Spurious correlation #3,733 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Cottage cheese consumption and the second variable is AIG's stock price (AIG). The chart goes from 2002 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 Cottage cheese consumption and the second variable is AIG's stock price (AIG). The chart goes from 2002 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As people turned away from cottage cheese, the dairy industry took a hit. This led to a surplus of milk, which in turn caused a shortage of cartons for milk packaging. With the milk packaging industry in disarray, companies like AIG, which had inexplicably invested in a little-known carton manufacturing conglomerate, saw their stock prices curdle.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image with photorealistic style, depicting a group of actuaries gathered around the office kitchen fridge. The actuaries have disappointed looks on their faces as they discover the Cottage cheese has vanished. In the background, show a stock price monitor displaying AIG's stock price dropping as a result of the actuaries' strict Cottage cheese diet affecting their risk assessment abilities. 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: Cottage cheese consumption and AIG's stock price (AIG). 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: inspired by bauhaus Cute cartoon Pop art A photo-realistic image Photorealism
ChatGPT: Photorealism

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 Cottage cheese consumption and AIG's stock price (AIG), in the following situation: Because Cottage cheese consumption decreased, AIG's stock price decreased - turns out, their actuaries were all on a strict Cottage cheese diet, and when it vanished from the office fridge, so did good risk assessment!. Keep the description simple.
ChatGPT: In the office kitchen, a group of actuaries is gathered around the fridge, with a disappointed look on their faces as they discover that the Cottage cheese has vanished. In the background, a stock price monitor shows AIG's stock price dropping as the actuaries' strict Cottage cheese diet begins to affect their risk assessment abilities.

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: [ Photorealism ] and depicting this scene: In the office kitchen, a group of actuaries is gathered around the fridge, with a disappointed look on their faces as they discover that the Cottage cheese has vanished. In the background, a stock price monitor shows AIG's stock price dropping as the actuaries' strict Cottage cheese diet begins to affect their risk assessment abilities. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image with photorealistic style, depicting a group of actuaries gathered around the office kitchen fridge. The actuaries have disappointed looks on their faces as they discover the Cottage cheese has vanished. In the background, show a stock price monitor displaying AIG's stock price dropping as a result of the actuaries' strict Cottage cheese diet affecting their risk assessment abilities.

*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 a decrease in Cottage cheese consumption caused AIG's stock price (AIG) to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

The Journal of Dairy Economics and Financial Analysis

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 Cottage cheese consumption and AIG's stock price (AIG). 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 some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

[[ABSTRACT]]
The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.

Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The enigmatic dance between food consumption and stock prices continues to captivate the attention of researchers and investors alike. As the old adage goes, "you are what you eat," but could it be that what you eat also influences the stock market? In this paper, we embark on a journey to explore the unexpected and, one might even say, whey-ward relationship between cottage cheese consumption and the stock price of American International Group (AIG).
One might be forgiven for thinking that the study of cottage cheese and stock prices belongs in the realm of whimsical musings rather than rigorous academic investigation. However, as we wade through the data, a curious correlation emerges, much like the whey rising to the top of a tub of cottage cheese. We aim to present our findings with the requisite solemnity, although we cannot resist the temptation to sprinkle in a dash of levity where appropriate.
The connection between the consumption of this curdled dairy delight and the ebb and flow of AIG's stock price raises eyebrows and prompts contemplation. This investigation is bound to generate a quizzical expression or two, and perhaps even elicit a lighthearted chuckle from our esteemed readers. While we exercise caution in claiming a direct causal relationship, the strength of the correlation we unearthed invites further probing into the intersection of gastronomic habits and financial markets.
In peeling back the layers of this unexpected correlation, we invite our readers to approach our findings with an open mind, a discerning palate, and perhaps a dollop of skepticism. As we delve into the intersection of fromage and finance, we trust that our scholarly endeavor will be both illuminating and, dare we say, gratefully received.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith (2015) examines the relationship between food consumption and stock prices, presenting a comprehensive analysis of various food items and their potential impact on market dynamics. Doe and Jones (2018) delve into the behavioral aspects of investment and the influence of dietary habits on decision-making processes. The literature is replete with studies that scrutinize the intricate interplay between nutrition and financial markets, offering a smorgasbord of insights into this unconventional relationship.

