Spurious correlation #1,020 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Google searches for 'why do i have green poop' and the second variable is US bank failures. The chart goes from 2004 to 2023, 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 Google searches for 'why do i have green poop' and the second variable is US bank failures. The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The increased consumption of kale and spinach, popular green superfoods, led to higher levels of chlorophyll in people's digestive systems. As a result, more money was inadvertently being "greened," causing banks to fail from an unexpected influx of eco-friendly currency. This led to a financial crisis of salad proportions, leaving bankers and customers alike feeling kale-pressed for cash.

^{Show image generation prompt} Model: dalle-3
Prompt: An image generation prompt to create an interesting visual of this scene in the style of sci-fi fantasy could be: "Generate an image of a bustling futuristic bank, with a long line of people waiting outside. Inside the bank, the tellers are handling a surge of clients, many of whom are holding futuristic jars and containers filled with glowing green orbs and crystals, as they inquire about opening a 'Green Poop Savings Account.' The tellers' expressions grow increasingly perplexed and flustered as the unusual requests continue to pour in. Meanwhile, in the background, a holographic computer monitor displays a rapid increase in virtual searches for 'why do I have green poop,' highlighting the unexpected connection between the surge in online queries and the chaos in the bank." 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: An increase in Google searches for "why do I have green poop" is causing US bank failures to increase due to the unexpected popularity of the "Green Poop Savings Account", a new banking trend where clients deposit money based on the color of their latest bowel movement. As interest in green poop rises, so do the unexpected financial consequences for the banks involved.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Parallax art Concept art Sci-fi fantacy An image that looks like it is a scene from a Pixar movie Whimsical illustration
ChatGPT: Sci-fi fantasy

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. An increase in Google searches for "why do I have green poop" is causing US bank failures to increase due to the unexpected popularity of the "Green Poop Savings Account", a new banking trend where clients deposit money based on the color of their latest bowel movement. As interest in green poop rises, so do the unexpected financial consequences for the banks involved.
ChatGPT: In the scene, a bustling bank is depicted with a line of people forming outside the entrance. Inside, the bank tellers are handling an influx of clients, many of whom are holding jars and containers filled with green-colored items, as they eagerly inquire about opening a "Green Poop Savings Account." The tellers are looking increasingly perplexed and flustered as the unusual requests continue to pour in. Meanwhile, in the background, a computer monitor displays a rapid increase in Google searches for "why do I have green poop," highlighting the unexpected connection between the surge in online queries and the banking mayhem.

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: [ Sci-fi fantasy ] and depicting this scene: In the scene, a bustling bank is depicted with a line of people forming outside the entrance. Inside, the bank tellers are handling an influx of clients, many of whom are holding jars and containers filled with green-colored items, as they eagerly inquire about opening a "Green Poop Savings Account." The tellers are looking increasingly perplexed and flustered as the unusual requests continue to pour in. Meanwhile, in the background, a computer monitor displays a rapid increase in Google searches for "why do I have green poop," highlighting the unexpected connection between the surge in online queries and the banking mayhem. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image generation prompt to create an interesting visual of this scene in the style of sci-fi fantasy could be: "Generate an image of a bustling futuristic bank, with a long line of people waiting outside. Inside the bank, the tellers are handling a surge of clients, many of whom are holding futuristic jars and containers filled with glowing green orbs and crystals, as they inquire about opening a 'Green Poop Savings Account.' The tellers' expressions grow increasingly perplexed and flustered as the unusual requests continue to pour in. Meanwhile, in the background, a holographic computer monitor displays a rapid increase in virtual searches for 'why do I have green poop,' highlighting the unexpected connection between the surge in online queries and the chaos in the bank."

*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 why do i have green poop (Google searches for 'why do i have green poop') caused US bank failures to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures

Journal of Unconventional Correlations

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 the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Google searches for 'why do i have green poop' and US bank failures. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Google Trends and FDIC . You used data from 2004 to 2023

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures

[[ABSTRACT]]
The present study delves into an unexpected and perhaps gut-wrenching connection between the frequency of Google searches for 'why do i have green poop' and the incidence of US bank failures. Leveraging data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our research team scrutinized a time span encompassing eighteen years, from 2004 to 2023. Our analysis revealed a striking correlation coefficient of 0.8689026 and p < 0.01, suggesting a significant relationship between these seemingly disparate phenomena. We proffer possible explanations for this eyebrow-raising finding and explore its implications for both the financial and gastrointestinal domains. Our multidisciplinary approach sheds light on the unexpected interplay between economic indicators and toilet troubles, urging further investigation into this feculent frontier.

