Spurious correlation #3,594 · 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 fashion designers in South Carolina and the second variable is Jet fuel used in Bulgaria. The chart goes from 2004 to 2018, 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 fashion designers in South Carolina and the second variable is Jet fuel used in Bulgaria. The chart goes from 2004 to 2018, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As more fashion designers set up shop in South Carolina, the demand for over-the-top, extravagant fashion shows skyrocketed. These fashion shows became so elaborate that they started using private jets to transport the latest trends to Bulgaria. And as we all know, there's nothing like a high-altitude fashion showcase! So, it's safe to say that the South Carolina fashion scene has taken Bulgarian fashion to new heights, quite literally.

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate an image that features a minimalist representation of a bustling fashion district in South Carolina, capturing the scene of fashion designers setting up their ateliers with mannequins displaying their latest creations. In the background, showcase Bulgarian jet fuel trucks lined up at the local airport, ready to refuel private jets arriving for exclusive high-end fashion shows. Ensure the visual is clean, minimalistic, and conveys the contrast between the fashion district and the airport without including any words or speech bubbles. 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 fashion designers in South Carolina and Jet fuel used in Bulgaria. 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: Art nouveau Minimalism Cubism Parallax art Celtic art
ChatGPT: Minimalism

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 fashion designers in South Carolina and Jet fuel used in Bulgaria, in the following situation: Because as more fashion designers set up shop in South Carolina, there was a surge in demand for high-end fashion shows, leading to an influx of Bulgarian jet setters flying in for front row seats. This increase in air traffic caused Bulgaria to import more jet fuel to keep up with the demand, resulting in a rise in jet fuel usage.. Keep the description simple.
ChatGPT: In a bustling fashion district in South Carolina, a group of fashion designers are setting up their ateliers, with mannequins displaying their latest creations. Meanwhile, at the local airport, Bulgarian jet fuel trucks are lined up, ready to refuel private jets arriving for exclusive high-end fashion shows.

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: [ Minimalism ] and depicting this scene: In a bustling fashion district in South Carolina, a group of fashion designers are setting up their ateliers, with mannequins displaying their latest creations. Meanwhile, at the local airport, Bulgarian jet fuel trucks are lined up, ready to refuel private jets arriving for exclusive high-end fashion shows. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image that features a minimalist representation of a bustling fashion district in South Carolina, capturing the scene of fashion designers setting up their ateliers with mannequins displaying their latest creations. In the background, showcase Bulgarian jet fuel trucks lined up at the local airport, ready to refuel private jets arriving for exclusive high-end fashion shows. Ensure the visual is clean, minimalistic, and conveys the contrast between the fashion district and the airport without including any words or speech bubbles.

*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 The number of fashion designers in South Carolina caused Jet fuel used in Bulgaria to increase.

AI academic paper

(Because p < 0.01)

The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

The International Journal of Eclectic Fashion and Global Energy Trends

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 fashion designers in South Carolina and Jet fuel used in Bulgaria. 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]]
The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

[[ABSTRACT]]
This paper investigates a seemingly improbable connection between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration for the time period from 2004 to 2018, we uncover a striking correlation coefficient of 0.8789501 with a level of significance of p < 0.01. Our findings may seem as unexpected as discovering a high heel at a gas station, yet they highlight the intricate interplay between seemingly unrelated economic and social factors. We provide a scholarly analysis of this peculiar relationship and offer tongue-in-cheek speculations on the potential causative mechanisms and implications.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intertwining of seemingly disconnected phenomena in the world of economics and social dynamics has long been a source of fascination and bewilderment. In this paper, we embark on a curious journey through the labyrinth of statistics and economic data, seeking to unravel the enigmatic link between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. One might say we are delving into the nitty-gritty of fashion and fuel, exploring the stitches and seams that unite these apparently disparate industries.
At first glance, one might wonder how these two seemingly unrelated variables could possibly be correlated. After all, what connection could there possibly be between the creativity of fashion designers in the American South and the logistical demands of jet fuel in the Eastern European nation? It's as perplexing as trying to match plaid with polka dots. Nevertheless, as researchers with a penchant for unearthing the unexpected, we could not resist the allure of exploring this incongruous relationship.
As we conducted our investigation, we were initially met with skepticism and raised eyebrows. After all, the notion of a connection between couture and kerosene seems about as likely as finding a runway show at an airfield. However, our analytical pursuits bore fruit, revealing a surprising and robust correlation that cannot simply be brushed aside. The mystery deepens, and in the spirit of intellectual inquiry, we aim to shed light on this unanticipated bond with all due seriousness, despite the whimsical nature of the linkage.
In the following sections, we will dive into a detailed exploration of the empirical evidence, statistical analyses, and potential underlying mechanisms that may underpin this curious association. As we unravel the fabric of our findings, we encourage our readers to approach our scholarly endeavor with a discerning eye, perhaps even a raised eyebrow, as we delve into the unexpected and the inexplicable. The stage is set, the spotlight is on – let us now unveil the theatrics of fashion and fuel.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

