Spurious correlation #1,483 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of fast food cooks in Guam and the second variable is Kerosene used in Saint Kitts and Nevis. The chart goes from 2003 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 The number of fast food cooks in Guam and the second variable is Kerosene used in Saint Kitts and Nevis. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the sizzling sounds of burgers and fries filled the air in Guam, it created a wave of excitement among Kerosene molecules in Saint Kitts and Nevis, leading to a surge in their combustion enthusiasm. Perhaps the real recipe for a fuel-up feast is a sprinkle of fast food magic!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s, depicting a small fast food restaurant in Guam. Inside, two cooks with classic white hats and aprons are skillfully preparing burgers and fries behind the counter. Outside the restaurant, a small delivery of kerosene barrels from Saint Kitts and Nevis is being unloaded by the delivery personnel. The scene should capture a sense of retro charm and simplicity, with a focus on the actions of the cooks and the delivery process. 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: The number of fast food cooks in Guam and Kerosene used in Saint Kitts and Nevis. 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: Cute cartoon Pop art Cubism Glitch art A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

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 The number of fast food cooks in Guam and Kerosene used in Saint Kitts and Nevis together. Keep the description simple.
ChatGPT: In a small fast food restaurant in Guam, two cooks are skillfully preparing burgers and fries while a small delivery of kerosene barrels from Saint Kitts and Nevis is being unloaded outside the restaurant.

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 comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: In a small fast food restaurant in Guam, two cooks are skillfully preparing burgers and fries while a small delivery of kerosene barrels from Saint Kitts and Nevis is being unloaded outside the restaurant. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s, depicting a small fast food restaurant in Guam. Inside, two cooks with classic white hats and aprons are skillfully preparing burgers and fries behind the counter. Outside the restaurant, a small delivery of kerosene barrels from Saint Kitts and Nevis is being unloaded by the delivery personnel. The scene should capture a sense of retro charm and simplicity, with a focus on the actions of the cooks and the delivery process.

*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 increases in The number of fast food cooks in Guam positively influenced Kerosene used in Saint Kitts and Nevis. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis

The Journal of Culinary Chemistry & Ecological Economics

Jan 2024

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

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

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of fast food cooks in Guam and Kerosene used in Saint Kitts and Nevis. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis"

[[ABSTRACT]]
This paper aims to investigate the enigmatic and seemingly unrelated domains of fast food labor in Guam and kerosene consumption in Saint Kitts and Nevis. Using data from the Bureau of Labor Statistics and the Energy Information Administration for the time period spanning 2003 to 2021, our research team employed advanced statistical methods to unravel this seemingly absurd connection. Our analysis revealed a surprising correlation coefficient of 0.7945429 with statistical significance at p < 0.01, suggesting a tantalizing link between the number of fast food cooks in Guam and the kerosene consumption in the distant island nation of Saint Kitts and Nevis. In this paper, we delve into the data, exploring the potential implications and underlying mechanisms, while seasoning our findings with a dash of humor and a side of quirky observations.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The seemingly tangential relationship between the number of fast food cooks in Guam and the kerosene consumption in Saint Kitts and Nevis has raised eyebrows and piqued the curiosity of researchers worldwide. While discussing fast food and kerosene in the same breath may seem as incongruous as pairing a milkshake with a lobster, our team of intrepid researchers embarked on this fry-volous investigation to uncover the hidden connections lurking beneath the surface.
One might wonder what fast food cooks in Guam and kerosene users in Saint Kitts and Nevis could possibly have in common. After all, one group is responsible for producing greasy, tantalizing delicacies, while the other is busy lighting up the night in a small island nation. However, upon closer inspection, the sizzling and the flickering might not be as unrelated as one might initially assume – much like finding an unexpected pickle slice in the depths of your french fries.
The Bureau of Labor Statistics and the Energy Information Administration graciously provided us with the data that formed the bedrock of our investigation. We meticulously combed through the numbers from 2003 to 2021, aiming to suss out any underlying patterns or correlations that might be lurking beneath the surface, much like a hidden toy in a kid's meal. To our surprise, our statistical analysis revealed a correlation coefficient of 0.7945429, waving a figurative flag in the air and beckoning us to pay attention to this seemingly whimsical link.
In this paper, we aim to tantalize your academic taste buds with our findings and explore the potential implications of this curious connection. Our approach will be akin to unwrapping a mystery burger from a fast food joint – slowly and with an air of cautious excitement. We will season our analysis with a sprinkle of humor and a garnish of quirky observations, in the hopes that our readers will find the journey as delectable as a well-seasoned dish.
So, dear reader, buckle up as we embark on this unexpectedly flavorful journey, where Guam's fast food cooks and the kerosene consumers of Saint Kitts and Nevis converge in a confluence of statistical peculiarity and culinary delight.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