Turning to non-fiction works, "The Omnivore's Dilemma" by Michael Pollan provides a thought-provoking exploration of food choices and their ramifications, while "Freakonomics" by Steven D. Levitt and Stephen J. Dubner offers a fresh perspective on the unexpected connections that shape our world. On the fictional front, "The Hunger Games" by Suzanne Collins and "The Grapes of Wrath" by John Steinbeck offer allegorical reflections on food, society, and power dynamics.

In the animated realm, the anthropomorphic adventures in "SpongeBob SquarePants" serve as a whimsical backdrop for contemplating the surreal fusion of maritime cuisine and capitalist undercurrents. Meanwhile, the animated series "Adventure Time" presents a surrealist landscape of culinary delights and financial folly, providing an unconventional lens through which to view the juxtaposition of cottage cheese consumption and stock prices. These cultural touchstones offer playful yet pertinent reflections on the intersection of gastronomy and economic forces.

As we navigate through the scholarly literature and cultural touchstones, we are reminded of the multidimensional nature of this investigation, which combines erudition with a sense of levity. While we remain firmly rooted in empirical analysis, we cannot resist the occasional injection of humor and lightheartedness, much like the unexpected tang of cottage cheese in an otherwise serious salad.

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 Cottage cheese consumption and AIG's stock price (AIG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from USDA and LSEG Analytics (Refinitiv) . You used data from 2002 to 2021

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

[[ABSTRACT]]
The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.

Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

[[INTRODUCTION]]
INTRODUCTION
The enigmatic dance between food consumption and stock prices continues to captivate the attention of researchers and investors alike. As the old adage goes, "you are what you eat," but could it be that what you eat also influences the stock market? In this paper, we embark on a journey to explore the unexpected and, one might even say, whey-ward relationship between cottage cheese consumption and the stock price of American International Group (AIG).
One might be forgiven for thinking that the study of cottage cheese and stock prices belongs in the realm of whimsical musings rather than rigorous academic investigation. However, as we wade through the data, a curious correlation emerges, much like the whey rising to the top of a tub of cottage cheese. We aim to present our findings with the requisite solemnity, although we cannot resist the temptation to sprinkle in a dash of levity where appropriate.
The connection between the consumption of this curdled dairy delight and the ebb and flow of AIG's stock price raises eyebrows and prompts contemplation. This investigation is bound to generate a quizzical expression or two, and perhaps even elicit a lighthearted chuckle from our esteemed readers. While we exercise caution in claiming a direct causal relationship, the strength of the correlation we unearthed invites further probing into the intersection of gastronomic habits and financial markets.
In peeling back the layers of this unexpected correlation, we invite our readers to approach our findings with an open mind, a discerning palate, and perhaps a dollop of skepticism. As we delve into the intersection of fromage and finance, we trust that our scholarly endeavor will be both illuminating and, dare we say, gratefully received.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study was designed to sift through the cornucopia of data available from the USDA and LSEG Analytics (Refinitiv) in order to tease out the potential relationship between cottage cheese consumption and AIG's stock price. Our research team, fueled by copious amounts of caffeine and an unyielding determination to uncover the quirks of the market, set out to tackle this rather unorthodox investigation with an arsenal of statistical tools and an ample dose of dairy-related humor.

To quantify the consumption of cottage cheese, we scoured through a plethora of agricultural and food consumption databases, utilizing an assortment of keywords such as "cottage cheese," "curds and whey," and "cheese curds," among others. By leveraging sophisticated web scraping techniques and data mining algorithms, we cast a wide net across the internet to capture the nuances of cottage cheese consumption patterns from 2002 to 2021. Our endeavor to capture the essence of cottage cheese consumption was akin to navigating a labyrinth of dairy aisles, as we faced the perennial challenge of distinguishing cottage cheese from its dairy compatriots.

