Spurious correlation #1,264 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Butter consumption and the second variable is McDonald's stock price (MCD). 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 Butter consumption and the second variable is McDonald's stock price (MCD). The chart goes from 2002 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As butter consumption goes up, so does the demand for delicious, buttery biscuits at McDonald's. This leads to higher customer satisfaction, more repeat business, and ultimately boosts McDonald's stock price. It's like a golden, buttery domino effect!

^{Show image generation prompt} Model: dalle-3
Prompt: Using the style of Vaporwave, I would envision a vibrant and nostalgic scene. In a visually dazzling and retro-futuristic McDonald's restaurant, patrons are depicted enjoying golden, buttery biscuits in a dreamy, pastel-colored atmosphere. The setting exudes a nostalgic charm with hues of electric pinks, purples, and blues, combined with elements reminiscent of 80s and 90s aesthetics. The customers, their faces filled with contentment, glow with a soft neon aura as they relish each delectable bite. Meanwhile, a stylized representation of the McDonald's stock market ticker is visible in the background, pulsating with iridescent neon lights and symbols of financial success. The entire scene is imbued with a sense of whimsical euphoria and retro-futuristic delight, capturing the essence of the buttery, flaky, and joyous experience. 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: Butter consumption and McDonald's stock price (MCD). 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: Magic realism Parallax art Steampunk Vaporwave Cute 2D animation
ChatGPT: Vaporwave

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 Butter consumption and McDonald's stock price (MCD), in the following situation: As butter consumption goes up, so does the demand for delicious, buttery biscuits at McDonald's. This leads to higher customer satisfaction, more repeat business, and ultimately boosts McDonald's stock price. It's like a golden, buttery domino effect!. Keep the description simple.
ChatGPT: In a bustling McDonald's restaurant, a warm, delicious scent of freshly baked biscuits fills the air. Customers happily bite into buttery, flaky biscuits, enjoying each mouthful. As they savor the rich taste of butter, the delighted expressions on their faces reflect satisfaction. Meanwhile, the stock ticker for McDonald's (MCD) cheerfully climbs upward, its green arrow pointing to new heights with each passing moment. The interplay of increasing butter consumption and McDonald's stock price creates a golden, buttery domino effect of success.

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: [ Vaporwave ] and depicting this scene: In a bustling McDonald's restaurant, a warm, delicious scent of freshly baked biscuits fills the air. Customers happily bite into buttery, flaky biscuits, enjoying each mouthful. As they savor the rich taste of butter, the delighted expressions on their faces reflect satisfaction. Meanwhile, the stock ticker for McDonald's (MCD) cheerfully climbs upward, its green arrow pointing to new heights with each passing moment. The interplay of increasing butter consumption and McDonald's stock price creates a golden, buttery domino effect of success. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Using the style of Vaporwave, I would envision a vibrant and nostalgic scene. In a visually dazzling and retro-futuristic McDonald's restaurant, patrons are depicted enjoying golden, buttery biscuits in a dreamy, pastel-colored atmosphere. The setting exudes a nostalgic charm with hues of electric pinks, purples, and blues, combined with elements reminiscent of 80s and 90s aesthetics. The customers, their faces filled with contentment, glow with a soft neon aura as they relish each delectable bite. Meanwhile, a stylized representation of the McDonald's stock market ticker is visible in the background, pulsating with iridescent neon lights and symbols of financial success. The entire scene is imbued with a sense of whimsical euphoria and retro-futuristic delight, capturing the essence of the buttery, flaky, and joyous experience.

*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 humerus 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 Butter consumption caused McDonald's stock price (MCD) to increase.

AI academic paper

(Because p < 0.01)

Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

Journal of Gastronomic Economics

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Butter consumption and McDonald's stock price (MCD). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

[[ABSTRACT]]
In this paper, we delve into the unlikely and perhaps dairy-intense relationship between butter consumption and the stock performance of the fast food giant, McDonald's (MCD). Utilizing data sourced from the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv), we set out to churn the numbers and analyze the fluctuations of butter consumption and MCD stock prices from 2002 to 2021.

Our findings indeed spread some light on this matter—revealing a surprisingly high correlation coefficient of 0.9752748 and statistical significance with p < 0.01. This butterly strong correlation raises some eyebrows—and not just due to the potential cholesterol-inducing effects of butter. It seems that there may be more to this creamy, golden substance than meets the eye and that it could have an udderly unexpected influence on the financial realm.

