Spurious correlation #1,725 · 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 Albemarle's stock price (ALB). 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 Albemarle's stock price (ALB). 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 buttery popcorn at movie theaters. This led to higher ticket sales for blockbuster films. With more people flocking to the movies, there was a surge in demand for comfortable foam seating, which happens to contain flame-retardant chemicals produced by Albemarle. This unexpected connection ultimately contributed to the rise in Albemarle's stock price. It's a slippery slope from butter to booming stocks!

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image of a person sitting at a breakfast table, elegantly dressed just as in 1920s, spreading luscious butter onto a perfectly toasted slice of bread. They are partially silhouetted by the morning light streaming through the window. In the background, a black-and-white newspaper lies open, its style reminiscent of vintage illustrations. Meanwhile, the person is engrossed in a sleek smartphone, checking the fluctuating stock price of Albemarle, creating a captivating juxtaposition of the old and new. 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 Albemarle's stock price. 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: A black-and-white newspaper illustration Photorealism A TIME magazine cover image Cutsy graphics Symbolism
ChatGPT: A black-and-white newspaper illustration

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 Albemarle's stock price together. Keep the description simple.
ChatGPT: A person spreading rich butter on a warm piece of toast while checking the fluctuating stock price of Albemarle on their phone.

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: [ A black-and-white newspaper illustration ] and depicting this scene: A person spreading rich butter on a warm piece of toast while checking the fluctuating stock price of Albemarle on their phone. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a person sitting at a breakfast table, elegantly dressed just as in 1920s, spreading luscious butter onto a perfectly toasted slice of bread. They are partially silhouetted by the morning light streaming through the window. In the background, a black-and-white newspaper lies open, its style reminiscent of vintage illustrations. Meanwhile, the person is engrossed in a sleek smartphone, checking the fluctuating stock price of Albemarle, creating a captivating juxtaposition of the old and new.

*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 Albemarle's stock price (ALB) to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Spreading Margarine: Exploring the Butter-ALB Stock Price Connection

The Journal of Dairy Economics and Finance

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Albemarle's stock price (ALB). 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Spreading Margarine: Exploring the Butter-ALB Stock Price Connection

[[ABSTRACT]]
This paper delves into the intriguing relationship between butter consumption and the stock price of Albemarle Corporation (ALB). Despite initial skepticism, our research uncovers a surprising correlation between these seemingly unrelated entities, shedding light on the whimsical nature of market influences. Leveraging data from the USDA and LSEG Analytics (Refinitiv), our analysis reveals a robust correlation coefficient of 0.8837787 and a statistically significant p-value of less than 0.01 for the period spanning 2002 to 2021. As we spread through the data, our findings suggest that butter consumption may hold unforeseen implications for the fluctuation of ALB stock prices. Amidst the churn of financial analysis, this peculiar connection lends insight into the buttery smooth dynamics of market forces, leaving us to ponder the buttery reality of capital markets.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The correlation between dietary habits and financial markets has long been a topic of fascination, often generating a mixture of skepticism and amusement among researchers. In this study, we delve into the uncharted territory of butter consumption and its potential influence on the stock price of Albemarle Corporation (ALB). While the notion of butter affecting stock prices may initially seem as far-fetched as margarine attempting to pass off as the real deal, our investigation unveils a surprising correlation that may churn the conventional wisdom of market analysis.
As researchers, we often find ourselves wading through the murky waters of data, seeking to uncover hidden relationships that may be as elusive as a vegan in a cheese shop. However, armed with robust statistical methods and a dollop of curiosity, we navigated through the labyrinthine dataset from the USDA and LSEG Analytics (Refinitiv) to examine the buttery trail leading to the fluctuations in ALB stock prices. Our findings, much like a good croissant, are both flaky and intriguing, sparking a reevaluation of the potential impact of butter consumption on financial markets.
The underlying hypothesis guiding this research is as compelling as a sizzling slab of butter melting on a hot pancake – does the consumption of butter possess the unsuspected power to influence the ebb and flow of stock prices? Through rigorous statistical analysis spanning nearly two decades, we sought to add a unique flavor to the field of financial research by exploring this unusual connection, hoping to discover whether butter indeed has the ability to butter up ALB stock prices.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The existing body of literature on the association between dietary factors and stock prices provides valuable insights, albeit with a focus on more conventional food items such as coffee, chocolate, and even avocado toast. Smith et al. (2015) demonstrate that the consumption of artisanal coffee is positively correlated with the performance of tech stocks, while Doe and Jones (2017) present evidence linking the price of chocolate to the volatility of commodity markets. These studies, while informative, overlook the potential impact of a dairy product as ubiquitous as butter on the dynamics of stock prices.

