about · email me · subscribe
Spurious correlation #4,351 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is US Bottled Water Consumption per Person and the second variable is Total likes of Tom Scott's YouTube videos.  The chart goes from 2009 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

People were just trying to aqua-punch to improve their like-ability. And as their hydration levels rose, so did their appreciation for Tom Scott's content. It's like the water was conducting a like orchestra in their bodies, and Tom Scott's videos were the perfect symphony for their H2O-infused brains. Stay thirsty for knowledge, and keep those likes flowing!

Model: dalle-3
Prompt: [ Whimsical illustration ] Create an image of a lively park with a group of diverse people sitting on a grassy lawn, each holding a bottle of water. In the center, a large screen shows Tom Scott's YouTube video, capturing the attention of the audience. The people are smiling and visibly enjoying the content, and as they take sips from their water bottles, their expressions become more animated. Show a visual representation of the rising like count for Tom Scott's video, perhaps in the form of colorful emojis or balloons floating in the air. The overall scene should exude a sense of joy and community engagement, with a light-hearted and vibrant atmosphere. 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: US Bottled Water Consumption per Person and Total likes of Tom Scott 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: Hyper-realistic Whimsical illustration Oragami Psychedelic Surrealism
ChatGPT: Whimsical illustration

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 US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos, in the following situation: People were just trying to aqua-punch to improve their like-ability. And as their hydration levels rose, so did their appreciation for Tom Scott's content. It's like the water was conducting a like orchestra in their bodies, and Tom Scott's videos were the perfect symphony for their H2O-infused brains. Stay thirsty for knowledge, and keep those likes flowing!. Keep the description simple.
ChatGPT: In the scene, people are drinking bottled water while watching Tom Scott's YouTube videos. As they sip from their water bottles, their excitement grows and they enthusiastically like Tom's videos. With each gulp of water, their interest in the content increases, causing a surge in the total likes for Tom Scott's videos. It's a refreshing sight as the water-drinking audience propels the like count higher, creating a symphony of appreciation for his educational content.

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: [ Whimsical illustration ] and depicting this scene: In the scene, people are drinking bottled water while watching Tom Scott's YouTube videos. As they sip from their water bottles, their excitement grows and they enthusiastically like Tom's videos. With each gulp of water, their interest in the content increases, causing a surge in the total likes for Tom Scott's videos. It's a refreshing sight as the water-drinking audience propels the like count higher, creating a symphony of appreciation for his educational content. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Whimsical illustration ] Create an image of a lively park with a group of diverse people sitting on a grassy lawn, each holding a bottle of water. In the center, a large screen shows Tom Scott's YouTube video, capturing the attention of the audience. The people are smiling and visibly enjoying the content, and as they take sips from their water bottles, their expressions become more animated. Show a visual representation of the rising like count for Tom Scott's video, perhaps in the form of colorful emojis or balloons floating in the air. The overall scene should exude a sense of joy and community engagement, with a light-hearted and vibrant atmosphere.

*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 US Bottled Water Consumption per Person caused Total likes of Tom Scott YouTube videos to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

The Journal of Internet Influences and Consumption Trends

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You 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 US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from Statista and YouTube to assess this nagging question. You found a correlation coefficient of 0.9115407 and p < 0.01 for 2009 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]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of 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]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the labyrinthine landscape of statistical analysis, one often stumbles upon intriguing and unexpected correlations that leave us scratching our heads in bemusement. This paper aims to unravel the enigmatic entanglement between the burgeoning affinity for Tom Scott's YouTube videos and the insatiable thirst for bottled water in the United States. While one may initially dismiss such a connection as the whimsical wanderings of statistical noise, our findings present a compelling case for a tangible association between these seemingly unrelated variables.

As scholars of the arcane arts of research and analysis, we are no strangers to the capricious capers of data. In a world where correlation does not necessarily imply causation, one must tread cautiously and approach such unexpected findings with a healthy dose of skepticism. However, our quest for knowledge has led us to uncover a correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning over a decade of data. It is as if our statistical analysis has become a matchmaker, deftly pairing the seemingly incongruous companions of bottled water consumption and Tom Scott's YouTube likes.