As we spread through the data, we discovered that butter consumption and MCD stock prices moved in sync more often than not, melting away at any doubts about the potential link between these seemingly unrelated elements. These findings could butter up our understanding of financial markets and the influence of everyday consumer choices on stock performances.

So, while some might just view butter as a mere dairy staple, our research suggests that it might be a key ingredient in cooking up a stock portfolio's success. After all, in the world of finance, as in cooking, sometimes you just need to let things churn for a while and see what delicious outcomes arise. Let's butter believe it!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
For decades, researchers have been spreading themselves thin in an effort to understand the myriad factors that can potentially impact stock prices. From economic indicators to company financials, the quest to unravel the mysteries of the stock market has been as challenging as trying to butter a piece of bread without tearing it. However, in recent years, a rather unexpected entrant has emerged in this financial gastronomy—an entrant that's creamy, delicious, and not traditionally associated with Wall Street: butter.
In this study, we aim to untangle the enigmatic relationship between butter consumption and the stock performance of the ubiquitous fast food powerhouse, McDonald's (MCD). This rather strange pairing may have left some scratching their heads, but as we dig deeper into this churn of events, we aim to deliver some butterly surprising findings.
You might say we're on the slippery slope of financial analysis here, but let's not margarine-alize the potential impact of butter on the stock market just yet. Just as a well-seasoned chef knows that butter is the secret ingredient to many culinary delights, could it be that butter holds a similar secret to understanding stock market movements? The proof, as they say, is in the pudding—or perhaps in this case, the buttered croissant.
While some may find the idea of butter and stock prices as an odd couple hard to swallow, we must not spread ourselves too thin in dismissing the potential influence of this dairy delight. As the saying goes, when life gives you lemons, make lemonade, and when life gives you data on butter consumption and stock prices, make intriguing research inquiries.
So, let's dive into this buttery blend of finance and food science, and see if we can't churn up some enlightening insights. After all, in the world of academic research, sometimes you just have to spread your wings and take the leap, even if it leads you to some rather unexpected places.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.'s 2020 study," the authors find that butter consumption is positively associated with the stock price of McDonald's (MCD), indicating a potential relationship between dairy consumption and fast food stock performance. This surprising finding challenges traditional notions of stock market influences and introduces a new, creamy dimension to financial analysis.

Now, we turn our attention to "Doe and Jones' 2018 research," where the authors uncover a significant correlation between butter sales and the stock price of MCD. This suggests that butter consumption may play a butterly crucial role in shaping the stock performance of the fast food industry giant. It seems that the stock market may be more complex—and perhaps more buttery—than previously thought.

Speaking of buttery complexities, let's not margarine-alize the potential impact of consumer preferences on stock prices. As they say, "you can't have your cake and eat it too," but can you have your butter and stock it too? Let's spread some light on that.

In "Butter: A Rich History," the authors explore the cultural and culinary significance of butter throughout history. As we delve into the richness of this dairy product's past, we can't help but wonder—could butter's historical journey also be intertwined with the historical trends of stock prices, particularly those of fast food chains like McDonald's?

Moreover, in the fictional world, Rowling's "Harry Potter and the Butterbeer Brew" piques our interest. While the Harry Potter series doesn't directly address stock market dynamics, it does remind us of the magical, almost whimsical potential of unexpected pairings—much like butter and stock prices.

On a lighter note, the cartoon "SpongeBob SquarePants" provides an interesting case study in the consumption of a sea creature's favorite food, Krabby Patties, which shares some similarities with the fast food industry. Could SpongeBob's culinary adventures hold clues to the stock performance of real-life fast food chains? We may need more than some tartar sauce to answer that.

As we mull over these unexpected connections in the literary and animated realms, we're reminded that sometimes, the most outlandish combinations can lead to enlightening discoveries. After all, who would've thought that the mellow embrace of butter could blend in so smoothly with the rambunctious world of stock prices? But here we are, spreading the wealth of knowledge one buttery pun at a time.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Butter consumption and McDonald's stock price (MCD). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 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]]
Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

[[ABSTRACT]]
In this paper, we delve into the unlikely and perhaps dairy-intense relationship between butter consumption and the stock performance of the fast food giant, McDonald's (MCD). Utilizing data sourced from the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv), we set out to churn the numbers and analyze the fluctuations of butter consumption and MCD stock prices from 2002 to 2021.

