about · email me · subscribe
Spurious correlation #3,936 · 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 Google searches for 'i have a headache'.  The chart goes from 2004 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As people drank more bottled water, they realized they needed to pee all the time, leading to frequent bathroom trips. These repeated encounters with reflective surfaces made them acutely aware of their often neglected daily hydration levels. The guilt of not drinking enough water caught up with them, causing stress and tension headaches. So, remember, the next time your head is pounding, just blame it on the bottled water industry - they're in cahoots with the mirror manufacturers! Stay hydrated, folks, and maybe invest in some headache medicine stock while you're at it.

Model: dalle-3
Prompt: Generate an image in the style of a meme where a person is sitting at a cluttered desk, amidst empty bottled water containers, holding their head in discomfort. On the computer screen, the Google search bar displays "i have a headache." In the background, a graph visually represents an upward trend in both bottled water consumption per person and Google searches for "i have a headache." Ensure the visual depiction is both relatable and thought-provoking. 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 Google searches for 'i have a headache'. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: A scene from Skyrim a meme a meme Realistic Celtic art
ChatGPT: a meme

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 Google searches for 'i have a headache', in the following situation: Because as bottled water consumption increased, people drank more, leading to increased dehydration, causing more headaches, resulting in increased Google searches for "i have a headache.". Keep the description simple.
ChatGPT: A person sits at a desk, surrounded by empty bottled water containers, as they hold their head in pain. On the computer screen, the Google search bar displays "i have a headache." In the background, a graph shows an upward trend in both bottled water consumption per person and Google searches for "i have a headache."

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 meme ] and depicting this scene: A person sits at a desk, surrounded by empty bottled water containers, as they hold their head in pain. On the computer screen, the Google search bar displays "i have a headache." In the background, a graph shows an upward trend in both bottled water consumption per person and Google searches for "i have a headache." Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in the style of a meme where a person is sitting at a cluttered desk, amidst empty bottled water containers, holding their head in discomfort. On the computer screen, the Google search bar displays "i have a headache." In the background, a graph visually represents an upward trend in both bottled water consumption per person and Google searches for "i have a headache." Ensure the visual depiction is both relatable and thought-provoking.

*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 i have a headache (Google searches for 'i have a headache') to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'

Journal of Quirky Correlations in Consumer Behavior

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Google searches for 'i have a headache'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Statista and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9417390 and p < 0.01 for 2004 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Google searches for 'i have a headache'. 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
**INTRODUCTION**

In the realm of research, one often encounters unexpected and curious correlations that pique the interest of both scholars and casual observers. The dynamics between seemingly unrelated phenomena can offer insights into human behavior, societal trends, and the intricate web of cause-and-effect relationships. The present study delves into one such peculiar correlation, aiming to unravel the enigmatic connection between the per capita consumption of bottled water in the United States and the frequency of Google searches for the plaintive expression, "i have a headache."

As academic researchers, we often embark on journeys that lead us to unexpected destinations, and this investigation was no exception. The quest to unearth the relationship between the hydration habits of individuals and their virtual quests for headache remedies led us down a path filled with statistical analyses, data visualizations, and the occasional water cooler conversation about the puzzling nature of human behavior. The intellectual thirst to explore this quirky correlation culminated in a rigorous examination of the available data, resulting in findings that may quench the curiosity of both research enthusiasts and aficionados of the absurd.

Our investigation draws upon data from reputable sources, including Statista and Google Trends, to shed light on the statistical liaison between bottled water consumption and the digital echoes of human discomfort. Through meticulous analysis and a keen eye for patterns, we uncovered a remarkably robust correlation coefficient of 0.9417390, supported by a p-value that denounces mere coincidence with a resounding “less than 0.01.” This statistical embrace between the liquid allure of bottled water and the metaphorical throb of a headache beckons us to contemplate the intricate dance of consumer preferences and the digital pursuit of relief.

While it is imperative to exercise caution in attributing causality to this captivating correlation, our findings invite speculation about the whimsical interplay of consumer beverage habits and the virtual expressions of discomfort. As we embark on this scholarly exploration, we invite our readers to imbibe in the delightful absurdity of statistical relationships and the intellectual quenching of curiosity in the pursuit of knowledge.

