Spurious correlation #3,766 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of Breweries in the United States and the second variable is Solar power generated in Philippines. The chart goes from 2005 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of Breweries in the United States and the second variable is Solar power generated in Philippines. The chart goes from 2005 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of breweries in the United States has gone up, so has the production of beer. This has led to an increase in the demand for refrigeration to keep all that beer cold. The surge in the refrigeration industry has inadvertently created a need for more efficient energy solutions. This sudden demand for refrigeration has caused a ripple effect all the way to the Philippines, prompting a spike in the adoption of solar power technology. It's a sudsy situation that's sparking a bright idea for renewable energy in the Philippines! Looks like the power of fermentation is not just brewing beer, but also brewing up some solar energy initiatives. It's a real ale-truism that the sun's got some competition from these hops and barle(y) watts!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that combines the vast, open landscapes of the United States and the Philippines, showcasing the growth of breweries and sustainable solar energy. Picture a serene setting with rolling hills in the background and solar panels glistening under the bright sun. In the foreground, establish a cluster of lively breweries emerging from the landscape, each emitting the inviting aroma of freshly brewed beer. Show a beer garden bustling with people, enjoying the delightful ambiance of solar-powered lights, music, and the delicious craft brews. Capture a sense of community and sustainability, emphasizing the harmony between traditional brewing techniques and modern energy practices. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: The number of Breweries in the United States and Solar power generated in Philippines. 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: Cyber folk A scene from Skyrim Realistic An image that looks like it is a scene from a Pixar movie a meme
ChatGPT: A scene from Skyrim

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of Breweries in the United States and Solar power generated in Philippines, in the following situation: As the number of breweries in the US increased, so did the production of beer. This led to a rise in demand for solar energy in the Philippines, as locals wanted to power up to party under the sun and "beer-garden" more efficiently.. Keep the description simple.
ChatGPT: In the United States, the number of breweries has been steadily increasing over the years. Visualize a growing cluster of breweries across the country, with new ones popping up frequently, each filled with the delicious aroma of freshly brewed beer. At the same time, picture the sunny landscape of the Philippines, with solar panels soaking up the abundant sunshine, powering up as locals strive for more sustainable energy sources. Amidst this, envision people gathered in a vibrant beer garden, enjoying the fruits of the breweries' labor under the warm glow of solar-powered lights and music, creating a lively and eco-friendly atmosphere.

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 scene from Skyrim ] and depicting this scene: In the United States, the number of breweries has been steadily increasing over the years. Visualize a growing cluster of breweries across the country, with new ones popping up frequently, each filled with the delicious aroma of freshly brewed beer. At the same time, picture the sunny landscape of the Philippines, with solar panels soaking up the abundant sunshine, powering up as locals strive for more sustainable energy sources. Amidst this, envision people gathered in a vibrant beer garden, enjoying the fruits of the breweries' labor under the warm glow of solar-powered lights and music, creating a lively and eco-friendly atmosphere. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that combines the vast, open landscapes of the United States and the Philippines, showcasing the growth of breweries and sustainable solar energy. Picture a serene setting with rolling hills in the background and solar panels glistening under the bright sun. In the foreground, establish a cluster of lively breweries emerging from the landscape, each emitting the inviting aroma of freshly brewed beer. Show a beer garden bustling with people, enjoying the delightful ambiance of solar-powered lights, music, and the delicious craft brews. Capture a sense of community and sustainability, emphasizing the harmony between traditional brewing techniques and modern energy practices.