Our findings indeed spread some light on this matter—revealing a surprisingly high correlation coefficient of 0.9752748 and statistical significance with p < 0.01. This butterly strong correlation raises some eyebrows—and not just due to the potential cholesterol-inducing effects of butter. It seems that there may be more to this creamy, golden substance than meets the eye and that it could have an udderly unexpected influence on the financial realm.

As we spread through the data, we discovered that butter consumption and MCD stock prices moved in sync more often than not, melting away at any doubts about the potential link between these seemingly unrelated elements. These findings could butter up our understanding of financial markets and the influence of everyday consumer choices on stock performances.

So, while some might just view butter as a mere dairy staple, our research suggests that it might be a key ingredient in cooking up a stock portfolio's success. After all, in the world of finance, as in cooking, sometimes you just need to let things churn for a while and see what delicious outcomes arise. Let's butter believe it!

[[INTRODUCTION]]
For decades, researchers have been spreading themselves thin in an effort to understand the myriad factors that can potentially impact stock prices. From economic indicators to company financials, the quest to unravel the mysteries of the stock market has been as challenging as trying to butter a piece of bread without tearing it. However, in recent years, a rather unexpected entrant has emerged in this financial gastronomy—an entrant that's creamy, delicious, and not traditionally associated with Wall Street: butter.
In this study, we aim to untangle the enigmatic relationship between butter consumption and the stock performance of the ubiquitous fast food powerhouse, McDonald's (MCD). This rather strange pairing may have left some scratching their heads, but as we dig deeper into this churn of events, we aim to deliver some butterly surprising findings.
You might say we're on the slippery slope of financial analysis here, but let's not margarine-alize the potential impact of butter on the stock market just yet. Just as a well-seasoned chef knows that butter is the secret ingredient to many culinary delights, could it be that butter holds a similar secret to understanding stock market movements? The proof, as they say, is in the pudding—or perhaps in this case, the buttered croissant.
While some may find the idea of butter and stock prices as an odd couple hard to swallow, we must not spread ourselves too thin in dismissing the potential influence of this dairy delight. As the saying goes, when life gives you lemons, make lemonade, and when life gives you data on butter consumption and stock prices, make intriguing research inquiries.
So, let's dive into this buttery blend of finance and food science, and see if we can't churn up some enlightening insights. After all, in the world of academic research, sometimes you just have to spread your wings and take the leap, even if it leads you to some rather unexpected places.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To tackle the creamy conundrum of the potential relationship between butter consumption and McDonald's stock price (MCD), we employed a blend of quantitative analysis and financial wizardry. Our research team scoured the depths of the internet, diving deep into the treasure troves of data made available by the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv). We churned through the data spanning from 2002 to 2021, extracting the buttery essence of consumption patterns and stock prices to whip up our analytical approach.

Our first step involved the meticulous collection of monthly butter consumption data from the USDA, encompassing both retail and wholesale volumes. As the saying goes, we didn't want to spread ourselves too thin, so we made sure to include all the pertinent data to achieve a comprehensive understanding of the butter market. We then indulged in a thorough exploration of MCD's stock price data, obtained from the LSEG Analytics (Refinitiv) database, meticulously tracking the daily fluctuations in the value of everyone's favorite Golden Arches.

With our data in hand, we set forth on a journey that could easily be likened to navigating a labyrinth of ingredients in search of the perfect recipe. Our chosen statistical method was the highly regarded Pearson correlation coefficient, as it allowed us to measure the strength and direction of the linear relationship between butter consumption and MCD stock prices. This method offered a butter-smooth way to discern whether there was a significant connection between these two seemingly unrelated variables.

To ensure a thorough analysis, we also delved into time series modeling, employing the robust Autoregressive Integrated Moving Average (ARIMA) modeling approach. This method allowed us to capture any potential butter-induced trends in MCD stock prices, like discovering a golden pat of insight within a churn of numbers and stats. With the ARIMA model, we could effectively forecast how changes in butter consumption might churn the tides of MCD stock prices, providing a dollop of future insight into this unexpected relationship.