Turning to the realm of non-fiction literature, works such as "Food Politics" by Marion Nestle and "The Omnivore's Dilemma" by Michael Pollan offer comprehensive analyses of the political, economic, and environmental implications of food consumption. However, the intersection of butter consumption with stock price movements, much like a rare cheese pairing, remains a conspicuously unexplored arena in both academic and popular literature.

On the fictional front, the narratives of financial intrigue in Michael Lewis' "Flash Boys" and the culinary escapades in Laura Esquivel's "Like Water for Chocolate" may appear tangentially related to the themes at hand. However, as we churn through the literature, it becomes evident that the direct exploration of butter's influence on stock prices is as scarce as unsalted butter in a French boulangerie.

In a somewhat unconventional approach to literature review, the authors also perused various fictional works and, as an unexpected turn of events, stumbled upon a series of doodles depicting stock price movements and butter sculptures on the back of CVS receipts. While not traditionally recognized as sources of scholarly information, these colorful and seemingly nonsensical artifacts ironically presented a more concrete depiction of the butter-ALB stock price connection than anticipated.

The culmination of our literature review, much like a freshly baked batch of buttery croissants, highlights the uncharted nature of the butter-ALB stock price connection in existing scholarly and fictional works. This underscores the inherent need for our research to not only fill the gap in academic understanding but also to spread light on the whimsical and often unexpected interplay between dietary habits and financial markets.

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 Albemarle's stock price (ALB). 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]]
Spreading Margarine: Exploring the Butter-ALB Stock Price Connection

[[ABSTRACT]]
This paper delves into the intriguing relationship between butter consumption and the stock price of Albemarle Corporation (ALB). Despite initial skepticism, our research uncovers a surprising correlation between these seemingly unrelated entities, shedding light on the whimsical nature of market influences. Leveraging data from the USDA and LSEG Analytics (Refinitiv), our analysis reveals a robust correlation coefficient of 0.8837787 and a statistically significant p-value of less than 0.01 for the period spanning 2002 to 2021. As we spread through the data, our findings suggest that butter consumption may hold unforeseen implications for the fluctuation of ALB stock prices. Amidst the churn of financial analysis, this peculiar connection lends insight into the buttery smooth dynamics of market forces, leaving us to ponder the buttery reality of capital markets.

[[LITERATURE REVIEW]]
The existing body of literature on the association between dietary factors and stock prices provides valuable insights, albeit with a focus on more conventional food items such as coffee, chocolate, and even avocado toast. Smith et al. (2015) demonstrate that the consumption of artisanal coffee is positively correlated with the performance of tech stocks, while Doe and Jones (2017) present evidence linking the price of chocolate to the volatility of commodity markets. These studies, while informative, overlook the potential impact of a dairy product as ubiquitous as butter on the dynamics of stock prices.
Turning to the realm of non-fiction literature, works such as "Food Politics" by Marion Nestle and "The Omnivore's Dilemma" by Michael Pollan offer comprehensive analyses of the political, economic, and environmental implications of food consumption. However, the intersection of butter consumption with stock price movements, much like a rare cheese pairing, remains a conspicuously unexplored arena in both academic and popular literature.
On the fictional front, the narratives of financial intrigue in Michael Lewis' "Flash Boys" and the culinary escapades in Laura Esquivel's "Like Water for Chocolate" may appear tangentially related to the themes at hand. However, as we churn through the literature, it becomes evident that the direct exploration of butter's influence on stock prices is as scarce as unsalted butter in a French boulangerie.
In a somewhat unconventional approach to literature review, the authors also perused various fictional works and, as an unexpected turn of events, stumbled upon a series of doodles depicting stock price movements and butter sculptures on the back of CVS receipts. While not traditionally recognized as sources of scholarly information, these colorful and seemingly nonsensical artifacts ironically presented a more concrete depiction of the butter-ALB stock price connection than anticipated.
The culmination of our literature review, much like a freshly baked batch of buttery croissants, highlights the uncharted nature of the butter-ALB stock price connection in existing scholarly and fictional works. This underscores the inherent need for our research to not only fill the gap in academic understanding but also to spread light on the whimsical and often unexpected interplay between dietary habits and financial markets.

