Spurious correlation #2,095 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Number of highschoolers in the US and the second variable is Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. The chart goes from 1990 to 2022, 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 Number of highschoolers in the US and the second variable is Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. The chart goes from 1990 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of highschoolers in the US increases, so does the competitive spirit. This has a ripple effect on the Nathan's Hot Dog Eating Competition champion. The youth's exuberance and hunger for success somehow translate to a surge in hotdog consumption by the reigning champion. It's a classic case of students raising the (mustard) bar, leading to a wiener-takes-all situation in the world of competitive eating. After all, when it comes to consuming hotdogs at an alarming rate, it seems that the more highschoolers there are, the greater the bun-believable achievements in the sport!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a bustling high school football stadium during a spirited game, with the stands filled with students wearing their school colors and cheering enthusiastically. In the foreground, hot dog vendors are frantically at work, serving up steaming Nathan's famous hot dogs to the excited crowd. Amidst the jubilant atmosphere, the champion of the Nathan's Hot Dog Eating Competition stands prominently in the center of the field, clutching the towering trophy and surrounded by discarded hot dog wrappers, exuding a sense of triumph and satisfaction. 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: Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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: Brutalism Steampunk Cyberpunk Photorealism Pop art
ChatGPT: Photorealism

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 Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion together. Keep the description simple.
ChatGPT: A crowded high school football stadium filled with cheering students, with hot dog vendors working overtime to keep up with the demand for Nathan's famous hot dogs. The champion of the Nathan's Hot Dog Eating Competition stands proudly at the center of the field, surrounded by empty hot dog wrappers, as he proudly holds the trophy.

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: [ Photorealism ] and depicting this scene: A crowded high school football stadium filled with cheering students, with hot dog vendors working overtime to keep up with the demand for Nathan's famous hot dogs. The champion of the Nathan's Hot Dog Eating Competition stands proudly at the center of the field, surrounded by empty hot dog wrappers, as he proudly holds the trophy. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling high school football stadium during a spirited game, with the stands filled with students wearing their school colors and cheering enthusiastically. In the foreground, hot dog vendors are frantically at work, serving up steaming Nathan's famous hot dogs to the excited crowd. Amidst the jubilant atmosphere, the champion of the Nathan's Hot Dog Eating Competition stands prominently in the center of the field, clutching the towering trophy and surrounded by discarded hot dog wrappers, exuding a sense of triumph and satisfaction.

*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 Number of highschoolers in the US caused Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

The Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

Journal of Gastronomical Sociology

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 Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make lots of 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
The Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

[[ABSTRACT]]
This study aims to delve into the apparent link between the number of highschoolers in the US and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition. Despite the seemingly unrelated nature of the two variables, our research uncovers a striking correlation coefficient of 0.9238591 and p < 0.01 for the years 1990 to 2022. The findings suggest a potential hidden influence of highschoolers on the competitive eating world, nudging the hotdog consumption trends of the reigning champions. This curious connection may provoke further investigation into the unanticipated impact of educational demographics on gastronomic achievements.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As we delve into the realm of statistical analysis and gastronomic feats, it becomes abundantly clear that the interplay between seemingly disparate variables can often yield surprising correlations. Such is the case with our study, where we endeavor to elucidate the intriguing relationship between the number of highschoolers in the United States and the prodigious hotdog consumption of the illustrious victors of Nathan's Hot Dog Eating Competition.
While one might initially dismiss these variables as unrelated, our preliminary analysis has unearthed a correlation coefficient that could make even the staunchest skeptics raise an inquisitive eyebrow. With a coefficient of 0.9238591 and a p-value of less than 0.01 for the years 1990 to 2022, the statistical connection between these factors is as unmistakable as the scent of grilling franks at a summer barbecue.
The intersection of highschoolers and competitive binge eating may seem as outlandish as a physics professor at a chili cook-off, but our investigation aims to elucidate this enigmatic relationship with unwavering scientific rigor. By peeling back the layers of data and employing robust statistical methods, we hope to shed light on this peculiar correlation and perhaps inject a dash of levity into the typically austere world of academic research.
Even as we embark on this research endeavor, we cannot help but ponder the myriad ways in which highschoolers, hotdogs, and competitive eating intersect. Could it be the youthful exuberance fueling the contestants' gustatory endeavors, or perhaps the sheer magnitude of highschoolers collectively exerting a subliminal influence on the reigning champions' appetites?
In the grand tradition of esoteric correlations and unorthodox research pursuits, the Wiener-Take-All study promises to unravel an unexpected saga at the intersection of educational demographics and competitive consumption. Let us embark on this scholarly odyssey, armed with our data, our skepticism, and perhaps a touch of irreverent humor, to unravel the tantalizing enigma of hotdogs, highschoolers, and the savory statistics that bind them.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The apparent correlation between the number of highschoolers in the United States and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition has baffled and intrigued scholars and enthusiasts alike. While the initial connection may seem as unlikely as a unicorn in a hot dog costume, the burgeoning body of research in this domain suggests that there may be more to this curious relationship than meets the eye.

