Spurious correlation #1,899 · 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 Wind power generated in Canada. The chart goes from 1992 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 Wind power generated in Canada. The chart goes from 1992 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 hops up, there's a related surge in demand for beer. This leads to an increase in the production of hops, a key ingredient in beer. More hop production means more farmers investing in wind power to meet the energy needs of their hop farms. It's a real ale-wind situation! You could say it's all about brews and breezes creating a ferment of renewable energy across the border. The connection is quite hoppy, I mean, happy!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image in a 3D Pixar Style of a bustling city street lined with charming breweries, each with its vibrant signage and outdoor seating areas. In the distance, a serene landscape is visible, dotted with graceful wind turbines turning in the wind and generating clean energy for the country. The scene should capture the lively atmosphere of the city while showcasing the natural beauty and sustainability of the surrounding countryside. 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 Wind power generated in Canada. 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: Cybernetic art Macabre 3D Pixar Style Cubism Cutsy art illustration
ChatGPT: 3D Pixar Style

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 Wind power generated in Canada together. Keep the description simple.
ChatGPT: In a bustling city, there is a row of charming breweries with their vibrant signs and outdoor seating areas. In the distance, a serene landscape is dotted with wind turbines gracefully turning in the wind, generating clean energy for the country.

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: [ 3D Pixar Style ] and depicting this scene: In a bustling city, there is a row of charming breweries with their vibrant signs and outdoor seating areas. In the distance, a serene landscape is dotted with wind turbines gracefully turning in the wind, generating clean energy for the country. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in a 3D Pixar Style of a bustling city street lined with charming breweries, each with its vibrant signage and outdoor seating areas. In the distance, a serene landscape is visible, dotted with graceful wind turbines turning in the wind and generating clean energy for the country. The scene should capture the lively atmosphere of the city while showcasing the natural beauty and sustainability of the surrounding countryside.

*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 Wind power generated in Canada to increase. Include one good pun.

AI academic paper

(Because p < 0.01)

Hops and Props: The Link Between Breweries in the States and Wind Power in Canada

The Journal of Fermented Energy and Environmental Dynamics

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 Wind power generated in Canada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Hops and Props: The Link Between Breweries in the States and Wind Power in Canada

[[ABSTRACT]]
This study delved into the often-overlooked relationship between the number of breweries in the United States and the wind power generated in Canada. Utilizing data from the Brewers Association and the Energy Information Administration, we sought to uncover whether there exists a meaningful correlation between these seemingly disparate phenomena. The findings revealed a striking correlation coefficient of 0.9606153 with a p-value less than 0.01 over the period spanning 1992 to 2021. This surprising association prompts a reevaluation of traditional economic and environmental indicators and offers a refreshing perspective on the interconnectedness of seemingly unrelated industries. The results, while unexpected, furnish valuable insights into the potential cross-border influence of craft brewing on renewable energy production, and vice versa.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The interplay between seemingly unrelated industries has long fascinated economists, environmentalists, and beverage enthusiasts alike. In this study, we sought to unravel the intriguing link between the proliferation of breweries in the United States and the generation of wind power in Canada. While these two sectors may appear as unrelated as a stout and a squall, our analysis aimed to shed light on any potential connections between them.
In recent years, the craft brewing industry in the United States has experienced a boom, with enthusiasts fervently discussing the merits of hazy IPAs and barrel-aged stouts. Meanwhile, in Canada, wind power has been gaining momentum as a renewable energy source, quietly churning out kilowatts of clean electricity. One might wonder what these two disparate phenomena could possibly have in common, aside from perhaps the occasional gust of wind being put to good use in both brewing and electricity generation.
The prevailing wisdom in economic and environmental circles has traditionally treated these industries as independent and self-contained. However, our investigation has unearthed surprising evidence of a significant statistical association between the number of breweries in the United States and the wind power generated in Canada. This unexpected connection has the potential to revolutionize the way we perceive the influence of beer production on renewable energy sources, and vice versa.
The unearthing of such an unexpected correlation is akin to discovering that two seemingly unrelated puzzle pieces actually fit together snugly, forming a picture that challenges our assumptions. Thus, it is with great anticipation that we present our findings, which may prompt a rethinking of traditional economic and environmental paradigms. Through this analysis, we endeavor to elucidate the clandestine ties between taps and turbines, hops and horsepower, and brews and breezes.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The literature pertaining to the relationship between the number of breweries in the United States and wind power generated in Canada is relatively scarce, reflecting the surprising nature of this paradigm-shifting connection. However, the extant studies on related phenomena provide a foundation for understanding the unexpected correlations unveiled in the current investigation.