So, put on your thinking caps, hold onto your proverbial hats, and join us on this whimsical exploration of the unexpected connections that lie beneath the surface of everyday phenomena. As we navigate the waters of statistical analysis and search for meaning amid the digital noise, we aim to unravel the intricacies of human behavior with a hint of humor and a splash of insight.

In the following sections, we will dive into the methodology, results, and implications of our investigation, all while maintaining a buoyant spirit of scientific inquiry and the occasional nod to the delightfully absurd.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Google searches for 'i have a headache'. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of research, one often encounters unexpected and curious correlations that pique the interest of both scholars and casual observers. The dynamics between seemingly unrelated phenomena can offer insights into human behavior, societal trends, and the intricate web of cause-and-effect relationships. The present study delves into one such peculiar correlation, aiming to unravel the enigmatic connection between the per capita consumption of bottled water in the United States and the frequency of Google searches for the plaintive expression, "i have a headache."
As academic researchers, we often embark on journeys that lead us to unexpected destinations, and this investigation was no exception. The quest to unearth the relationship between the hydration habits of individuals and their virtual quests for headache remedies led us down a path filled with statistical analyses, data visualizations, and the occasional water cooler conversation about the puzzling nature of human behavior. The intellectual thirst to explore this quirky correlation culminated in a rigorous examination of the available data, resulting in findings that may quench the curiosity of both research enthusiasts and aficionados of the absurd.
Our investigation draws upon data from reputable sources, including Statista and Google Trends, to shed light on the statistical liaison between bottled water consumption and the digital echoes of human discomfort. Through meticulous analysis and a keen eye for patterns, we uncovered a remarkably robust correlation coefficient of 0.9417390, supported by a p-value that denounces mere coincidence with a resounding “less than 0.01.” This statistical embrace between the liquid allure of bottled water and the metaphorical throb of a headache beckons us to contemplate the intricate dance of consumer preferences and the digital pursuit of relief.
While it is imperative to exercise caution in attributing causality to this captivating correlation, our findings invite speculation about the whimsical interplay of consumer beverage habits and the virtual expressions of discomfort. As we embark on this scholarly exploration, we invite our readers to imbibe in the delightful absurdity of statistical relationships and the intellectual quenching of curiosity in the pursuit of knowledge.
So, put on your thinking caps, hold onto your proverbial hats, and join us on this whimsical exploration of the unexpected connections that lie beneath the surface of everyday phenomena. As we navigate the waters of statistical analysis and search for meaning amid the digital noise, we aim to unravel the intricacies of human behavior with a hint of humor and a splash of insight.
In the following sections, we will dive into the methodology, results, and implications of our investigation, all while maintaining a buoyant spirit of scientific inquiry and the occasional nod to the delightfully absurd.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the relationship between US bottled water consumption per person and Google searches for 'i have a headache' yields a medley of scholarly and whimsical inquiries. Smith and Doe (2015) examined the consumption patterns of bottled water in the United States, elucidating the evolving preferences and market dynamics that shape the liquid landscape of beverage consumption. Meanwhile, Jones (2018) delved into the nuances of online search behaviors, uncovering the digital footprints left by individuals seeking remedies for common ailments, including the perennial plight of headaches.

Transitioning from the serious to the absurd, the search for relevant non-fiction literature led the researchers to "Thirst: Water and Power in the Ancient World" by Steven Mithen and "The Headache Myth" by French neuroscientist and author, Joël Dor. These works, though not directly related to the quirky correlation at hand, provided intriguing perspectives on the historical significance of water and the physiological intricacies of headaches, sparking contemplations as effervescent as bottled fizz.

In the realm of fiction, the works of Haruki Murakami, with his surrealist narratives blending reality and fantasy, and Zadie Smith's explorations of modern society in "White Teeth" offer a whimsical escape into the twists and turns of human experiences, much like the unexpected correlation under investigation. Perhaps, amidst the pages of these literary creations, the answer to the enigmatic connection between hydration and online headache quests lies waiting to be uncovered.

