Spurious correlation #2,788 · 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 Realty Income's stock price (O). The chart goes from 2002 to 2022, 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 Realty Income's stock price (O). The chart goes from 2002 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The breweries' beer runoff created a unique aroma that attracted more people to Realty Income's properties, leading to higher demand and ultimately driving up the stock price.

^{Show image generation prompt} Model: dalle-3
Prompt: Generating prompt for DALL·E-3: [ Cute cartoon ] style image prompt: Create a vibrant and bustling street scene with a row of colorful breweries. Cheerful people excitedly queue up outside the breweries, eagerly anticipating a taste of the latest craft beers. In the background, a digital display shows the stock ticker for Realty Income (O) steadily climbing upwards, symbolizing the positive impact of the bustling foot traffic on the company's stock price. The entire scene exudes warmth, energy, and excitement. 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 Realty Income's stock price (O). 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: Brutalism Brutalism Charcoal Cute cartoon Cutsy graphics
ChatGPT: Cute cartoon

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 Realty Income's stock price (O), in the following situation: Because as more breweries open, more people are likely to indulge in craft beer, leading to increased foot traffic in retail spaces owned by Realty Income. As a result, the higher demand for retail space boosts the company's revenue and shareholder confidence, causing its stock price to rise.. Keep the description simple.
ChatGPT: Picture a bustling street with several vibrant and colorful breweries dotted along it. People happily line up outside these breweries, eagerly waiting to sample the latest craft beers. Meanwhile, the stock ticker for Realty Income (O) steadily climbs upwards on a nearby digital display, symbolizing the positive impact of the increased foot traffic on the company's stock price.

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: [ Cute cartoon ] and depicting this scene: Picture a bustling street with several vibrant and colorful breweries dotted along it. People happily line up outside these breweries, eagerly waiting to sample the latest craft beers. Meanwhile, the stock ticker for Realty Income (O) steadily climbs upwards on a nearby digital display, symbolizing the positive impact of the increased foot traffic on the company's stock price. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generating prompt for DALL·E-3: [ Cute cartoon ] style image prompt: Create a vibrant and bustling street scene with a row of colorful breweries. Cheerful people excitedly queue up outside the breweries, eagerly anticipating a taste of the latest craft beers. In the background, a digital display shows the stock ticker for Realty Income (O) steadily climbing upwards, symbolizing the positive impact of the bustling foot traffic on the company's stock price. The entire scene exudes warmth, energy, and excitement.

*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 Realty Income's stock price (O) to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

The Journal of Fermented Finance

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 Realty Income's stock price (O). Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

[[ABSTRACT]]
This paper examines the intriguing link between the number of breweries in the United States and Realty Income's stock price (O). Our research team delved into this frothy topic using data from the Brewers Association and LSEG Analytics (Refinitiv) over the twenty-year period from 2002 to 2022. We uncovered a surprisingly strong correlation coefficient of 0.9685992 and a statistically significant p-value of less than 0.01, demonstrating a clear relationship between these seemingly disparate industries. Our findings suggest that as the number of breweries in the US increases, Realty Income's stock price also enjoys a sudsy surge. This intriguing connection may shed light on the complex interplay between consumer trends, investment behavior, and the thirst for both craft beer and financial gains.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intertwining of beer and finance may seem like an odd pairing - like mixing a stout with a sauvignon blanc. However, as our research has revealed, there is indeed a compelling relationship between the number of breweries in the United States and Realty Income's stock price (O). This unexpected connection invites us to explore the potential influence of craft beer culture on the world of real estate investment trusts (REITs).
Over the past two decades, the craft beer industry in the United States has experienced a remarkable resurgence. With the number of breweries soaring to unprecedented heights, one might wonder if there is more than just foam and froth behind this bubbly phenomenon. Meanwhile, Realty Income, known for its steady dividend payouts and stability, has garnered the attention of investors seeking reliable income streams. Yet, who would have thought that the fate of these two seemingly disparate domains could be intertwined in such a sudsy fashion?
In this paper, we unveil the findings of our investigation into this peculiar relationship. By analyzing data from the Brewers Association and LSEG Analytics (Refinitiv) from 2002 to 2022, we sought to decipher the baffling correlation between the craft beer boom and the performance of Realty Income's stock. Our exploration has led to the unearthing of a striking correlation coefficient of 0.9685992 and a p-value that would make any statistician raise an eyebrow - less than 0.01! These figures point to a robust and statistically significant association between the burgeoning brewery count and the stock price of Realty Income.
While it may seem like these findings come straight out of left field, they offer a tantalizing glimpse into the curious ways in which consumer preferences and investment landscapes intersect. As we delve into the factors underlying this frothy link, we invite readers to join us in raising a glass to the unexpected correlations that can be found amidst the brew of economic data and market dynamics.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe (2018)," the authors find that the number of breweries in the United States has experienced a substantial increase in recent years. This surge in brewery establishments has led to a vibrant and competitive landscape within the craft beer industry. Similarly, "Jones (2017)" observes a parallel trend in the real estate investment trust market, with particular attention to the performance of Realty Income (O). These serious studies set the stage for our investigation into the potential connection between the two spheres.

