about · email me · subscribe
Spurious correlation #4,961 · 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 SmarterEveryDay YouTube videos.  The chart goes from 2007 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of Breweries in the United States rises, more people are hoppin' on the craft beer bandwagon. With their newfound appreciation for ales and lagers, they ferment a strong sense of community. This spills over into online interactions, causing a spike in the average number of comments on SmarterEveryDay YouTube videos. United by their love for brews and brainy content, viewers are ale-ways eager to lager their thoughts in the comment section. It's a sudsy social phenomenon that's all about raising a pint... I mean, point!

Model: dalle-3
Prompt: Create an image of a bustling brewpub, with rows of glistening fermentation tanks and happy patrons sipping on craft beer. In the background, display a computer screen showing the SmarterEveryDay YouTube video playing, surrounded by a flurry of comments, indicating the spike in engagement. 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 SmarterEveryDay 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: An image that looks like it is a scene from a Pixar movie Cyberpunk a funny image you would see on reddit Macabre a meme
ChatGPT: a funny image you would see on reddit

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 SmarterEveryDay YouTube videos, in the following situation: As the number of Breweries in the United States rises, more people are hoppin' on the craft beer bandwagon. With their newfound appreciation for ales and lagers, they ferment a strong sense of community. This spills over into online interactions, causing a spike in the average number of comments on SmarterEveryDay YouTube videos. United by their love for brews and brainy content, viewers are ale-ways eager to lager their thoughts in the comment section. It's a sudsy social phenomenon that's all about raising a pint... I mean, point!. Keep the description simple.
ChatGPT: In a bustling and lively brewpub, the number of breweries in the United States is evident in the rows of shiny fermentation tanks and the laughter of patrons enjoying craft beer. Meanwhile, on a computer screen, the SmarterEveryDay YouTube video plays, surrounded by a flurry of comments, showcasing the spike in the average number of comments. The intertwining of these scenes reflects the rising enthusiasm for craft beer and the robust online engagement sparked by this sudsy social phenomenon.

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 funny image you would see on reddit ] and depicting this scene: In a bustling and lively brewpub, the number of breweries in the United States is evident in the rows of shiny fermentation tanks and the laughter of patrons enjoying craft beer. Meanwhile, on a computer screen, the SmarterEveryDay YouTube video plays, surrounded by a flurry of comments, showcasing the spike in the average number of comments. The intertwining of these scenes reflects the rising enthusiasm for craft beer and the robust online engagement sparked by this sudsy social phenomenon. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a bustling brewpub, with rows of glistening fermentation tanks and happy patrons sipping on craft beer. In the background, display a computer screen showing the SmarterEveryDay YouTube video playing, surrounded by a flurry of comments, indicating the spike in engagement.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in The number of Breweries in the United States caused Average number of comments on SmarterEveryDay YouTube videos to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Crafty Connections: Breweries and Brewtubes

Journal of Fermentation 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 silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from Brewers Association and YouTube to assess this nagging question. You found a correlation coefficient of 0.9026661 and p < 0.01 for 2007 to 2022.

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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Breweries and YouTube videos – two domains that, at first glance, appear as unrelated as a cat and a cucumber. One might be inclined to wonder: what could possibly be the connection between the frothy world of craft beer and the virtual smorgasbord of knowledge and entertainment that is SmarterEveryDay? However, as we delve into this bubbling cauldron of data, we begin to uncover a correlation as harmonious as the perfectly poured pint.

In this paper, we embark on a spirited exploration of the intertwined fates of breweries and Brewtubes, with a curious twinkle in our eye. Our journey takes us through the hoppy fields of statistical analysis, where we stumble upon a brewtal truth – a surprising correlation between the number of craft breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. We didn’t intend to brew up a storm, but as it turns out, there is indeed a frothy association to be uncovered.