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

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

AI academic paper

(Because p < 0.01)

Ale and Kale: The Pale Tale of Breweries and Solar Flare

The Journal of Culinary Chemobiology

Jan 2024

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

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

Model: gpt-3.5-turbo-1106
System prompt: You are a 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 The number of Breweries in the United States and Solar power generated in Philippines. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"Ale and Kale: The Pale Tale of Breweries and Solar Flare"

[[ABSTRACT]]
This research paper investigates the curious connection between the number of breweries in the United States and the solar power generated in the Philippines. With a dash of hops and a sprinkle of sunlight, our research team delved into the intertwining worlds of craft beer and renewable energy. Data from the Brewers Association and the Energy Information Administration were carefully examined, revealing a surprisingly strong correlation coefficient of 0.9521889 and p < 0.01 for the years 2005 to 2021. Join us in uncapping this frothy mystery as we shed light on the unexpected relationship between these disparate industries.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
"Beer and sunshine, a match made in statistical heaven," one might quip upon hearing of the improbable link between the number of breweries in the United States and the solar power generated in the Philippines. While one may initially assume that these two industries have about as much in common as a pint of stout and a kale smoothie, our investigation has unearthed a fascinating correlation that challenges preconceived notions and tickles the intellect.
The world of craft beer has been bubbling with enthusiasm, as the number of breweries in the United States has been steadily fermenting over the past decade. Simultaneously, the Philippines has been basking in the glow of solar energy, harnessing the power of the sun to illuminate homes and power industries. What could possibly link these seemingly disparate phenomena? That is the frothy mystery we aim to unravel in this study.
This intercontinental investigation is not merely an esoteric exercise in number-crunching. Rather, it serves as a refreshing departure from traditional cross-industry analyses, injecting a touch of excitement into the sometimes staid field of statistical research. Like a well-pulled pint, this study promises to deliver a heady concoction of unexpected insights and, dare we say, a twist of statistical humor. So, join us as we embark on this intellectual pub crawl down the avenue of statistical correlation and causation. Cheers to shedding light on this pale tale of breweries and solar flare!

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Several studies have examined the relationship between seemingly unrelated industries, offering insights into unexpected connections and correlations. Smith et al. (2017) delved into the world of renewable energy and economic development, while Doe (2014) explored the dynamics of the brewing industry in the United States. Jones (2019) examined the factors influencing solar power generation in various regions across the globe. These serious studies laid the groundwork for our investigation into the intriguing alliance between the number of breweries in the United States and the solar power generated in the Philippines.

In "Renewable Energy and Economic Development," Smith et al. (2017) uncovered intriguing parallels between the growth of renewable energy sources and economic prosperity in developing countries. The study highlighted the potential for renewable energy, such as solar power, to contribute to sustainable economic development. Meanwhile, Doe (2014) provided a comprehensive analysis of the brewing industry in the United States, detailing the exponential rise in the number of craft breweries and their impact on the national economy. On the solar front, Jones (2019) offered valuable insights into the factors influencing solar power generation, emphasizing the significance of environmental conditions and policy frameworks.

Drawing inspiration from non-fiction literature, our research team turned to books such as "The Economics of Solar Power" by Green and "The Craft Beer Revolution" by Bernstein to gain a deeper understanding of the economic and environmental dynamics surrounding the solar power and brewing industries. These sources provided a solid foundation for our exploration into the unexpected interplay between these realms.

However, in a somewhat unorthodox departure from conventional literature review practices, we also drew inspiration from the world of fiction and board games. The science fiction novel "Solaris" by Stanislaw Lem and the mystery thriller "The Brewer's Tale" by Karen Brooks offered imaginative musings on the convergence of celestial forces and earthly libations, providing a whimsical backdrop to our research endeavors. Furthermore, the board game "Brewcraft: Solar Edition" introduced a playful element into our investigation, fueling our scholarly pursuits with an undercurrent of joviality and unexpected connections.

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 The number of Breweries in the United States and Solar power generated in Philippines. Make lots of jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Brewers Association and Energy Information Administration . You used data from 2005 to 2021

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]]
"Ale and Kale: The Pale Tale of Breweries and Solar Flare"

[[ABSTRACT]]
This research paper investigates the curious connection between the number of breweries in the United States and the solar power generated in the Philippines. With a dash of hops and a sprinkle of sunlight, our research team delved into the intertwining worlds of craft beer and renewable energy. Data from the Brewers Association and the Energy Information Administration were carefully examined, revealing a surprisingly strong correlation coefficient of 0.9521889 and p < 0.01 for the years 2005 to 2021. Join us in uncapping this frothy mystery as we shed light on the unexpected relationship between these disparate industries.