Venturing even further off the scholarly path, the researchers turned to the whimsical world of cartoons and children's shows for inspiration, drawing parallels between the erratic yet endearing antics of "SpongeBob SquarePants" and the unpredictability of statistical relationships. The jocular escapades of "Phineas and Ferb" served as a reminder that unconventional insights often emerge from the most unlikely sources, prompting a lighthearted approach to the solemn pursuit of academic inquiry.

As the scholarly pursuit intersects with the whimsical and the unexpected, the literature review illuminates the multifaceted nature of research, inviting the readers to chuckle along the way and embrace the delightful absurdity that accompanies the quest for knowledge.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Google searches for 'i have a headache'. 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 Statista and Google Trends . You used data from 2004 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

[[INTRODUCTION]]
In the realm of research, one often encounters unexpected and curious correlations that pique the interest of both scholars and casual observers. The dynamics between seemingly unrelated phenomena can offer insights into human behavior, societal trends, and the intricate web of cause-and-effect relationships. The present study delves into one such peculiar correlation, aiming to unravel the enigmatic connection between the per capita consumption of bottled water in the United States and the frequency of Google searches for the plaintive expression, "i have a headache."
As academic researchers, we often embark on journeys that lead us to unexpected destinations, and this investigation was no exception. The quest to unearth the relationship between the hydration habits of individuals and their virtual quests for headache remedies led us down a path filled with statistical analyses, data visualizations, and the occasional water cooler conversation about the puzzling nature of human behavior. The intellectual thirst to explore this quirky correlation culminated in a rigorous examination of the available data, resulting in findings that may quench the curiosity of both research enthusiasts and aficionados of the absurd.
Our investigation draws upon data from reputable sources, including Statista and Google Trends, to shed light on the statistical liaison between bottled water consumption and the digital echoes of human discomfort. Through meticulous analysis and a keen eye for patterns, we uncovered a remarkably robust correlation coefficient of 0.9417390, supported by a p-value that denounces mere coincidence with a resounding “less than 0.01.” This statistical embrace between the liquid allure of bottled water and the metaphorical throb of a headache beckons us to contemplate the intricate dance of consumer preferences and the digital pursuit of relief.
While it is imperative to exercise caution in attributing causality to this captivating correlation, our findings invite speculation about the whimsical interplay of consumer beverage habits and the virtual expressions of discomfort. As we embark on this scholarly exploration, we invite our readers to imbibe in the delightful absurdity of statistical relationships and the intellectual quenching of curiosity in the pursuit of knowledge.
So, put on your thinking caps, hold onto your proverbial hats, and join us on this whimsical exploration of the unexpected connections that lie beneath the surface of everyday phenomena. As we navigate the waters of statistical analysis and search for meaning amid the digital noise, we aim to unravel the intricacies of human behavior with a hint of humor and a splash of insight.
In the following sections, we will dive into the methodology, results, and implications of our investigation, all while maintaining a buoyant spirit of scientific inquiry and the occasional nod to the delightfully absurd.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To quench the thirst for understanding the correlation between bottled water consumption per person in the United States and the frequency of Google searches for the phrase "i have a headache," our research team embarked on a data-driven escapade that spanned the digital realm of Google Trends and the statistical reservoir of Statista. Our methodology, much like a finely crafted beverage, blended elements of data collection, manipulation, and analysis to distill insights from the bubbling cauldron of online consumer behavior and search trends.

Data Collection:
Our intrepid journey into the digital wilderness began with the retrieval of data on US bottled water consumption from Statista. We amassed annual data ranging from 2004 to 2022, immersing ourselves in the waves of numerical figures that ebbed and flowed like the currents of consumer preferences. The tides of Google search trends for the phrase "i have a headache" were similarly captured from Google Trends, allowing us to cast our net wide enough to encapsulate the varied expressions of virtual discomfort over the same temporal expanse.