[[INTRODUCTION]]
INTRODUCTION
Money, power, and...green poop? While the link between financial stability and gastrointestinal distress may seem outlandish at first glance, the present study thrusts this unlikely association into the limelight. In a twist worthy of a stomach-churning mystery novel, our research uncovers a peculiar correlation between Google searches for 'why do i have green poop' and US bank failures. While this duo may not seem like the most obvious pair, our findings reveal a statistical relationship that likely left both economists and gastroenterologists scratching their heads.
As researchers, we are often urged to explore uncharted territory, but this investigation took us to an unexpected and, quite frankly, odorous crossroads. This feculent frontier of inquiry required us to venture beyond the conventional realms of financial modeling and, well, delve deep into the underbelly of human health and behavior. Armed with data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our team endeavored to unravel the enigma of why individuals were frantically searching for the color of their excrement and what it could possibly have to do with the stability of the US banking system.
Now, before you wrinkle your nose in disbelief, let's set the stage for this, shall we say, unconventional exploration. We must acknowledge that in the vast landscape of statistical analyses, there are often unexpected correlations and spurious relationships that, much like an unsolved riddle, beg for further scrutiny. Our investigation into the peculiar pairing of green stool queries and bank failures served as a reminder that in the realm of data analytics, one must always be prepared to confront the inexplicable and the downright bizarre.
(Feel free to add any more jokes or puns you like!)

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Given the unusual nature of our research question, our methodology was tailored to encompass both the financial and gastrointestinal realms, as we sought to uncover any potential links between green poop inquiries and bank failures. Our approach involved a blend of statistical analysis, digital trend tracking, and, of course, a healthy dose of humor to navigate these aromatic waters.

Data Collection and Processing
To commence our study, we gathered Google search data for the term 'why do i have green poop' from Google Trends, which provided us with a fecund field of search popularity scores. Concurrently, we tapped into the repository of financial turbulence by extracting information on US bank failures from the Federal Deposit Insurance Corporation (FDIC). Essentially, we cast a wide net to capture both the ebb and flow of financial fortunes and digestive discomfort.

Correlation Analysis
With a dataset in hand that spanned nearly two decades, from 2004 to 2023, we set about wrangling the numbers and subjecting them to rigorous statistical scrutiny. Through the magic of correlation analysis, we teased out the relationship between the frequency of Internet searches for green stool conundrums and the ignominious instances of bank collapses. Armed with our trusty statistical software (and a not-so-trusty jar of air freshener), we calculated correlation coefficients, identifying a surprisingly robust association between these two seemingly disparate phenomena.

Caveat Emptor: Causal Inference
Now, before we get carried away and declare that green poop queries are the harbinger of financial doom, it is imperative to issue a word of caution. As any seasoned researcher knows, correlation does not imply causation. While our findings point to a noteworthy statistical relationship, we must tread carefully in ascribing direct causative links between stool inquiries and financial instability. As tempting as it may be to spin a tale of financial markets bowing to the whims of intestinal distress, we resist the urge to leap to such sensational conclusions.

Multivariate Regression Modeling
In an attempt to bolster the robustness of our findings and account for potential confounders, we ventured into the terrain of multivariate regression modeling. By introducing a smorgasbord of economic indicators, health factors, and perhaps a pinch of wishful thinking, we sought to untangle the web of influences that converge at this peculiar nexus of green excreta and fiscal upheaval. With a healthy dollop of humor and a sprinkle of skepticism, our modeling endeavors aimed to illuminate the pathways through which these two domains may, in some bizarre universe, intersect.

Ethical Considerations
As we waded through this unorthodox terrain of research, we remained mindful of the ethical implications of our findings. Recognizing the sensitive nature of discussions around human health and financial stability, we approached our investigation with the utmost respect for privacy and confidentiality. Rest assured, neither your financial portfolio nor the contents of your toilet were divulged in the pursuit of knowledge.

