Spurious correlation #4,007 · 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 Royal Bank of Canada's stock price (RY). 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 Royal Bank of Canada's stock price (RY). 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 increased, so did the demand for baked goods. This led to a rise in profits for bakeries, causing them to invest more money in the stock market, including RY. It's like the saying goes, "Butter makes everything better, even stock prices!" Remember, this is just a funny made-up explanation and not based on real causation.

^{Show image generation prompt} Model: dalle-3
Prompt: [Concept art] Generate an image of a group of people sitting around a sleek, modern table, each holding a slice of perfectly buttered toast. Their eyes are fixed on a large digital screen displaying the Royal Bank of Canada's logo and stock price prominently. Capture the growing excitement in the room as the RY stock price surges, and subtly symbolize the connection with the increasing consumption of buttered toast. The setting should be clean and minimalist, allowing the focal point to be the group's reaction and the digital screen. 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 Royal Bank of Canada's stock price (RY). 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: Celtic art Magic realism Whimsical illustration Pop art Concept art
ChatGPT: Concept art

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 Royal Bank of Canada's stock price (RY), in the following situation: As butter consumption increased, more people discovered the joy of buttering up their financial portfolios, leading to a surge in demand for RY stock and driving up its price.. Keep the description simple.
ChatGPT: A group of people enjoying slices of buttered toast while closely monitoring the stock market, with the Royal Bank of Canada's logo and stock price prominently displayed on a digital screen behind them. The increasing consumption of butter symbolizes the growing interest in "buttering up" the financial portfolios, coinciding with the surge in demand for RY stock and its rising price.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Concept art ] and depicting this scene: A group of people enjoying slices of buttered toast while closely monitoring the stock market, with the Royal Bank of Canada's logo and stock price prominently displayed on a digital screen behind them. The increasing consumption of butter symbolizes the growing interest in "buttering up" the financial portfolios, coinciding with the surge in demand for RY stock and its rising price. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Concept art] Generate an image of a group of people sitting around a sleek, modern table, each holding a slice of perfectly buttered toast. Their eyes are fixed on a large digital screen displaying the Royal Bank of Canada's logo and stock price prominently. Capture the growing excitement in the room as the RY stock price surges, and subtly symbolize the connection with the increasing consumption of buttered toast. The setting should be clean and minimalist, allowing the focal point to be the group's reaction and the digital screen.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Butter consumption caused Royal Bank of Canada's stock price (RY) to increase.

AI academic paper

(Because p < 0.01)

Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price

The Journal of Gastronomic Economics and Financial Alchemy

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 Royal Bank of Canada's stock price (RY). 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 movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price

[[ABSTRACT]]
The interplay between consumer habits and stock market performance continues to captivate both academic researchers and Wall Street enthusiasts. Our study delves into the peculiar and perhaps unsuspected relationship between butter consumption and the stock price of the Royal Bank of Canada (RY). Leveraging comprehensive data from the USDA and LSEG Analytics (Refinitiv) over the period from 2002 to 2021, we have uncovered a remarkable correlation coefficient of 0.9098095 and a statistically significant p-value of less than 0.01.
Our findings suggest that there may be a buttery link between the demand for butter and the movement of RY stock price. While we acknowledge the potential for mere coincidence or confounding variables, the robustness of our results cannot be dismissed lightly. As we butter up to the idea of food trends influencing financial markets, we encourage further investigation into the delectable world of unexpected economic indicators.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
As the saying goes, "you can't have your cake and eat it too," but what about butter? In the world of finance, the confluence of seemingly unrelated variables has long been a source of fascination and bemusement. While avocado toast and cryptocurrency may have stolen the spotlight in recent years, our study boldly ventures into the uncharted territory of butter consumption and its curious connection to the stock price of the Royal Bank of Canada (RY). It seems that the age-old question of "butter or margarine?" might have greater implications than anticipated.
Against the backdrop of modern finance, where algorithms and high-frequency trading reign supreme, the notion of butter holding sway over stock prices may appear utterly preposterous. However, armed with copious amounts of data from the USDA's pats of butter and LSEG Analytics' mountain charts, we embarked on a voyage that would churn up surprising revelations.
In this paper, we present our findings derived from rigorous statistical analysis covering nearly two decades of butter consumption patterns and RY stock price movements. Our exploration has led us to uncover a correlation coefficient of 0.9098095, a figure that may leave some wondering whether a stick of butter could hold the key to predicting stock market trends. While we tread cautiously in our interpretations, we can't help but toast to the delectable prospect of butter becoming more than just a savory spread – potentially a savory predictor of financial performance.
As we delve into this rather unorthodox avenue of research, it's important to acknowledge the skepticism and raised eyebrows that may greet our investigation. Yet, with a wink and a dash of statistical rigor, we aim to demonstrate the relevance of butter - long revered for its culinary prowess - as an unexpected economic indicator. So, let's butter up to the challenge and unravel the enigma of butter's influence on the Royal Bank of Canada's stock price. After all, in the words of Louis Pasteur, "a bit of butter never spoils the broth of research."

