0.9347448 (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 = 0.8737479 (Coefficient of determination)
This means 87.4% of the change in the one variable (i.e., Average number of comments on Mark Rober YouTube videos) is predictable based on the change in the other (i.e., The number of Breweries in the United States) over the 12 years from 2011 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.3E-6.^Show 0.0000083463414953385640000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.93 in 0.00083% of random cases. Said differently, if you correlated 119,813 random variables^Note You don't actually need 119 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 11 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 11 because we have two variables measured over a period of 12 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.

[ 0.78, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
The number of Breweries in the United States (Number of breweries)	2525	2670	3162	4014	4847	5780	6767	7722	8557	9092	9384	9709
Average number of comments on Mark Rober YouTube videos (Average Comments)	3653.5	2426.1	2662.56	4632.67	14907.5	14982.4	25863.9	33396.3	45466.6	38590.3	48086.4	28708

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([2525,2670,3162,4014,4847,5780,6767,7722,8557,9092,9384,9709,])
array_2 = np.array([3653.5,2426.1,2662.56,4632.67,14907.5,14982.4,25863.9,33396.3,45466.6,38590.3,48086.4,28708,])
array_1_name = "The number of Breweries in the United States"
array_2_name = "Average number of comments on Mark Rober YouTube videos"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of Breweries in the United States
Line chart for only Average number of comments on Mark Rober YouTube videos
AI-generated correlation image
The spurious research paper: Cheers to Comments: A Sudsy Correlation Between Breweries and YouTube Engagement

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 4673 · Black Variable ID: 34 · Red Variable ID: 25568


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