Smith et al. (2018) conducted a comprehensive analysis of the craft brewing industry in the United States, uncovering trends in the geographical distribution of breweries and the proliferation of microbreweries and brewpubs. Their study, while not explicitly focused on cross-border influences, lays the groundwork for understanding the dynamics of brewery expansion and regional concentrations. Doe and Jones (2016) explored the complex web of factors driving wind power growth in Canada, delving into policy initiatives, technological advancements, and environmental impacts. While their work did not anticipate the intriguing interplay with the U.S. brewing landscape, it sheds light on the multifaceted nature of renewable energy development.

Moving beyond the academic realm, several non-fiction sources offer insights into the craft brewing and renewable energy sectors, which may indirectly inform the unanticipated linkage observed in the present study. In "Brewing Up a Business" by Sam Calagione, the author details the trials and triumphs of building a craft brewery, providing a close-up view of the industry's internal workings. Likewise, "The Quest for Wind Energy" by Ben Chandler delves into the quest for harnessing wind as a sustainable energy source, offering a glimpse into the challenges and innovations of wind power generation.

On a more imaginative note, works of fiction with thematic resonances shed light on the cultural and imaginative dimensions of brewing and wind power. In "The Alehouse at the End of the World" by Stevan Allred, the fantastical tale of a fabled alehouse transports readers to a surreal world where the boundaries between reality and myth blur, paralleling the unexpected entwining of brewing and wind power in this investigation. Similarly, "The Windup Girl" by Paolo Bacigalupi offers a dystopian vision of future energy struggles, drawing thematic parallels to the intertwining of brewery growth and wind power generation.

To gain a more holistic understanding of the cultural and societal dimensions surrounding these industries, the researchers also expanded their investigations to popular television shows. "Brew Dogs" and "Brew Masters" provided an insider’s look into the craft brewing world, highlighting the passion and innovation that drive the industry forward. "Mega Builders" and "Rise of the Machines" delved into the engineering marvels and logistical challenges of wind turbine installation, offering a glimpse into the formidable infrastructure underpinning the wind power sector.

The diverse array of literature, spanning academic studies, non-fiction works, fiction novels, and television programs, collectively enriches our understanding of the unexpected kinship between breweries in the United States and wind power in Canada. These sources, while not explicitly addressing the nexus of beer and breezes, offer valuable contextual insights that inform the current investigation and infuse it with a sense of intrigue and discovery.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of 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 Wind power generated in Canada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Hops and Props: The Link Between Breweries in the States and Wind Power in Canada

[[ABSTRACT]]
This study delved into the often-overlooked relationship between the number of breweries in the United States and the wind power generated in Canada. Utilizing data from the Brewers Association and the Energy Information Administration, we sought to uncover whether there exists a meaningful correlation between these seemingly disparate phenomena. The findings revealed a striking correlation coefficient of 0.9606153 with a p-value less than 0.01 over the period spanning 1992 to 2021. This surprising association prompts a reevaluation of traditional economic and environmental indicators and offers a refreshing perspective on the interconnectedness of seemingly unrelated industries. The results, while unexpected, furnish valuable insights into the potential cross-border influence of craft brewing on renewable energy production, and vice versa.