In "Statistics of Competitive Eating," Smith and Doe delve into the world of competitive eating with a focus on the tantalizing triumphs at Nathan's Hot Dog Eating Competition. Although their work primarily centers on the techniques and training regimens of competitive eaters, a passing mention is made of the potential external influences on contestants' consumption patterns. Meanwhile, Jones et al. in "Demographic Dynamics: A Comprehensive Analysis" explore the complex interplay between demographic shifts and societal phenomena, hinting at the far-reaching impact of educational demographics on seemingly unrelated spheres.

Expanding beyond the realms of traditional research, we encounter a myriad of seemingly unrelated non-fiction works that inadvertently shed light on the enigmatic correlation in question. "The Economics of Fast Food" by Ronald McDonald, not to be confused with the founder of a well-known fast-food chain, presents a comprehensive exploration of the economic forces driving the consumption of fast food, including hotdogs. Similarly, "The Highschoolers' Dilemma: From Cafeteria to Competition" seamlessly weaves together the narratives of highschoolers' dietary choices and the competitive eating landscape.

Delving into the realm of fiction, "The Hotdog Diaries" by Frank Furter and "Highschool Hijinks: A Culinary Chronicle" by Patty O'Furniture provide whimsical yet oddly resonant accounts of the intersections between highschoolers, hotdogs, and unexpected triumphs. While these works may not adhere to the rigorous standards of academic research, they offer captivating narratives that mirror the quixotic nature of our investigation.

In a serendipitous turn of events, social media posts have surfaced, providing anecdotal accounts of highschoolers expressing pride and elation at the accomplishments of Nathan's Hot Dog Eating Competition champions. The fervor and enthusiasm displayed in these posts hint at a potential undercurrent of highschoolers' influence on the competitive eating landscape, serving as an intriguing supplement to our quantitative findings.

The confluence of academic, non-fiction, and fictional literature, coupled with the anecdotal evidence from social media, serves to underscore the multifaceted nature of the inquiry at hand. As we proceed with our exploration, this eclectic blend of sources promises to inject a dash of mirth into our pursuit of unraveling the profound mysteries of highschoolers, hotdogs, and the unexpected correlations that bind them.

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 Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from National Center for Education Statistics and Wikipedia . You used data from 1990 to 2022

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 Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

[[ABSTRACT]]
This study aims to delve into the apparent link between the number of highschoolers in the US and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition. Despite the seemingly unrelated nature of the two variables, our research uncovers a striking correlation coefficient of 0.9238591 and p < 0.01 for the years 1990 to 2022. The findings suggest a potential hidden influence of highschoolers on the competitive eating world, nudging the hotdog consumption trends of the reigning champions. This curious connection may provoke further investigation into the unanticipated impact of educational demographics on gastronomic achievements.

[[INTRODUCTION]]
As we delve into the realm of statistical analysis and gastronomic feats, it becomes abundantly clear that the interplay between seemingly disparate variables can often yield surprising correlations. Such is the case with our study, where we endeavor to elucidate the intriguing relationship between the number of highschoolers in the United States and the prodigious hotdog consumption of the illustrious victors of Nathan's Hot Dog Eating Competition.
While one might initially dismiss these variables as unrelated, our preliminary analysis has unearthed a correlation coefficient that could make even the staunchest skeptics raise an inquisitive eyebrow. With a coefficient of 0.9238591 and a p-value of less than 0.01 for the years 1990 to 2022, the statistical connection between these factors is as unmistakable as the scent of grilling franks at a summer barbecue.
The intersection of highschoolers and competitive binge eating may seem as outlandish as a physics professor at a chili cook-off, but our investigation aims to elucidate this enigmatic relationship with unwavering scientific rigor. By peeling back the layers of data and employing robust statistical methods, we hope to shed light on this peculiar correlation and perhaps inject a dash of levity into the typically austere world of academic research.
Even as we embark on this research endeavor, we cannot help but ponder the myriad ways in which highschoolers, hotdogs, and competitive eating intersect. Could it be the youthful exuberance fueling the contestants' gustatory endeavors, or perhaps the sheer magnitude of highschoolers collectively exerting a subliminal influence on the reigning champions' appetites?
In the grand tradition of esoteric correlations and unorthodox research pursuits, the Wiener-Take-All study promises to unravel an unexpected saga at the intersection of educational demographics and competitive consumption. Let us embark on this scholarly odyssey, armed with our data, our skepticism, and perhaps a touch of irreverent humor, to unravel the tantalizing enigma of hotdogs, highschoolers, and the savory statistics that bind them.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To examine the curiously robust relationship between the number of highschoolers in the United States and the prodigious consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition, our research team conducted an extensive analysis utilizing data from the years 1990 to 2022. The primary sources of information included the National Center for Education Statistics and the ever-reliable treasure trove of knowledge, Wikipedia. Although some may question the veracity of data obtained from the latter, we took great care to validate the information through cross-referencing and rigorous fact-checking.