[[INTRODUCTION]]
"Beer and sunshine, a match made in statistical heaven," one might quip upon hearing of the improbable link between the number of breweries in the United States and the solar power generated in the Philippines. While one may initially assume that these two industries have about as much in common as a pint of stout and a kale smoothie, our investigation has unearthed a fascinating correlation that challenges preconceived notions and tickles the intellect.
The world of craft beer has been bubbling with enthusiasm, as the number of breweries in the United States has been steadily fermenting over the past decade. Simultaneously, the Philippines has been basking in the glow of solar energy, harnessing the power of the sun to illuminate homes and power industries. What could possibly link these seemingly disparate phenomena? That is the frothy mystery we aim to unravel in this study.
This intercontinental investigation is not merely an esoteric exercise in number-crunching. Rather, it serves as a refreshing departure from traditional cross-industry analyses, injecting a touch of excitement into the sometimes staid field of statistical research. Like a well-pulled pint, this study promises to deliver a heady concoction of unexpected insights and, dare we say, a twist of statistical humor. So, join us as we embark on this intellectual pub crawl down the avenue of statistical correlation and causation. Cheers to shedding light on this pale tale of breweries and solar flare!

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To unravel the intertwined saga of breweries and solar power, our research team embarked on a convoluted but thoroughly enlightening methodological journey. We began by greedily consuming an assortment of data from the Brewers Association and the Energy Information Administration, savoring the rich flavors of statistical information from the years 2005 to 2021.

Firstly, we concocted a heady brew of statistical analyses, incorporating a potent blend of correlation coefficients, regression models, and time series analysis. These methods acted as the yeast to ferment our raw data, allowing us to distill the essence of the relationship between breweries in the United States and solar power generated in the Philippines.

Our data collection process resembled a lively scavenger hunt, as we scoured the depths of the internet, dodging dubious sources and navigating through the maze of online databases. We faced many ale-ments along the way (pun intended), including missing data, conflicting statistics, and the occasional misleading graph that tried to lead us astray.

Following the assembly of our data collection, we meticulously sieved through the voluminous information, separating the frothy facts from the skimmings. This rigorous filtering process ensured that only the purest, most robust data remained to be distilled into the final concoction of results.

To quantify the degree of association between the number of breweries in the United States and the solar power generated in the Philippines, we employed various statistical tools, including Pearson's correlation coefficient, multiple regression analysis, and perhaps a dash of statistical magic. These analytical tools allowed us to gauge the strength and direction of the relationship between these seemingly disparate industries.

Furthermore, we harnessed the power of statistical software, engaging in a ceremonial dance with the likes of R, Python, and other statistical sorcery to extract meaningful insights from our data. This collaboration of man and machine yielded a cornucopia of results, illuminating the mysterious connection between the proliferation of breweries and the radiant solar power in the Philippines.

In summary, our methodology was a flavorful blend of data wrangling, statistical sorcery, and a touch of whimsy, ultimately delivering a crisp analysis of the curious correlation between breweries in the United States and solar energy generation in the Philippines.

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 The number of Breweries in the United States and Solar power generated in Philippines. Make lots of jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Ale and Kale: The Pale Tale of Breweries and Solar Flare"

[[ABSTRACT]]
This research paper investigates the curious connection between the number of breweries in the United States and the solar power generated in the Philippines. With a dash of hops and a sprinkle of sunlight, our research team delved into the intertwining worlds of craft beer and renewable energy. Data from the Brewers Association and the Energy Information Administration were carefully examined, revealing a surprisingly strong correlation coefficient of 0.9521889 and p < 0.01 for the years 2005 to 2021. Join us in uncapping this frothy mystery as we shed light on the unexpected relationship between these disparate industries.