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

While the notion of butter consumption affecting stock prices may at first seem like a spread-too-thin hypothesis, our exploration into the existing literature reveals intriguing insights that have spread like, well, butter. In "The Economics of Butter: A Creamy Commodity," Smith investigates the historical trends in butter production and consumption, shedding light on the economic significance of this dairy delicacy. Doe, in "Margarine Wars: An Economic Analysis," discusses the fierce competition between butter and margarine, offering a thoughtful examination of the market dynamics that could potentially impact broader economic indicators.

However, delving deeper into the annals of culinary and financial history, we encounter unconventional perspectives that may cause eyebrows to rise higher than a perfectly baked soufflé. In "The Art of Butter: From Farm to Table," Jones unveils the cultural and economic impact of butter throughout the ages. This work, though focused on the gastronomic realm, inadvertently opens the door to considering butter as a potential economic harbinger, much to the surprise of traditional scholars.

As we move beyond the confines of scholarly work, real-world insights from notable non-fiction literature become ingredients in our thought-provoking stew. "The Big Short: Inside the Doomsday Machine" by Michael Lewis, while not directly related to dairy products or financial institutions, provides a compelling narrative on the unpredictability of markets and the far-reaching implications of seemingly innocuous events. Similarly, "Fooled by Randomness: The Hidden Role of Chance in Life and in the Markets" by Nassim Nicholas Taleb, introduces us to the whims of chance and serendipity in financial matters, adding a sprinkle of humility to our quest for causality.

Now, taking a whimsical turn, we consider how fictional narratives may inadvertently sprinkle our minds with curious notions that, when boiled down, may be more relevant than meets the eye. In J.K. Rowling's "Harry Potter and the Philosopher's Stone," the character of Albus Dumbledore often imparts wisdom that transcends the magical world, reminding us that understanding the seemingly inexplicable may reveal profound truths. Similarly, in Douglas Adams's "The Hitchhiker's Guide to the Galaxy," the absurdities of the universe prompt contemplation of the unexpected connections that underpin reality.

Turning our attention to the silver screen, we find ourselves pondering the tangential associations brought forth by cinema. In "The Wolf of Wall Street," the chaotic and often irrational behavior of stockbrokers raises questions about the tenuous relationship between human behavior and market movements. Likewise, the quirky humor of "The Grand Budapest Hotel" encourages us to consider the whimsical and unpredictable nature of economic systems, just as unpredictable as the whims of a young pastry chef whipping up a surprise dessert.

As we savor the diverse flavors of literature and film, we are reminded that truth often lurks in the unlikeliest of places, waiting to be churned up and savored. With this eclectic mix of sources, we embark on our own unique journey to untangle the enigma of butter's influence on the Royal Bank of Canada's stock price, eager to blend the seemingly disparate worlds of dairy and finance into a creamy, compelling narrative. Let the journey begin!

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 Royal Bank of Canada's stock price (RY). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price

[[ABSTRACT]]
The interplay between consumer habits and stock market performance continues to captivate both academic researchers and Wall Street enthusiasts. Our study delves into the peculiar and perhaps unsuspected relationship between butter consumption and the stock price of the Royal Bank of Canada (RY). Leveraging comprehensive data from the USDA and LSEG Analytics (Refinitiv) over the period from 2002 to 2021, we have uncovered a remarkable correlation coefficient of 0.9098095 and a statistically significant p-value of less than 0.01.
Our findings suggest that there may be a buttery link between the demand for butter and the movement of RY stock price. While we acknowledge the potential for mere coincidence or confounding variables, the robustness of our results cannot be dismissed lightly. As we butter up to the idea of food trends influencing financial markets, we encourage further investigation into the delectable world of unexpected economic indicators.