The seemingly incongruent combination of these variables piqued our inquisitive intellects, prompting us to embark on this scholarly odyssey. Much like a scientific detective, we probed the depths of data from the hallowed grounds of Statista and YouTube, endeavoring to shed light on this unexpected relationship. Our findings offer a tantalizing glimpse into the intricate tapestry of human behavior, where the ebb and flow of consumer preferences intersect with the digital eminence of a celebrated content creator.

Join us on this whimsical foray into the whims of statistical analysis, where the convergence of hydrophilic habits and digital adoration invites us to reconsider the familiar tropes of causation and correlation. As we delve into the implications of this improbable alliance, let us revel in the delightful absurdity of the scientific endeavor and embrace the unforeseen connections that lie within the labyrinthine halls of data.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the labyrinthine landscape of statistical analysis, one often stumbles upon intriguing and unexpected correlations that leave us scratching our heads in bemusement. This paper aims to unravel the enigmatic entanglement between the burgeoning affinity for Tom Scott's YouTube videos and the insatiable thirst for bottled water in the United States. While one may initially dismiss such a connection as the whimsical wanderings of statistical noise, our findings present a compelling case for a tangible association between these seemingly unrelated variables.
As scholars of the arcane arts of research and analysis, we are no strangers to the capricious capers of data. In a world where correlation does not necessarily imply causation, one must tread cautiously and approach such unexpected findings with a healthy dose of skepticism. However, our quest for knowledge has led us to uncover a correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning over a decade of data. It is as if our statistical analysis has become a matchmaker, deftly pairing the seemingly incongruous companions of bottled water consumption and Tom Scott's YouTube likes.
The seemingly incongruent combination of these variables piqued our inquisitive intellects, prompting us to embark on this scholarly odyssey. Much like a scientific detective, we probed the depths of data from the hallowed grounds of Statista and YouTube, endeavoring to shed light on this unexpected relationship. Our findings offer a tantalizing glimpse into the intricate tapestry of human behavior, where the ebb and flow of consumer preferences intersect with the digital eminence of a celebrated content creator.
Join us on this whimsical foray into the whims of statistical analysis, where the convergence of hydrophilic habits and digital adoration invites us to reconsider the familiar tropes of causation and correlation. As we delve into the implications of this improbable alliance, let us revel in the delightful absurdity of the scientific endeavor and embrace the unforeseen connections that lie within the labyrinthine halls of data.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith (2015) investigates the patterns of US bottled water consumption, revealing a steady increase in per capita consumption over the years. Similarly, Doe (2018) delves into the captivating world of YouTube analytics, shedding light on the nuances of garnering likes and engagement on the platform. Meanwhile, Jones (2020) explores the peculiarities of consumer behavior, offering insights into the fickle nature of human preferences.

In "Liquid Assets: The Economics of Bottled Water," the authors find that the rise of bottled water consumption is intricately linked to societal trends and marketing strategies, shaping consumer behavior in unforeseen ways. Conversely, "YouTube Success: The Art of Going Viral" delves into the enigmatic algorithms and viewer engagement that contribute to the success of content creators on the platform, providing a nuanced understanding of digital fame.

Turning to fictional narratives, "The Thirsty Games" by Author X whimsically explores a dystopian world where access to bottled water becomes a coveted privilege, sparking a series of competitive YouTube challenges to win a lifetime supply of hydration. On a lighter note, "The Water Whisperer" by Author Y delves into the quirky adventures of a YouTuber who crafts ASMR videos centered around the soothing sounds of water, attracting a devoted following of hydrophilic enthusiasts.

Furthermore, the theatrically inclined may find resonance in films such as "Aquaman: The Search for Subaquatic Likes," where the eponymous hero navigates the treacherous depths of the digital realm to amass likes for his underwater exploits. In a more introspective portrayal, "The Shape of Water's Likes" explores the captivating connection between a mute custodian and an enigmatic sea creature, paralleling the unforeseen bond between US bottled water consumption and Tom Scott's YouTube likes.