As we delve into the labyrinth of academic inquiry, we first turn our attention to the extant literature pertaining to the unlikely intersection of fashion design and jet fuel consumption. Smith et al. (2017) provide a comprehensive examination of regional labor trends in the United States, shedding light on the burgeoning population of fashion designers in South Carolina. Likewise, Doe (2015) explores the intricate link between economic development and creative industries, offering a nuanced perspective on the burgeoning fashion scene in the American South.

As we venture further into the realm of literature, one cannot overlook the seminal work of Jones (2018), who delves into the geopolitical dimensions of energy consumption in Eastern Europe. This work forms a crucial backdrop for our investigation, setting the stage for our curious exploration of jet fuel demand in Bulgaria.

Turning to broader socioeconomic analyses, "Economics of Fashion" by Fashionista and "Fueling the Future: The Economics of Jet Propulsion" by Aviation Economist offer invaluable insights into the respective industries under scrutiny. These texts, although seemingly divergent, unwittingly set the stage for our own scholarly foray into the unexpected nexus of fashion and fuel.

Furthermore, the fictional realm offers unexpected parallels to our research endeavor. "The Devil Wears Prada" by Lauren Weisberger and "The Jetsetters" by Amanda Eyre Ward, while seemingly unrelated to our empirical focus, playfully tease at the whimsical and unpredictable nature of the industries we seek to unravel.

Moreover, it would be remiss not to acknowledge the unlikely marriage of internet memes and our scholarly pursuit. The "Fashion vs. Fuel" meme, which humorously juxtaposes haute couture with aviation imagery, serves as a lighthearted reminder of the interconnectedness of seemingly disparate spheres.

As we embark on our own investigation, it is with a sense of scholarly duty and, dare we say, an irrepressible sense of whimsy that we navigate this terrain of the atypical. With a nod to the serious undercurrent of our inquiry, we are poised to dissect the symbiosis between two ostensibly unrelated domains.

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 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 The number of fashion designers in South Carolina and Jet fuel used in Bulgaria. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration . You used data from 2004 to 2018

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]]
The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

[[ABSTRACT]]
This paper investigates a seemingly improbable connection between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration for the time period from 2004 to 2018, we uncover a striking correlation coefficient of 0.8789501 with a level of significance of p < 0.01. Our findings may seem as unexpected as discovering a high heel at a gas station, yet they highlight the intricate interplay between seemingly unrelated economic and social factors. We provide a scholarly analysis of this peculiar relationship and offer tongue-in-cheek speculations on the potential causative mechanisms and implications.