Expanding beyond the conventional discourse, "Beeronomics: How Beer Explains the World" by Johan Swinnen and Devin Briski sheds light on the cultural and economic impacts of beer consumption. Meanwhile, "High Financier: The Lives and Time of Siegmund Warburg" by Niall Ferguson delves into the intriguing world of high finance, offering a complementary perspective to our exploration of Realty Income's stock price.

Venturing into the realm of fiction, the classic "The Grapes of Wrath" by John Steinbeck touches on the struggles of the working class, providing an allegorical backdrop for our analysis of economic disparities. Furthermore, the whimsical "Brewster's Millions" by George Barr McCutcheon serves as a lighthearted juxtaposition to the weighty consideration of investment behavior.

As the interplay between consumer preferences and investment landscapes unfolds, cinematic works such as "Brewster's Millions" (1985) and "The Big Short" (2015) offer an entertaining lens through which to contemplate the unpredictability of market dynamics. While the former may offer a lighthearted take on wealth and inheritance, the latter delves into the intricacies of the financial crisis, enriching our understanding of the complexities inherent in investment behavior.

In summary, the literature reviewed encompasses a spectrum of perspectives, from empirical studies to fictional accounts, inviting readers to embark on a journey through the interconnected worlds of breweries and real estate investment.

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 Realty Income's stock price (O). Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Brewers Association and LSEG Analytics (Refinitiv) . You used data from 2002 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

[[ABSTRACT]]
This paper examines the intriguing link between the number of breweries in the United States and Realty Income's stock price (O). Our research team delved into this frothy topic using data from the Brewers Association and LSEG Analytics (Refinitiv) over the twenty-year period from 2002 to 2022. We uncovered a surprisingly strong correlation coefficient of 0.9685992 and a statistically significant p-value of less than 0.01, demonstrating a clear relationship between these seemingly disparate industries. Our findings suggest that as the number of breweries in the US increases, Realty Income's stock price also enjoys a sudsy surge. This intriguing connection may shed light on the complex interplay between consumer trends, investment behavior, and the thirst for both craft beer and financial gains.

[[INTRODUCTION]]
The intertwining of beer and finance may seem like an odd pairing - like mixing a stout with a sauvignon blanc. However, as our research has revealed, there is indeed a compelling relationship between the number of breweries in the United States and Realty Income's stock price (O). This unexpected connection invites us to explore the potential influence of craft beer culture on the world of real estate investment trusts (REITs).
Over the past two decades, the craft beer industry in the United States has experienced a remarkable resurgence. With the number of breweries soaring to unprecedented heights, one might wonder if there is more than just foam and froth behind this bubbly phenomenon. Meanwhile, Realty Income, known for its steady dividend payouts and stability, has garnered the attention of investors seeking reliable income streams. Yet, who would have thought that the fate of these two seemingly disparate domains could be intertwined in such a sudsy fashion?
In this paper, we unveil the findings of our investigation into this peculiar relationship. By analyzing data from the Brewers Association and LSEG Analytics (Refinitiv) from 2002 to 2022, we sought to decipher the baffling correlation between the craft beer boom and the performance of Realty Income's stock. Our exploration has led to the unearthing of a striking correlation coefficient of 0.9685992 and a p-value that would make any statistician raise an eyebrow - less than 0.01! These figures point to a robust and statistically significant association between the burgeoning brewery count and the stock price of Realty Income.
While it may seem like these findings come straight out of left field, they offer a tantalizing glimpse into the curious ways in which consumer preferences and investment landscapes intersect. As we delve into the factors underlying this frothy link, we invite readers to join us in raising a glass to the unexpected correlations that can be found amidst the brew of economic data and market dynamics.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed for this investigation involved a thorough and robust analysis of data obtained from the Brewers Association and LSEG Analytics (Refinitiv) spanning from 2002 to 2022. To commence this convoluted concoction of methods, we first conducted a comprehensive trawl of online databases and resources to gather information about the number of breweries in the United States. This step involved sifting through countless volumes of brewing industry reports, market analyses, and beer aficionado forums to obtain a comprehensive account of brewery counts over the past two decades.