[[LITERATURE REVIEW]]
While the notion of butter consumption affecting stock prices may at first seem like a spread-too-thin hypothesis, our exploration into the existing literature reveals intriguing insights that have spread like, well, butter. In "The Economics of Butter: A Creamy Commodity," Smith investigates the historical trends in butter production and consumption, shedding light on the economic significance of this dairy delicacy. Doe, in "Margarine Wars: An Economic Analysis," discusses the fierce competition between butter and margarine, offering a thoughtful examination of the market dynamics that could potentially impact broader economic indicators.
However, delving deeper into the annals of culinary and financial history, we encounter unconventional perspectives that may cause eyebrows to rise higher than a perfectly baked soufflé. In "The Art of Butter: From Farm to Table," Jones unveils the cultural and economic impact of butter throughout the ages. This work, though focused on the gastronomic realm, inadvertently opens the door to considering butter as a potential economic harbinger, much to the surprise of traditional scholars.
As we move beyond the confines of scholarly work, real-world insights from notable non-fiction literature become ingredients in our thought-provoking stew. "The Big Short: Inside the Doomsday Machine" by Michael Lewis, while not directly related to dairy products or financial institutions, provides a compelling narrative on the unpredictability of markets and the far-reaching implications of seemingly innocuous events. Similarly, "Fooled by Randomness: The Hidden Role of Chance in Life and in the Markets" by Nassim Nicholas Taleb, introduces us to the whims of chance and serendipity in financial matters, adding a sprinkle of humility to our quest for causality.
Now, taking a whimsical turn, we consider how fictional narratives may inadvertently sprinkle our minds with curious notions that, when boiled down, may be more relevant than meets the eye. In J.K. Rowling's "Harry Potter and the Philosopher's Stone," the character of Albus Dumbledore often imparts wisdom that transcends the magical world, reminding us that understanding the seemingly inexplicable may reveal profound truths. Similarly, in Douglas Adams's "The Hitchhiker's Guide to the Galaxy," the absurdities of the universe prompt contemplation of the unexpected connections that underpin reality.
Turning our attention to the silver screen, we find ourselves pondering the tangential associations brought forth by cinema. In "The Wolf of Wall Street," the chaotic and often irrational behavior of stockbrokers raises questions about the tenuous relationship between human behavior and market movements. Likewise, the quirky humor of "The Grand Budapest Hotel" encourages us to consider the whimsical and unpredictable nature of economic systems, just as unpredictable as the whims of a young pastry chef whipping up a surprise dessert.
As we savor the diverse flavors of literature and film, we are reminded that truth often lurks in the unlikeliest of places, waiting to be churned up and savored. With this eclectic mix of sources, we embark on our own unique journey to untangle the enigma of butter's influence on the Royal Bank of Canada's stock price, eager to blend the seemingly disparate worlds of dairy and finance into a creamy, compelling narrative. Let the journey begin!

[[RESULTS]]
The analysis of the data spanning the years 2002 to 2021 revealed a striking correlation between butter consumption and the stock price of the Royal Bank of Canada (RY). The Pearson correlation coefficient of 0.9098095 indicated a strong positive linear relationship between these seemingly unrelated variables. This coefficient implies that as butter consumption increased, so did the RY stock price - a buttery phenomenon, indeed.
Additionally, the r-squared value of 0.8277534 suggested that approximately 82.77% of the variability in the RY stock price can be explained by changes in butter consumption. It's as if the financial markets were churning and churning, following the ebb and flow of butter preferences across households.
Most notably, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis and suggested that the observed correlation is statistically significant. This means that the likelihood of such a strong correlation occurring by mere chance is less than 1 in 100, prompting us to consider the potential influence of butter on RY stock price with a mixture of incredulity and curiosity.
Figure 1, a scatterplot illustrating the relationship between butter consumption and RY stock price, reinforces our findings. The figure accentuates the positively sloped linear trend, showcasing a consistent pattern where increased butter consumption aligns with higher RY stock prices. It's a visual feast for the eyes, and one that might just leave you craving both butter and a bullish stock market.
In summary, our results provide compelling evidence of a robust connection between butter consumption and the stock price of the Royal Bank of Canada. While we resist the temptation to spread ourselves too thin with grandiose claims, the data has certainly churned up some food for thought. These findings beckon further exploration into the surprising interplay of seemingly unrelated variables in financial markets and may just butter up the appetite for unconventional economic indicators.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The connubial relationship between butter consumption and the stock price of the Royal Bank of Canada (RY) has certainly churned up some intriguing findings. Our results have lent credence to the rise in popularity of butter-based economics, wherein the dairy aisle and the trading floor converge in unexpected harmony. It appears that our data has proven to be quite the butter churning revelation, turning conventional wisdom on its head and scooping up a rich yield of insights.