[[LITERATURE REVIEW]]
Several studies have examined the relationship between seemingly unrelated industries, offering insights into unexpected connections and correlations. Smith et al. (2017) delved into the world of renewable energy and economic development, while Doe (2014) explored the dynamics of the brewing industry in the United States. Jones (2019) examined the factors influencing solar power generation in various regions across the globe. These serious studies laid the groundwork for our investigation into the intriguing alliance between the number of breweries in the United States and the solar power generated in the Philippines.
In "Renewable Energy and Economic Development," Smith et al. (2017) uncovered intriguing parallels between the growth of renewable energy sources and economic prosperity in developing countries. The study highlighted the potential for renewable energy, such as solar power, to contribute to sustainable economic development. Meanwhile, Doe (2014) provided a comprehensive analysis of the brewing industry in the United States, detailing the exponential rise in the number of craft breweries and their impact on the national economy. On the solar front, Jones (2019) offered valuable insights into the factors influencing solar power generation, emphasizing the significance of environmental conditions and policy frameworks.
Drawing inspiration from non-fiction literature, our research team turned to books such as "The Economics of Solar Power" by Green and "The Craft Beer Revolution" by Bernstein to gain a deeper understanding of the economic and environmental dynamics surrounding the solar power and brewing industries. These sources provided a solid foundation for our exploration into the unexpected interplay between these realms.
However, in a somewhat unorthodox departure from conventional literature review practices, we also drew inspiration from the world of fiction and board games. The science fiction novel "Solaris" by Stanislaw Lem and the mystery thriller "The Brewer's Tale" by Karen Brooks offered imaginative musings on the convergence of celestial forces and earthly libations, providing a whimsical backdrop to our research endeavors. Furthermore, the board game "Brewcraft: Solar Edition" introduced a playful element into our investigation, fueling our scholarly pursuits with an undercurrent of joviality and unexpected connections.

[[RESULTS]]
The results of our investigation into the connection between the number of breweries in the United States and the solar power generated in the Philippines revealed a staggering correlation coefficient of 0.9521889 and an r-squared value of 0.9066637 for the time period of 2005 to 2021. The p-value was found to be less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.
As seen in Fig. 1, our scatterplot graphically illustrates the strong positive correlation between the number of breweries in the United States and the solar power generated in the Philippines. It's as clear as a sunny day that there is a striking pattern between these two disparate industries.
The findings suggest that as the craft beer revolution continued to brew and ferment in the United States, there was a parallel surge in solar power generation in the Philippines. This unexpected correlation sent shockwaves through the research team, leaving us in awe of the mysterious interconnectedness of global industries.
In conclusion, our results indicate a compelling link between the number of breweries in the United States and the solar power generated in the Philippines. This novel discovery paves the way for further investigation into the intricate web of connections that underlie seemingly unrelated sectors. Just when you thought you had seen it all, along comes a frothy tale of ale and kale, shedding light on the unexpected synergies between beer and sunshine.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of this study have shed light on the intriguing relationship between the number of breweries in the United States and the solar power generated in the Philippines, providing compelling evidence to support the prior research that examined unexpected connections between disparate industries. Our findings revealed a remarkably high correlation coefficient, indicating a strong positive relationship between these seemingly unrelated variables. This aligns with the work of Smith et al. (2017), who explored the potential for renewable energy, such as solar power, to contribute to sustainable economic development. Our results underscore the significance of solar power generation in driving economic dynamics and hint at the potential influence of breweries in the U.S. on this renewable energy source.

In a somewhat eccentric departure from traditional literature review practices, we harked back to the inspirational world of fiction and board games, which spurred our scholarly pursuits with an undercurrent of playfulness and unexpected connections. While some may view these references as frivolous, they actually provided a whimsical backdrop to our research and helped us approach the investigation with a creative perspective, much like the creative use of hops in crafting a fine brew.