As we embark on this journey, let us savor the bitter-sweet symphony of numbers and revel in the lager than life implications of our findings. For those holding their breath in anticipation of a mundane, ho-hum analysis, fear not – our findings are anything but watered down. So, grab your data goggles and prepare for a hoppy ride through the unexpected connections in the world of crafty correlations!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay 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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Breweries and YouTube videos – two domains that, at first glance, appear as unrelated as a cat and a cucumber. One might be inclined to wonder: what could possibly be the connection between the frothy world of craft beer and the virtual smorgasbord of knowledge and entertainment that is SmarterEveryDay? However, as we delve into this bubbling cauldron of data, we begin to uncover a correlation as harmonious as the perfectly poured pint.
In this paper, we embark on a spirited exploration of the intertwined fates of breweries and Brewtubes, with a curious twinkle in our eye. Our journey takes us through the hoppy fields of statistical analysis, where we stumble upon a brewtal truth – a surprising correlation between the number of craft breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. We didn’t intend to brew up a storm, but as it turns out, there is indeed a frothy association to be uncovered.
As we embark on this journey, let us savor the bitter-sweet symphony of numbers and revel in the lager than life implications of our findings. For those holding their breath in anticipation of a mundane, ho-hum analysis, fear not – our findings are anything but watered down. So, grab your data goggles and prepare for a hoppy ride through the unexpected connections in the world of crafty correlations!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Numerous scholarly studies have explored the curious confluence of seemingly unrelated factors, seeking to unravel the enigmatic correlation between disparate entities. Smith and Doe (2010) conducted a comprehensive investigation into the proliferation of craft breweries in the United States, providing insights into the economic, cultural, and sociological factors driving the exponential growth of the brewing industry. Concurrently, Jones (2015) delved into the complex dynamics of user engagement on digital platforms, shedding light on the intricacies of online interactions and the factors influencing viewer participation.

Building upon this foundation, our research team delves even deeper into the frothy seas of correlation, guided by the perennial wisdom of O'Hoppy (2017) and Brewster's (2019) seminal works on the craft beer revolution, which offer a nuanced understanding of the interplay between consumer preferences, market trends, and the ethos of artisanal brewing.

Venturing into the expansive realm of digital media and virtual engagement, we draw inspiration from the musings of Watterson (1986) and Vonnegut (1969), whose fictional narratives resonate with the zeitgeist of technological evolution and the idiosyncratic nature of online communities.

While our pursuits may appear tangential to the subject at hand, we cannot overlook the undeniable influence of cinematic narratives in shaping our perceptions of interconnectedness. As avid enthusiasts of visual storytelling, our research team draws upon the whimsical narratives of films such as "Brewback Mountain" and "Fermented Green Tomatoes," which, while ostensibly unrelated to our research, infuse our exploration with a playful spirit and an appreciation for the unexpected twists and turns inherent in the web of correlations.

In synthesizing these diverse sources, we navigate through a maze of scholarly, creative, and cinematic narratives, and in doing so, unearth the frothy bouquet of correlations that underpins the curious relationship between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. Cheers to the uncharted territories of interconnectedness and the rib-tickling revelations that await!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Brewers Association and YouTube . You used data from 2007 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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

[[INTRODUCTION]]
Breweries and YouTube videos – two domains that, at first glance, appear as unrelated as a cat and a cucumber. One might be inclined to wonder: what could possibly be the connection between the frothy world of craft beer and the virtual smorgasbord of knowledge and entertainment that is SmarterEveryDay? However, as we delve into this bubbling cauldron of data, we begin to uncover a correlation as harmonious as the perfectly poured pint.
In this paper, we embark on a spirited exploration of the intertwined fates of breweries and Brewtubes, with a curious twinkle in our eye. Our journey takes us through the hoppy fields of statistical analysis, where we stumble upon a brewtal truth – a surprising correlation between the number of craft breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. We didn’t intend to brew up a storm, but as it turns out, there is indeed a frothy association to be uncovered.
As we embark on this journey, let us savor the bitter-sweet symphony of numbers and revel in the lager than life implications of our findings. For those holding their breath in anticipation of a mundane, ho-hum analysis, fear not – our findings are anything but watered down. So, grab your data goggles and prepare for a hoppy ride through the unexpected connections in the world of crafty correlations!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To distill the essence of this intriguing relationship between breweries and Brewtubes, we embarked on a data collection odyssey that would make Odysseus's journey seem like a mere stroll in the park. Our intrepid team scoured the digital realm, compiling a trove of data from sources such as the Brewers Association and the vast expanse of YouTube. The time span of our data collection extended from 2007 to 2022, offering a comprehensive panorama of the fluctuations in both craft brewery numbers and the effervescence of comments on SmarterEveryDay videos.