To contextualize our findings, a survey of existing literature was conducted. Smith and Doe (2015) examined the impact of fast food labor on small island economies, highlighting the nuanced interplay between culinary trends and economic indicators. They observed a notable correlation between the proliferation of fast food establishments and the consumption of commodity goods, positioning fast food cooks as inadvertent influencers of consumer behavior. Similarly, Jones (2018) investigated the usage of kerosene in remote island communities, offering insights into the cultural and socioeconomic underpinnings of energy consumption. The juxtaposition of these two seemingly disparate realms sets the stage for our fry-volous investigation into the entwined fate of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis.

Upon venturing beyond the scholarly landscape, a dive into non-fiction works further enriched our understanding. In "Fast Food Nation" by Eric Schlosser, the intricate web of fast food production and its multifaceted impacts on global consumer behavior is dissected with meticulous detail. This work served as a savory appetizer for our exploration into the world of fast food labor. Conversely, "Kerosene: A History" by John Robson provided a illuminating perspective on the historical, cultural, and practical dimensions of kerosene usage, shedding light on the underexplored domain of energy consumption in island communities.

Taking an unexpected turn, fictional literature also offered tantalizing parallels to our investigation. In "Kitchen Confidential" by Anthony Bourdain, the vibrant and chaotic world of professional kitchens emerges, further cementing the image of fast food cooks as central figures in the culinary landscape. On the other hand, "Light My Fire" by Katie MacAlister, while ostensibly a romance novel, inadvertently kindled our intrigue in kerosene-related thematic elements, adding an unexpected layer of literary kindling to our scholarly pursuit.

Furthermore, the internet age has birthed memes such as the "Kerosene Cat," a whimsical online sensation revolving around feline fascination with kerosene lamps, adding a touch of levity to the otherwise serious discourse on energy consumption. This curious digital artifact, albeit lighthearted in nature, underscores the ubiquity of kerosene in popular consciousness.

In sum, the diverse array of literature and cultural references examined proffered an eclectic tapestry of insights and analogies, infusing our investigation with a dash of unexpected zest and a sprinkle of serendipitous humor.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of fast food cooks in Guam and Kerosene used in Saint Kitts and Nevis. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis"

[[ABSTRACT]]
This paper aims to investigate the enigmatic and seemingly unrelated domains of fast food labor in Guam and kerosene consumption in Saint Kitts and Nevis. Using data from the Bureau of Labor Statistics and the Energy Information Administration for the time period spanning 2003 to 2021, our research team employed advanced statistical methods to unravel this seemingly absurd connection. Our analysis revealed a surprising correlation coefficient of 0.7945429 with statistical significance at p < 0.01, suggesting a tantalizing link between the number of fast food cooks in Guam and the kerosene consumption in the distant island nation of Saint Kitts and Nevis. In this paper, we delve into the data, exploring the potential implications and underlying mechanisms, while seasoning our findings with a dash of humor and a side of quirky observations.

[[LITERATURE REVIEW]]
To contextualize our findings, a survey of existing literature was conducted. Smith and Doe (2015) examined the impact of fast food labor on small island economies, highlighting the nuanced interplay between culinary trends and economic indicators. They observed a notable correlation between the proliferation of fast food establishments and the consumption of commodity goods, positioning fast food cooks as inadvertent influencers of consumer behavior. Similarly, Jones (2018) investigated the usage of kerosene in remote island communities, offering insights into the cultural and socioeconomic underpinnings of energy consumption. The juxtaposition of these two seemingly disparate realms sets the stage for our fry-volous investigation into the entwined fate of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis.
Upon venturing beyond the scholarly landscape, a dive into non-fiction works further enriched our understanding. In "Fast Food Nation" by Eric Schlosser, the intricate web of fast food production and its multifaceted impacts on global consumer behavior is dissected with meticulous detail. This work served as a savory appetizer for our exploration into the world of fast food labor. Conversely, "Kerosene: A History" by John Robson provided a illuminating perspective on the historical, cultural, and practical dimensions of kerosene usage, shedding light on the underexplored domain of energy consumption in island communities.
Taking an unexpected turn, fictional literature also offered tantalizing parallels to our investigation. In "Kitchen Confidential" by Anthony Bourdain, the vibrant and chaotic world of professional kitchens emerges, further cementing the image of fast food cooks as central figures in the culinary landscape. On the other hand, "Light My Fire" by Katie MacAlister, while ostensibly a romance novel, inadvertently kindled our intrigue in kerosene-related thematic elements, adding an unexpected layer of literary kindling to our scholarly pursuit.
Furthermore, the internet age has birthed memes such as the "Kerosene Cat," a whimsical online sensation revolving around feline fascination with kerosene lamps, adding a touch of levity to the otherwise serious discourse on energy consumption. This curious digital artifact, albeit lighthearted in nature, underscores the ubiquity of kerosene in popular consciousness.
In sum, the diverse array of literature and cultural references examined proffered an eclectic tapestry of insights and analogies, infusing our investigation with a dash of unexpected zest and a sprinkle of serendipitous humor.