Data Processing:
As we delved into the ocean of statistical analytics, we carefully sieved through the data to ensure its purity and reliability. Our reservoir of statistical tools included the formidable capabilities of spreadsheets, programming languages, and the occasional incantation to summon the powers of data manipulation. With our digital sorcery at hand, we transformed the raw data into a harmonious ensemble of numbers and trends, bridging the practical magic of data preprocessing with the enchanting dance of information transformation.

Statistical Analysis:
Like alchemists of old, we forged ahead to unravel the mysterious connections concealed within the dataset. Armed with the arcane knowledge of correlation coefficients and p-values, we wielded the tools of statistical inquiry to unveil the subtle interplay between bottled water consumption and virtual expressions of cranial discomfort. Our analysis culminated in the calculation of a robust correlation coefficient of 0.9417390, a numerical testament to the tantalizing liaison between the two variables. The p-value, akin to a mystical gatekeeper, appeared with a resounding declaration of "less than 0.01," lending credence to the statistical significance of our findings.

Assumptions and Limitations:
While our foray into the digital labyrinth yielded intriguing findings, it is essential to acknowledge the caveats that accompany our expedition. The assumption of causality, much like a mirage in the statistical desert, remains elusive and subject to further exploration. Additionally, the idiosyncrasies of online search behavior and the complexities of consumer preferences echo like enigmatic whispers in the halls of analytical inquiry, reminding us of the intangible nature of human interactions with the digital domain.

Overall, our methodology mirrors the innate curiosity of the scientific mind, combining the rigor of data-driven inquiry with a touch of digital whimsy. In the next section, we will uncork the results of our analysis, inviting you to savor the flavorful blend of statistical intrigue and the unexpected correlations that lie beneath the surface of seemingly disparate phenomena.


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

Please make up the results section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Google searches for 'i have a headache'. 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 Statista and Google Trends .

For the time period 2004 to 2022, you found a correlation 0.9417390, r-squared of 0.8868724, 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of research, one often encounters unexpected and curious correlations that pique the interest of both scholars and casual observers. The dynamics between seemingly unrelated phenomena can offer insights into human behavior, societal trends, and the intricate web of cause-and-effect relationships. The present study delves into one such peculiar correlation, aiming to unravel the enigmatic connection between the per capita consumption of bottled water in the United States and the frequency of Google searches for the plaintive expression, "i have a headache."
As academic researchers, we often embark on journeys that lead us to unexpected destinations, and this investigation was no exception. The quest to unearth the relationship between the hydration habits of individuals and their virtual quests for headache remedies led us down a path filled with statistical analyses, data visualizations, and the occasional water cooler conversation about the puzzling nature of human behavior. The intellectual thirst to explore this quirky correlation culminated in a rigorous examination of the available data, resulting in findings that may quench the curiosity of both research enthusiasts and aficionados of the absurd.
Our investigation draws upon data from reputable sources, including Statista and Google Trends, to shed light on the statistical liaison between bottled water consumption and the digital echoes of human discomfort. Through meticulous analysis and a keen eye for patterns, we uncovered a remarkably robust correlation coefficient of 0.9417390, supported by a p-value that denounces mere coincidence with a resounding “less than 0.01.” This statistical embrace between the liquid allure of bottled water and the metaphorical throb of a headache beckons us to contemplate the intricate dance of consumer preferences and the digital pursuit of relief.
While it is imperative to exercise caution in attributing causality to this captivating correlation, our findings invite speculation about the whimsical interplay of consumer beverage habits and the virtual expressions of discomfort. As we embark on this scholarly exploration, we invite our readers to imbibe in the delightful absurdity of statistical relationships and the intellectual quenching of curiosity in the pursuit of knowledge.
So, put on your thinking caps, hold onto your proverbial hats, and join us on this whimsical exploration of the unexpected connections that lie beneath the surface of everyday phenomena. As we navigate the waters of statistical analysis and search for meaning amid the digital noise, we aim to unravel the intricacies of human behavior with a hint of humor and a splash of insight.
In the following sections, we will dive into the methodology, results, and implications of our investigation, all while maintaining a buoyant spirit of scientific inquiry and the occasional nod to the delightfully absurd.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis undertaken in this study unveiled a striking correlation between the per capita consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." The correlation coefficient, a measure of the strength and direction of the linear relationship between the two variables, was calculated to be 0.9417390. This value approaches the upper echelons of correlation coefficients, prompting us to raise a figurative eyebrow at the robust relationship unfurled before us.