[[RESULTS]]
The analysis of the relationship between butter consumption and the stock price of Albemarle Corporation (ALB) yielded some surprising and butterly delightful results. Our statistical examination revealed a substantial correlation coefficient of 0.8837787, suggesting a strong positive relationship between these seemingly unrelated variables. This finding, much like a perfectly toasted bagel, is both unexpected and comforting in its robustness.
Furthermore, the r-squared value of 0.7810648 indicates that approximately 78.11% of the variability in ALB stock prices can be explained by changes in butter consumption. This level of explanation is akin to finding the perfect blend of peanut butter and jelly – just the right amount of sweetness and tanginess to satisfy the financial appetite.
The statistical significance of our findings is supported by a p-value of less than 0.01, reaffirming the strength of the relationship between butter consumption and ALB stock prices. This result is as rare and delectable as a prized truffle, highlighting the substantial impact of butter consumption on the whims of the market.
Figure 1 illustrates the scatterplot depicting the striking correlation between butter consumption and ALB stock prices. The data points, much like popcorn in a movie theater, follow a clear trend, affirming the convergence of these two variables over time.
In summary, our analysis not only uncovers a tangible connection between butter consumption and ALB stock prices but also invites further exploration into the deliciously complex dynamics of market influences. This research may just be the beginning of a journey into the rich and filling world of culinary finance, where butter truly makes everything better.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study provide compelling evidence to support the curious connection between butter consumption and stock prices, particularly in the case of Albemarle Corporation (ALB). It is curious to note that the unexpected correlation coefficient of 0.8837787 aligns with the unexplored potential of dietary elements to influence market movements, reminiscent of a surprising twist in a well-crafted culinary masterpiece. These findings not only add substance to the existing literature on the intersection of food consumption and financial dynamics but also highlight the need for further exploration into the buttery realm of market influences.

Interestingly, our results align with previous research that has delved into the influence of dietary habits on stock prices. The parallels between the association of artisanal coffee with tech stocks and the correlation we uncovered between butter consumption and ALB stock prices suggest a flavorful common thread in the intricate fabric of market influences. While the link between chocolate prices and commodity market volatility has been explored, our study introduces the creamy richness of the butter-ALB stock price connection, effectively expanding the palette of culinary market influences.

Our unconventional literature review, which playfully intertwined non-fiction and fictional works, inadvertently led us to uncover the unexpected depiction of stock price movements and butter sculptures on the back of CVS receipts. This fortuitous discovery, while initially whimsical, strangely converged with our statistical findings, serving as a peculiar validation of the tangible impact of butter consumption on stock prices. This unexpected alignment is reminiscent of stumbling upon an Easter egg in a scientific inquiry - a delightful surprise that adds layers of richness to the research landscape.

In light of our robust statistical results, it becomes apparent that the butter-ALB stock price connection holds substantial implications for financial analysis. The remarkable level of variability in ALB stock prices explained by changes in butter consumption, akin to the perfect blend of peanut butter and jelly, underscores the nuanced interplay between dietary habits and market forces. Furthermore, the statistical significance of our findings, as rare and delectable as a prized truffle, reinforces the substantial impact of butter consumption on the whims of the market, presenting a flavorful intrigue in the domain of financial analysis.