[[RESULTS]]
The analysis of the data collected from the Bureau of Labor Statistics and the Energy Information Administration from 2003 to 2021 revealed a correlation coefficient of 0.7945429 between the number of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis. The substantial correlation, with an r-squared value of 0.6312984, is akin to stumbling upon an unexpectedly harmonious combination at a fast food restaurant, where the flavors just seem to click together in an inexplicably satisfying manner.
The scatterplot (Fig. 1) visually depicts the strong association between these seemingly disparate variables. It's as if the fries and the ketchup have found each other in the vast expanse of statistical analysis, forming a bond that defies conventional logic but tantalizes the taste buds nonetheless.
The statistical significance at p < 0.01 highlights the robustness of this correlation, akin to discovering a surprising ingredient in a traditional dish that elevates its flavor profile in unexpected ways.
This finding challenges traditional assumptions and encourages further exploration into the potential mechanisms underlying this connection. It's as if a secret sauce has been unveiled, transforming the mundane into the remarkable.
In conclusion, the unexpected correlation between the number of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis raises intriguing questions and invites future research to savor the complexity and richness of this seemingly unrelated pairing.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of our study provide compelling evidence for the existence of a robust and significant correlation between the number of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis. This unforeseen connection serves as an appetizing conundrum, akin to stumbling upon an unexpected fusion cuisine that defies traditional culinary norms but proves oddly satisfying to the palate.

Our results corroborate the prior research by Smith and Doe (2015), who alluded to the potential influence of fast food labor on consumer behavior. The proliferation of fast food establishments, it seems, may have broader ramifications that extend beyond the realm of gastronomy, much like a secret ingredient that imparts unexpected depth to a dish. In a similar vein, the work of Jones (2018) shed light on the cultural and socioeconomic dimensions of kerosene consumption, uncovering the nuanced interplay of energy usage in island communities. And here we are, encountering a savory synergy between these two disparate domains – fast food labor and kerosene consumption – much like the marriage of contrasting flavors that somehow harmonize in a delectable dish.

The interplay of literature and popular culture in our exploration further adds to the piquancy of our findings. The unexpected parallels drawn from works such as "Kitchen Confidential" and "Light My Fire," though seemingly tangential, subtly infused our inquiry with an extra layer of flavor, much like an unpredictable seasoning that elevates the overall gustatory experience. Even the emergence of the "Kerosene Cat" meme on the internet, while whimsical in nature, serves as a playful embellishment on the canvas of our scholarly pursuit, much like a garnish that imparts visual appeal to a culinary masterpiece.

The substantial correlation coefficient that we uncovered, aside from its statistical significance, bears resemblance to a fortuitous culinary discovery, where the juxtaposition of ingredients elicits an unexpectedly harmonious balance of flavors. It is as if the fast food cooks in Guam are dishing out not just delectable meals, but inadvertently orchestrating a flavorful domino effect that traverses oceans to shape the kerosene consumption habits in Saint Kitts and Nevis.

In light of our findings, we are left with a tantalizing array of unanswered questions, akin to the lingering aftertaste of a truly remarkable culinary experience. What mechanisms underlie this unexpected correlation? How might cultural, economic, and geographical factors intertwine to yield such a surprising connection? Like enterprising chefs experimenting with novel flavor combinations, we encourage future researchers to savor the complexity and richness of this seemingly disparate pairing, embracing the enigma with a spirit of gastronomic curiosity.

In the realm of scholarly inquiry, as in the realm of gastronomy, the unexpected juxtaposition of seemingly incongruous elements may yield an intellectual feast that transcends conventional wisdom, satisfying the appetite of knowledge with a platter of flavorful surprises. This study stands as a testament to the intricate and often whimsical interconnectedness of human activities, urging scholars to savor the flavors of serendipitous discovery and embrace the enticing mergers that defy conventional expectations.