In conclusion, our methodology encapsulated a peculiar blend of statistical analyses, financial acumen, and a touch of whimsy as we navigated the unexpected correlation between green poop queries and bank failures. Through a prism of data-driven exploration and the occasional whiff of irony, we inched closer to unraveling the enigma at the feculent frontier of finance and physiology.

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 Google searches for 'why do i have green poop' and US bank failures. Make lots of 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]]
Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures

[[ABSTRACT]]
The present study delves into an unexpected and perhaps gut-wrenching connection between the frequency of Google searches for 'why do i have green poop' and the incidence of US bank failures. Leveraging data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our research team scrutinized a time span encompassing eighteen years, from 2004 to 2023. Our analysis revealed a striking correlation coefficient of 0.8689026 and p < 0.01, suggesting a significant relationship between these seemingly disparate phenomena. We proffer possible explanations for this eyebrow-raising finding and explore its implications for both the financial and gastrointestinal domains. Our multidisciplinary approach sheds light on the unexpected interplay between economic indicators and toilet troubles, urging further investigation into this feculent frontier.

[[LITERATURE REVIEW]]
While the present study may appear to wander off the beaten path of traditional financial and medical inquiry, it is not without the backing of various serious-sounding research studies and academic pieces that provide a substantial grounding for our unexpected investigation. Smith et al. uncovered surprising connections between societal search behavior and economic indicators in "The Interplay of Google Searches and Financial Markets." Similarly, Doe and Jones delved into the realm of consumer behavior and its implications for economic stability in their seminal work, "Consumer Habits and Macroeconomic Trends." These scholarly explorations set the stage for our own unexpected foray into the intersection of Google queries about peculiar bodily functions and the health of the banking sector.
As we veer further off the conventional academic track, our research also finds resonance in popular non-fiction works, such as "Gut: The Inside Story of Our Body’s Most Underrated Organ" by Giulia Enders and "Your Money or Your Life" by Vicki Robin and Joe Dominguez. These publications, while not directly related to our peculiar investigation, lay the groundwork for the broader implications of our findings – it's all about the gut and the green, after all.
On the fictional front, the works of Kafka and his absurd narratives of unwarranted bureaucracy may not offer direct insights into the relationship between Google searches for intestinal anomalies and financial upheaval, but they do set the stage for understanding the perplexing nature of unexpected connections. In addition, the mysterious allure of Dan Brown's "The Da Vinci Code" and its emphasis on decoding enigmatic symbols provided a dash of inspiration for our investigation - after all, what could be more enigmatic than the link between the color of one's excrement and the fate of financial institutions?
As we further submerge ourselves into this unlikely scholarly pursuit, we must also acknowledge the influence of our childhood influences – the infectious curiosity of "Magic School Bus" and its intrepid teacher, Ms. Frizzle, encouraged us to explore the nooks and crannies of scientific inquiry, even when those crannies are, well, less than pleasant. And who can forget the ever-curious George's antics in "Curious George" – a reminder that the quest for knowledge knows no bounds, even if it leads us to unexpected and somewhat green pastures.
It is within this eclectic tapestry of serious scholarship, offbeat literature, and childhood whimsy that our peculiar investigation unfolds, weaving together the disparate threads of finance, feces, and unfathomable fascination.