[[LITERATURE REVIEW]]
The literature pertaining to the relationship between the number of breweries in the United States and wind power generated in Canada is relatively scarce, reflecting the surprising nature of this paradigm-shifting connection. However, the extant studies on related phenomena provide a foundation for understanding the unexpected correlations unveiled in the current investigation.
Smith et al. (2018) conducted a comprehensive analysis of the craft brewing industry in the United States, uncovering trends in the geographical distribution of breweries and the proliferation of microbreweries and brewpubs. Their study, while not explicitly focused on cross-border influences, lays the groundwork for understanding the dynamics of brewery expansion and regional concentrations. Doe and Jones (2016) explored the complex web of factors driving wind power growth in Canada, delving into policy initiatives, technological advancements, and environmental impacts. While their work did not anticipate the intriguing interplay with the U.S. brewing landscape, it sheds light on the multifaceted nature of renewable energy development.
Moving beyond the academic realm, several non-fiction sources offer insights into the craft brewing and renewable energy sectors, which may indirectly inform the unanticipated linkage observed in the present study. In "Brewing Up a Business" by Sam Calagione, the author details the trials and triumphs of building a craft brewery, providing a close-up view of the industry's internal workings. Likewise, "The Quest for Wind Energy" by Ben Chandler delves into the quest for harnessing wind as a sustainable energy source, offering a glimpse into the challenges and innovations of wind power generation.
On a more imaginative note, works of fiction with thematic resonances shed light on the cultural and imaginative dimensions of brewing and wind power. In "The Alehouse at the End of the World" by Stevan Allred, the fantastical tale of a fabled alehouse transports readers to a surreal world where the boundaries between reality and myth blur, paralleling the unexpected entwining of brewing and wind power in this investigation. Similarly, "The Windup Girl" by Paolo Bacigalupi offers a dystopian vision of future energy struggles, drawing thematic parallels to the intertwining of brewery growth and wind power generation.
To gain a more holistic understanding of the cultural and societal dimensions surrounding these industries, the researchers also expanded their investigations to popular television shows. "Brew Dogs" and "Brew Masters" provided an insider’s look into the craft brewing world, highlighting the passion and innovation that drive the industry forward. "Mega Builders" and "Rise of the Machines" delved into the engineering marvels and logistical challenges of wind turbine installation, offering a glimpse into the formidable infrastructure underpinning the wind power sector.
The diverse array of literature, spanning academic studies, non-fiction works, fiction novels, and television programs, collectively enriches our understanding of the unexpected kinship between breweries in the United States and wind power in Canada. These sources, while not explicitly addressing the nexus of beer and breezes, offer valuable contextual insights that inform the current investigation and infuse it with a sense of intrigue and discovery.

[[RESULTS]]
The analysis of the data collected from the Brewers Association and the Energy Information Administration yielded a remarkably strong correlation between the number of breweries in the United States and the wind power generated in Canada over the period from 1992 to 2021. The correlation coefficient was calculated to be 0.9606153, indicating a close to perfect positive linear relationship between the two variables. This finding suggests that as the number of breweries in the United States increased, there was a corresponding increase in the wind power generated in Canada, and vice versa. Additionally, the coefficient of determination (r-squared) was determined to be 0.9227817, signifying that approximately 92.28% of the variability in wind power generated in Canada can be explained by the number of breweries in the United States.
The statistical significance of this correlation was further confirmed with a p-value of less than 0.01. This implies that the likelihood of observing such a strong association between the number of breweries in the United States and the wind power generated in Canada due to chance alone is less than 1%, rendering the results highly statistically significant. It is important to note that while correlation does not necessarily imply causation, the strength of the association uncovered in this study warrants further exploration into potential causal mechanisms and underlying factors driving this unexpected relationship.
Figure 1 displays a scatterplot illustrating the robust correlation between the number of breweries in the United States and the wind power generated in Canada. The tightly packed data points form a clear linear pattern, affirming the strength of the association and highlighting the coherence between these seemingly disparate variables. The scatterplot elucidates the coalescence of these industries, presenting a visual representation of the surprising interconnectedness between craft brewing and renewable energy production on a cross-border scale.
The striking correlation uncovered in this study challenges conventional thinking and beckons researchers and industry professionals to consider the unexplored interplay between the craft brewing sector in the United States and the wind power industry in Canada. These findings may serve as a catalyst for further investigations into the potential influence of hops on the harnessing of wind energy and the reciprocal impact of wind power on the brewing landscape. The implications of this unanticipated relationship extend beyond mere statistical associations and call for a reevaluation of traditional economic and environmental paradigms, illuminating the intricate interweaving of seemingly unrelated industries in a manner that would make even the most discerning ale enthusiast pause for thought.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this investigation substantiate the unanticipated yet intriguing link between the number of breweries in the United States and wind power generated in Canada, affirming the robustness of the correlation outlined in the previous sections. The remarkably high correlation coefficient of 0.9606153, coupled with a strikingly low p-value, attests to the statistical significance and reliability of this unexpected association. These results, despite their unconventional nature, align with and build upon the existing literature, which, while not directly anticipating this unique relationship, provided a rich backdrop for understanding the interplay between these seemingly disparate industries.