The methodology employed in this study harnessed the power of quantitative analysis, harnessing the wiles of statistical procedures to wrangle the data into submission. We merrily skipped through the fields of regression analysis and correlation coefficients, armed with a cornucopia of spreadsheet wizardry and number-crunching prowess to unveil the hidden connections between highschoolers and hotdogs. The use of such quantitative methods allowed for a systematic exploration of the relationship, free from the capricious sway of anecdotal evidence and hunches.

Furthermore, in our quest for enlightenment, we also dabbled in time series analysis, allowing us to sift through temporal patterns and unearth any temporal fluctuations in the consumption of buns and links. It was not unlike embarking on a gastronomic safari through the annals of historical data, tracking the migration of hotdog consumption trends across the years with the precision of an intrepid scientist tracking elusive prey.

In addition to these time-honored statistical methodologies, we also indulged in a spot of data visualization, crafting colorful bar charts and captivating line graphs to illustrate the trends and co-movements of our variables. With the artistry of a master chef embellishing a gourmet dish, we arranged the data points and regression lines into aesthetically pleasing visualizations, ensuring that the complex interplay between highschoolers and frankfurters would not escape the discerning eye of the observant reader.

Moreover, the research team conducted sensitivity analyses to discern the robustness of the discovered correlation, subjecting the data to rigorous stress tests and probing the connection from every conceivable angle. Just as a chef insists on multiple tastings before deeming a dish fit for the palate, we subjected our findings to relentless scrutiny, ensuring that the connection between highschoolers and hotdogs endured the harshest of statistical gustatory trials.

Ultimately, through the judicious amalgamation of statistical tools, data validation, and a hint of scholarly whimsy, we endeavored to peel back the layers of correlation between highschoolers in the U.S. and the consumption of hotdogs by the victors of Nathan's Hot Dog Eating Competition, offering a veritable feast of findings for the discerning academic palate.

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 Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

[[ABSTRACT]]
This study aims to delve into the apparent link between the number of highschoolers in the US and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition. Despite the seemingly unrelated nature of the two variables, our research uncovers a striking correlation coefficient of 0.9238591 and p < 0.01 for the years 1990 to 2022. The findings suggest a potential hidden influence of highschoolers on the competitive eating world, nudging the hotdog consumption trends of the reigning champions. This curious connection may provoke further investigation into the unanticipated impact of educational demographics on gastronomic achievements.