As the literature converges on the intersecting themes of hydration, digital content, and human fascination, the findings set the stage for a whimsical exploration of the improbable relationship between US bottled water consumption per person and the total likes of Tom Scott's YouTube videos.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of 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 Statista and YouTube . You used data from 2009 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]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

[[INTRODUCTION]]
In the labyrinthine landscape of statistical analysis, one often stumbles upon intriguing and unexpected correlations that leave us scratching our heads in bemusement. This paper aims to unravel the enigmatic entanglement between the burgeoning affinity for Tom Scott's YouTube videos and the insatiable thirst for bottled water in the United States. While one may initially dismiss such a connection as the whimsical wanderings of statistical noise, our findings present a compelling case for a tangible association between these seemingly unrelated variables.
As scholars of the arcane arts of research and analysis, we are no strangers to the capricious capers of data. In a world where correlation does not necessarily imply causation, one must tread cautiously and approach such unexpected findings with a healthy dose of skepticism. However, our quest for knowledge has led us to uncover a correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning over a decade of data. It is as if our statistical analysis has become a matchmaker, deftly pairing the seemingly incongruous companions of bottled water consumption and Tom Scott's YouTube likes.
The seemingly incongruent combination of these variables piqued our inquisitive intellects, prompting us to embark on this scholarly odyssey. Much like a scientific detective, we probed the depths of data from the hallowed grounds of Statista and YouTube, endeavoring to shed light on this unexpected relationship. Our findings offer a tantalizing glimpse into the intricate tapestry of human behavior, where the ebb and flow of consumer preferences intersect with the digital eminence of a celebrated content creator.
Join us on this whimsical foray into the whims of statistical analysis, where the convergence of hydrophilic habits and digital adoration invites us to reconsider the familiar tropes of causation and correlation. As we delve into the implications of this improbable alliance, let us revel in the delightful absurdity of the scientific endeavor and embrace the unforeseen connections that lie within the labyrinthine halls of data.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In this section, we elucidate our modus operandi in disentangling the perplexing nexus between US bottled water consumption per capita and the total likes accrued by the versatile virtuoso, Tom Scott, on the ubiquitous platform of YouTube. Our research techniques, much like a well-crafted magic potion, involved a blend of data collection, statistical analysis, and the occasional sprinkling of wit and whimsy.

Data Collection:
To capture the undulating waves of bottled water consumption in the United States, we turned to the vast expanse of Statista, where a trove of tidbits awaited our eager perusal. Our team diligently sifted through the annals of data spanning from 2009 to 2022, carefully capturing the undulating trends in per capita bottled water intake. As for the enigmatic appeal of Tom Scott's YouTube escapades, our intrepid researchers delved into the realm of YouTube's public data, extracting the treasure trove of likes attributed to his erudite exhibitions. After all, what could be more fitting than leveraging the almighty power of public information to unravel this conundrum?

Analytical Framework:
Armed with a plethora of data, we invoked the formidable prowess of Pearson's correlation coefficient to gauge the strength and direction of the association between these seemingly incongruous variables. With a kernel of skepticism and a glimmer of curiosity, we subjected the data to the rigors of statistical analysis, aiming to divine any semblance of connection amidst this whimsical juxtaposition. The emergence of a correlation coefficient of 0.9115407, accompanied by a p-value of less than 0.01, left us simultaneously astounded and elated. Such an unanticipated union between bottled water consumption and Tom Scott's YouTube likes appeared to defy the conventional logic of statistical inquiry, yet there it was, staring back at us with unrelenting certitude.

Caveats and Contemplations:
Naturally, our quasi-mystical insights into this erstwhile unexplored territory come with the customary caveats and contemplations. While our findings reveal a robust correlation, the elusive specter of causation remains aloof, shrouded in the enigmatic mist of uncertainty. Additionally, the idiosyncrasies of human behavior and the capricious quirks of online engagement beckon us to proceed with caution, lest we succumb to the seductive allure of spurious correlations.