Revisiting the literature review, the offhand references to fictional works such as "The Alehouse at the End of the World" and "The Windup Girl," despite their seemingly whimsical nature, in fact, offer thematic parallels to the tangible connection unearthed in this study. While initially adding a touch of amusement, these references serve to underscore the surprising fusion of brewing and wind power, hinting at the interconnectedness of cultural imaginings and real-world economic dynamics. Similarly, the inclusion of television programs like "Brew Dogs" and "Rise of the Machines" provided incidental insights into the passion and engineering marvels that drive the brewing and wind power industries, indirectly nourishing our comprehension of the underlying forces driving their unexpected correlation.

Furthermore, the statistical robustness of the correlation coefficient and the coefficient of determination offer compelling evidence in support of the substantial relationship between the number of breweries in the United States and the wind power generated in Canada. The visual representation of this association in the form of the scatterplot not only underscores the coherence between these industries but also serves as a visual pun, so to speak, portraying the convergence of "hops" and "props" in a literal and figurative sense.

The compelling nature of these findings urges a reconsideration of traditional economic and environmental indicators, prompting a reevaluation of the entwined influences of craft brewing and renewable energy production. The implications extend beyond the confines of statistical associations, propelling us to contemplate the potential causal mechanisms and underlying factors driving this unexpected relationship. Whether it is the gusts of fermentation reaching across borders or the swirling winds of sustainable energy shaping brewing landscapes, this study serves as a poignant reminder of the multifaceted interconnectedness pervading our economic and environmental tapestry.

In conclusion, the unexpected entwining of breweries in the United States and wind power in Canada unravels a novel chapter in the interconnected narrative of cross-border industries, amalgamating seemingly unrelated realms into a harmonious symphony of economic and environmental influences. These findings infuse the academic sphere with a refreshing perspective, challenging preconceived notions and opening avenues for further exploration into the captivating interplay of hops and props, as it were.

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 Wind power generated in Canada. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Hops and Props: The Link Between Breweries in the States and Wind Power in Canada

[[ABSTRACT]]
This study delved into the often-overlooked relationship between the number of breweries in the United States and the wind power generated in Canada. Utilizing data from the Brewers Association and the Energy Information Administration, we sought to uncover whether there exists a meaningful correlation between these seemingly disparate phenomena. The findings revealed a striking correlation coefficient of 0.9606153 with a p-value less than 0.01 over the period spanning 1992 to 2021. This surprising association prompts a reevaluation of traditional economic and environmental indicators and offers a refreshing perspective on the interconnectedness of seemingly unrelated industries. The results, while unexpected, furnish valuable insights into the potential cross-border influence of craft brewing on renewable energy production, and vice versa.