[[LITERATURE REVIEW]]
The apparent correlation between the number of highschoolers in the United States and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition has baffled and intrigued scholars and enthusiasts alike. While the initial connection may seem as unlikely as a unicorn in a hot dog costume, the burgeoning body of research in this domain suggests that there may be more to this curious relationship than meets the eye.
In "Statistics of Competitive Eating," Smith and Doe delve into the world of competitive eating with a focus on the tantalizing triumphs at Nathan's Hot Dog Eating Competition. Although their work primarily centers on the techniques and training regimens of competitive eaters, a passing mention is made of the potential external influences on contestants' consumption patterns. Meanwhile, Jones et al. in "Demographic Dynamics: A Comprehensive Analysis" explore the complex interplay between demographic shifts and societal phenomena, hinting at the far-reaching impact of educational demographics on seemingly unrelated spheres.
Expanding beyond the realms of traditional research, we encounter a myriad of seemingly unrelated non-fiction works that inadvertently shed light on the enigmatic correlation in question. "The Economics of Fast Food" by Ronald McDonald, not to be confused with the founder of a well-known fast-food chain, presents a comprehensive exploration of the economic forces driving the consumption of fast food, including hotdogs. Similarly, "The Highschoolers' Dilemma: From Cafeteria to Competition" seamlessly weaves together the narratives of highschoolers' dietary choices and the competitive eating landscape.
Delving into the realm of fiction, "The Hotdog Diaries" by Frank Furter and "Highschool Hijinks: A Culinary Chronicle" by Patty O'Furniture provide whimsical yet oddly resonant accounts of the intersections between highschoolers, hotdogs, and unexpected triumphs. While these works may not adhere to the rigorous standards of academic research, they offer captivating narratives that mirror the quixotic nature of our investigation.
In a serendipitous turn of events, social media posts have surfaced, providing anecdotal accounts of highschoolers expressing pride and elation at the accomplishments of Nathan's Hot Dog Eating Competition champions. The fervor and enthusiasm displayed in these posts hint at a potential undercurrent of highschoolers' influence on the competitive eating landscape, serving as an intriguing supplement to our quantitative findings.
The confluence of academic, non-fiction, and fictional literature, coupled with the anecdotal evidence from social media, serves to underscore the multifaceted nature of the inquiry at hand. As we proceed with our exploration, this eclectic blend of sources promises to inject a dash of mirth into our pursuit of unraveling the profound mysteries of highschoolers, hotdogs, and the unexpected correlations that bind them.

[[RESULTS]]
The analysis of the data collected yielded a robust and eye-catching correlation coefficient of 0.9238591 and an r-squared value of 0.8535157 for the years 1990 to 2022. With a p-value of less than 0.01, the statistical relationship between the number of highschoolers in the US and the hotdogs consumed by the Nathan's Hot Dog Eating Competition champion is as unmistakable as a condiment-drenched bun at a summer cookout.
In Figure 1, a scatterplot graphically illustrates the formidable correlation between the two variables. The plot practically screams, "Look at me, I'm as statistically significant as a jumbo-sized hotdog in a world of cocktail franks!"
This unexpected connection between highschoolers and competitive hotdog consumption prompts a veritable smorgasbord of hypothetical explanations. Perhaps the fervor of youth secretly fuels the champions' insatiable appetites or the sheer presence of highschoolers exerts a subliminal influence on the competitive eaters, akin to the scent of sizzling sausages wafting through the air.
Evidently, the insatiable hunger for hotdogs transcends the realm of mere culinary delight, weaving itself into the intricate tapestry of educational demographics with all the finesse of a master pâtissier crafting an elaborate confection.
While the unorthodox nature of this correlation may raise a few eyebrows, it certainly spices up the usually bland world of statistical analysis – much like a well-timed dash of chili powder enlivens an otherwise pedestrian dish. This unexpected confluence of educational statistics and competitive eating unveils a rich and flavorful narrative that invites further investigation, promising an eclectic blend of academic rigor and unwavering culinary curiosity.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The notable correlation coefficient of 0.9238591 and a p-value of less than 0.01 between the number of highschoolers in the US and the hotdogs consumed by the Nathan's Hot Dog Eating Competition champion substantially bolsters the accumulating evidence of this quirky relationship. Our findings align closely with the whimsical yet oddly resonant accounts in "The Hotdog Diaries" by Frank Furter and "Highschool Hijinks: A Culinary Chronicle" by Patty O'Furniture, which, although framed as works of fiction, seem to echo the unexpected correlation revealed in our empirical analysis.

It is intriguing to note that our statistical exploration mirrors the tantalizing triumphs featured in the "Statistics of Competitive Eating" by Smith and Doe, who also hinted at the potential external influences on contestants' consumption patterns. While their focus primarily lay in the techniques and training regimens of competitive eaters, our work uncovers a startling link between educational demographics and the remarkable feats at Nathan's Hot Dog Eating Competition.

The unexpected convergence of educational statistics and competitive eating provides an amply flavorful narrative, akin to a culinary delight that not only satiates but also piques the senses with its unanticipated zest. Our findings serve as a testament to the serendipitous connections that lay dormant within the labyrinth of numerical data, waiting to be unearthed with the precision of a skilled archaeologist delicately brushing away layers of soil to reveal a hidden treasure.

The formidable correlation between the number of highschoolers in the US and the hotdogs consumed by the Nathan's Hot Dog Eating Competition champion unveils a rich tapestry of enigmatic correlations, exuding the piquancy of a marinated relish dancing on the taste buds. It challenges traditional notions of causal relationships, injecting a dash of mirth into the seemingly staid discipline of statistical analysis, much like a well-timed quip enlivens a formal gathering.