Our study has not only strengthened the findings of prior research but has also stirred new questions and considerations. It is evident that the astronomical rise in the number of craft breweries in the United States may have had an unforeseen impact on the solar power landscape in the Philippines. This unexpected correlation has punctuated the complex web of global interconnections across industries, challenging conventional wisdom and sparking intrigue.

In the lexicon of unexpected connections, the alliance between ale and kale, or rather, breweries and solar power, stands out as a frothy tale with profound implications. As we move forward, it will be crucial to delve deeper into the underlying mechanisms driving this association. Just when we thought we had seen it all, the convergence of celestial forces and earthly libations has left us pondering the unexpected synergies between beer and sunshine.

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 The number of Breweries in the United States and Solar power generated in Philippines. Make lots of jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Ale and Kale: The Pale Tale of Breweries and Solar Flare"

[[ABSTRACT]]
This research paper investigates the curious connection between the number of breweries in the United States and the solar power generated in the Philippines. With a dash of hops and a sprinkle of sunlight, our research team delved into the intertwining worlds of craft beer and renewable energy. Data from the Brewers Association and the Energy Information Administration were carefully examined, revealing a surprisingly strong correlation coefficient of 0.9521889 and p < 0.01 for the years 2005 to 2021. Join us in uncapping this frothy mystery as we shed light on the unexpected relationship between these disparate industries.

[[INTRDUCTION]]
"Beer and sunshine, a match made in statistical heaven," one might quip upon hearing of the improbable link between the number of breweries in the United States and the solar power generated in the Philippines. While one may initially assume that these two industries have about as much in common as a pint of stout and a kale smoothie, our investigation has unearthed a fascinating correlation that challenges preconceived notions and tickles the intellect.
The world of craft beer has been bubbling with enthusiasm, as the number of breweries in the United States has been steadily fermenting over the past decade. Simultaneously, the Philippines has been basking in the glow of solar energy, harnessing the power of the sun to illuminate homes and power industries. What could possibly link these seemingly disparate phenomena? That is the frothy mystery we aim to unravel in this study.
This intercontinental investigation is not merely an esoteric exercise in number-crunching. Rather, it serves as a refreshing departure from traditional cross-industry analyses, injecting a touch of excitement into the sometimes staid field of statistical research. Like a well-pulled pint, this study promises to deliver a heady concoction of unexpected insights and, dare we say, a twist of statistical humor. So, join us as we embark on this intellectual pub crawl down the avenue of statistical correlation and causation. Cheers to shedding light on this pale tale of breweries and solar flare!

[[RESULTS]]
The results of our investigation into the connection between the number of breweries in the United States and the solar power generated in the Philippines revealed a staggering correlation coefficient of 0.9521889 and an r-squared value of 0.9066637 for the time period of 2005 to 2021. The p-value was found to be less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.
As seen in Fig. 1, our scatterplot graphically illustrates the strong positive correlation between the number of breweries in the United States and the solar power generated in the Philippines. It's as clear as a sunny day that there is a striking pattern between these two disparate industries.
The findings suggest that as the craft beer revolution continued to brew and ferment in the United States, there was a parallel surge in solar power generation in the Philippines. This unexpected correlation sent shockwaves through the research team, leaving us in awe of the mysterious interconnectedness of global industries.
In conclusion, our results indicate a compelling link between the number of breweries in the United States and the solar power generated in the Philippines. This novel discovery paves the way for further investigation into the intricate web of connections that underlie seemingly unrelated sectors. Just when you thought you had seen it all, along comes a frothy tale of ale and kale, shedding light on the unexpected synergies between beer and sunshine.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]
In conclusion, our research has illuminated a surprisingly robust and statistically significant connection between the number of breweries in the United States and the solar power generated in the Philippines. It appears that while one industry was busy "brewing" up a storm, the other was harnessing the power of the sun in a delightful and unexpected symphony of statistical harmony. It's as if the craft beer movement said, "Let there be light," and lo and behold, solar power flourished in response.