Now, the air in the room is getting quite dairy—sorry, I meant "deary," because if you can't appreciate a good dairy pun, you're probably not reading this far. Anyway, to further solidify our findings, we also employed a battery of robustness checks, including Granger causality tests and impulse response functions, to ensure that our results weren't just a fluke—pun intended. These tests allowed us to examine the potential causal relationship between butter consumption and MCD stock prices, shedding light on whether butter was simply along for the ride or actively shaping the financial fate of the fast food giant.

In summary, our methodology took us on quite the dairy-filled odyssey as we sifted through mountains of data and applied sophisticated analytical techniques. From turning through time series models to causality tests, we certainly had our hands buttered with a plethora of methods. As the saying goes, though, the proof of the pudding is in the eating—so let's move on to the tasty findings that emerged from this udderly fascinating research endeavor.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Butter consumption and McDonald's stock price (MCD). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

[[ABSTRACT]]
In this paper, we delve into the unlikely and perhaps dairy-intense relationship between butter consumption and the stock performance of the fast food giant, McDonald's (MCD). Utilizing data sourced from the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv), we set out to churn the numbers and analyze the fluctuations of butter consumption and MCD stock prices from 2002 to 2021.

Our findings indeed spread some light on this matter—revealing a surprisingly high correlation coefficient of 0.9752748 and statistical significance with p < 0.01. This butterly strong correlation raises some eyebrows—and not just due to the potential cholesterol-inducing effects of butter. It seems that there may be more to this creamy, golden substance than meets the eye and that it could have an udderly unexpected influence on the financial realm.

As we spread through the data, we discovered that butter consumption and MCD stock prices moved in sync more often than not, melting away at any doubts about the potential link between these seemingly unrelated elements. These findings could butter up our understanding of financial markets and the influence of everyday consumer choices on stock performances.

So, while some might just view butter as a mere dairy staple, our research suggests that it might be a key ingredient in cooking up a stock portfolio's success. After all, in the world of finance, as in cooking, sometimes you just need to let things churn for a while and see what delicious outcomes arise. Let's butter believe it!

[[LITERATURE REVIEW]]
In "Smith et al.'s 2020 study," the authors find that butter consumption is positively associated with the stock price of McDonald's (MCD), indicating a potential relationship between dairy consumption and fast food stock performance. This surprising finding challenges traditional notions of stock market influences and introduces a new, creamy dimension to financial analysis.
Now, we turn our attention to "Doe and Jones' 2018 research," where the authors uncover a significant correlation between butter sales and the stock price of MCD. This suggests that butter consumption may play a butterly crucial role in shaping the stock performance of the fast food industry giant. It seems that the stock market may be more complex—and perhaps more buttery—than previously thought.
Speaking of buttery complexities, let's not margarine-alize the potential impact of consumer preferences on stock prices. As they say, "you can't have your cake and eat it too," but can you have your butter and stock it too? Let's spread some light on that.
In "Butter: A Rich History," the authors explore the cultural and culinary significance of butter throughout history. As we delve into the richness of this dairy product's past, we can't help but wonder—could butter's historical journey also be intertwined with the historical trends of stock prices, particularly those of fast food chains like McDonald's?
Moreover, in the fictional world, Rowling's "Harry Potter and the Butterbeer Brew" piques our interest. While the Harry Potter series doesn't directly address stock market dynamics, it does remind us of the magical, almost whimsical potential of unexpected pairings—much like butter and stock prices.
On a lighter note, the cartoon "SpongeBob SquarePants" provides an interesting case study in the consumption of a sea creature's favorite food, Krabby Patties, which shares some similarities with the fast food industry. Could SpongeBob's culinary adventures hold clues to the stock performance of real-life fast food chains? We may need more than some tartar sauce to answer that.
As we mull over these unexpected connections in the literary and animated realms, we're reminded that sometimes, the most outlandish combinations can lead to enlightening discoveries. After all, who would've thought that the mellow embrace of butter could blend in so smoothly with the rambunctious world of stock prices? But here we are, spreading the wealth of knowledge one buttery pun at a time.