The first ferment in our methodology involved gathering data on the number of breweries, employing a veritable army of web-scouring bots to ensure we left no stone unturned in our pursuit of brewery statistics. We meticulously tracked the growth and dispersal of breweries across the United States. With an eye as sharp as a brewmaster's precision, we documented the ebbing and flowing tide of this frothy industry.

The next stage of our convoluted concoction involved the extraction of YouTube data, a process that saw us navigating through the high seas of video analytics and comment counts. We gathered a menagerie of data points, capturing the undulating rhythm of comments on SmarterEveryDay's videos. This intricate dance between viewers and their bubbly commentary provided us with the essential ingredients for our analysis.

Once we had amassed this treasure trove of data, we employed the alchemical brew of statistical techniques to unravel the hidden patterns within. We leveraged the enchanting powers of correlation analysis, allowing us to peer beneath the surface and uncover the tantalizing interplay between brewery numbers and SmarterEveryDay comments. With regression analysis serving as our trusty ale-wand, we probed deeper into the causative forces that underpin this curious connection.

In order to ensure the robustness of our findings, we subjected our data to rigorous scrutiny, channeling our inner skeptics to evaluate the statistical significance of our results. Our analytical arsenal brimmed with hypothesis testing, cross-validation, and bootstrapping - each serving as a guardian of the gate, preventing flimsy correlations from seeping into our hallowed chamber of results.

In the spirit of full disclosure, it must be noted that our methodology, like any good brew, has its peculiarities and idiosyncrasies. However, we approached our analysis with a blend of scientific rigor and playful curiosity, recognizing that the finest brews, much like the finest analyses, emerge from a fusion of exacting precision and fervent creativity. With a generous dose of humility and a pinch of whimsy, we present the findings of our merry expedition into the peculiar intersection of breweries and Brewtubes.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2007 to 2022, you found a correlation 0.9026661, r-squared of 0.8148060, 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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Breweries and YouTube videos – two domains that, at first glance, appear as unrelated as a cat and a cucumber. One might be inclined to wonder: what could possibly be the connection between the frothy world of craft beer and the virtual smorgasbord of knowledge and entertainment that is SmarterEveryDay? However, as we delve into this bubbling cauldron of data, we begin to uncover a correlation as harmonious as the perfectly poured pint.
In this paper, we embark on a spirited exploration of the intertwined fates of breweries and Brewtubes, with a curious twinkle in our eye. Our journey takes us through the hoppy fields of statistical analysis, where we stumble upon a brewtal truth – a surprising correlation between the number of craft breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. We didn’t intend to brew up a storm, but as it turns out, there is indeed a frothy association to be uncovered.
As we embark on this journey, let us savor the bitter-sweet symphony of numbers and revel in the lager than life implications of our findings. For those holding their breath in anticipation of a mundane, ho-hum analysis, fear not – our findings are anything but watered down. So, grab your data goggles and prepare for a hoppy ride through the unexpected connections in the world of crafty correlations!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis revealed a strikingly strong correlation between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. The correlation coefficient of 0.9026661 suggests a robust positive relationship between these seemingly unrelated variables. This correlation was further supported by the high r-squared value of 0.8148060, indicating that a substantial proportion of the variance in the average number of comments on SmarterEveryDay videos can be explained by the number of breweries in the United States. With a p-value of less than 0.01, our findings are statistically significant, cementing the association between these unexpected bedfellows.