Following this exhaustive data collection phase, we engaged in a rigorous process of data scrubbing and validation, akin to the meticulous inspection of a fine ale for impurities. This step included cross-referencing information from diverse sources to ensure the accuracy and reliability of the brewery count data, thereby minimizing the risk of introducing any intoxicating errors into our analysis.

Once the brewery count data was carefully vetted and deemed fit for consumption, we proceeded to the next stage, which involved the procurement of Realty Income's stock price (O) from LSEG Analytics (Refinitiv). This process demanded precision and consistency akin to the art of crafting a perfectly balanced brew – no room for haphazard measurements or shortcuts. It is worth noting that our team partook in copious sip-testing breaks throughout this labor-intensive endeavor, ensuring that our focus remained unwavering amid the heady haze of financial data.

With both sets of data in hand, we embarked on the process of correlation analysis, employing statistical tools and software to distill the relationship between the number of breweries in the United States and the stock price of Realty Income. Our choice of statistical methods mirrored the precision required in the art of crafting beer, with the aim of uncovering the hidden flavors in this seemingly incongruous blend of industries.

In addition to the statistical analysis, we also conducted a series of sensitivity tests to evaluate the robustness of the observed correlation, akin to subjecting a new craft beer recipe to rigorous taste tests from discerning connoisseurs. This step involved examining the impact of outliers and alternative specifications to ensure that the identified relationship between breweries and Realty Income's stock price did not succumb to the intoxicating effects of statistical anomalies.

Moreover, to enhance the depth of our investigation, we delved into existing literature on consumer trends, investment patterns, and the interplay between industries, akin to reviewing the rich histories and narratives behind diverse beer styles. By incorporating insights from the broader domains of economics, finance, and market behavior, we endeavored to enrich our understanding of the underlying mechanisms driving the observed correlation.

Lastly, to guard against the possibility of spurious relationships clouding our findings, we conducted a battery of diagnostic tests to assess for potential confounding factors and omitted variable biases, akin to conducting stringent quality control checks in the realm of brewery operations.

In sum, this study brewed together a potently palatable blend of data collection, statistical analysis, and literature review to decipher the frothy relationship between breweries and Realty Income's stock price, offering a unique blend of insights into the whimsical ways of market dynamics.

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 Realty Income's stock price (O). Make lots of 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]]
Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

[[ABSTRACT]]
This paper examines the intriguing link between the number of breweries in the United States and Realty Income's stock price (O). Our research team delved into this frothy topic using data from the Brewers Association and LSEG Analytics (Refinitiv) over the twenty-year period from 2002 to 2022. We uncovered a surprisingly strong correlation coefficient of 0.9685992 and a statistically significant p-value of less than 0.01, demonstrating a clear relationship between these seemingly disparate industries. Our findings suggest that as the number of breweries in the US increases, Realty Income's stock price also enjoys a sudsy surge. This intriguing connection may shed light on the complex interplay between consumer trends, investment behavior, and the thirst for both craft beer and financial gains.

[[LITERATURE REVIEW]]
In "Smith and Doe (2018)," the authors find that the number of breweries in the United States has experienced a substantial increase in recent years. This surge in brewery establishments has led to a vibrant and competitive landscape within the craft beer industry. Similarly, "Jones (2017)" observes a parallel trend in the real estate investment trust market, with particular attention to the performance of Realty Income (O). These serious studies set the stage for our investigation into the potential connection between the two spheres.
Expanding beyond the conventional discourse, "Beeronomics: How Beer Explains the World" by Johan Swinnen and Devin Briski sheds light on the cultural and economic impacts of beer consumption. Meanwhile, "High Financier: The Lives and Time of Siegmund Warburg" by Niall Ferguson delves into the intriguing world of high finance, offering a complementary perspective to our exploration of Realty Income's stock price.
Venturing into the realm of fiction, the classic "The Grapes of Wrath" by John Steinbeck touches on the struggles of the working class, providing an allegorical backdrop for our analysis of economic disparities. Furthermore, the whimsical "Brewster's Millions" by George Barr McCutcheon serves as a lighthearted juxtaposition to the weighty consideration of investment behavior.
As the interplay between consumer preferences and investment landscapes unfolds, cinematic works such as "Brewster's Millions" (1985) and "The Big Short" (2015) offer an entertaining lens through which to contemplate the unpredictability of market dynamics. While the former may offer a lighthearted take on wealth and inheritance, the latter delves into the intricacies of the financial crisis, enriching our understanding of the complexities inherent in investment behavior.
In summary, the literature reviewed encompasses a spectrum of perspectives, from empirical studies to fictional accounts, inviting readers to embark on a journey through the interconnected worlds of breweries and real estate investment.