Simultaneously, in the realm of financial data, our team embarked on a quest to extract AIG's stock prices with the precision of a skilled dairy farmer extracting the finest curds from a vat of milk. Data on AIG's stock price was meticulously gathered from reputable financial databases, where we diligently sieved through the ever-fluctuating market figures and harnessed the power of statistical software to wrangle the numbers into submission.

Once the datasets were corralled, we performed a series of statistical analyses, including correlation analysis and regression modeling, to scrutinize the potential relationship between cottage cheese consumption and AIG's stock price. Our analytical approach was as thorough as combing through the nooks and crannies of a crumbly block of cheese, leaving no outlier unturned and no autocorrelation unexamined.

In essence, the methodology undertaken to investigate the peculiar liaison between cottage cheese consumption and AIG's stock price combined the rigorous rigor of academic research with the whimsical spirit of a gastronomic adventure, resulting in a tapestry of data analysis that is, dare we say, as rich and flavorful as a well-aged cheddar.

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

Please make up the results section of an academic research paper presenting the findings of the connection between Cottage cheese consumption and AIG's stock price (AIG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from USDA and LSEG Analytics (Refinitiv) .

For the time period 2002 to 2021, you found a correlation 0.8487679, r-squared of 0.7204070, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

[[ABSTRACT]]
The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.

Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The enigmatic dance between food consumption and stock prices continues to captivate the attention of researchers and investors alike. As the old adage goes, "you are what you eat," but could it be that what you eat also influences the stock market? In this paper, we embark on a journey to explore the unexpected and, one might even say, whey-ward relationship between cottage cheese consumption and the stock price of American International Group (AIG).
One might be forgiven for thinking that the study of cottage cheese and stock prices belongs in the realm of whimsical musings rather than rigorous academic investigation. However, as we wade through the data, a curious correlation emerges, much like the whey rising to the top of a tub of cottage cheese. We aim to present our findings with the requisite solemnity, although we cannot resist the temptation to sprinkle in a dash of levity where appropriate.
The connection between the consumption of this curdled dairy delight and the ebb and flow of AIG's stock price raises eyebrows and prompts contemplation. This investigation is bound to generate a quizzical expression or two, and perhaps even elicit a lighthearted chuckle from our esteemed readers. While we exercise caution in claiming a direct causal relationship, the strength of the correlation we unearthed invites further probing into the intersection of gastronomic habits and financial markets.
In peeling back the layers of this unexpected correlation, we invite our readers to approach our findings with an open mind, a discerning palate, and perhaps a dollop of skepticism. As we delve into the intersection of fromage and finance, we trust that our scholarly endeavor will be both illuminating and, dare we say, gratefully received.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

Our analysis revealed a surprisingly robust correlation between cottage cheese consumption and AIG's stock price over the period from 2002 to 2021. The correlation coefficient of 0.8487679 suggests a strong positive relationship between these seemingly disparate variables. This finding may raise a few eyebrows and prompt contemplation on the bizarre and delightful mysteries of market behavior.

Furthermore, the r-squared value of 0.7204070 indicates that approximately 72.04% of the variability in AIG's stock price can be explained by changes in cottage cheese consumption. One could say that this relationship is quite cheesy, but the statistical significance of the p-value (< 0.01) adds a layer of credibility to our findings.

In Fig. 1, a scatterplot visually depicts the remarkable correlation between cottage cheese consumption and AIG's stock price. The plot illustrates the close relationship between these two variables, perhaps inviting observers to humorously speculate on the curds and whey of market movements.

Overall, our results bring to light an unexpected and intriguing association between the consumption of cottage cheese and the performance of a prominent financial stock. While we exercise caution in inferring causality, the strength of this correlation encourages further exploration into the peculiar interplay of culinary preferences and market dynamics. One might say that this finding is quite "gouda" for thought.

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 Cottage cheese consumption and AIG's stock price (AIG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

[[ABSTRACT]]
The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.

Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

[[LITERATURE REVIEW]]
Smith (2015) examines the relationship between food consumption and stock prices, presenting a comprehensive analysis of various food items and their potential impact on market dynamics. Doe and Jones (2018) delve into the behavioral aspects of investment and the influence of dietary habits on decision-making processes. The literature is replete with studies that scrutinize the intricate interplay between nutrition and financial markets, offering a smorgasbord of insights into this unconventional relationship.
Turning to non-fiction works, "The Omnivore's Dilemma" by Michael Pollan provides a thought-provoking exploration of food choices and their ramifications, while "Freakonomics" by Steven D. Levitt and Stephen J. Dubner offers a fresh perspective on the unexpected connections that shape our world. On the fictional front, "The Hunger Games" by Suzanne Collins and "The Grapes of Wrath" by John Steinbeck offer allegorical reflections on food, society, and power dynamics.
In the animated realm, the anthropomorphic adventures in "SpongeBob SquarePants" serve as a whimsical backdrop for contemplating the surreal fusion of maritime cuisine and capitalist undercurrents. Meanwhile, the animated series "Adventure Time" presents a surrealist landscape of culinary delights and financial folly, providing an unconventional lens through which to view the juxtaposition of cottage cheese consumption and stock prices. These cultural touchstones offer playful yet pertinent reflections on the intersection of gastronomy and economic forces.
As we navigate through the scholarly literature and cultural touchstones, we are reminded of the multidimensional nature of this investigation, which combines erudition with a sense of levity. While we remain firmly rooted in empirical analysis, we cannot resist the occasional injection of humor and lightheartedness, much like the unexpected tang of cottage cheese in an otherwise serious salad.

[[RESULTS]]
Our analysis revealed a surprisingly robust correlation between cottage cheese consumption and AIG's stock price over the period from 2002 to 2021. The correlation coefficient of 0.8487679 suggests a strong positive relationship between these seemingly disparate variables. This finding may raise a few eyebrows and prompt contemplation on the bizarre and delightful mysteries of market behavior.
Furthermore, the r-squared value of 0.7204070 indicates that approximately 72.04% of the variability in AIG's stock price can be explained by changes in cottage cheese consumption. One could say that this relationship is quite cheesy, but the statistical significance of the p-value (< 0.01) adds a layer of credibility to our findings.
In Fig. 1, a scatterplot visually depicts the remarkable correlation between cottage cheese consumption and AIG's stock price. The plot illustrates the close relationship between these two variables, perhaps inviting observers to humorously speculate on the curds and whey of market movements.
Overall, our results bring to light an unexpected and intriguing association between the consumption of cottage cheese and the performance of a prominent financial stock. While we exercise caution in inferring causality, the strength of this correlation encourages further exploration into the peculiar interplay of culinary preferences and market dynamics. One might say that this finding is quite "gouda" for thought.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of our study, which unveiled a remarkably robust correlation between cottage cheese consumption and AIG's stock price, align with the existing literature on the curious nexus of gastronomy and market dynamics. Our results corroborate the insights put forth by Smith (2015), who paved the way for examining the impact of food consumption on stock prices. Moreover, the behavioral underpinnings of investment, as expounded by Doe and Jones (2018), find resonance in our exploration of the relationship between dietary habits and market fluctuations.

Delving into the whimsical realm of cultural touchstones, our analysis finds affinity with the playful yet pertinent reflections offered by "SpongeBob SquarePants" and "Adventure Time." These animated works, in their own idiosyncratic ways, provide a surrealist lens through which to contemplate the interplay of cottage cheese consumption and stock prices. The unexpected tang of cottage cheese in an otherwise serious salad, as succinctly highlighted in our literature review, mirrors the uncanny fusion of culinary and financial elements observed in our empirical findings.

The substantial correlation coefficient and the statistically significant p-value that underpin our results not only lend credence to the strength of the association but also invite observers to humorously indulge in speculations on the curds and whey of market movements. The level of statistical significance may be likened to the sharpness of a mature cheddar, adding a layer of depth and complexity to our findings.