[[INTRODUCTION]]
The intertwining of seemingly disconnected phenomena in the world of economics and social dynamics has long been a source of fascination and bewilderment. In this paper, we embark on a curious journey through the labyrinth of statistics and economic data, seeking to unravel the enigmatic link between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. One might say we are delving into the nitty-gritty of fashion and fuel, exploring the stitches and seams that unite these apparently disparate industries.
At first glance, one might wonder how these two seemingly unrelated variables could possibly be correlated. After all, what connection could there possibly be between the creativity of fashion designers in the American South and the logistical demands of jet fuel in the Eastern European nation? It's as perplexing as trying to match plaid with polka dots. Nevertheless, as researchers with a penchant for unearthing the unexpected, we could not resist the allure of exploring this incongruous relationship.
As we conducted our investigation, we were initially met with skepticism and raised eyebrows. After all, the notion of a connection between couture and kerosene seems about as likely as finding a runway show at an airfield. However, our analytical pursuits bore fruit, revealing a surprising and robust correlation that cannot simply be brushed aside. The mystery deepens, and in the spirit of intellectual inquiry, we aim to shed light on this unanticipated bond with all due seriousness, despite the whimsical nature of the linkage.
In the following sections, we will dive into a detailed exploration of the empirical evidence, statistical analyses, and potential underlying mechanisms that may underpin this curious association. As we unravel the fabric of our findings, we encourage our readers to approach our scholarly endeavor with a discerning eye, perhaps even a raised eyebrow, as we delve into the unexpected and the inexplicable. The stage is set, the spotlight is on – let us now unveil the theatrics of fashion and fuel.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study involved data collection, processing, and analysis in order to uncover the intricate relationship between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. The primary sources of data included the Bureau of Labor Statistics (BLS) and the Energy Information Administration (EIA), where reliable and comprehensive information pertaining to fashion industry employment and jet fuel consumption, respectively, could be obtained.

To begin the investigation, we embarked on a virtual journey through the world wide web, navigated the intricacies of the BLS and EIA websites, and harnessed the power of search engines to gather data spanning the years 2004 to 2018. Our quest for information led us down the corridors of numerical archives, akin to seeking out rare fabrics in a digital marketplace.

The data retrieval process necessitated a careful and meticulous approach. Like skilled tailors scrutinizing the quality of fabric, we meticulously examined datasets, ensuring that every data point was impeccably aligned and free from imperfections. After the arduous process of data curation, we reconciled any discrepancies and hemmed together the diverse data sources into a seamless, cohesive fabric of information, ensuring the integrity and reliability of our dataset.

With our dataset curated and prepared, we applied robust statistical methods to stitch together the disparate variables of fashion designers in South Carolina and jet fuel consumption in Bulgaria. Our analytical techniques included correlation analyses, regression models, and time-series evaluations, allowing us to weave a comprehensive understanding of the interconnectedness of these seemingly unrelated variables. Just as a designer meticulously drapes fabric to create a harmonious garment, we adorned our statistical analyses with the precision and artistry required to discern the underlying patterns within the data.

Despite the apparent incongruity of our subject matter, the methodology employed in this study was grounded in empirical rigor and analytical precision. Our approach mirrored the craftsmanship of a skilled artisan, meticulously piecing together disparate elements to reveal unexpected connections and patterns. With our methodological approach, we aim to exemplify that even in the world of scholarly inquiry, unexpected relationships can be brought to light with the right blend of intellectual rigor and a touch of sartorial whimsy.

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 fashion designers in South Carolina and Jet fuel used in Bulgaria. 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]]
The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

[[ABSTRACT]]
This paper investigates a seemingly improbable connection between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration for the time period from 2004 to 2018, we uncover a striking correlation coefficient of 0.8789501 with a level of significance of p < 0.01. Our findings may seem as unexpected as discovering a high heel at a gas station, yet they highlight the intricate interplay between seemingly unrelated economic and social factors. We provide a scholarly analysis of this peculiar relationship and offer tongue-in-cheek speculations on the potential causative mechanisms and implications.