In summary, our research journey, not unlike a whimsical neuroscientific odyssey, has unveiled a brazenly conspicuous connection between US bottled water consumption per capita and the total likes garnered by the prodigious polymath, Tom Scott, on YouTube. With an arsenal of statistical tools and a pinch of resolute curiosity, we have embarked on this vibrant escapade, paving the way for future explorations into the unexpected cadence of human preferences and digital dalliances.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the 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 US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of 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 Statista and YouTube .

For the time period 2009 to 2022, you found a correlation 0.9115407, r-squared of 0.8309065, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the labyrinthine landscape of statistical analysis, one often stumbles upon intriguing and unexpected correlations that leave us scratching our heads in bemusement. This paper aims to unravel the enigmatic entanglement between the burgeoning affinity for Tom Scott's YouTube videos and the insatiable thirst for bottled water in the United States. While one may initially dismiss such a connection as the whimsical wanderings of statistical noise, our findings present a compelling case for a tangible association between these seemingly unrelated variables.
As scholars of the arcane arts of research and analysis, we are no strangers to the capricious capers of data. In a world where correlation does not necessarily imply causation, one must tread cautiously and approach such unexpected findings with a healthy dose of skepticism. However, our quest for knowledge has led us to uncover a correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning over a decade of data. It is as if our statistical analysis has become a matchmaker, deftly pairing the seemingly incongruous companions of bottled water consumption and Tom Scott's YouTube likes.
The seemingly incongruent combination of these variables piqued our inquisitive intellects, prompting us to embark on this scholarly odyssey. Much like a scientific detective, we probed the depths of data from the hallowed grounds of Statista and YouTube, endeavoring to shed light on this unexpected relationship. Our findings offer a tantalizing glimpse into the intricate tapestry of human behavior, where the ebb and flow of consumer preferences intersect with the digital eminence of a celebrated content creator.
Join us on this whimsical foray into the whims of statistical analysis, where the convergence of hydrophilic habits and digital adoration invites us to reconsider the familiar tropes of causation and correlation. As we delve into the implications of this improbable alliance, let us revel in the delightful absurdity of the scientific endeavor and embrace the unforeseen connections that lie within the labyrinthine halls of data.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of data spanning the years 2009 to 2022 revealed a remarkably robust correlation coefficient of 0.9115407 between US bottled water consumption per capita and the total likes received by the erudite Tom Scott on YouTube. This correlation was accompanied by an r-squared value of 0.8309065, further substantiating the strength of the relationship. The p-value of less than 0.01 serves as an indication of the statistical significance of this unexpected alliance.

The scatterplot (Fig. 1) portrays this strong positive correlation, showcasing the almost synchronized rise in US bottled water consumption and the total likes of Tom Scott's YouTube videos. It is as if the hydrophilic habits of Americans and the captivating allure of Tom Scott's content have become dance partners in a statistical waltz, moving in harmonious tandem across the years.

While our analysis cannot definitively assert causation, it does prompt one to ponder the curious interconnectedness of seemingly unrelated phenomena. Our findings provoke a whimsical wonder about the intricacies of human behavior and the unforeseen threads that weave together the tapestry of popular culture and consumer preferences. It is indeed a curious case of liquid and likes coalescing in a statistical symphony, inviting both amusement and contemplation.

This serendipitous discovery invites further investigation into the underlying mechanisms that may underpin this perplexing correlation. Whether driven by subconscious psychological factors or a more obscure medley of influences, the connection between US bottled water consumption and the total likes of Tom Scott's YouTube videos beckons us to explore the uncharted territories of consumer behavior and digital engagement.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of 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]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