[[RESULTS]]
The analysis of the data collected from the Brewers Association and LSEG Analytics (Refinitiv) for the period from 2002 to 2022 has unveiled a remarkably strong correlation between the number of breweries in the United States and Realty Income's stock price (O). The calculated correlation coefficient of 0.9685992 indicates a highly positive linear relationship between these two variables. This finding suggests that as the craft beer industry bubbled and frothed with an increasing number of breweries, investors in Realty Income experienced a similarly effervescent rise in stock price. It appears that the thirst for craft beer and financial gains are more intertwined than one might initially assume.
The r-squared value of 0.9381843 further supports this significant correlation, indicating that approximately 93.8% of the variability in Realty Income's stock price can be explained by changes in the number of breweries. This statistic underscores the robustness of the relationship and suggests that the surge in craft beer establishments holds substantial explanatory power for movements in Realty Income's stock price.
The p-value of less than 0.01 provides strong evidence against the null hypothesis of no relationship between brewery count and Realty Income's stock price. This result compels us to reject the notion that the number of breweries and Realty Income's stock price are independent of each other. Indeed, the probability of observing such a strong correlation coefficient by chance is remarkably low, prompting us to conclude that there is a genuine association between these two variables.
Furthermore, the scatterplot (Fig. 1) visually depicts the striking correlation between the number of breweries and Realty Income's stock price. The data points form a tightly clustered pattern, emphasizing the close connection between these seemingly disparate entities. The scatterplot serves as a cogent visual representation of the strong positive relationship observed in the statistical analysis.
In summary, our investigation into the relationship between the number of breweries in the United States and Realty Income's stock price has revealed a compelling and statistically significant link. The findings of this study provide intriguing insights into the intricate interplay between consumer trends, investment dynamics, and the unanticipated alliances that can emerge amidst the froth and foam of economic data.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our investigation yield a compelling discourse on the intertwining of the craft beer industry and real estate investment. Our findings support the prior research by Smith and Doe (2018) and Jones (2017), who highlighted the surging number of breweries and observed parallel trends in the real estate investment trust market, particularly with respect to Realty Income (O). These serious inquiries into the two seemingly incongruous spheres have been buoyed by our empirical analysis, affirming the existence of a remarkably strong correlation between brewery proliferation and Realty Income's stock price. It appears that the surge in craft beer establishments exerts a tangible influence on the financial realm, akin to the effervescence of a freshly poured pint.

The literary works harkened back to in our investigation, such as "Beeronomics: How Beer Explains the World" and "Brewster's Millions," provide insightful context for the interplay between consumer preferences and investment landscapes. They prepare readers for the solemn consideration of the economic impacts of brewery surges and real estate dynamics and establish a whimsical juxtaposition to the weightier considerations of investment behavior. These seemingly disparate sources of knowledge converge to advocate for the existence of a frothy relationship between breweries and Realty Income's stock price.

The strong correlation coefficient, r-squared value, and p-value derived from our statistical analysis lend quantitative support to the anecdotal and empirical evidence presented in the prior literature. The statistically significant findings suggest that the thirst for craft beer and financial gains indeed coalesce in a manner that is not wholly dissimilar to the mingling of citrusy hops and malty sweetness in a well-crafted brew. Our results underscore the robustness of this quenchable relationship and imply that approximately 93.8% of the variability in Realty Income's stock price can be attributed to changes in the number of breweries, compelling us to reject the notion of independence between these two entities.

The scatterplot visually encapsulates the robust correlation, mirroring the tightly clustered pattern observed in the statistical analysis and emphasizing the intimate connection between brewery count and Realty Income's stock price. This cogent visual representation serves to reiterate the striking alignment that was uncovered amidst the froth and foam of economic data. The findings of this study firmly underscore the unique and compelling relationship between what may have initially seemed like an unlikely pair - breweries and real estate investment - and invite further exploration into the complex dynamics at play.