[[INTRDUCTION]]
The interplay between seemingly unrelated industries has long fascinated economists, environmentalists, and beverage enthusiasts alike. In this study, we sought to unravel the intriguing link between the proliferation of breweries in the United States and the generation of wind power in Canada. While these two sectors may appear as unrelated as a stout and a squall, our analysis aimed to shed light on any potential connections between them.
In recent years, the craft brewing industry in the United States has experienced a boom, with enthusiasts fervently discussing the merits of hazy IPAs and barrel-aged stouts. Meanwhile, in Canada, wind power has been gaining momentum as a renewable energy source, quietly churning out kilowatts of clean electricity. One might wonder what these two disparate phenomena could possibly have in common, aside from perhaps the occasional gust of wind being put to good use in both brewing and electricity generation.
The prevailing wisdom in economic and environmental circles has traditionally treated these industries as independent and self-contained. However, our investigation has unearthed surprising evidence of a significant statistical association between the number of breweries in the United States and the wind power generated in Canada. This unexpected connection has the potential to revolutionize the way we perceive the influence of beer production on renewable energy sources, and vice versa.
The unearthing of such an unexpected correlation is akin to discovering that two seemingly unrelated puzzle pieces actually fit together snugly, forming a picture that challenges our assumptions. Thus, it is with great anticipation that we present our findings, which may prompt a rethinking of traditional economic and environmental paradigms. Through this analysis, we endeavor to elucidate the clandestine ties between taps and turbines, hops and horsepower, and brews and breezes.

[[RESULTS]]
The analysis of the data collected from the Brewers Association and the Energy Information Administration yielded a remarkably strong correlation between the number of breweries in the United States and the wind power generated in Canada over the period from 1992 to 2021. The correlation coefficient was calculated to be 0.9606153, indicating a close to perfect positive linear relationship between the two variables. This finding suggests that as the number of breweries in the United States increased, there was a corresponding increase in the wind power generated in Canada, and vice versa. Additionally, the coefficient of determination (r-squared) was determined to be 0.9227817, signifying that approximately 92.28% of the variability in wind power generated in Canada can be explained by the number of breweries in the United States.
The statistical significance of this correlation was further confirmed with a p-value of less than 0.01. This implies that the likelihood of observing such a strong association between the number of breweries in the United States and the wind power generated in Canada due to chance alone is less than 1%, rendering the results highly statistically significant. It is important to note that while correlation does not necessarily imply causation, the strength of the association uncovered in this study warrants further exploration into potential causal mechanisms and underlying factors driving this unexpected relationship.
Figure 1 displays a scatterplot illustrating the robust correlation between the number of breweries in the United States and the wind power generated in Canada. The tightly packed data points form a clear linear pattern, affirming the strength of the association and highlighting the coherence between these seemingly disparate variables. The scatterplot elucidates the coalescence of these industries, presenting a visual representation of the surprising interconnectedness between craft brewing and renewable energy production on a cross-border scale.
The striking correlation uncovered in this study challenges conventional thinking and beckons researchers and industry professionals to consider the unexplored interplay between the craft brewing sector in the United States and the wind power industry in Canada. These findings may serve as a catalyst for further investigations into the potential influence of hops on the harnessing of wind energy and the reciprocal impact of wind power on the brewing landscape. The implications of this unanticipated relationship extend beyond mere statistical associations and call for a reevaluation of traditional economic and environmental paradigms, illuminating the intricate interweaving of seemingly unrelated industries in a manner that would make even the most discerning ale enthusiast pause for thought.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the findings of this study have unveiled an intriguing correlation between the number of breweries in the United States and the wind power generated in Canada, illuminating an unexpected interconnectedness between seemingly disparate industries. The remarkably strong correlation coefficient of 0.9606153, coupled with a p-value of less than 0.01, not only challenges traditional economic and environmental paradigms but also prompts a rethinking of the influence of hop-fueled endeavors on renewable energy production, and vice versa.

This surprising association between "brews and breezes" calls for a deeper exploration of the potential drivers behind this unexpected relationship. While we must exercise caution in inferring causation from correlation, the robustness of the statistical association warrants further investigation into the mechanisms underpinning this unanticipated interplay. Perhaps there are hidden forces at work, akin to the yeast quietly fermenting a beer or the gentle currents propelling wind turbines, shaping the landscape of these industries in tandem.

The visual representation of the correlation through the scatterplot elegantly captures the coherence between these industries, depicting a harmonious dance between taps and turbines that challenges our preconceived notions of their autonomy. This unexpected confluence of craft brewing and renewable energy production serves as a tantalizing enigma, beckoning researchers to explore the uncharted territory of the "hops and horsepower" dynamic.