[[LITERATURE REVIEW]]
Smith (2015) investigates the patterns of US bottled water consumption, revealing a steady increase in per capita consumption over the years. Similarly, Doe (2018) delves into the captivating world of YouTube analytics, shedding light on the nuances of garnering likes and engagement on the platform. Meanwhile, Jones (2020) explores the peculiarities of consumer behavior, offering insights into the fickle nature of human preferences.
In "Liquid Assets: The Economics of Bottled Water," the authors find that the rise of bottled water consumption is intricately linked to societal trends and marketing strategies, shaping consumer behavior in unforeseen ways. Conversely, "YouTube Success: The Art of Going Viral" delves into the enigmatic algorithms and viewer engagement that contribute to the success of content creators on the platform, providing a nuanced understanding of digital fame.
Turning to fictional narratives, "The Thirsty Games" by Author X whimsically explores a dystopian world where access to bottled water becomes a coveted privilege, sparking a series of competitive YouTube challenges to win a lifetime supply of hydration. On a lighter note, "The Water Whisperer" by Author Y delves into the quirky adventures of a YouTuber who crafts ASMR videos centered around the soothing sounds of water, attracting a devoted following of hydrophilic enthusiasts.
Furthermore, the theatrically inclined may find resonance in films such as "Aquaman: The Search for Subaquatic Likes," where the eponymous hero navigates the treacherous depths of the digital realm to amass likes for his underwater exploits. In a more introspective portrayal, "The Shape of Water's Likes" explores the captivating connection between a mute custodian and an enigmatic sea creature, paralleling the unforeseen bond between US bottled water consumption and Tom Scott's YouTube likes.
As the literature converges on the intersecting themes of hydration, digital content, and human fascination, the findings set the stage for a whimsical exploration of the improbable relationship between US bottled water consumption per person and the total likes of Tom Scott's YouTube videos.

[[RESULTS]]
The analysis of data spanning the years 2009 to 2022 revealed a remarkably robust correlation coefficient of 0.9115407 between US bottled water consumption per capita and the total likes received by the erudite Tom Scott on YouTube. This correlation was accompanied by an r-squared value of 0.8309065, further substantiating the strength of the relationship. The p-value of less than 0.01 serves as an indication of the statistical significance of this unexpected alliance.
The scatterplot (Fig. 1) portrays this strong positive correlation, showcasing the almost synchronized rise in US bottled water consumption and the total likes of Tom Scott's YouTube videos. It is as if the hydrophilic habits of Americans and the captivating allure of Tom Scott's content have become dance partners in a statistical waltz, moving in harmonious tandem across the years.
While our analysis cannot definitively assert causation, it does prompt one to ponder the curious interconnectedness of seemingly unrelated phenomena. Our findings provoke a whimsical wonder about the intricacies of human behavior and the unforeseen threads that weave together the tapestry of popular culture and consumer preferences. It is indeed a curious case of liquid and likes coalescing in a statistical symphony, inviting both amusement and contemplation.
This serendipitous discovery invites further investigation into the underlying mechanisms that may underpin this perplexing correlation. Whether driven by subconscious psychological factors or a more obscure medley of influences, the connection between US bottled water consumption and the total likes of Tom Scott's YouTube videos beckons us to explore the uncharted territories of consumer behavior and digital engagement.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our investigation into the unexpected correlation between US bottled water consumption per person and the total likes of Tom Scott on YouTube have unveiled a serendipitous and statistically significant relationship. Our findings align with the existing literature, which has touched upon the enigmatic realm of human preferences and digital engagement with a degree of whimsy and curiosity.

In line with Smith's (2015) exploration of US bottled water consumption, our study reinforces the trajectory of increasing per capita consumption, which seems to harmonize with the ascending total likes garnered by Tom Scott. This peculiar parallelism in the upward trends of these seemingly unrelated variables adds a layer of intrigue to the hydrophilic habits of Americans and their appreciation for Tom Scott's elucidative content.

Doe's (2018) insights into YouTube analytics acquire a jocular undertone as we observe the pronounced correlation between total likes and US bottled water consumption, inviting one to ponder whether there exists a latent quench for knowledge and entertainment that transcends traditional boundaries. The fickle nature of human preferences, as elucidated by Jones (2020), finds an unexpected manifestation in the statistically synchronized rise and fall of US bottled water consumption and Tom Scott's likes, prompting a lighthearted contemplation of the capricious tides of consumer behavior.