Accompanying this correlation, the coefficient of determination, denoted as r-squared, stood at an impressive 0.8868724. This means that approximately 88.7% of the variance in Google searches for headache-related phrases can be explained by the per capita consumption of bottled water in the United States. We found ourselves marveling at the meticulous dance of data points, each whispering tales of statistical interconnectivity and perhaps a touch of hydrophilic wisdom.

Furthermore, the statistical significance of this correlation was underscored by a p-value of less than 0.01. This minuscule p-value sent ripples of statistical affirmation through our data-centric hearts, gently whispering, "Oh, this is no mere happenstance; it's statistically significant!"

To visually encapsulate the compelling correlation uncovered in our analysis, we present Fig. 1, a scatterplot that encapsulates the intriguing relationship between US bottled water consumption per person and Google searches for 'i have a headache.' This scatterplot serves as a visual testament to the statistical concordance observed, inviting both awe and amusement at the unlikely pairing of liquid consumption and digital manifestations of cranial discomfort. If a picture is worth a thousand words, then this scatterplot may just leave you searching for the right words to articulate the whimsy and wonder nestled within our findings.

In summary, our results illuminate a riveting correlation between the consumption of bottled water and the virtual pursuit of relief from cranial woes. This association transcends the mundane and invites us to delve deeper into the nuances of human behavior, all while prompting a chuckle in appreciation of the unexpected bedfellows we encounter in our statistical voyages.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Google searches for 'i have a headache'. 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

[[LITERATURE REVIEW]]
The investigation into the relationship between US bottled water consumption per person and Google searches for 'i have a headache' yields a medley of scholarly and whimsical inquiries. Smith and Doe (2015) examined the consumption patterns of bottled water in the United States, elucidating the evolving preferences and market dynamics that shape the liquid landscape of beverage consumption. Meanwhile, Jones (2018) delved into the nuances of online search behaviors, uncovering the digital footprints left by individuals seeking remedies for common ailments, including the perennial plight of headaches.
Transitioning from the serious to the absurd, the search for relevant non-fiction literature led the researchers to "Thirst: Water and Power in the Ancient World" by Steven Mithen and "The Headache Myth" by French neuroscientist and author, Joël Dor. These works, though not directly related to the quirky correlation at hand, provided intriguing perspectives on the historical significance of water and the physiological intricacies of headaches, sparking contemplations as effervescent as bottled fizz.
In the realm of fiction, the works of Haruki Murakami, with his surrealist narratives blending reality and fantasy, and Zadie Smith's explorations of modern society in "White Teeth" offer a whimsical escape into the twists and turns of human experiences, much like the unexpected correlation under investigation. Perhaps, amidst the pages of these literary creations, the answer to the enigmatic connection between hydration and online headache quests lies waiting to be uncovered.
Venturing even further off the scholarly path, the researchers turned to the whimsical world of cartoons and children's shows for inspiration, drawing parallels between the erratic yet endearing antics of "SpongeBob SquarePants" and the unpredictability of statistical relationships. The jocular escapades of "Phineas and Ferb" served as a reminder that unconventional insights often emerge from the most unlikely sources, prompting a lighthearted approach to the solemn pursuit of academic inquiry.
As the scholarly pursuit intersects with the whimsical and the unexpected, the literature review illuminates the multifaceted nature of research, inviting the readers to chuckle along the way and embrace the delightful absurdity that accompanies the quest for knowledge.