The unexpected link between fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis strikes a chord that reverberates beyond the confines of traditional disciplinary boundaries, tantalizing the intellect with a gustatory metaphor that beckons exploratory culinary and scholarly odysseys.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of fast food cooks in Guam and Kerosene used in Saint Kitts and Nevis. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis"

[[ABSTRACT]]
This paper aims to investigate the enigmatic and seemingly unrelated domains of fast food labor in Guam and kerosene consumption in Saint Kitts and Nevis. Using data from the Bureau of Labor Statistics and the Energy Information Administration for the time period spanning 2003 to 2021, our research team employed advanced statistical methods to unravel this seemingly absurd connection. Our analysis revealed a surprising correlation coefficient of 0.7945429 with statistical significance at p < 0.01, suggesting a tantalizing link between the number of fast food cooks in Guam and the kerosene consumption in the distant island nation of Saint Kitts and Nevis. In this paper, we delve into the data, exploring the potential implications and underlying mechanisms, while seasoning our findings with a dash of humor and a side of quirky observations.

[[INTRDUCTION]]
The seemingly tangential relationship between the number of fast food cooks in Guam and the kerosene consumption in Saint Kitts and Nevis has raised eyebrows and piqued the curiosity of researchers worldwide. While discussing fast food and kerosene in the same breath may seem as incongruous as pairing a milkshake with a lobster, our team of intrepid researchers embarked on this fry-volous investigation to uncover the hidden connections lurking beneath the surface.
One might wonder what fast food cooks in Guam and kerosene users in Saint Kitts and Nevis could possibly have in common. After all, one group is responsible for producing greasy, tantalizing delicacies, while the other is busy lighting up the night in a small island nation. However, upon closer inspection, the sizzling and the flickering might not be as unrelated as one might initially assume – much like finding an unexpected pickle slice in the depths of your french fries.
The Bureau of Labor Statistics and the Energy Information Administration graciously provided us with the data that formed the bedrock of our investigation. We meticulously combed through the numbers from 2003 to 2021, aiming to suss out any underlying patterns or correlations that might be lurking beneath the surface, much like a hidden toy in a kid's meal. To our surprise, our statistical analysis revealed a correlation coefficient of 0.7945429, waving a figurative flag in the air and beckoning us to pay attention to this seemingly whimsical link.
In this paper, we aim to tantalize your academic taste buds with our findings and explore the potential implications of this curious connection. Our approach will be akin to unwrapping a mystery burger from a fast food joint – slowly and with an air of cautious excitement. We will season our analysis with a sprinkle of humor and a garnish of quirky observations, in the hopes that our readers will find the journey as delectable as a well-seasoned dish.
So, dear reader, buckle up as we embark on this unexpectedly flavorful journey, where Guam's fast food cooks and the kerosene consumers of Saint Kitts and Nevis converge in a confluence of statistical peculiarity and culinary delight.

[[RESULTS]]
The analysis of the data collected from the Bureau of Labor Statistics and the Energy Information Administration from 2003 to 2021 revealed a correlation coefficient of 0.7945429 between the number of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis. The substantial correlation, with an r-squared value of 0.6312984, is akin to stumbling upon an unexpectedly harmonious combination at a fast food restaurant, where the flavors just seem to click together in an inexplicably satisfying manner.
The scatterplot (Fig. 1) visually depicts the strong association between these seemingly disparate variables. It's as if the fries and the ketchup have found each other in the vast expanse of statistical analysis, forming a bond that defies conventional logic but tantalizes the taste buds nonetheless.
The statistical significance at p < 0.01 highlights the robustness of this correlation, akin to discovering a surprising ingredient in a traditional dish that elevates its flavor profile in unexpected ways.
This finding challenges traditional assumptions and encourages further exploration into the potential mechanisms underlying this connection. It's as if a secret sauce has been unveiled, transforming the mundane into the remarkable.
In conclusion, the unexpected correlation between the number of fast food cooks in Guam and kerosene consumption in Saint Kitts and Nevis raises intriguing questions and invites future research to savor the complexity and richness of this seemingly unrelated pairing.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In bringing this sizzling saga to a close, our fry-volous investigation has illuminated a correlation of 0.7945429 between the number of fast food cooks in Guam and the kerosene consumption in Saint Kitts and Nevis. This unexpected pairing has left us pondering the possibility of a secret recipe that intertwines these seemingly disparate elements, much like discovering an unexpected condiment that transforms the familiar into something delightfully unique.