The unexpected association illuminated by our findings underscores the interplay between societal trends, consumer behavior, and digital content, echoing the findings of "Liquid Assets: The Economics of Bottled Water" and "YouTube Success: The Art of Going Viral." The statistical waltz enunciated by our correlation coefficient and scatterplot draws inspiration from the playful narratives of "The Thirsty Games" and "The Water Whisperer," breathing life into the improbable connection between liquid refreshment and digital acclaim.

While we must exercise caution in attributing a causal link between US bottled water consumption and the total likes of Tom Scott, our results beckon a whimsical wonder about the enigmatic mechanisms that may underpin this statistical symphony. The unexpected convergence of these variables invites both amusement and contemplation, encapsulating the quintessential spirit of scientific inquiry and discovery.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Total likes of Tom Scott YouTube videos. Make lots of 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]]
The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita

[[ABSTRACT]]
This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

[[INTRDUCTION]]
In the labyrinthine landscape of statistical analysis, one often stumbles upon intriguing and unexpected correlations that leave us scratching our heads in bemusement. This paper aims to unravel the enigmatic entanglement between the burgeoning affinity for Tom Scott's YouTube videos and the insatiable thirst for bottled water in the United States. While one may initially dismiss such a connection as the whimsical wanderings of statistical noise, our findings present a compelling case for a tangible association between these seemingly unrelated variables.
As scholars of the arcane arts of research and analysis, we are no strangers to the capricious capers of data. In a world where correlation does not necessarily imply causation, one must tread cautiously and approach such unexpected findings with a healthy dose of skepticism. However, our quest for knowledge has led us to uncover a correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning over a decade of data. It is as if our statistical analysis has become a matchmaker, deftly pairing the seemingly incongruous companions of bottled water consumption and Tom Scott's YouTube likes.
The seemingly incongruent combination of these variables piqued our inquisitive intellects, prompting us to embark on this scholarly odyssey. Much like a scientific detective, we probed the depths of data from the hallowed grounds of Statista and YouTube, endeavoring to shed light on this unexpected relationship. Our findings offer a tantalizing glimpse into the intricate tapestry of human behavior, where the ebb and flow of consumer preferences intersect with the digital eminence of a celebrated content creator.
Join us on this whimsical foray into the whims of statistical analysis, where the convergence of hydrophilic habits and digital adoration invites us to reconsider the familiar tropes of causation and correlation. As we delve into the implications of this improbable alliance, let us revel in the delightful absurdity of the scientific endeavor and embrace the unforeseen connections that lie within the labyrinthine halls of data.

[[RESULTS]]
The analysis of data spanning the years 2009 to 2022 revealed a remarkably robust correlation coefficient of 0.9115407 between US bottled water consumption per capita and the total likes received by the erudite Tom Scott on YouTube. This correlation was accompanied by an r-squared value of 0.8309065, further substantiating the strength of the relationship. The p-value of less than 0.01 serves as an indication of the statistical significance of this unexpected alliance.
The scatterplot (Fig. 1) portrays this strong positive correlation, showcasing the almost synchronized rise in US bottled water consumption and the total likes of Tom Scott's YouTube videos. It is as if the hydrophilic habits of Americans and the captivating allure of Tom Scott's content have become dance partners in a statistical waltz, moving in harmonious tandem across the years.
While our analysis cannot definitively assert causation, it does prompt one to ponder the curious interconnectedness of seemingly unrelated phenomena. Our findings provoke a whimsical wonder about the intricacies of human behavior and the unforeseen threads that weave together the tapestry of popular culture and consumer preferences. It is indeed a curious case of liquid and likes coalescing in a statistical symphony, inviting both amusement and contemplation.
This serendipitous discovery invites further investigation into the underlying mechanisms that may underpin this perplexing correlation. Whether driven by subconscious psychological factors or a more obscure medley of influences, the connection between US bottled water consumption and the total likes of Tom Scott's YouTube videos beckons us to explore the uncharted territories of consumer behavior and digital engagement.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]
In concluding our investigation into the perplexing partnership between US bottled water consumption per capita and the total likes garnered by the erudite Tom Scott on YouTube, it is evident that a substantial correlation of 0.9115407, accompanied by a p-value of less than 0.01, has been unearthed. It seems that statistically, Americans' predilection for H2O in a bottle and their admiration for Tom Scott's wit and wisdom go together like two peas in a statistically significant pod.
While the exact causative link remains as elusive as a furtive feline in a labyrinth, the robustness of the correlation suggests a connection that tantalizes the mind and tickles the statistical sensibilities. It appears that the hydrophilic habits of the populace and the magnetism of Tom Scott's content have engaged in a statistical dance akin to a well-choreographed ballet – quite the unlikely pas de deux, we must say.
Our findings, while bringing laughter and puzzled expressions in equal measure, invite us to reflect on the capricious capers of consumer behavior and the enigmatic allure of digital content. It is as if the symphony of liquid consumption and digital appreciation has orchestrated a whimsical overture that tickles the fancy of statistical curiosities and elicits a wry smile from the discerning researcher.
In light of these findings, it is with uncharacteristic confidence that we assert that no further research is needed in this curious realm of liquid libations and digital dalliances. The statistical musings have spoken, and the mysterious linkage between bottled water habits and YouTube likes shall remain a perennial enigma 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 The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Internet Influences and Consumption Trends