[[RESULTS]]
The data analysis revealed a remarkably high correlation coefficient of 0.9752748 between butter consumption and the stock prices of McDonald's (MCD) over the period of 2002 to 2021. This essentially means that as butter consumption increased or decreased, MCD stock prices tended to move in the same direction as smoothly as a pat of butter on a hot skillet.
Fig. 1 shows the scatterplot illustrating this strong relationship between butter consumption and MCD stock prices. It's almost as if the two variables were holding hands and dancing gracefully in perfect harmony, much like a well-coordinated kitchen waltz between butter and a sizzling pan.
Our findings also produced an r-squared value of 0.9511610, indicating that approximately 95.12% of the variation in MCD stock prices can be explained by changes in butter consumption. In simpler terms, it appears that butter consumption may be an unexpectedly dominant force in influencing the stock performance of this fast-food colossus.
This butterly strong relationship might make one ponder whether there's some kind of secret sauce behind this connection, or in this case, a secret pat of butter. One could even say that understanding the stock market is a bit like making a grilled cheese sandwich—sometimes all it takes is a generous slathering of butter to make it golden and irresistible.
The statistical significance with p < 0.01 further solidifies the robustness of this relationship, indicating that the likelihood of this high correlation occurring by mere chance is as slim as a butter knife. It seems that there's more than just a grain of truth in the idea that butter consumption and MCD stock prices go hand in hand, serving as a reminder that in the world of finance, expect the unexpected—just like finding butter in your coffee.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study aimed to spread some light on the surprisingly strong connection between butter consumption and the stock performance of McDonald's (MCD). The results reveal a remarkable correlation coefficient of 0.9752748 and a statistically significant relationship with p < 0.01, validating the findings of prior research and adding a creamy layer of evidence to the established link between butter and stock prices. Indeed, it seems that butter might not just be a toast topper but a potential financial influencer in the fast food industry.

The correlation we unearthed not only melts away any doubts about the association between butter consumption and MCD stock prices but also highlights the dairy-intense nature of this relationship, reminiscent of the richness of a well-made béchamel sauce. It's clear that the influence of butter transcends the culinary realm, seeping into the financial markets with a flavor that's much more than just a passing butter.

As we spread through the data, our findings align with previous studies that have churned out similar results. The analysis of the buttery connection between butter consumption and MCD stock prices affirms the work of Smith et al. (2020) and Doe and Jones (2018), providing a pat of support for the idea that butter indeed plays a significant role in shaping the stock performance of fast food industry giants. It appears that butter's potential impact extends far beyond simply making cookies taste better.

The butterly strong relationship we observed raises intriguing questions about the underlying mechanisms at play, sparking thoughts about whether there's a secret ingredient in this financial recipe. This finding reminds us that sometimes, in the complex world of finance, a seemingly mundane ingredient can hold the key to understanding market dynamics—a bit like uncovering a hidden treasure in a batch of brownies.

Moreover, the high r-squared value of 0.9511610 suggests that approximately 95.12% of the variation in MCD stock prices can be explained by changes in butter consumption. This supports the idea that butter consumption may wield an unexpectedly strong influence over the stock performance of fast food giants, serving as a reminder that sometimes, the most unassuming factors can take center stage in the financial arena, not unlike a surprise cameo appearance in a blockbuster movie.

In closing, our findings serve as a testament to the dairy-intense relationship between butter consumption and MCD stock prices, adding a buttery layer of understanding to the complexities of financial markets. It seems that in the grand buffet of market influencers, butter might just be the unsung hero, quietly churning its way into the portfolios of astute investors. With this newfound knowledge, we encourage investors to approach their financial decisions with an open mind, always ready to embrace the unexpected—even if it means finding butter in the most unlikely places.

I dare say, this research has really helped us spread the wealth of knowledge, hasn't it?

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Butter consumption and McDonald's stock price (MCD). You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

[[ABSTRACT]]
In this paper, we delve into the unlikely and perhaps dairy-intense relationship between butter consumption and the stock performance of the fast food giant, McDonald's (MCD). Utilizing data sourced from the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv), we set out to churn the numbers and analyze the fluctuations of butter consumption and MCD stock prices from 2002 to 2021.

Our findings indeed spread some light on this matter—revealing a surprisingly high correlation coefficient of 0.9752748 and statistical significance with p < 0.01. This butterly strong correlation raises some eyebrows—and not just due to the potential cholesterol-inducing effects of butter. It seems that there may be more to this creamy, golden substance than meets the eye and that it could have an udderly unexpected influence on the financial realm.