Upon visually inspecting the relationship between breweries and the average number of comments on SmarterEveryDay videos, our team generated a scatterplot (Fig. 1) to illustrate the remarkable correlation. This plot captures the essence of our findings, showcasing the brewtiful connection between these two seemingly distinct realms. The data points coalesce in a way that is as harmonious as a well-balanced IPA, highlighting the unbeerlievable interplay between the frothy world of craft beer and the virtual domain of educational exploration.

These results not only raise a frothy toast to the interconnectedness of diverse domains but also underscore the importance of approaching data analysis with a curious and open mind. For, as our research has demonstrated, one must be vigilant in the pursuit of unexpected connections, as they may yield insights that are as refreshing as a chilled pint on a scorching summer day. This unlikely pairing of breweries and Brewtubes serves as a reminder that, in the realm of data analysis, the most ale-uring discoveries often lie at the intersection of seemingly disparate elements.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

[[LITERATURE REVIEW]]
Numerous scholarly studies have explored the curious confluence of seemingly unrelated factors, seeking to unravel the enigmatic correlation between disparate entities. Smith and Doe (2010) conducted a comprehensive investigation into the proliferation of craft breweries in the United States, providing insights into the economic, cultural, and sociological factors driving the exponential growth of the brewing industry. Concurrently, Jones (2015) delved into the complex dynamics of user engagement on digital platforms, shedding light on the intricacies of online interactions and the factors influencing viewer participation.
Building upon this foundation, our research team delves even deeper into the frothy seas of correlation, guided by the perennial wisdom of O'Hoppy (2017) and Brewster's (2019) seminal works on the craft beer revolution, which offer a nuanced understanding of the interplay between consumer preferences, market trends, and the ethos of artisanal brewing.
Venturing into the expansive realm of digital media and virtual engagement, we draw inspiration from the musings of Watterson (1986) and Vonnegut (1969), whose fictional narratives resonate with the zeitgeist of technological evolution and the idiosyncratic nature of online communities.
While our pursuits may appear tangential to the subject at hand, we cannot overlook the undeniable influence of cinematic narratives in shaping our perceptions of interconnectedness. As avid enthusiasts of visual storytelling, our research team draws upon the whimsical narratives of films such as "Brewback Mountain" and "Fermented Green Tomatoes," which, while ostensibly unrelated to our research, infuse our exploration with a playful spirit and an appreciation for the unexpected twists and turns inherent in the web of correlations.
In synthesizing these diverse sources, we navigate through a maze of scholarly, creative, and cinematic narratives, and in doing so, unearth the frothy bouquet of correlations that underpins the curious relationship between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. Cheers to the uncharted territories of interconnectedness and the rib-tickling revelations that await!

[[RESULTS]]
The results of our analysis revealed a strikingly strong correlation between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. The correlation coefficient of 0.9026661 suggests a robust positive relationship between these seemingly unrelated variables. This correlation was further supported by the high r-squared value of 0.8148060, indicating that a substantial proportion of the variance in the average number of comments on SmarterEveryDay videos can be explained by the number of breweries in the United States. With a p-value of less than 0.01, our findings are statistically significant, cementing the association between these unexpected bedfellows.
Upon visually inspecting the relationship between breweries and the average number of comments on SmarterEveryDay videos, our team generated a scatterplot (Fig. 1) to illustrate the remarkable correlation. This plot captures the essence of our findings, showcasing the brewtiful connection between these two seemingly distinct realms. The data points coalesce in a way that is as harmonious as a well-balanced IPA, highlighting the unbeerlievable interplay between the frothy world of craft beer and the virtual domain of educational exploration.
These results not only raise a frothy toast to the interconnectedness of diverse domains but also underscore the importance of approaching data analysis with a curious and open mind. For, as our research has demonstrated, one must be vigilant in the pursuit of unexpected connections, as they may yield insights that are as refreshing as a chilled pint on a scorching summer day. This unlikely pairing of breweries and Brewtubes serves as a reminder that, in the realm of data analysis, the most ale-uring discoveries often lie at the intersection of seemingly disparate elements.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings paint a compelling picture of the unexpectedly tight relationship between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. As per the amusingly bounteous literature review, the observed correlation between these seemingly unrelated variables mirrors the intricate dynamics elucidated by Smith and Doe (2010) in their examination of the craft brewing industry. It is certainly ale-arming how our results align with the prior research, hinting at the fermentable synergy at play.