Ultimately, the revelation of such an unexpected correlation demonstrates the need to remain open-minded in the pursuit of knowledge and to appreciate the serendipitous connections that may arise in the most unforeseen places. It is in these moments of unexpected discovery that the true richness of exploration and inquiry lies, akin to stumbling upon a hidden gem amidst a labyrinth of data.

In light of these revelatory findings, it is evident that further research in this area is unnecessary. The depth of the correlation uncovered leaves little doubt about the intertwined fate of craft brewing in the United States and the wind power industry in Canada. The aphorism "where there's ales, there's gales" may just hold more truth than we initially surmised. With that, we raise a glass to the surprising interconnectedness of the world around us and bid adieu to further study in this domain.

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 Hops and Props: The Link Between Breweries in the States and Wind Power in Canada. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Fermented Energy and Environmental Dynamics

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 Hops and Props: The Link Between Breweries in the States and Wind Power in Canada. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Sustainable Suds and Sustainable Energy

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 Hops and Props: The Link Between Breweries in the States and Wind Power in Canada with an abstract of This study delved into the often-overlooked relationship between the number of breweries in the United States and the wind power generated in Canada. Utilizing data from the Brewers Association and the Energy Information Administration, we sought to uncover whether there exists a meaningful correlation between these seemingly disparate phenomena. The findings revealed a striking correlation coefficient of 0.9606153 with a p-value less than 0.01 over the period spanning 1992 to 2021. This surprising association prompts a reevaluation of traditional economic and environmental indicators and offers a refreshing perspective on the interconnectedness of seemingly unrelated industries. The results, while unexpected, furnish valuable insights into the potential cross-border influence of craft brewing on renewable energy production, and vice versa.

ChatGPT:

breweries, wind power, United States, Canada, correlation, association, data analysis, Brewers Association, Energy Information Administration, economic impact, environmental impact, renewable energy production, craft brewing

*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

Wind power generated in Canada
Detailed data title: Total wind power generated in Canada in billion kWh
Source: Energy Information Administration
See what else correlates with Wind power generated in Canada

Correlation r = 0.9606153 (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 = 0.9227817 (Coefficient of determination)
This means 92.3% of the change in the one variable (i.e., Wind power generated in Canada) is predictable based on the change in the other (i.e., The number of Breweries in the United States) over the 30 years from 1992 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.2E-17.^Show 0.0000000000000000415732873896
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 0.96 in 4.2E-15% of random cases. Said differently, if you correlated 24,053,907,275,327,972 random variables^Note You don't actually need 24 quadrillion 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 29 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 29 because we have two variables measured over a period of 30 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.

[ 0.92, 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.

	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	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)	405	490	634	1006	1305	1475	1651	1577	1493	1499	1575	1629	1635	1612	1741	1805	1896	1933	2131	2525	2670	3162	4014	4847	5780	6767	7722	8557	9092	9384
Wind power generated in Canada (Billion kWh)	0.059	0.059	0.059	0.059	0.062	0.062	0.062	0.164	0.264	0.337	0.408	0.826	0.954	1.567	2.473	3.007	3.788	6.641	8.637	10.086	11.198	17.785	22.315	26.697	30.623	31.198	32.854	32.333	35.7414	35.2068

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.
Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.

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([405,490,634,1006,1305,1475,1651,1577,1493,1499,1575,1629,1635,1612,1741,1805,1896,1933,2131,2525,2670,3162,4014,4847,5780,6767,7722,8557,9092,9384,])
array_2 = np.array([0.059,0.059,0.059,0.059,0.062,0.062,0.062,0.164,0.264,0.337,0.408,0.826,0.954,1.567,2.473,3.007,3.788,6.641,8.637,10.086,11.198,17.785,22.315,26.697,30.623,31.198,32.854,32.333,35.7414,35.2068,])
array_1_name = "The number of Breweries in the United States"
array_2_name = "Wind power generated in Canada"

# 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 Wind power generated in Canada
AI-generated correlation image
The spurious research paper: Hops and Props: The Link Between Breweries in the States and Wind Power in Canada

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 1899 · Black Variable ID: 34 · Red Variable ID: 23577


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