[[RESULTS]]
The startling findings of our research leave economists and gastroenterologists alike with a raised eyebrow and perhaps a slightly queasy stomach. Our analysis of data spanning from 2004 to 2023 uncovered a remarkable correlation coefficient of 0.8689026, an r-squared of 0.7549917, and a p-value less than 0.01, suggesting a robust and statistically significant relationship between Google searches for 'why do i have green poop' and US bank failures.
In less technical terms, this means that the frequency of people frantically seeking answers to their abnormal bowel movements on the internet appears to be oddly intertwined with the tumultuous events in the US banking sector. The strength of this connection is visually represented in the scatterplot (see Fig. 1), where the data points form a compelling line that would make any statistician do a double-take.
Now, we understand that these results might leave you feeling a bit, well, flushed with confusion. How on earth could the color of feces and financial catastrophes be linked? Trust us, we share your sense of bewilderment. This unexpected correlation might seem as improbable as stumbling upon a unicorn in a cornfield, but there it is, staring back at us from the depths of the data.
To add a layer of context to our findings, it's important to remember that correlation does not imply causation. Just because two variables seem to dance in step with one another doesn't mean that one causes the other. We are not here to suggest that green poop is the secret harbinger of economic doom or that a banking crisis induces vibrant bowel movements. At the risk of stating the obvious, a healthy dose of skepticism should accompany any eyebrow-raising result, and we are the first to acknowledge that our findings demand further scrutiny and research.
That being said, the statistical relationship we unearthed between these two seemingly incongruous subjects dares us to contemplate the uncharted territory of this feculent frontier. It calls for a reexamination of the interconnectedness of human behavior and market dynamics, inviting multidisciplinary discussions that extend beyond traditional economic analyses.
In conclusion, our research serves to remind us that science, much like life, can throw us a surprise or two when we least expect it. This unexpected connection between Google searches for 'why do i have green poop' and US bank failures challenges us to embrace the oddities of statistical inquiry and the unexpected insights it can bring. It's a reminder that, in the colorful and sometimes confounding world of data analysis, we must be prepared for the occasional whirlwind romance between statistics and the downright bizarre.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The present study has catapulted us into an intriguing realm at the confluence of finance and fecal matter. The eyebrow-raising correlation we unearthed between Google searches for 'why do i have green poop' and US bank failures lends itself to a spirited discussion that takes us deep into the murkier, albeit colorful, territories of statistical inquiry. As we embark on this exhilarating intellectual odyssey, we must remember the sage advice of our research forebears – that correlation is not causation, and green poop alone is unlikely to topple financial giants.

Our findings align with the scholarly works of Smith et al. and Doe and Jones, who ventured into the uncharted waters of behavioral indicators and economic trends. Just as they uncovered unexpected interplays between societal search behavior and financial markets, we now stand shoulder to shoulder with these intrepid explorers, offering a whimsical twist in the form of colorful intestinal distress. The thread of unexpected connections woven by our predecessors fortifies our understanding of the intricate dance between human behavior and market forces, affirming the value of interdisciplinary inquiry in untangling the enigmatic web of human experience and its impact on economic fluctuations.

As we delve deeper into the implications of our findings, we invite a nuanced perspective that transcends the mere statistical novelty of our results. While the allure of an ostensibly comical correlation might provoke chuckles, our research beckons us to contemplate the sobering undercurrents beneath the surface. The unexpected linkage between gastrointestinal concerns and financial instability underscores a complex interplay of societal stressors, consumer confidence, and perhaps a touch of cyber hypochondria. It prompts us to reconsider the intricate tapestry of human behavior and its unanticipated ripple effects across seemingly disparate domains.

It is worth noting that our findings do not exist in a vacuum – they arise from a confluence of serious scholarship, fanciful literature, and childhood wonder. In navigating this unlikely confluence, we demonstrate the symbiotic relationship between scholarly rigor and the unorthodox, embracing the unexpected with the fervor of a scientist stumbling upon a rare species in the jungle of data analysis. Our peculiar investigation serves as a poignant testament to the unpredictability of inquiry, reminding us that scientific exploration is often a whimsical romp through the unpredictable landscapes of human curiosity and statistical eccentricities.

In the vibrant and at times confounding arena of data analysis, our research challenges us to embrace the whimsical dance of statistics and the uncanny insights it can unearth. As we tiptoe through this feculent frontier, we are primed to confront the unexpected with a blend of scholarly rigor and whimsical wonder, for within the unmistakable line of correlation between green poop and bank failures lies an invitation to broaden our intellectual horizons and embrace the enchanting, if somewhat odoriferous, mysteries of statistical inquiry.

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 Google searches for 'why do i have green poop' and US bank failures. Make lots of 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]]
Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures

[[ABSTRACT]]
The present study delves into an unexpected and perhaps gut-wrenching connection between the frequency of Google searches for 'why do i have green poop' and the incidence of US bank failures. Leveraging data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our research team scrutinized a time span encompassing eighteen years, from 2004 to 2023. Our analysis revealed a striking correlation coefficient of 0.8689026 and p < 0.01, suggesting a significant relationship between these seemingly disparate phenomena. We proffer possible explanations for this eyebrow-raising finding and explore its implications for both the financial and gastrointestinal domains. Our multidisciplinary approach sheds light on the unexpected interplay between economic indicators and toilet troubles, urging further investigation into this feculent frontier.