Overall, our study not only contributes to the burgeoning field of culinary finance, but it also serves as a whimsical reminder of the unpredictability and delight that can be found in the unlikeliest of places, unraveling the rich and complex flavors of market influences. While we refrain from spreading ourselves too thin with far-reaching interpretations, the buttery reality of our findings invites further exploration into the delightfully complex dynamics of culinary market influences – where butter truly makes everything better.

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 Albemarle's stock price (ALB). 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]]
Spreading Margarine: Exploring the Butter-ALB Stock Price Connection

[[ABSTRACT]]
This paper delves into the intriguing relationship between butter consumption and the stock price of Albemarle Corporation (ALB). Despite initial skepticism, our research uncovers a surprising correlation between these seemingly unrelated entities, shedding light on the whimsical nature of market influences. Leveraging data from the USDA and LSEG Analytics (Refinitiv), our analysis reveals a robust correlation coefficient of 0.8837787 and a statistically significant p-value of less than 0.01 for the period spanning 2002 to 2021. As we spread through the data, our findings suggest that butter consumption may hold unforeseen implications for the fluctuation of ALB stock prices. Amidst the churn of financial analysis, this peculiar connection lends insight into the buttery smooth dynamics of market forces, leaving us to ponder the buttery reality of capital markets.

[[INTRDUCTION]]
The correlation between dietary habits and financial markets has long been a topic of fascination, often generating a mixture of skepticism and amusement among researchers. In this study, we delve into the uncharted territory of butter consumption and its potential influence on the stock price of Albemarle Corporation (ALB). While the notion of butter affecting stock prices may initially seem as far-fetched as margarine attempting to pass off as the real deal, our investigation unveils a surprising correlation that may churn the conventional wisdom of market analysis.
As researchers, we often find ourselves wading through the murky waters of data, seeking to uncover hidden relationships that may be as elusive as a vegan in a cheese shop. However, armed with robust statistical methods and a dollop of curiosity, we navigated through the labyrinthine dataset from the USDA and LSEG Analytics (Refinitiv) to examine the buttery trail leading to the fluctuations in ALB stock prices. Our findings, much like a good croissant, are both flaky and intriguing, sparking a reevaluation of the potential impact of butter consumption on financial markets.
The underlying hypothesis guiding this research is as compelling as a sizzling slab of butter melting on a hot pancake – does the consumption of butter possess the unsuspected power to influence the ebb and flow of stock prices? Through rigorous statistical analysis spanning nearly two decades, we sought to add a unique flavor to the field of financial research by exploring this unusual connection, hoping to discover whether butter indeed has the ability to butter up ALB stock prices.

[[RESULTS]]
The analysis of the relationship between butter consumption and the stock price of Albemarle Corporation (ALB) yielded some surprising and butterly delightful results. Our statistical examination revealed a substantial correlation coefficient of 0.8837787, suggesting a strong positive relationship between these seemingly unrelated variables. This finding, much like a perfectly toasted bagel, is both unexpected and comforting in its robustness.
Furthermore, the r-squared value of 0.7810648 indicates that approximately 78.11% of the variability in ALB stock prices can be explained by changes in butter consumption. This level of explanation is akin to finding the perfect blend of peanut butter and jelly – just the right amount of sweetness and tanginess to satisfy the financial appetite.
The statistical significance of our findings is supported by a p-value of less than 0.01, reaffirming the strength of the relationship between butter consumption and ALB stock prices. This result is as rare and delectable as a prized truffle, highlighting the substantial impact of butter consumption on the whims of the market.
Figure 1 illustrates the scatterplot depicting the striking correlation between butter consumption and ALB stock prices. The data points, much like popcorn in a movie theater, follow a clear trend, affirming the convergence of these two variables over time.
In summary, our analysis not only uncovers a tangible connection between butter consumption and ALB stock prices but also invites further exploration into the deliciously complex dynamics of market influences. This research may just be the beginning of a journey into the rich and filling world of culinary finance, where butter truly makes everything better.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has churned out some compelling findings on the surprising connection between butter consumption and the stock price of Albemarle Corporation (ALB). The robust correlation coefficient and statistical significance of our analysis suggest that butter consumption may indeed hold the key to understanding the whimsical fluctuations in ALB stock prices. This revelation is as satisfying as a warm croissant with a generous spread of butter, adding a dash of flavor to the field of financial analysis.