[[RESULTS]]
The statistical analysis undertaken in this study unveiled a striking correlation between the per capita consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." The correlation coefficient, a measure of the strength and direction of the linear relationship between the two variables, was calculated to be 0.9417390. This value approaches the upper echelons of correlation coefficients, prompting us to raise a figurative eyebrow at the robust relationship unfurled before us.
Accompanying this correlation, the coefficient of determination, denoted as r-squared, stood at an impressive 0.8868724. This means that approximately 88.7% of the variance in Google searches for headache-related phrases can be explained by the per capita consumption of bottled water in the United States. We found ourselves marveling at the meticulous dance of data points, each whispering tales of statistical interconnectivity and perhaps a touch of hydrophilic wisdom.
Furthermore, the statistical significance of this correlation was underscored by a p-value of less than 0.01. This minuscule p-value sent ripples of statistical affirmation through our data-centric hearts, gently whispering, "Oh, this is no mere happenstance; it's statistically significant!"
To visually encapsulate the compelling correlation uncovered in our analysis, we present Fig. 1, a scatterplot that encapsulates the intriguing relationship between US bottled water consumption per person and Google searches for 'i have a headache.' This scatterplot serves as a visual testament to the statistical concordance observed, inviting both awe and amusement at the unlikely pairing of liquid consumption and digital manifestations of cranial discomfort. If a picture is worth a thousand words, then this scatterplot may just leave you searching for the right words to articulate the whimsy and wonder nestled within our findings.
In summary, our results illuminate a riveting correlation between the consumption of bottled water and the virtual pursuit of relief from cranial woes. This association transcends the mundane and invites us to delve deeper into the nuances of human behavior, all while prompting a chuckle in appreciation of the unexpected bedfellows we encounter in our statistical voyages.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our investigation have unveiled a delightfully quirky and statistically robust relationship between US bottled water consumption per person and Google searches for the phrase "i have a headache." The strong correlation coefficient of 0.9417390 bolstered by an r-squared value of 0.8868724 would make even the most ardent data skeptic raise a metaphorical eyebrow in awe. It seems the flow of bottled water consumption in the United States and the flow of digital quests for headache remedies have intertwined like the helices of a DNA strand, creating a statistical double helix of liquid and lamentation.

These findings not only corroborate prior research into the idiosyncrasies of consumer beverage habits but also lend empirical weight to the medley of scholarly and whimsical inquiries that have characterized the discourse surrounding this eccentric correlation. Much like the surrealist narratives of Haruki Murakami or the whimsical escapades of "Phineas and Ferb," our study has thrust the improbable into the spotlight of statistical significance, evoking a chuckle amidst the solemn pursuit of academic inquiry.

Akin to the fluids coursing through the human body, the correlation between bottled water consumption and headache-related searches has flowed through the channels of our statistical analysis, rendering the connection as clear as, dare we say, H2O. While causation remains an elusive specter trailing on the peripheries of our findings, the robust statistical relationship invites contemplations as effervescent as fizzy bottled water.

In the grand scheme of scientific revelations, it is often the unlikeliest of correlations that prompt the most profound insights. Our investigation may have started as a whimsical endeavor into the realm of statistical oddities, but it has culminated in shedding light on the intriguing interplay between consumer behaviors and digital quest for relief. The unexpected bedfellows of liquid consumption and virtual expressions of cranial discomfort have sparked contemplations as effervescent as bottled fizz, leaving us marveling at the whimsicality of statistical voyages and the delightful peculiarity of human pursuits.

As we peer into the depths of statistical relationships, we are reminded that the world of data is not merely a sterile landscape of numbers and correlations but a playground of whimsy and wonder, where even the most peculiar pairings can reveal unexpected truths. Much like the laughter provoked by a strategically placed pun, the unveiling of this correlation has left us both enlightened and amused, beckoning us to revel in the delightful absurdity that often accompanies the pursuit of statistical knowledge.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between US Bottled Water Consumption per Person and Google searches for 'i have a headache'. 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]]
"Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'"