In conclusion, our investigation has illuminated a captivating and statistically significant connection between the number of breweries in the United States and Realty Income's stock price. The findings offer tantalizing insights into the nuanced interplay between consumer trends, investment dynamics, and the unexpected alliances that can emerge amidst the ebullient complexity of economic phenomena. It appears that in the world of investments, as in the world of craft beer, opportunity and potential for growth bubble and froth in unexpected places.

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 Realty Income's stock price (O). Make lots of 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]]
Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

[[ABSTRACT]]
This paper examines the intriguing link between the number of breweries in the United States and Realty Income's stock price (O). Our research team delved into this frothy topic using data from the Brewers Association and LSEG Analytics (Refinitiv) over the twenty-year period from 2002 to 2022. We uncovered a surprisingly strong correlation coefficient of 0.9685992 and a statistically significant p-value of less than 0.01, demonstrating a clear relationship between these seemingly disparate industries. Our findings suggest that as the number of breweries in the US increases, Realty Income's stock price also enjoys a sudsy surge. This intriguing connection may shed light on the complex interplay between consumer trends, investment behavior, and the thirst for both craft beer and financial gains.

[[INTRDUCTION]]
The intertwining of beer and finance may seem like an odd pairing - like mixing a stout with a sauvignon blanc. However, as our research has revealed, there is indeed a compelling relationship between the number of breweries in the United States and Realty Income's stock price (O). This unexpected connection invites us to explore the potential influence of craft beer culture on the world of real estate investment trusts (REITs).
Over the past two decades, the craft beer industry in the United States has experienced a remarkable resurgence. With the number of breweries soaring to unprecedented heights, one might wonder if there is more than just foam and froth behind this bubbly phenomenon. Meanwhile, Realty Income, known for its steady dividend payouts and stability, has garnered the attention of investors seeking reliable income streams. Yet, who would have thought that the fate of these two seemingly disparate domains could be intertwined in such a sudsy fashion?
In this paper, we unveil the findings of our investigation into this peculiar relationship. By analyzing data from the Brewers Association and LSEG Analytics (Refinitiv) from 2002 to 2022, we sought to decipher the baffling correlation between the craft beer boom and the performance of Realty Income's stock. Our exploration has led to the unearthing of a striking correlation coefficient of 0.9685992 and a p-value that would make any statistician raise an eyebrow - less than 0.01! These figures point to a robust and statistically significant association between the burgeoning brewery count and the stock price of Realty Income.
While it may seem like these findings come straight out of left field, they offer a tantalizing glimpse into the curious ways in which consumer preferences and investment landscapes intersect. As we delve into the factors underlying this frothy link, we invite readers to join us in raising a glass to the unexpected correlations that can be found amidst the brew of economic data and market dynamics.

[[RESULTS]]
The analysis of the data collected from the Brewers Association and LSEG Analytics (Refinitiv) for the period from 2002 to 2022 has unveiled a remarkably strong correlation between the number of breweries in the United States and Realty Income's stock price (O). The calculated correlation coefficient of 0.9685992 indicates a highly positive linear relationship between these two variables. This finding suggests that as the craft beer industry bubbled and frothed with an increasing number of breweries, investors in Realty Income experienced a similarly effervescent rise in stock price. It appears that the thirst for craft beer and financial gains are more intertwined than one might initially assume.
The r-squared value of 0.9381843 further supports this significant correlation, indicating that approximately 93.8% of the variability in Realty Income's stock price can be explained by changes in the number of breweries. This statistic underscores the robustness of the relationship and suggests that the surge in craft beer establishments holds substantial explanatory power for movements in Realty Income's stock price.
The p-value of less than 0.01 provides strong evidence against the null hypothesis of no relationship between brewery count and Realty Income's stock price. This result compels us to reject the notion that the number of breweries and Realty Income's stock price are independent of each other. Indeed, the probability of observing such a strong correlation coefficient by chance is remarkably low, prompting us to conclude that there is a genuine association between these two variables.
Furthermore, the scatterplot (Fig. 1) visually depicts the striking correlation between the number of breweries and Realty Income's stock price. The data points form a tightly clustered pattern, emphasizing the close connection between these seemingly disparate entities. The scatterplot serves as a cogent visual representation of the strong positive relationship observed in the statistical analysis.
In summary, our investigation into the relationship between the number of breweries in the United States and Realty Income's stock price has revealed a compelling and statistically significant link. The findings of this study provide intriguing insights into the intricate interplay between consumer trends, investment dynamics, and the unanticipated alliances that can emerge amidst the froth and foam of economic data.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has shed light on a captivating correlation between the proliferation of breweries in the United States and Realty Income's stock price (O). The robust correlation coefficient of 0.9685992 and a p-value of less than 0.01 underscore the unexpectedly strong connection between these seemingly incongruous domains. It appears that as the craft beer industry has bubbled, fizzed, and fermented with an increasing number of breweries, investors in Realty Income have experienced a similarly effervescent rise in stock price. Who would have thought that the world of REITs could be so intertwined with the world of IPAs and stouts?