As we wrap up this study, it's evident that the butter-ALB relationship is not simply a flaky hypothesis but rather a substantial finding that deserves to be spread across the financial research landscape. The level of explanation provided by our results is akin to discovering the perfect blend of market variables, creating a delectable symphony of statistical significance.

The scatterplot depicting the correlation between butter consumption and ALB stock prices serves as a visual testament to this intriguing relationship, much like a carefully arranged charcuterie board – a delightful fusion of data points and market dynamics.

In light of these findings, it is safe to say that our research has buttered its way into unearthing a truly unexpected yet substantial link between dietary habits and financial markets. As we savor the unexpected flavors of our results, it becomes clear that further exploration into the buttery world of culinary finance may hold the key to unlocking even more tasty insights into market influences.

With that said, it's evident that no more research is needed in this area. The results have been as clear as the distinction between butter and margarine – and the verdict is in: butter influences ALB stock prices in a real and statistically significant way. It’s time to spread the word and let this endeavor melt into the annals of financial research, leaving a buttery legacy for future studies to toast to.

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 Margarine: Exploring the Butter-ALB Stock Price Connection. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Economics and Finance

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Spreading Margarine: Exploring the Butter-ALB Stock Price Connection. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Marginalized Margarine Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Spreading Margarine: Exploring the Butter-ALB Stock Price Connection with an abstract of This paper delves into the intriguing relationship between butter consumption and the stock price of Albemarle Corporation (ALB). Despite initial skepticism, our research uncovers a surprising correlation between these seemingly unrelated entities, shedding light on the whimsical nature of market influences. Leveraging data from the USDA and LSEG Analytics (Refinitiv), our analysis reveals a robust correlation coefficient of 0.8837787 and a statistically significant p-value of less than 0.01 for the period spanning 2002 to 2021. As we spread through the data, our findings suggest that butter consumption may hold unforeseen implications for the fluctuation of ALB stock prices. Amidst the churn of financial analysis, this peculiar connection lends insight into the buttery smooth dynamics of market forces, leaving us to ponder the buttery reality of capital markets.

ChatGPT:

Butter consumption, ALB stock price, market influences, correlation coefficient, USDA data, LSEG Analytics, stock price fluctuation, butter consumption implications, capital market dynamics.

*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

Albemarle's stock price (ALB)
Detailed data title: Opening price of Albemarle (ALB) 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 Albemarle's stock price (ALB)

Correlation r = 0.8837787 (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 = 0.7810648 (Coefficient of determination)
This means 78.1% of the change in the one variable (i.e., Albemarle's stock price (ALB)) 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 2.4E-7.^Show 0.0000002392569071547196600000
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 0.88 in 2.4E-5% of random cases. Said differently, if you correlated 4,179,608 random variables^Note You don't actually need 4 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.

[ 0.72, 0.95 ] 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
Albemarle's stock price (ALB) (Stock price)	12	14.2	15.05	19.51	19.29	36.5	41.14	22.24	36.91	56.12	52.91	63.69	63.38	60.37	54.97	87.15	128.93	75.8	73.5	152.9

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([12,14.2,15.05,19.51,19.29,36.5,41.14,22.24,36.91,56.12,52.91,63.69,63.38,60.37,54.97,87.15,128.93,75.8,73.5,152.9,])
array_1_name = "Butter consumption"
array_2_name = "Albemarle's stock price (ALB)"

# 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 Albemarle's stock price (ALB)
AI-generated correlation image
The spurious research paper: Spreading Margarine: Exploring the Butter-ALB Stock Price Connection

View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!

Correlation ID: 1725 · Black Variable ID: 557 · Red Variable ID: 1906


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