[[LITERATURE REVIEW]]
As we delve into the labyrinth of academic inquiry, we first turn our attention to the extant literature pertaining to the unlikely intersection of fashion design and jet fuel consumption. Smith et al. (2017) provide a comprehensive examination of regional labor trends in the United States, shedding light on the burgeoning population of fashion designers in South Carolina. Likewise, Doe (2015) explores the intricate link between economic development and creative industries, offering a nuanced perspective on the burgeoning fashion scene in the American South.
As we venture further into the realm of literature, one cannot overlook the seminal work of Jones (2018), who delves into the geopolitical dimensions of energy consumption in Eastern Europe. This work forms a crucial backdrop for our investigation, setting the stage for our curious exploration of jet fuel demand in Bulgaria.
Turning to broader socioeconomic analyses, "Economics of Fashion" by Fashionista and "Fueling the Future: The Economics of Jet Propulsion" by Aviation Economist offer invaluable insights into the respective industries under scrutiny. These texts, although seemingly divergent, unwittingly set the stage for our own scholarly foray into the unexpected nexus of fashion and fuel.
Furthermore, the fictional realm offers unexpected parallels to our research endeavor. "The Devil Wears Prada" by Lauren Weisberger and "The Jetsetters" by Amanda Eyre Ward, while seemingly unrelated to our empirical focus, playfully tease at the whimsical and unpredictable nature of the industries we seek to unravel.
Moreover, it would be remiss not to acknowledge the unlikely marriage of internet memes and our scholarly pursuit. The "Fashion vs. Fuel" meme, which humorously juxtaposes haute couture with aviation imagery, serves as a lighthearted reminder of the interconnectedness of seemingly disparate spheres.
As we embark on our own investigation, it is with a sense of scholarly duty and, dare we say, an irrepressible sense of whimsy that we navigate this terrain of the atypical. With a nod to the serious undercurrent of our inquiry, we are poised to dissect the symbiosis between two ostensibly unrelated domains.

[[RESULTS]]
The analysis of the data collected from the Bureau of Labor Statistics and the Energy Information Administration for the period spanning from 2004 to 2018 revealed a striking correlation between the number of fashion designers in South Carolina and jet fuel consumption in Bulgaria. The correlation coefficient of 0.8789501 indicated a strong positive relationship between these seemingly incongruous variables. This coefficient, combined with the r-squared value of 0.7725532, suggests that approximately 77.26% of the variation in jet fuel usage in Bulgaria can be explained by the number of fashion designers in South Carolina, a finding that is as unexpected as encountering a tuxedo at a BP gas station.
The level of significance, with a p-value less than 0.01, adds a layer of robustness to our results, akin to finding a dependable seam in an intricately designed garment. The figure (Fig. 1) visually portrays this unexpected yet undeniable correlation, providing a scatterplot that vividly depicts the strong relationship between the two variables. This correlation almost jumps out at the viewer, much like an avant-garde fashion statement.
These findings challenge conventional wisdom and beckon researchers to explore the underlying mechanisms and implications of this improbable bond. The connection between the creativity of fashion designers in South Carolina and the logistical demands of jet fuel in Bulgaria is indeed a puzzle worth unraveling, akin to a fashion mystery waiting to be solved.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

The identification of a substantial correlation between the number of fashion designers in South Carolina and jet fuel consumption in Bulgaria underscores the intertwined nature of seemingly unrelated economic and social phenomena. Our findings complement and corroborate prior research conducted by Smith et al. (2017) and Doe (2015) on the proliferation of fashion designers in South Carolina. The robust correlation we observed aligns with their observations and extends their work by elucidating an unexpected association with international energy consumption patterns. It is as if these prior studies unwittingly laid the runway for our scholarly exploration of the unanticipated fusion of fashion and fuel.

Furthermore, the work of Jones (2018) on energy usage in Eastern Europe provides a crucial context for our investigation, serving as a parallel thread in the intricate tapestry of our findings. The broader socioeconomic analyses of the respective industries by Fashionista and Aviation Economist, while seemingly divergent, inadvertently set the stage for our scrutiny of the symbiosis between the two domains. These scholarly contributions, albeit not explicitly aiming to link fashion designers in South Carolina and jet fuel usage in Bulgaria, inadvertently served as a supporting fabric for our own findings.

The inclusion of literary and cultural references in our literature review, such as "The Devil Wears Prada" and the "Fashion vs. Fuel" meme, might initially appear tangential. However, these lighthearted allusions subtly underscore the whimsical and unpredictable nature of the industries under investigation. They impishly nod to the interconnections and juxtapositions that our rigorous data analysis has now substantiated.

The statistical results from our research echo the sentiment expressed by a refined tailored suit or an impeccably designed dress – providing a robust fit (or in statistical terms, a high r-squared value) between the number of fashion designers in South Carolina and jet fuel consumption in Bulgaria. The strong correlation coefficient of 0.8789501, akin to a sharp crease in a well-pressed garment, underscores the unexpected intertwining of these variables. The level of significance, with a p-value less than 0.01, adds a layer of confidence to our findings, akin to the seam-strength of a finely crafted textile.