Although we must proceed with caution in attributing causality, the findings of this study prompt us to contemplate the multifaceted dimensions of market behavior and dietary trends. One might muse that this correlation is quite "gouda" for thought, inviting a hearty chuckle in the midst of scholarly rigor. As we peel back the layers of this peculiar association, we urge readers to savor our findings with a garnish of skepticism and, perhaps, a dollop of wry amusement.

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 Cottage cheese consumption and AIG's stock price (AIG). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

[[ABSTRACT]]
The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.

Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

[[INTRDUCTION]]
INTRODUCTION
The enigmatic dance between food consumption and stock prices continues to captivate the attention of researchers and investors alike. As the old adage goes, "you are what you eat," but could it be that what you eat also influences the stock market? In this paper, we embark on a journey to explore the unexpected and, one might even say, whey-ward relationship between cottage cheese consumption and the stock price of American International Group (AIG).
One might be forgiven for thinking that the study of cottage cheese and stock prices belongs in the realm of whimsical musings rather than rigorous academic investigation. However, as we wade through the data, a curious correlation emerges, much like the whey rising to the top of a tub of cottage cheese. We aim to present our findings with the requisite solemnity, although we cannot resist the temptation to sprinkle in a dash of levity where appropriate.
The connection between the consumption of this curdled dairy delight and the ebb and flow of AIG's stock price raises eyebrows and prompts contemplation. This investigation is bound to generate a quizzical expression or two, and perhaps even elicit a lighthearted chuckle from our esteemed readers. While we exercise caution in claiming a direct causal relationship, the strength of the correlation we unearthed invites further probing into the intersection of gastronomic habits and financial markets.
In peeling back the layers of this unexpected correlation, we invite our readers to approach our findings with an open mind, a discerning palate, and perhaps a dollop of skepticism. As we delve into the intersection of fromage and finance, we trust that our scholarly endeavor will be both illuminating and, dare we say, gratefully received.

[[RESULTS]]
Our analysis revealed a surprisingly robust correlation between cottage cheese consumption and AIG's stock price over the period from 2002 to 2021. The correlation coefficient of 0.8487679 suggests a strong positive relationship between these seemingly disparate variables. This finding may raise a few eyebrows and prompt contemplation on the bizarre and delightful mysteries of market behavior.
Furthermore, the r-squared value of 0.7204070 indicates that approximately 72.04% of the variability in AIG's stock price can be explained by changes in cottage cheese consumption. One could say that this relationship is quite cheesy, but the statistical significance of the p-value (< 0.01) adds a layer of credibility to our findings.
In Fig. 1, a scatterplot visually depicts the remarkable correlation between cottage cheese consumption and AIG's stock price. The plot illustrates the close relationship between these two variables, perhaps inviting observers to humorously speculate on the curds and whey of market movements.
Overall, our results bring to light an unexpected and intriguing association between the consumption of cottage cheese and the performance of a prominent financial stock. While we exercise caution in inferring causality, the strength of this correlation encourages further exploration into the peculiar interplay of culinary preferences and market dynamics. One might say that this finding is quite "gouda" for thought.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the relationship between cottage cheese consumption and AIG's stock price yields a rather unexpected, yet undeniably robust correlation. The evidence presented in our study suggests that the high positive correlation coefficient of 0.8487679 and the statistically significant p-value of less than 0.01 all point to a connection that is not to be dismissed as mere happenstance.

The implications of our findings cannot be overstated, much like the generous dollop of cottage cheese atop a freshly tossed salad. While we approach these results with the appropriate level of caution, it is difficult to ignore the fact that approximately 72.04% of the variability in AIG's stock price can be explained by changes in cottage cheese consumption. This prompts us to seriously consider the potential impact of dairy delicacies on the intricate dance of market dynamics.

Our scatterplot visually encapsulates the rather cheesy, yet captivating relationship between cottage cheese consumption and AIG's stock price, perhaps leaving onlookers with a delightful mental image of curds and whey shaping market movements. It is indeed a curious phenomenon, one that may elicit a raised eyebrow or a bemused smile from even the most stoic of observers.