The r-squared value of 0.9381843 further bolsters this finding, suggesting that approximately 93.8% of the variability in Realty Income's stock price can be explained by changes in the number of breweries. It seems that the thirst for craft beer and financial gains are more interconnected than a pair of beer mugs in a traditional German beer garden.

The scatterplot (Fig. 1) visually depicts this striking correlation, resembling the foam atop a freshly poured pint of beer. The tightly clustered pattern of data points serves as a compelling visual representation of the close relationship between brewery count and Realty Income's stock price. It appears that the intricate interplay between consumer trends, investment dynamics, and the unanticipated alliances that can emerge amidst the froth and foam of economic data has, indeed, rendered the connection between breweries and real estate investment trusts anything but stale.

Therefore, we dare to assert that no further research is needed in this area. This investigation stands as a testament to the unexpected connections that can emerge amidst the bubbles of economic data and market dynamics, leaving us with a newfound appreciation for the whimsical interplay between hops and stocks.

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 Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Fermented Finance

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 Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Sudsy Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income with an abstract of This paper examines the intriguing link between the number of breweries in the United States and Realty Income's stock price (O). Our research team delved into this frothy topic using data from the Brewers Association and LSEG Analytics (Refinitiv) over the twenty-year period from 2002 to 2022. We uncovered a surprisingly strong correlation coefficient of 0.9685992 and a statistically significant p-value of less than 0.01, demonstrating a clear relationship between these seemingly disparate industries. Our findings suggest that as the number of breweries in the US increases, Realty Income's stock price also enjoys a sudsy surge. This intriguing connection may shed light on the complex interplay between consumer trends, investment behavior, and the thirst for both craft beer and financial gains.

ChatGPT:

breweries, Realty Income, stock price, correlation, Brewers Association, LSEG Analytics, Refinitiv, consumer trends, investment behavior, craft beer, financial gains

*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

Realty Income's stock price (O)
Detailed data title: Opening price of Realty Income (O) on the first trading day of the year
Source: LSEG Analytics (Refinitiv)
Additional Info: ^{See full details} Via Microsoft Excel Stockhistory function

See what else correlates with Realty Income's stock price (O)

Correlation r = 0.9685992 (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 = 0.9381843 (Coefficient of determination)
This means 93.8% of the change in the one variable (i.e., Realty Income's stock price (O)) is predictable based on the change in the other (i.e., The number of Breweries in the United States) over the 21 years from 2002 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.09E-13.^Show 0.0000000000006092430454550529
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 0.97 in 6.09E-11% of random cases. Said differently, if you correlated 1,641,381,066,981 random variables^Note You don't actually need 1 trillion 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 20 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 20 because we have two variables measured over a period of 21 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, 0.99 ] 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.

	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
The number of Breweries in the United States (Number of breweries)	1575	1629	1635	1612	1741	1805	1896	1933	2131	2525	2670	3162	4014	4847	5780	6767	7722	8557	9092	9384	9709
Realty Income's stock price (O) (Stock price)	14.75	17.5	20.06	25.26	21.86	27.66	26.68	23.26	26.26	34.41	35.46	40.85	37.38	47.98	51.14	57.74	57.02	62.61	73.85	62.18	71.73

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([1575,1629,1635,1612,1741,1805,1896,1933,2131,2525,2670,3162,4014,4847,5780,6767,7722,8557,9092,9384,9709,])
array_2 = np.array([14.75,17.5,20.06,25.26,21.86,27.66,26.68,23.26,26.26,34.41,35.46,40.85,37.38,47.98,51.14,57.74,57.02,62.61,73.85,62.18,71.73,])
array_1_name = "The number of Breweries in the United States"
array_2_name = "Realty Income's stock price (O)"

# 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 Realty Income's stock price (O)
AI-generated correlation image
The spurious research paper: Hoppy Investments: A Bitter Relationship Between Breweries and Realty Income

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 2788 · Black Variable ID: 34 · Red Variable ID: 1784


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