As we spread through the data, we discovered that butter consumption and MCD stock prices moved in sync more often than not, melting away at any doubts about the potential link between these seemingly unrelated elements. These findings could butter up our understanding of financial markets and the influence of everyday consumer choices on stock performances.

So, while some might just view butter as a mere dairy staple, our research suggests that it might be a key ingredient in cooking up a stock portfolio's success. After all, in the world of finance, as in cooking, sometimes you just need to let things churn for a while and see what delicious outcomes arise. Let's butter believe it!

[[INTRDUCTION]]
For decades, researchers have been spreading themselves thin in an effort to understand the myriad factors that can potentially impact stock prices. From economic indicators to company financials, the quest to unravel the mysteries of the stock market has been as challenging as trying to butter a piece of bread without tearing it. However, in recent years, a rather unexpected entrant has emerged in this financial gastronomy—an entrant that's creamy, delicious, and not traditionally associated with Wall Street: butter.
In this study, we aim to untangle the enigmatic relationship between butter consumption and the stock performance of the ubiquitous fast food powerhouse, McDonald's (MCD). This rather strange pairing may have left some scratching their heads, but as we dig deeper into this churn of events, we aim to deliver some butterly surprising findings.
You might say we're on the slippery slope of financial analysis here, but let's not margarine-alize the potential impact of butter on the stock market just yet. Just as a well-seasoned chef knows that butter is the secret ingredient to many culinary delights, could it be that butter holds a similar secret to understanding stock market movements? The proof, as they say, is in the pudding—or perhaps in this case, the buttered croissant.
While some may find the idea of butter and stock prices as an odd couple hard to swallow, we must not spread ourselves too thin in dismissing the potential influence of this dairy delight. As the saying goes, when life gives you lemons, make lemonade, and when life gives you data on butter consumption and stock prices, make intriguing research inquiries.
So, let's dive into this buttery blend of finance and food science, and see if we can't churn up some enlightening insights. After all, in the world of academic research, sometimes you just have to spread your wings and take the leap, even if it leads you to some rather unexpected places.

[[RESULTS]]
The data analysis revealed a remarkably high correlation coefficient of 0.9752748 between butter consumption and the stock prices of McDonald's (MCD) over the period of 2002 to 2021. This essentially means that as butter consumption increased or decreased, MCD stock prices tended to move in the same direction as smoothly as a pat of butter on a hot skillet.
Fig. 1 shows the scatterplot illustrating this strong relationship between butter consumption and MCD stock prices. It's almost as if the two variables were holding hands and dancing gracefully in perfect harmony, much like a well-coordinated kitchen waltz between butter and a sizzling pan.
Our findings also produced an r-squared value of 0.9511610, indicating that approximately 95.12% of the variation in MCD stock prices can be explained by changes in butter consumption. In simpler terms, it appears that butter consumption may be an unexpectedly dominant force in influencing the stock performance of this fast-food colossus.
This butterly strong relationship might make one ponder whether there's some kind of secret sauce behind this connection, or in this case, a secret pat of butter. One could even say that understanding the stock market is a bit like making a grilled cheese sandwich—sometimes all it takes is a generous slathering of butter to make it golden and irresistible.
The statistical significance with p < 0.01 further solidifies the robustness of this relationship, indicating that the likelihood of this high correlation occurring by mere chance is as slim as a butter knife. It seems that there's more than just a grain of truth in the idea that butter consumption and MCD stock prices go hand in hand, serving as a reminder that in the world of finance, expect the unexpected—just like finding butter in your coffee.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has churned up some udderly surprising insights into the curious connection between butter consumption and McDonald's (MCD) stock prices. The remarkably high correlation coefficient of 0.9752748 and the r-squared value of 0.9511610 point to a butterly strong relationship between these seemingly unrelated variables. It's almost as if the financial markets are saying, "I can't believe it's not butter!"

Our findings raise some thought-provoking questions about the potential influence of household butter purchases on the stock performances of major corporations. Who knew that a simple stick of butter could hold such sway over the financial world? It seems that in the grand recipe of stock price movements, butter might just be the secret ingredient that brings it all together.