The robust correlation coefficient, akin to a finely brewed ale, highlights the significance of this connection. The high r-squared value underscores the hopportunity to explain a substantial proportion of the variance in SmarterEveryDay video comments using the number of breweries as a frothy explanatory variable. Yes, puns might seem hoppy-go-lucky, but they keep spirits high!

But wait, it's not all fun and puns at the brewery! The statistically significant p-value of less than 0.01 further corroborates the veritable link between these disparate domains. Our research spins a delightful tale, echoing the sentiments of Brewster's (2019) work, where the deepening understanding of consumer preferences and market dynamics parallels the unfolding correlation we've uncapped.

The scatterplot (Fig. 1) forms the icing on the cake, or in this case, the foam on the pint. It captures the essence of our findings in a visually revealing manner, leaving us as uplifted as an effervescent lager on a Friday evening. Embracing the spirit of Watterson's (1986) musings, our data visualization mirrors the whimsical nature of correlations, proving once again that truth is stranger than fiction and often more hilarious.

This raucously delightful expedition through data analysis has yielded results as rich and complex as a mature malt. It's a reminder that, as Vonnegut (1969) might suggest, the most laughable correlations are often uncovered in the unlikeliest of places. So, as we revel in the foamy embrace of statistics, we remember that the world of research isn't just dry and serious – it's also frothy, effervescent, and, sometimes, downright pun-believable!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly 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 The number of Breweries in the United States and Average number of comments on SmarterEveryDay YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
"Crafty Connections: Breweries and Brewtubes"

[[ABSTRACT]]
This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

[[INTRDUCTION]]
Breweries and YouTube videos – two domains that, at first glance, appear as unrelated as a cat and a cucumber. One might be inclined to wonder: what could possibly be the connection between the frothy world of craft beer and the virtual smorgasbord of knowledge and entertainment that is SmarterEveryDay? However, as we delve into this bubbling cauldron of data, we begin to uncover a correlation as harmonious as the perfectly poured pint.
In this paper, we embark on a spirited exploration of the intertwined fates of breweries and Brewtubes, with a curious twinkle in our eye. Our journey takes us through the hoppy fields of statistical analysis, where we stumble upon a brewtal truth – a surprising correlation between the number of craft breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. We didn’t intend to brew up a storm, but as it turns out, there is indeed a frothy association to be uncovered.
As we embark on this journey, let us savor the bitter-sweet symphony of numbers and revel in the lager than life implications of our findings. For those holding their breath in anticipation of a mundane, ho-hum analysis, fear not – our findings are anything but watered down. So, grab your data goggles and prepare for a hoppy ride through the unexpected connections in the world of crafty correlations!

[[RESULTS]]
The results of our analysis revealed a strikingly strong correlation between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. The correlation coefficient of 0.9026661 suggests a robust positive relationship between these seemingly unrelated variables. This correlation was further supported by the high r-squared value of 0.8148060, indicating that a substantial proportion of the variance in the average number of comments on SmarterEveryDay videos can be explained by the number of breweries in the United States. With a p-value of less than 0.01, our findings are statistically significant, cementing the association between these unexpected bedfellows.
Upon visually inspecting the relationship between breweries and the average number of comments on SmarterEveryDay videos, our team generated a scatterplot (Fig. 1) to illustrate the remarkable correlation. This plot captures the essence of our findings, showcasing the brewtiful connection between these two seemingly distinct realms. The data points coalesce in a way that is as harmonious as a well-balanced IPA, highlighting the unbeerlievable interplay between the frothy world of craft beer and the virtual domain of educational exploration.
These results not only raise a frothy toast to the interconnectedness of diverse domains but also underscore the importance of approaching data analysis with a curious and open mind. For, as our research has demonstrated, one must be vigilant in the pursuit of unexpected connections, as they may yield insights that are as refreshing as a chilled pint on a scorching summer day. This unlikely pairing of breweries and Brewtubes serves as a reminder that, in the realm of data analysis, the most ale-uring discoveries often lie at the intersection of seemingly disparate elements.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our findings have poured light on the surprising relationship between the number of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. The remarkably high correlation coefficient and statistically significant p-value hint at an unexpectedly hoppy marriage between these two seemingly distinct entities. We've certainly tapped into a rich seam of interconnectedness, proving that when it comes to statistical relationships, the yeast expected pairings can yield the most flavorful results.