In closing, our findings uncover a puzzle worthy of unraveling, akin to a fashion mystery waiting to be solved. The intricate relationship between the creativity of fashion designers in South Carolina and the logistical demands of jet fuel in Bulgaria provides a rich terrain for further scholarly exploration and perhaps even a sartorially inspired twist in economic theory.

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 fashion designers in South Carolina and Jet fuel used in Bulgaria. 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]]
The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

[[ABSTRACT]]
This paper investigates a seemingly improbable connection between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration for the time period from 2004 to 2018, we uncover a striking correlation coefficient of 0.8789501 with a level of significance of p < 0.01. Our findings may seem as unexpected as discovering a high heel at a gas station, yet they highlight the intricate interplay between seemingly unrelated economic and social factors. We provide a scholarly analysis of this peculiar relationship and offer tongue-in-cheek speculations on the potential causative mechanisms and implications.

[[INTRDUCTION]]
The intertwining of seemingly disconnected phenomena in the world of economics and social dynamics has long been a source of fascination and bewilderment. In this paper, we embark on a curious journey through the labyrinth of statistics and economic data, seeking to unravel the enigmatic link between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. One might say we are delving into the nitty-gritty of fashion and fuel, exploring the stitches and seams that unite these apparently disparate industries.
At first glance, one might wonder how these two seemingly unrelated variables could possibly be correlated. After all, what connection could there possibly be between the creativity of fashion designers in the American South and the logistical demands of jet fuel in the Eastern European nation? It's as perplexing as trying to match plaid with polka dots. Nevertheless, as researchers with a penchant for unearthing the unexpected, we could not resist the allure of exploring this incongruous relationship.
As we conducted our investigation, we were initially met with skepticism and raised eyebrows. After all, the notion of a connection between couture and kerosene seems about as likely as finding a runway show at an airfield. However, our analytical pursuits bore fruit, revealing a surprising and robust correlation that cannot simply be brushed aside. The mystery deepens, and in the spirit of intellectual inquiry, we aim to shed light on this unanticipated bond with all due seriousness, despite the whimsical nature of the linkage.
In the following sections, we will dive into a detailed exploration of the empirical evidence, statistical analyses, and potential underlying mechanisms that may underpin this curious association. As we unravel the fabric of our findings, we encourage our readers to approach our scholarly endeavor with a discerning eye, perhaps even a raised eyebrow, as we delve into the unexpected and the inexplicable. The stage is set, the spotlight is on – let us now unveil the theatrics of fashion and fuel.

[[RESULTS]]
The analysis of the data collected from the Bureau of Labor Statistics and the Energy Information Administration for the period spanning from 2004 to 2018 revealed a striking correlation between the number of fashion designers in South Carolina and jet fuel consumption in Bulgaria. The correlation coefficient of 0.8789501 indicated a strong positive relationship between these seemingly incongruous variables. This coefficient, combined with the r-squared value of 0.7725532, suggests that approximately 77.26% of the variation in jet fuel usage in Bulgaria can be explained by the number of fashion designers in South Carolina, a finding that is as unexpected as encountering a tuxedo at a BP gas station.
The level of significance, with a p-value less than 0.01, adds a layer of robustness to our results, akin to finding a dependable seam in an intricately designed garment. The figure (Fig. 1) visually portrays this unexpected yet undeniable correlation, providing a scatterplot that vividly depicts the strong relationship between the two variables. This correlation almost jumps out at the viewer, much like an avant-garde fashion statement.
These findings challenge conventional wisdom and beckon researchers to explore the underlying mechanisms and implications of this improbable bond. The connection between the creativity of fashion designers in South Carolina and the logistical demands of jet fuel in Bulgaria is indeed a puzzle worth unraveling, akin to a fashion mystery waiting to be solved.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

Our investigation has uncovered an unlikely yet robust correlation between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. As unexpected as finding stilettos at a gas station, this correlation has far-reaching implications for the fields of economics, fashion, and energy. Despite the initial skepticism akin to questioning the sartorial choices of a runway model, our findings reveal a significant relationship that cannot simply be hemmed in.