As we wrap up this study, it's clear that there's more to be spread and digested in understanding the quirky connections in the financial universe. However, when it comes to the butter and stock price relationship, it seems we've churned out some pretty convincing evidence. With findings this strong, it's hard not to feel a little gouda about our research accomplishment.

Therefore, based on our butterly compelling results, we confidently maintain that no further research is needed in this area. After all, the proof of the pudding—or perhaps in this case, the buttery croissant—is in the eating. It's time to bid adieu to this line of inquiry and let it Butter Rest in Peace.

No more research is needed in this area, unless of course, we discover that peanut butter affects the stock price of Planters or that almond butter moves the market for almond milk. But let's not get too carried away with spreads just yet!

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 Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Gastronomic Economics

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 Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute of Dairy Economics and Financial Analysis

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 Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price with an abstract of In this paper, we delve into the unlikely and perhaps dairy-intense relationship between butter consumption and the stock performance of the fast food giant, McDonald's (MCD). Utilizing data sourced from the United States Department of Agriculture (USDA) and London Stock Exchange Group (LSEG) Analytics (Refinitiv), we set out to churn the numbers and analyze the fluctuations of butter consumption and MCD stock prices from 2002 to 2021.
Our findings indeed spread some light on this matter—revealing a surprisingly high correlation coefficient of 0.9752748 and statistical significance with p < 0.01. This butterly strong correlation raises some eyebrows—and not just due to the potential cholesterol-inducing effects of butter. It seems that there may be more to this creamy, golden substance than meets the eye and that it could have an udderly unexpected influence on the financial realm.
As we spread through the data, we discovered that butter consumption and MCD stock prices moved in sync more often than not, melting away at any doubts about the potential link between these seemingly unrelated elements. These findings could butter up our understanding of financial markets and the influence of everyday consumer choices on stock performances.
So, while some might just view butter as a mere dairy staple, our research suggests that it might be a key ingredient in cooking up a stock portfolio's success. After all, in the world of finance, as in cooking, sometimes you just need to let things churn for a while and see what delicious outcomes arise. Let's butter believe it!

ChatGPT:

butter consumption, McDonald's stock price, correlation, USDA data, LSEG Analytics, stock performance, financial markets, consumer choices, dairy industry, stock portfolio, statistical significance

*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

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

McDonald's stock price (MCD)
Detailed data title: Opening price of McDonald's (MCD) 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 McDonald's stock price (MCD)

Correlation r = 0.9752748 (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 = 0.9511610 (Coefficient of determination)
This means 95.1% of the change in the one variable (i.e., McDonald's stock price (MCD)) is predictable based on the change in the other (i.e., Butter consumption) over the 20 years from 2002 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.0E-13.^Show 0.0000000000002998745831729298
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 0.98 in 3.0E-11% of random cases. Said differently, if you correlated 3,334,727,436,447 random variables^Note You don't actually need 3 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 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.

[ 0.94, 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
Butter consumption (Pounds per person)	4.4	4.5	4.5	4.5	4.7	4.7	5	5	4.9	5.4	5.5	5.5	5.5	5.6	5.7	5.7	6	6.2	6.3	6.5
McDonald's stock price (MCD) (Stock price)	26.47	16.17	24.95	31.6	34.29	43.65	59.48	62.38	62.63	77.1	101.33	89.4	96.81	94.13	117.25	121.86	173.73	175.41	198	214.49

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([4.4,4.5,4.5,4.5,4.7,4.7,5,5,4.9,5.4,5.5,5.5,5.5,5.6,5.7,5.7,6,6.2,6.3,6.5,])
array_2 = np.array([26.47,16.17,24.95,31.6,34.29,43.65,59.48,62.38,62.63,77.1,101.33,89.4,96.81,94.13,117.25,121.86,173.73,175.41,198,214.49,])
array_1_name = "Butter consumption"
array_2_name = "McDonald's stock price (MCD)"

# 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 Butter consumption
Line chart for only McDonald's stock price (MCD)
AI-generated correlation image
The spurious research paper: Spreading the Wealth: A Butterly Connection Between Butter Consumption and McDonald's Stock Price

View another random correlation

How fun was this correlation?

You're a rater extraordinaire!

Correlation ID: 1264 · Black Variable ID: 557 · Red Variable ID: 1576


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