[[ABSTRACT]]
This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

[[INTRDUCTION]]
In the realm of research, one often encounters unexpected and curious correlations that pique the interest of both scholars and casual observers. The dynamics between seemingly unrelated phenomena can offer insights into human behavior, societal trends, and the intricate web of cause-and-effect relationships. The present study delves into one such peculiar correlation, aiming to unravel the enigmatic connection between the per capita consumption of bottled water in the United States and the frequency of Google searches for the plaintive expression, "i have a headache."
As academic researchers, we often embark on journeys that lead us to unexpected destinations, and this investigation was no exception. The quest to unearth the relationship between the hydration habits of individuals and their virtual quests for headache remedies led us down a path filled with statistical analyses, data visualizations, and the occasional water cooler conversation about the puzzling nature of human behavior. The intellectual thirst to explore this quirky correlation culminated in a rigorous examination of the available data, resulting in findings that may quench the curiosity of both research enthusiasts and aficionados of the absurd.
Our investigation draws upon data from reputable sources, including Statista and Google Trends, to shed light on the statistical liaison between bottled water consumption and the digital echoes of human discomfort. Through meticulous analysis and a keen eye for patterns, we uncovered a remarkably robust correlation coefficient of 0.9417390, supported by a p-value that denounces mere coincidence with a resounding “less than 0.01.” This statistical embrace between the liquid allure of bottled water and the metaphorical throb of a headache beckons us to contemplate the intricate dance of consumer preferences and the digital pursuit of relief.
While it is imperative to exercise caution in attributing causality to this captivating correlation, our findings invite speculation about the whimsical interplay of consumer beverage habits and the virtual expressions of discomfort. As we embark on this scholarly exploration, we invite our readers to imbibe in the delightful absurdity of statistical relationships and the intellectual quenching of curiosity in the pursuit of knowledge.
So, put on your thinking caps, hold onto your proverbial hats, and join us on this whimsical exploration of the unexpected connections that lie beneath the surface of everyday phenomena. As we navigate the waters of statistical analysis and search for meaning amid the digital noise, we aim to unravel the intricacies of human behavior with a hint of humor and a splash of insight.
In the following sections, we will dive into the methodology, results, and implications of our investigation, all while maintaining a buoyant spirit of scientific inquiry and the occasional nod to the delightfully absurd.

[[RESULTS]]
The statistical analysis undertaken in this study unveiled a striking correlation between the per capita consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." The correlation coefficient, a measure of the strength and direction of the linear relationship between the two variables, was calculated to be 0.9417390. This value approaches the upper echelons of correlation coefficients, prompting us to raise a figurative eyebrow at the robust relationship unfurled before us.
Accompanying this correlation, the coefficient of determination, denoted as r-squared, stood at an impressive 0.8868724. This means that approximately 88.7% of the variance in Google searches for headache-related phrases can be explained by the per capita consumption of bottled water in the United States. We found ourselves marveling at the meticulous dance of data points, each whispering tales of statistical interconnectivity and perhaps a touch of hydrophilic wisdom.
Furthermore, the statistical significance of this correlation was underscored by a p-value of less than 0.01. This minuscule p-value sent ripples of statistical affirmation through our data-centric hearts, gently whispering, "Oh, this is no mere happenstance; it's statistically significant!"
To visually encapsulate the compelling correlation uncovered in our analysis, we present Fig. 1, a scatterplot that encapsulates the intriguing relationship between US bottled water consumption per person and Google searches for 'i have a headache.' This scatterplot serves as a visual testament to the statistical concordance observed, inviting both awe and amusement at the unlikely pairing of liquid consumption and digital manifestations of cranial discomfort. If a picture is worth a thousand words, then this scatterplot may just leave you searching for the right words to articulate the whimsy and wonder nestled within our findings.
In summary, our results illuminate a riveting correlation between the consumption of bottled water and the virtual pursuit of relief from cranial woes. This association transcends the mundane and invites us to delve deeper into the nuances of human behavior, all while prompting a chuckle in appreciation of the unexpected bedfellows we encounter in our statistical voyages.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In culmination, our exploration into the symbiotic dance of bottled water consumption and digital expressions of cranial distress has quenched our academic curiosity with a statistical splash. The robust correlation coefficient and minuscule p-value served as buoyant guides through the sea of data, navigating us toward the shores of statistical significance with the occasional chuckle at the whimsical statistical bedfellows we encountered along the way.

As we reflect on the findings, one cannot help but marvel at the statistical embrace between quenching one's physical thirst and the metaphorical thirst for relief from cranial discomfort. The statistical interconnectivity, much like a refreshing gulp of water on a parched day, quenches the thirst for knowledge while also leaving one pondering the enigmatic quirks of human behavior.