As we raise a pint to the conclusion of this research, it's clear that there is more to the seemingly disparate realms of craft beer and educational videos than meets the eye – or the palate. The robust positive relationship uncovered in our analysis serves as a reminder that in the vast sea of data, unexpected connections can bubble up to the surface and quench our thirst for knowledge in unexpected ways. It's a refreshing reminder to approach statistical analysis with an open mind and a taste for the unforeseen.

In essence, our findings suggest that the world of craft beer and the Brewtubes of educational content are not so ale-ien to each other after all. However, as much as we've relished uncovering this unexpected correlation, it's fair to say that further research in this domain may yield diminishing returns. It's time to tap out on this particular brew. Let's raise a glass to the unBEERlievable adventure we've had and set our sights on new frontiers of statistical exploration – where the hops are as high and the youtube comments are as numerous as the data points in a robust regression analysis. Cheers to the frothy world of statistical serendipity!


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 Crafty Connections: Breweries and Brewtubes. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Fermentation 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 Crafty Connections: Breweries and Brewtubes. Respond only with the name of a fictional organization.

ChatGPT:

The Fermentation Foundation


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 Crafty Connections: Breweries and Brewtubes with an abstract of This paper delves into the curious relationship between the proliferation of breweries in the United States and the average number of comments on SmarterEveryDay YouTube videos. With tongue planted firmly in cheek, we explore the correlation between these seemingly disparate entities. Utilizing data from the Brewers Association and YouTube, our research team uncovered a surprisingly high correlation coefficient of 0.9026661 and a statistically significant p-value of less than 0.01 for the period spanning 2007 to 2022. While our findings may sound ale-bit quizzical, they shed light on the unbeerlievable interplay between these realms. Cheers to uncovering unexpected connections in the foamy world of data analysis!

ChatGPT:

Breweries, brewtubes, correlation, United States, SmarterEveryDay, YouTube videos, Brewers Association, data analysis, statistics, p-value, correlation coefficient, unexpected connections, foamy world, craft beer industry, brewing industry

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

Correlation r = 0.9026661 (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 = 0.8148060 (Coefficient of determination)
This means 81.5% of the change in the one variable (i.e., Average number of comments on SmarterEveryDay YouTube videos) is predictable based on the change in the other (i.e., The number of Breweries in the United States) over the 16 years from 2007 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.7E-6. 0.0000017100105346069993000000
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 0.9 in 0.00017% of random cases. Said differently, if you correlated 584,792 random variables You don't actually need 584 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 15 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.74, 0.97 ] 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.
2007200820092010201120122013201420152016201720182019202020212022
The number of Breweries in the United States (Number of breweries)1805189619332131252526703162401448475780676777228557909293849709
Average number of comments on SmarterEveryDay YouTube videos (Average Comments)128.182241.7569274.938593.0181532.182997.093635.575163.575374.064361.055659.878626.7310755.39945.564831.92




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1805,1896,1933,2131,2525,2670,3162,4014,4847,5780,6767,7722,8557,9092,9384,9709,])
array_2 = np.array([128.182,241.75,69,274.938,593.018,1532.18,2997.09,3635.57,5163.57,5374.06,4361.05,5659.87,8626.73,10755.3,9945.56,4831.92,])
array_1_name = "The number of Breweries in the United States"
array_2_name = "Average number of comments on SmarterEveryDay 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. 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?

Kudos for rating!


Correlation ID: 4961 · Black Variable ID: 34 · Red Variable ID: 25492
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0