Our findings not only showcase the intricate dance of global industries but also serve as a reminder that in the realm of statistical relationships, just like in life, one should never underestimate the power of a good pairing. Perhaps in the vast tapestry of economic and environmental interactions, there are more surprising duos waiting to be discovered; who knows what other odd couples are out there, just waiting for researchers to uncork their potential?

So, as we raise a toast to the unanticipated kinship between breweries and solar power, it is clear that this research has provided a refreshing and effervescent glimpse into the interconnectedness of seemingly unrelated industries. Our study adds a frothy layer of understanding to the kaleidoscope of economic and environmental influences, and we hope it inspires future researchers to uncork their curiosity and delve into other unexplored correlations, even if they seem as unlikely as beer and sunshine.

It is our firm belief that no further research is needed in this area, as we have truly captured the essence of this unexpected relationship. As the saying goes, sometimes a statistical mystery is meant to remain beautifully enigmatic.

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 Ale and Kale: The Pale Tale of Breweries and Solar Flare. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Culinary Chemobiology

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 Ale and Kale: The Pale Tale of Breweries and Solar Flare. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Interdisciplinary Studies of Gastronomy and Astrophysics

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 Ale and Kale: The Pale Tale of Breweries and Solar Flare with an abstract of This research paper investigates the curious connection between the number of breweries in the United States and the solar power generated in the Philippines. With a dash of hops and a sprinkle of sunlight, our research team delved into the intertwining worlds of craft beer and renewable energy. Data from the Brewers Association and the Energy Information Administration were carefully examined, revealing a surprisingly strong correlation coefficient of 0.9521889 and p < 0.01 for the years 2005 to 2021. Join us in uncapping this frothy mystery as we shed light on the unexpected relationship between these disparate industries.

ChatGPT:

breweries, solar power, craft beer, renewable energy, United States, Philippines, correlation coefficient, Brewers Association, Energy Information Administration, 2005-2021

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

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

Solar power generated in Philippines
Detailed data title: Total solar power generated in Philippines in billion kWh
Source: Energy Information Administration
See what else correlates with Solar power generated in Philippines

Correlation r = 0.9521889 (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 = 0.9066637 (Coefficient of determination)
This means 90.7% of the change in the one variable (i.e., Solar power generated in Philippines) is predictable based on the change in the other (i.e., The number of Breweries in the United States) over the 17 years from 2005 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.0E-9.^Show 0.0000000039876895995245230000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.95 in 4.0E-7% of random cases. Said differently, if you correlated 250,771,775 random variables^Note You don't actually need 250 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 16 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 16 because we have two variables measured over a period of 17 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.

[ 0.87, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of Breweries in the United States (Number of breweries)	1612	1741	1805	1896	1933	2131	2525	2670	3162	4014	4847	5780	6767	7722	8557	9092	9384
Solar power generated in Philippines (Billion kWh)	0.002	0.001	0.001	0.001	0.001	0.001	0.001	0.001	0.001	0.018	0.141	1.099	1.204	1.253	1.263	1.389	1.5

Why this works

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

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([1612,1741,1805,1896,1933,2131,2525,2670,3162,4014,4847,5780,6767,7722,8557,9092,9384,])
array_2 = np.array([0.002,0.001,0.001,0.001,0.001,0.001,0.001,0.001,0.001,0.018,0.141,1.099,1.204,1.253,1.263,1.389,1.5,])
array_1_name = "The number of Breweries in the United States"
array_2_name = "Solar power generated in Philippines"

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

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

Reuseable content

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

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

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

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

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

Download images for these variables:

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

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

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of Breweries in the United States
Line chart for only Solar power generated in Philippines
AI-generated correlation image
The spurious research paper: Ale and Kale: The Pale Tale of Breweries and Solar Flare

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 3766 · Black Variable ID: 34 · Red Variable ID: 23900


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