While the shimmering allure of correlation beckons us with its statistical siren song, it is imperative to exercise caution in attributing causation to this quirky companionship between hydration habits and virtual quest for headache remedies. After all, correlation does not necessarily imply causation, much like how a magician's hat does not necessarily imply a rabbit (though we wouldn't mind a statistical magician to liven up the research conferences!).

In the grand tapestry of statistical investigations, our findings add a splash of whimsy and a hint of head-scratching amusement. The nuanced interplay between consumer beverage preferences and the ethereal echoes of digital discomfort invites us to ponder the quirkiness of human behavior, all while prompting a wry smile at the unexpected associations that statistical explorations unfurl.

With a nod to the delightful absurdity of statistical relationships and a metaphorical tip of the cap to the enigmatic nature of human behavior, we assert that no further research is needed in this curious realm of bottled water consumption and digital pursuits of cranial solace. For now, let us raise our glasses (of water, of course) to the delightful peculiarities that statistical investigations unveil, and embrace the whimsy of uncovering the unexpected in the realm of scholarly inquiry. Cheers to the quirky, the curious, and the statistically sublime!


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 Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Quirky Correlations in Consumer Behavior


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 Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache'. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Correlations in Public Health Research


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 Thirsting for Relief: A Quirky Correlation Between US Bottled Water Consumption per Person and Google Searches for 'I Have a Headache' with an abstract of This paper investigates the curious relationship between the consumption of bottled water in the United States and the frequency of Google searches for the phrase "i have a headache." Utilizing data from Statista and Google Trends, we aimed to quench the curiosity surrounding the potential connection between a thirst for bottled water and the figurative throb of a headache. Our findings revealed a remarkably strong correlation coefficient of 0.9417390 and a p-value of less than 0.01, suggesting a robust statistical relationship between these seemingly unrelated factors. While causation cannot be definitively established from this analysis, the association between quenching one's thirst and the digital pursuit of headache remedies is a fascinating spectacle to behold. This study may leave you with a headache of your own, pondering the whimsical interplay of consumer beverage habits and Internet search trends.

ChatGPT:

bottled water, consumption, United States, Google searches, headache, correlation, research, Statista, Google Trends, association, causation, consumer behavior, beverage habits, Internet search trends

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

Google searches for 'i have a headache'
Detailed data title: Relative volume of Google searches for 'i have a headache' (Worldwide), with quotes)
Source: Google Trends
Additional Info: Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'i have a headache'

Correlation r = 0.9417390 (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 = 0.8868724 (Coefficient of determination)
This means 88.7% of the change in the one variable (i.e., Google searches for 'i have a headache') is predictable based on the change in the other (i.e., US Bottled Water Consumption per Person) over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.8E-9. 0.0000000018149385595298698000
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 0.94 in 1.8E-7% of random cases. Said differently, if you correlated 550,982,839 random variables You don't actually need 550 million 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 18 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.85, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
2004200520062007200820092010201120122013201420152016201720182019202020212022
US Bottled Water Consumption per Person (Gallons)23.225.427.62928.527.628.329.230.83234.136.5394242.34445.24746.5
Google searches for 'i have a headache' (Rel. search volume)8.755.083335.916675.166679.2515.166720.2527.416733.416736.833339.583339.54245.333350.333354.8333818077.5833




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([23.2,25.4,27.6,29,28.5,27.6,28.3,29.2,30.8,32,34.1,36.5,39,42,42.3,44,45.2,47,46.5,])
array_2 = np.array([8.75,5.08333,5.91667,5.16667,9.25,15.1667,20.25,27.4167,33.4167,36.8333,39.5833,39.5,42,45.3333,50.3333,54.8333,81,80,77.5833,])
array_1_name = "US Bottled Water Consumption per Person"
array_2_name = "Google searches for 'i have a headache'"

# 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 rating is much appreciated!


Correlation ID: 3936 · Black Variable ID: 32 · Red Variable ID: 1524
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0