As we sit back and digest these findings, we cannot help but marvel at the whimsical nature of market forces, which, it seems, may harbor a hidden fondness for fromage. It is clear that the influence of cottage cheese consumption on AIG's stock price is not to be dismissed lightly. The implications of this study are rich and flavorful, not unlike a well-aged cheddar.

In light of our compelling results, we assert that further research in this domain is neither warranted nor "wheye" appropriate. It appears that our exploration into the peculiar connection between cottage cheese consumption and AIG's stock price has left us with a conclusion that is both satisfying and, dare we say, gratefully conclusive. The curd has been cut, so to speak, and it is time for us to move on to other equally enthralling pursuits, leaving this particular "wheyrd" relationship to linger in the whimsical annals of finance and gastronomy.

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 Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Economics and Financial Analysis

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 Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price. Respond only with the name of a fictional organization.

ChatGPT:

Society for the Advancement of Dairy Economics and Finance

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 Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price with an abstract of The relationship between food consumption and stock prices has intrigued scholars and investors alike. In this study, we delve into the curious connection between the consumption of cottage cheese and the stock price of American International Group (AIG). Utilizing data from the USDA and LSEG Analytics (Refinitiv) from 2002 to 2021, our research team discovered a rather striking correlation coefficient of 0.8487679 and a statistically significant p-value of < 0.01.
Our analysis provides compelling evidence that may provoke a raised eyebrow or two and perhaps even a chuckle. While we tread cautiously in attributing causality, the seemingly robust association prompts us to ponder the idiosyncrasies of market behavior and dietary trends. As we peel back the layers of this peculiar correlation, we invite readers to digest our findings with a grain of salt and perhaps a side of cottage cheese.

ChatGPT:

cottage cheese consumption, AIG stock price, food consumption and stock prices, correlation between food consumption and stock prices, market behavior and dietary trends, correlation coefficient, statistical significance, USDA data, LSEG Analytics, AIG stock price analysis

*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

Cottage cheese consumption
Detailed data title: Per capita consumption of Cottage cheese in the US
Source: USDA
See what else correlates with Cottage cheese consumption

AIG's stock price (AIG)
Detailed data title: Opening price of American International Group (AIG) 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 AIG's stock price (AIG)

Correlation r = 0.8487679 (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 = 0.7204070 (Coefficient of determination)
This means 72% of the change in the one variable (i.e., AIG's stock price (AIG)) is predictable based on the change in the other (i.e., Cottage cheese consumption) over the 20 years from 2002 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.2E-6.^Show 0.0000022394092150041710000000
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 0.85 in 0.00022% of random cases. Said differently, if you correlated 446,546 random variables^Note You don't actually need 446 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.65, 0.94 ] 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
Cottage cheese consumption (Pounds per person)	2.6	2.6	2.7	2.7	2.6	2.6	2.3	2.4	2.3	2.3	2.3	2.1	2.1	2.1	2.2	2.1	2.1	2.1	2	1.9
AIG's stock price (AIG) (Stock price)	1331.25	973.51	1114.26	1107.56	1155.14	1204.07	981.72	26.31	25.58	48.88	23.77	36.29	50.81	56.53	60.66	65.95	60	38.9	51.64	37.65

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

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{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([2.6,2.6,2.7,2.7,2.6,2.6,2.3,2.4,2.3,2.3,2.3,2.1,2.1,2.1,2.2,2.1,2.1,2.1,2,1.9,])
array_2 = np.array([1331.25,973.51,1114.26,1107.56,1155.14,1204.07,981.72,26.31,25.58,48.88,23.77,36.29,50.81,56.53,60.66,65.95,60,38.9,51.64,37.65,])
array_1_name = "Cottage cheese consumption"
array_2_name = "AIG's stock price (AIG)"

# 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 Cottage cheese consumption
Line chart for only AIG's stock price (AIG)
AI-generated correlation image
The spurious research paper: Whey Too Cheesy: The Curious Case of Cottage Cheese Consumption and AIG's Stock Price

View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!

Correlation ID: 3733 · Black Variable ID: 556 · Red Variable ID: 1759


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