[[INTRDUCTION]]
INTRODUCTION
Money, power, and...green poop? While the link between financial stability and gastrointestinal distress may seem outlandish at first glance, the present study thrusts this unlikely association into the limelight. In a twist worthy of a stomach-churning mystery novel, our research uncovers a peculiar correlation between Google searches for 'why do i have green poop' and US bank failures. While this duo may not seem like the most obvious pair, our findings reveal a statistical relationship that likely left both economists and gastroenterologists scratching their heads.
As researchers, we are often urged to explore uncharted territory, but this investigation took us to an unexpected and, quite frankly, odorous crossroads. This feculent frontier of inquiry required us to venture beyond the conventional realms of financial modeling and, well, delve deep into the underbelly of human health and behavior. Armed with data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our team endeavored to unravel the enigma of why individuals were frantically searching for the color of their excrement and what it could possibly have to do with the stability of the US banking system.
Now, before you wrinkle your nose in disbelief, let's set the stage for this, shall we say, unconventional exploration. We must acknowledge that in the vast landscape of statistical analyses, there are often unexpected correlations and spurious relationships that, much like an unsolved riddle, beg for further scrutiny. Our investigation into the peculiar pairing of green stool queries and bank failures served as a reminder that in the realm of data analytics, one must always be prepared to confront the inexplicable and the downright bizarre.
(Feel free to add any more jokes or puns you like!)

[[RESULTS]]
The startling findings of our research leave economists and gastroenterologists alike with a raised eyebrow and perhaps a slightly queasy stomach. Our analysis of data spanning from 2004 to 2023 uncovered a remarkable correlation coefficient of 0.8689026, an r-squared of 0.7549917, and a p-value less than 0.01, suggesting a robust and statistically significant relationship between Google searches for 'why do i have green poop' and US bank failures.
In less technical terms, this means that the frequency of people frantically seeking answers to their abnormal bowel movements on the internet appears to be oddly intertwined with the tumultuous events in the US banking sector. The strength of this connection is visually represented in the scatterplot (see Fig. 1), where the data points form a compelling line that would make any statistician do a double-take.
Now, we understand that these results might leave you feeling a bit, well, flushed with confusion. How on earth could the color of feces and financial catastrophes be linked? Trust us, we share your sense of bewilderment. This unexpected correlation might seem as improbable as stumbling upon a unicorn in a cornfield, but there it is, staring back at us from the depths of the data.
To add a layer of context to our findings, it's important to remember that correlation does not imply causation. Just because two variables seem to dance in step with one another doesn't mean that one causes the other. We are not here to suggest that green poop is the secret harbinger of economic doom or that a banking crisis induces vibrant bowel movements. At the risk of stating the obvious, a healthy dose of skepticism should accompany any eyebrow-raising result, and we are the first to acknowledge that our findings demand further scrutiny and research.
That being said, the statistical relationship we unearthed between these two seemingly incongruous subjects dares us to contemplate the uncharted territory of this feculent frontier. It calls for a reexamination of the interconnectedness of human behavior and market dynamics, inviting multidisciplinary discussions that extend beyond traditional economic analyses.
In conclusion, our research serves to remind us that science, much like life, can throw us a surprise or two when we least expect it. This unexpected connection between Google searches for 'why do i have green poop' and US bank failures challenges us to embrace the oddities of statistical inquiry and the unexpected insights it can bring. It's a reminder that, in the colorful and sometimes confounding world of data analysis, we must be prepared for the occasional whirlwind romance between statistics and the downright bizarre.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In the grand dance of statistics, our research has jived to the rhythm of the unexpected, showcasing a pas de deux between Google searches for 'why do i have green poop' and US bank failures that would make even the most stoic economist raise an eyebrow. As we wrap up this odorous odyssey, one thing is abundantly clear - the connection between intestinal inquiries and financial fiascos is one for the books, or perhaps the bowels.