As we look back at the amusing, yet surprisingly enlightening, literature review, we find that the breadcrumbs of prior research have led us to this delectable discovery. Just as Smith delved into the economics of butter and Doe dissected the margarine wars, we, too, have embarked on our own epic quest to unravel the incongruous bond between a dairy delight and a financial titan. And much like Jones's exploration of the cultural and economic impact of butter, our study has unveiled a correlation that, while initially befuddling, proves to be a buttery delight for the mind.

Our statistical findings, including the delectably high correlation coefficient of 0.9098095, the buttery smooth r-squared value of 0.8277534, and the sumptuously low p-value, have lent considerable weight to the notion that butter consumption is indeed more than just a tangential slice of the economic pie. It seems that the butter-related variables carry significant explanatory power regarding the RY stock price, serving as a reminder that sometimes, the unlikeliest ingredients can spice up the stock market stew in ways we never imagined.

Let us not forget the visual treat of our scatterplot, which vividly illustrates the positively sloped linear trend between butter consumption and RY stock price. It's as clear as day that these seemingly incongruent elements have, against all odds, harmonized to produce a symphony of financial flavor. The results are a testament to the surprising interplay of variables in the market, akin to a culinary masterpiece that leaves one pondering the undiscovered nuances of the financial palate.

In closing, while further research is warranted to fully understand the underlying mechanisms behind this buttery phenomenon, our work has undeniably elevated the discussion of dairy dynamics in financial spheres. We hope, in presenting these findings, to have, in some small measure, buttered up the appetite for bold and imaginative research within the world of unconventional economic indicators.

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 Royal Bank of Canada's stock price (RY). Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price

[[ABSTRACT]]
The interplay between consumer habits and stock market performance continues to captivate both academic researchers and Wall Street enthusiasts. Our study delves into the peculiar and perhaps unsuspected relationship between butter consumption and the stock price of the Royal Bank of Canada (RY). Leveraging comprehensive data from the USDA and LSEG Analytics (Refinitiv) over the period from 2002 to 2021, we have uncovered a remarkable correlation coefficient of 0.9098095 and a statistically significant p-value of less than 0.01.
Our findings suggest that there may be a buttery link between the demand for butter and the movement of RY stock price. While we acknowledge the potential for mere coincidence or confounding variables, the robustness of our results cannot be dismissed lightly. As we butter up to the idea of food trends influencing financial markets, we encourage further investigation into the delectable world of unexpected economic indicators.

[[INTRDUCTION]]
Introduction
As the saying goes, "you can't have your cake and eat it too," but what about butter? In the world of finance, the confluence of seemingly unrelated variables has long been a source of fascination and bemusement. While avocado toast and cryptocurrency may have stolen the spotlight in recent years, our study boldly ventures into the uncharted territory of butter consumption and its curious connection to the stock price of the Royal Bank of Canada (RY). It seems that the age-old question of "butter or margarine?" might have greater implications than anticipated.
Against the backdrop of modern finance, where algorithms and high-frequency trading reign supreme, the notion of butter holding sway over stock prices may appear utterly preposterous. However, armed with copious amounts of data from the USDA's pats of butter and LSEG Analytics' mountain charts, we embarked on a voyage that would churn up surprising revelations.
In this paper, we present our findings derived from rigorous statistical analysis covering nearly two decades of butter consumption patterns and RY stock price movements. Our exploration has led us to uncover a correlation coefficient of 0.9098095, a figure that may leave some wondering whether a stick of butter could hold the key to predicting stock market trends. While we tread cautiously in our interpretations, we can't help but toast to the delectable prospect of butter becoming more than just a savory spread – potentially a savory predictor of financial performance.
As we delve into this rather unorthodox avenue of research, it's important to acknowledge the skepticism and raised eyebrows that may greet our investigation. Yet, with a wink and a dash of statistical rigor, we aim to demonstrate the relevance of butter - long revered for its culinary prowess - as an unexpected economic indicator. So, let's butter up to the challenge and unravel the enigma of butter's influence on the Royal Bank of Canada's stock price. After all, in the words of Louis Pasteur, "a bit of butter never spoils the broth of research."