With the indomitable rapport established between highschoolers and competitive hotdog consumption, our study implores further research to unpack the intricate dynamics underpinning this unexpected correlation. This foray into the uncharted terrain of educational demographics and gastronomic achievements promises an enchanting blend of academic rigor and unwavering culinary curiosity, creating a delectable fusion where science and absurdity joyfully coalesce.

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 Number of highschoolers in the US and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

[[ABSTRACT]]
This study aims to delve into the apparent link between the number of highschoolers in the US and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition. Despite the seemingly unrelated nature of the two variables, our research uncovers a striking correlation coefficient of 0.9238591 and p < 0.01 for the years 1990 to 2022. The findings suggest a potential hidden influence of highschoolers on the competitive eating world, nudging the hotdog consumption trends of the reigning champions. This curious connection may provoke further investigation into the unanticipated impact of educational demographics on gastronomic achievements.

[[INTRDUCTION]]
As we delve into the realm of statistical analysis and gastronomic feats, it becomes abundantly clear that the interplay between seemingly disparate variables can often yield surprising correlations. Such is the case with our study, where we endeavor to elucidate the intriguing relationship between the number of highschoolers in the United States and the prodigious hotdog consumption of the illustrious victors of Nathan's Hot Dog Eating Competition.
While one might initially dismiss these variables as unrelated, our preliminary analysis has unearthed a correlation coefficient that could make even the staunchest skeptics raise an inquisitive eyebrow. With a coefficient of 0.9238591 and a p-value of less than 0.01 for the years 1990 to 2022, the statistical connection between these factors is as unmistakable as the scent of grilling franks at a summer barbecue.
The intersection of highschoolers and competitive binge eating may seem as outlandish as a physics professor at a chili cook-off, but our investigation aims to elucidate this enigmatic relationship with unwavering scientific rigor. By peeling back the layers of data and employing robust statistical methods, we hope to shed light on this peculiar correlation and perhaps inject a dash of levity into the typically austere world of academic research.
Even as we embark on this research endeavor, we cannot help but ponder the myriad ways in which highschoolers, hotdogs, and competitive eating intersect. Could it be the youthful exuberance fueling the contestants' gustatory endeavors, or perhaps the sheer magnitude of highschoolers collectively exerting a subliminal influence on the reigning champions' appetites?
In the grand tradition of esoteric correlations and unorthodox research pursuits, the Wiener-Take-All study promises to unravel an unexpected saga at the intersection of educational demographics and competitive consumption. Let us embark on this scholarly odyssey, armed with our data, our skepticism, and perhaps a touch of irreverent humor, to unravel the tantalizing enigma of hotdogs, highschoolers, and the savory statistics that bind them.

[[RESULTS]]
The analysis of the data collected yielded a robust and eye-catching correlation coefficient of 0.9238591 and an r-squared value of 0.8535157 for the years 1990 to 2022. With a p-value of less than 0.01, the statistical relationship between the number of highschoolers in the US and the hotdogs consumed by the Nathan's Hot Dog Eating Competition champion is as unmistakable as a condiment-drenched bun at a summer cookout.
In Figure 1, a scatterplot graphically illustrates the formidable correlation between the two variables. The plot practically screams, "Look at me, I'm as statistically significant as a jumbo-sized hotdog in a world of cocktail franks!"
This unexpected connection between highschoolers and competitive hotdog consumption prompts a veritable smorgasbord of hypothetical explanations. Perhaps the fervor of youth secretly fuels the champions' insatiable appetites or the sheer presence of highschoolers exerts a subliminal influence on the competitive eaters, akin to the scent of sizzling sausages wafting through the air.
Evidently, the insatiable hunger for hotdogs transcends the realm of mere culinary delight, weaving itself into the intricate tapestry of educational demographics with all the finesse of a master pâtissier crafting an elaborate confection.
While the unorthodox nature of this correlation may raise a few eyebrows, it certainly spices up the usually bland world of statistical analysis – much like a well-timed dash of chili powder enlivens an otherwise pedestrian dish. This unexpected confluence of educational statistics and competitive eating unveils a rich and flavorful narrative that invites further investigation, promising an eclectic blend of academic rigor and unwavering culinary curiosity.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unearthed a startling and sausage-tially significant correlation between the number of highschoolers in the US and the hotdogs engulfed by the reigning victors of Nathan's Hot Dog Eating Competition. The robust correlation coefficient of 0.9238591 is as eye-catching as a ketchup stain on a crisp white lab coat, leaving little room to doubt the statistical significance of this peculiar relationship.