The robust statistical significance at p < 0.01 emphasizes the validity of this connection, akin to stumbling upon a rare spice that enhances the flavor without overpowering the dish. The visualization of this relationship in the scatterplot (Fig. 1) invites contemplation of the dance between fast food creations and the flickering glow of kerosene, much like the choreography of a well-timed culinary presentation.

While the results of this study may seem whimsical at first glance, they raise tantalizing questions and inspire a sense of curiosity akin to pulling apart an intricately wrapped to-go order, pondering the unexpected delights within. The r-squared value of 0.6312984 speaks to the depth of this connection, much like the intricate layers of a delectable dessert, leaving us with a lingering sense of intrigue.

As we flavor our conclusions with a hint of humor and a pinch of amusement, it is evident that this peculiar pairing invites further exploration, much like encountering an enigmatic dish that beckons the palate to unravel its complexities. However, it is our firm assertion that no more research is needed in this area.

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 Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Culinary Chemistry & Ecological Economics

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis. Respond only with the name of a fictional organization.

ChatGPT:

Global Institute for Culinary and Energy 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 Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis with an abstract of This paper aims to investigate the enigmatic and seemingly unrelated domains of fast food labor in Guam and kerosene consumption in Saint Kitts and Nevis. Using data from the Bureau of Labor Statistics and the Energy Information Administration for the time period spanning 2003 to 2021, our research team employed advanced statistical methods to unravel this seemingly absurd connection. Our analysis revealed a surprising correlation coefficient of 0.7945429 with statistical significance at p < 0.01, suggesting a tantalizing link between the number of fast food cooks in Guam and the kerosene consumption in the distant island nation of Saint Kitts and Nevis. In this paper, we delve into the data, exploring the potential implications and underlying mechanisms, while seasoning our findings with a dash of humor and a side of quirky observations.

ChatGPT:

Flipping, connection, fast food cooks, Guam, kerosene consumption, Saint Kitts and Nevis, Bureau of Labor Statistics, Energy Information Administration, statistical methods, correlation coefficient, statistical significance, data analysis, implications, underlying mechanisms

*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

The number of fast food cooks in Guam
Detailed data title: BLS estimate of cooks, fast food in Guam
Source: Bureau of Larbor Statistics
See what else correlates with The number of fast food cooks in Guam

Kerosene used in Saint Kitts and Nevis
Detailed data title: Volume of kerosene used consumed in Saint Kitts and Nevis in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Saint Kitts and Nevis

Correlation r = 0.7945429 (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 = 0.6312984 (Coefficient of determination)
This means 63.1% of the change in the one variable (i.e., Kerosene used in Saint Kitts and Nevis) is predictable based on the change in the other (i.e., The number of fast food cooks in Guam) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.8E-5.^Show 0.0000483521817120353600000000
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 0.79 in 0.0048% of random cases. Said differently, if you correlated 20,682 random variables^Note You don't actually need 20 thousand variables to find a correlation like this one. 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.

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 18 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.53, 0.92 ] 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.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of fast food cooks in Guam (Cooks, Fast Food)	310	410	310	210	200	140	210	140	150	240	300	310	110	530	530	750	480	360	340
Kerosene used in Saint Kitts and Nevis (Million Barrels/Day)	0.00423562	0.00422404	0.00423562	0.00423562	0.00423562	0.00422404	0.00423562	0.00423562	0.00211781	0.00422404	0.00423562	0.00423562	0.004235	0.006353	0.00635342	0.00635342	0.00635342	0.00538944	0.00573608

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([310,410,310,210,200,140,210,140,150,240,300,310,110,530,530,750,480,360,340,])
array_2 = np.array([0.00423562,0.00422404,0.00423562,0.00423562,0.00423562,0.00422404,0.00423562,0.00423562,0.00211781,0.00422404,0.00423562,0.00423562,0.004235,0.006353,0.00635342,0.00635342,0.00635342,0.00538944,0.00573608,])
array_1_name = "The number of fast food cooks in Guam"
array_2_name = "Kerosene used in Saint Kitts and Nevis"

# 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 The number of fast food cooks in Guam
Line chart for only Kerosene used in Saint Kitts and Nevis
AI-generated correlation image
The spurious research paper: Flipping the Connection: A Fry-Volous Investigation into the Link between Fast Food Cooks in Guam and Kerosene Consumption in Saint Kitts and Nevis

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 1483 · Black Variable ID: 16582 · Red Variable ID: 24855


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