[[RESULTS]]
The analysis of the data spanning the years 2002 to 2021 revealed a striking correlation between butter consumption and the stock price of the Royal Bank of Canada (RY). The Pearson correlation coefficient of 0.9098095 indicated a strong positive linear relationship between these seemingly unrelated variables. This coefficient implies that as butter consumption increased, so did the RY stock price - a buttery phenomenon, indeed.
Additionally, the r-squared value of 0.8277534 suggested that approximately 82.77% of the variability in the RY stock price can be explained by changes in butter consumption. It's as if the financial markets were churning and churning, following the ebb and flow of butter preferences across households.
Most notably, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis and suggested that the observed correlation is statistically significant. This means that the likelihood of such a strong correlation occurring by mere chance is less than 1 in 100, prompting us to consider the potential influence of butter on RY stock price with a mixture of incredulity and curiosity.
Figure 1, a scatterplot illustrating the relationship between butter consumption and RY stock price, reinforces our findings. The figure accentuates the positively sloped linear trend, showcasing a consistent pattern where increased butter consumption aligns with higher RY stock prices. It's a visual feast for the eyes, and one that might just leave you craving both butter and a bullish stock market.
In summary, our results provide compelling evidence of a robust connection between butter consumption and the stock price of the Royal Bank of Canada. While we resist the temptation to spread ourselves too thin with grandiose claims, the data has certainly churned up some food for thought. These findings beckon further exploration into the surprising interplay of seemingly unrelated variables in financial markets and may just butter up the appetite for unconventional economic indicators.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

Conclusion

In the grand symphony of financial markets, our foray into the world of butter and stock prices has not only churned up intriguing findings but also set the stage for a delectable new avenue of economic inquiry. The robust correlation coefficient and statistically significant p-value have led us to consider the un-likely possibility of butter wielding influence over RY stock prices. While some might dismiss this connection as mere margarine of error, our data suggests otherwise.

As we wrap up this buttery saga, it's clear that the relationship between these two ostensibly incongruous variables warrants further attention. However, let's not spread ourselves too thin - our findings should be taken with a grain of salted butter. Perhaps it's time to contemplate whether the stock market truly does "rise" with the butter, or whether we're merely navigating through a statistical fondue of coincidence and confounding variables.

It seems that in the realm of economics, potential economic indicators can be as surprising as finding a raisin in the oatmeal (or did you mean grape in the cereal?). With this in mind, we posit that no further research is needed in this area. After all, why churn out more study when we've already found the cream of the crop?

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 Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Gastronomic Economics and Financial Alchemy

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 Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Dairy Economics and Financial Interconnections (SDEFI)

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 Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price with an abstract of The interplay between consumer habits and stock market performance continues to captivate both academic researchers and Wall Street enthusiasts. Our study delves into the peculiar and perhaps unsuspected relationship between butter consumption and the stock price of the Royal Bank of Canada (RY). Leveraging comprehensive data from the USDA and LSEG Analytics (Refinitiv) over the period from 2002 to 2021, we have uncovered a remarkable correlation coefficient of 0.9098095 and a statistically significant p-value of less than 0.01.
Our findings suggest that there may be a buttery link between the demand for butter and the movement of RY stock price. While we acknowledge the potential for mere coincidence or confounding variables, the robustness of our results cannot be dismissed lightly. As we butter up to the idea of food trends influencing financial markets, we encourage further investigation into the delectable world of unexpected economic indicators.

ChatGPT:

butter consumption, stock price, Royal Bank of Canada, RY, correlation, consumer habits, USDA data, LSEG Analytics, financial market performance, economic indicators, food trends, stock market relationship

*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

Royal Bank of Canada's stock price (RY)
Detailed data title: Opening price of Royal Bank of Canada (RY) 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 Royal Bank of Canada's stock price (RY)

Correlation r = 0.9098095 (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 = 0.8277534 (Coefficient of determination)
This means 82.8% of the change in the one variable (i.e., Royal Bank of Canada's stock price (RY)) 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 2.7E-8.^Show 0.0000000269316021626753520000
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 0.91 in 2.7E-6% of random cases. Said differently, if you correlated 37,131,100 random variables^Note You don't actually need 37 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 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.

[ 0.78, 0.96 ] 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
Royal Bank of Canada's stock price (RY) (Stock price)	16.17	18.26	24.02	26.72	38.9	47.48	51.12	29.55	54.1	52.71	51.77	61.5	67.1	68.84	52.7	67.92	81.81	67.8	79.34	82.62

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([16.17,18.26,24.02,26.72,38.9,47.48,51.12,29.55,54.1,52.71,51.77,61.5,67.1,68.84,52.7,67.92,81.81,67.8,79.34,82.62,])
array_1_name = "Butter consumption"
array_2_name = "Royal Bank of Canada's stock price (RY)"

# 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 Royal Bank of Canada's stock price (RY)
AI-generated correlation image
The spurious research paper: Better Butter, Bountiful Bank: A Boisterous Bridge between Butter Consumption and Royal Bank of Canada's RY Stock Price

View another random correlation

How fun was this correlation?

Kudos for rating!

Correlation ID: 4007 · Black Variable ID: 557 · Red Variable ID: 1611


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