Our findings, with a correlation coefficient that would turn heads at any statistical soiree, beckon researchers to heed the call of this feculent frontier. They remind us that the world of data analysis is a colorful, confounding tapestry that occasionally throws us a curveball - or in this case, a curveplot - that challenges our preconceptions and tickles our funny bones.

But let's not get ahead of ourselves. While we've uncovered a statistically significant link, let's not jump to conclusions in a single bound. As the age-old adage goes, correlation does not imply causation, and we're not here to claim that green stool is the harbinger of economic upheaval. We'll leave the wild speculation at the door, thank you very much.

In the end, this strange tango of statistics and stool samples is a compelling reminder that in the realm of research, embracing the unexpected and the downright bizarre is all part of the game. As much as we'd love to dive deeper into this enigmatic connection, perhaps this particular rabbit hole has been thoroughly explored. It's time to bid adieu to this peculiar pairing and leave the gastrointestinal whimsy to the gastroenterologists. After all, sometimes a statistical oddity is simply that - an oddity.

So, in the immortal words of Monty Python, "And now for something completely different." Let’s turn our attention to fresher pastures of inquiry, shall we? As far as Google searches for bodily functions and financial upheaval go, this saga has been thoroughly logged. No more research needed here, folks - time to flush this one down the academic toilet!

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 Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Unconventional Correlations

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 Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures. Respond only with the name of a fictional organization.

ChatGPT:

Society for Inexplicable Phenomena Research and Investigation (SIPRI)

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 Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures with an abstract of The present study delves into an unexpected and perhaps gut-wrenching connection between the frequency of Google searches for 'why do i have green poop' and the incidence of US bank failures. Leveraging data from Google Trends and the Federal Deposit Insurance Corporation (FDIC), our research team scrutinized a time span encompassing eighteen years, from 2004 to 2023. Our analysis revealed a striking correlation coefficient of 0.8689026 and p < 0.01, suggesting a significant relationship between these seemingly disparate phenomena. We proffer possible explanations for this eyebrow-raising finding and explore its implications for both the financial and gastrointestinal domains. Our multidisciplinary approach sheds light on the unexpected interplay between economic indicators and toilet troubles, urging further investigation into this feculent frontier.

ChatGPT:

google searches, green poop, bank failures, US bank failures, Google Trends, FDIC, correlation coefficient, gastrointestinal health, financial indicators, economic indicators, multidisciplinary research

*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

Google searches for 'why do i have green poop'
Detailed data title: Relative volume of Google searches for 'why do i have green poop' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'why do i have green poop'

US bank failures
Detailed data title: Bank failures in the US
Source: FDIC
See what else correlates with US bank failures

Correlation r = 0.8689026 (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 = 0.7549917 (Coefficient of determination)
This means 75.5% of the change in the one variable (i.e., US bank failures) is predictable based on the change in the other (i.e., Google searches for 'why do i have green poop') over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.7E-7.^Show 0.0000006685340997066356000000
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 0.87 in 6.7E-5% of random cases. Said differently, if you correlated 1,495,810 random variables^Note You don't actually need 1 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.

[ 0.69, 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Google searches for 'why do i have green poop' (Rel. search volume)	12.1667	19.25	18.0833	5.91667	14.25	36.0833	40.4167	35.25	24.5833	15.3333	16.25	15.3333	11	12.4167	12.5	14.0833	18	19.75	19.9167	24.1111
US bank failures (Failed banks)	4	0	0	3	25	140	157	92	51	24	18	8	5	8	0	4	4	0	0	4

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([12.1667,19.25,18.0833,5.91667,14.25,36.0833,40.4167,35.25,24.5833,15.3333,16.25,15.3333,11,12.4167,12.5,14.0833,18,19.75,19.9167,24.1111,])
array_2 = np.array([4,0,0,3,25,140,157,92,51,24,18,8,5,8,0,4,4,0,0,4,])
array_1_name = "Google searches for 'why do i have green poop'"
array_2_name = "US bank failures"

# 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 Google searches for 'why do i have green poop'
Line chart for only US bank failures
The spurious research paper: Money and Stools: An Unanticipated Association between Google Searches for 'Why Do I Have Green Poop' and US Bank Failures

View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!

Correlation ID: 1020 · Black Variable ID: 1539 · Red Variable ID: 899


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