The implications of this unorthodox correlation are as tantalizing as a plump, perfectly grilled hotdog on a summer day. Could it be that the exuberant energy of high school teens indirectly fuels the voracious appetites of the competitive eating champions, or perhaps the sheer presence of so many adolescent palates subliminally steers the hotdog consumption trends of the reigning superstars?

It is clear that the connection between educational demographics and gastronomic achievements runs deeper than a bun full of condiments. As we unweave the intricate tapestry of this unexpected correlation, we are reminded that statistical analysis, much like a finely crafted dish, can hold surprising flavors and nuanced layers that captivate and confound in equal measure.

However, it is safe to say that further research in this area would be as unnecessary as bringing a bib to a competitive eating competition. The statistical bond between highschoolers and Nathan's Hot Dog Eating Competition champions is as firm as a well-grilled sausage, leaving little room for doubt and much room for amusement in the world of academically rigorous but unexpectedly entertaining research.

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 Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Gastronomical Sociology

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 Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition. Respond only with the name of a fictional organization.

ChatGPT:

The National Institute for Sausage Sciences

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 Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition with an abstract of This study aims to delve into the apparent link between the number of highschoolers in the US and the hotdogs consumed by the champion of Nathan's Hot Dog Eating Competition. Despite the seemingly unrelated nature of the two variables, our research uncovers a striking correlation coefficient of 0.9238591 and p < 0.01 for the years 1990 to 2022. The findings suggest a potential hidden influence of highschoolers on the competitive eating world, nudging the hotdog consumption trends of the reigning champions. This curious connection may provoke further investigation into the unanticipated impact of educational demographics on gastronomic achievements.

ChatGPT:

Wiener-Take-All, highschoolers US, Nathan's Hot Dog Eating Competition, correlation, champion, hotdog consumption trends, competitive eating, educational demographics, gastronomic achievements

*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

Number of highschoolers in the US
Detailed data title: Enrollment in public elementary and secondary schools: 9-12th grade
Source: National Center for Education Statistics
See what else correlates with Number of highschoolers in the US

Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion
Detailed data title: Hotdog Consumption by Nathan's Hot Dog Eating Competition Champion
Source: Wikipedia
See what else correlates with Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion

Correlation r = 0.9238591 (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 = 0.8535157 (Coefficient of determination)
This means 85.4% of the change in the one variable (i.e., Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion) is predictable based on the change in the other (i.e., Number of highschoolers in the US) over the 33 years from 1990 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.8E-14.^Show 0.0000000000000179755976393476
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 0.92 in 1.8E-12% of random cases. Said differently, if you correlated 55,630,973,726,907 random variables^Note You don't actually need 55 trillion 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 32 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 32 because we have two variables measured over a period of 33 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.

[ 0.85, 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.

	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Number of highschoolers in the US (Students)	11340800	11544400	11737300	11963100	12215400	12502200	12848800	13055900	13194900	13370700	13517100	13735900	14068800	14339500	14617900	14909300	15081100	15086500	14980000	14951700	14859700	14748900	14753200	14793700	14942900	15050100	15137900	15189500	15196300	15245900	15313500	15435500	15538500
Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion (Hotdogs eaten)	16	21.5	19	17	20	19.5	22.25	24.5	19	20.25	25	50	50.5	44.5	53.33	49	53.75	66	59	68	54	62	68	69	61	62	70	72	74	71	75	76	63

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([11340800,11544400,11737300,11963100,12215400,12502200,12848800,13055900,13194900,13370700,13517100,13735900,14068800,14339500,14617900,14909300,15081100,15086500,14980000,14951700,14859700,14748900,14753200,14793700,14942900,15050100,15137900,15189500,15196300,15245900,15313500,15435500,15538500,])
array_2 = np.array([16,21.5,19,17,20,19.5,22.25,24.5,19,20.25,25,50,50.5,44.5,53.33,49,53.75,66,59,68,54,62,68,69,61,62,70,72,74,71,75,76,63,])
array_1_name = "Number of highschoolers in the US"
array_2_name = "Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion"

# 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 Number of highschoolers in the US
Line chart for only Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion
AI-generated correlation image
The spurious research paper: The Wiener-Take-All: Exploring the Correlation Between Highschoolers in the US and Nathan's Hot Dog Eating Competition

View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!

Correlation ID: 2095 · Black Variable ID: 1306 · Red Variable ID: 500


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