The strong positive correlation coefficient of 0.8789501, accompanied by a level of significance of p < 0.01, illustrates the surprising interconnectedness of these seemingly disparate variables. This connection is as striking as discovering a high fashion photo shoot on an airport tarmac. The r-squared value of 0.7725532 suggests that approximately 77.26% of the variation in jet fuel usage in Bulgaria can be attributed to the number of fashion designers in South Carolina, a relationship as snug as a tailored suit.

As we untangle the threads of this unexpected bond, we are reminded of the profound interdependence and interplay of economic factors, reminiscent of the intricate weaving of a tapestry. It seems that the world of economics, much like a fashion runway, is full of surprises and unexpected pairings. The visual representation of this correlation in our scatterplot (Fig. 1) brings to mind the avant-garde nature of both fashion and statistical revelations, showing that sometimes the most unlikely combinations can create a striking ensemble.

Therefore, our results highlight the need for further exploration and understanding of the mechanisms underpinning this peculiar relationship. As we take our final bow and close the curtains on this study, we assert with confidence that no further research on the connection between fashion designers in South Carolina and jet fuel consumption in Bulgaria is needed. After all, we've certainly stitched together a comprehensive understanding of this unanticipated correlation, leaving no fabric unraveled or hem unsewn.

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 The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Eclectic Fashion and Global Energy Trends

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 The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria. Respond only with the name of a fictional organization.

ChatGPT:

The Global Institute for Transcontinental Fashion 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 The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria with an abstract of This paper investigates a seemingly improbable connection between the number of fashion designers in South Carolina and the jet fuel consumption in Bulgaria. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration for the time period from 2004 to 2018, we uncover a striking correlation coefficient of 0.8789501 with a level of significance of p < 0.01. Our findings may seem as unexpected as discovering a high heel at a gas station, yet they highlight the intricate interplay between seemingly unrelated economic and social factors. We provide a scholarly analysis of this peculiar relationship and offer tongue-in-cheek speculations on the potential causative mechanisms and implications.

ChatGPT:

fashion designers South Carolina, jet fuel consumption Bulgaria, correlation economics, Bureau of Labor Statistics, Energy Information Administration, causative mechanisms, social factors, economic relationships, fashion industry impact, statistical analysis, surprising correlations

*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 fashion designers in South Carolina
Detailed data title: BLS estimate of fashion designers in South Carolina
Source: Bureau of Larbor Statistics
See what else correlates with The number of fashion designers in South Carolina

Jet fuel used in Bulgaria
Detailed data title: Volume of jet fuel used consumed in Bulgaria in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Jet fuel used in Bulgaria

Correlation r = 0.8789501 (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 = 0.7725532 (Coefficient of determination)
This means 77.3% of the change in the one variable (i.e., Jet fuel used in Bulgaria) is predictable based on the change in the other (i.e., The number of fashion designers in South Carolina) over the 15 years from 2004 through 2018.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.6E-5.^Show 0.0000160025910638710500000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.88 in 0.0016% of random cases. Said differently, if you correlated 62,490 random variables^Note You don't actually need 62 thousand 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 14 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 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.

[ 0.67, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!

All values for the years included above: ^Note If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018
The number of fashion designers in South Carolina (Fashion Designers)	40	30	80	70	80	50	40	50	30	30	50	50	80	80	100
Jet fuel used in Bulgaria (Million Barrels/Day)	3.61833	4.23658	4.32348	4.71455	4.89667	3.69342	3.84551	4.01932	3.68333	3.60652	3.7586	4	5	5.43802	5.77076

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([40,30,80,70,80,50,40,50,30,30,50,50,80,80,100,])
array_2 = np.array([3.61833,4.23658,4.32348,4.71455,4.89667,3.69342,3.84551,4.01932,3.68333,3.60652,3.7586,4,5,5.43802,5.77076,])
array_1_name = "The number of fashion designers in South Carolina"
array_2_name = "Jet fuel used in Bulgaria"

# 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 fashion designers in South Carolina
Line chart for only Jet fuel used in Bulgaria
AI-generated correlation image
The spurious research paper: The Fabric of Our Findings: Exploring the Unlikely Link Between Fashion Designers in South Carolina and Jet Fuel Consumption in Bulgaria

View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!

Correlation ID: 3594 · Black Variable ID: 17355 · Red Variable ID: 24243


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