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Social Media and Internet Culture Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Thirst for Tom: Tracking the Tenuous Relationship between Total Likes of Tom Scott on YouTube and US Bottled Water Consumption per Capita with an abstract of This research endeavors to quench the curiosity surrounding the improbable relationship between US bottled water consumption per person and the total likes garnered by the erudite Tom Scott on YouTube. Leveraging data from Statista and YouTube, our findings reveal a surprisingly pronounced correlation coefficient of 0.9115407, with a p-value of less than 0.01, spanning the years from 2009 to 2022. Despite initial skepticism, the results suggest a conspicuous link between these seemingly disparate entities. While the exact causation eludes us, there appears to be a jovial jive between the hydrophilic habits of Americans and their fondness for Tom Scott's captivating content. The implications of this unanticipated association are far-reaching and invite further examination.

ChatGPT:

Tom Scott, YouTube, total likes, US bottled water consumption, correlation, Statista, data analysis, relationship, association, causation, hydrophilic habits, Americans, content consumption, correlation coefficient, p-value

*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

US Bottled Water Consumption per Person
Source: Statista
See what else correlates with US Bottled Water Consumption per Person

Total likes of Tom Scott's YouTube videos
Detailed data title: Total likes of Tom Scott YouTube videos.
Source: Tom Scott's YouTube
See what else correlates with Total likes of Tom Scott's YouTube videos

Correlation r = 0.9115407 (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 = 0.8309065 (Coefficient of determination)
This means 83.1% of the change in the one variable (i.e., Total likes of Tom Scott's YouTube videos) is predictable based on the change in the other (i.e., US Bottled Water Consumption per Person) over the 14 years from 2009 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.7E-6. 0.0000057038624398128615000000
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 0.91 in 0.00057% of random cases. Said differently, if you correlated 175,320 random variables You don't actually need 175 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 13 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.
20092010201120122013201420152016201720182019202020212022
US Bottled Water Consumption per Person (Gallons)27.628.329.230.83234.136.5394242.34445.24746.5
Total likes of Tom Scott's YouTube videos (Total likes)10591204276788319580814649703268690307663038568604392100659246060152901170680086580206879920




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.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([27.6,28.3,29.2,30.8,32,34.1,36.5,39,42,42.3,44,45.2,47,46.5,])
array_2 = np.array([1059120,4276,7883,195808,1464970,3268690,3076630,3856860,4392100,6592460,6015290,11706800,8658020,6879920,])
array_1_name = "US Bottled Water Consumption per Person"
array_2_name = "Total likes of Tom Scott's 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?

Your dedication to rating warms my heart!


Correlation ID: 4351 · Black Variable ID: 32 · Red Variable ID: 25468
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0