about · email me · subscribe
Spurious correlation #4,523 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Republican Presidential candidate in North Carolina and the second variable is Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion.  The chart goes from 1979 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The excitement somehow creates a surge in the demand for processed meat products, leading to a spike in hotdog consumption. Furthermore, the competitive atmosphere may subconsciously influence people to partake in their own food challenges, inadvertently boosting the hotdog industry. It's a real dog-eat-dog world out there, and the link between politics and wieners has never been more relishable!

Model: dalle-3
Prompt: Generate an image of a bustling stadium nestled amidst the picturesque North Carolina landscape. In the foreground, a crowd of people is gathered around a voting booth, visibly excited to cast their votes for the Republican Presidential candidate. Meanwhile, nearby, the air is filled with the aroma of sizzling hotdogs, and a table is adorned with a variety of hotdog toppings. At the table, the Nathan's Hot Dog Eating Competition Champion is putting on an impressive display, devouring a multitude of hotdogs. The festive atmosphere is palpable as the surrounding crowd enthusiastically joins in, enjoying hotdogs and engaging in a fun and spirited celebration. 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: Votes for the Republican Presidential candidate in North Carolina 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: Sci-fi fantacy Cybernetic art A TIME magazine cover image Photorealism A Discovery magazine cover image
ChatGPT: A Discovery magazine cover image

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 Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion, in the following situation: The excitement somehow creates a surge in the demand for processed meat products, leading to a spike in hotdog consumption. Furthermore, the competitive atmosphere may subconsciously influence people to partake in their own food challenges, inadvertently boosting the hotdog industry. It's a real dog-eat-dog world out there, and the link between politics and wieners has never been more relishable!. Keep the description simple.
ChatGPT: Amidst the North Carolina landscape, a bustling stadium roars with excitement as people gather to vote for the Republican Presidential candidate. Meanwhile, nearby, the air is filled with the aroma of sizzling hotdogs, as the Nathan's Hot Dog Eating Competition Champion sits at a table, devouring an impressive number of hotdogs. The crowd, caught up in the competitive spirit, eagerly joins in, munching on hotdogs in a fun and festive atmosphere. The link between politics and wieners has never been more relishable!

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: Amidst the North Carolina landscape, a bustling stadium roars with excitement as people gather to vote for the Republican Presidential candidate. Meanwhile, nearby, the air is filled with the aroma of sizzling hotdogs, as the Nathan's Hot Dog Eating Competition Champion sits at a table, devouring an impressive number of hotdogs. The crowd, caught up in the competitive spirit, eagerly joins in, munching on hotdogs in a fun and festive atmosphere. The link between politics and wieners has never been more relishable! Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling stadium nestled amidst the picturesque North Carolina landscape. In the foreground, a crowd of people is gathered around a voting booth, visibly excited to cast their votes for the Republican Presidential candidate. Meanwhile, nearby, the air is filled with the aroma of sizzling hotdogs, and a table is adorned with a variety of hotdog toppings. At the table, the Nathan's Hot Dog Eating Competition Champion is putting on an impressive display, devouring a multitude of hotdogs. The festive atmosphere is palpable as the surrounding crowd enthusiastically joins in, enjoying hotdogs and engaging in a fun and spirited celebration.

*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.

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 Votes for the Republican Presidential candidate in North Carolina caused Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion to increase.

AI academic paper

(Because p < 0.01)
The Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

The Journal of Gastronomic Politics

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Wikipedia to assess this nagging question. You found a correlation coefficient of 0.9607301 and p < 0.01 for 1979 to 2020.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the introduction 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 introduction section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
The Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of politics and food consumption has been a source of both fascination and levity in academic circles. While the correlation between voting patterns and culinary preferences may not seem immediately apparent, it is a topic worthy of investigation for its potential societal implications – and its potential for sparking laughter at academic conferences. In this paper, we delve into the curious relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Amidst the sea of serious scholarly inquiries, we embark on an exploration that embraces the lighthearted and offbeat. As we burrow through the data gathered from esteemed sources such as MIT Election Data and Science Lab and the Harvard Dataverse, we are met with an unexpectedly tantalizing aroma of statistical significance. The resulting findings, much like a well-cooked sausage, are bound to leave an indelible impression on our understanding of human behavior and, hopefully, invoke an appetite for academic inquiry.

On the surface, one may harbor skepticism about the relevance of these two seemingly disparate domains. Nevertheless, as we peel back the layers of statistical analysis, we uncover a correlation coefficient of 0.9607301 with a p-value that gleams like a freshly polished condiment stand – lingering below the 0.01 threshold. These figures, while maintaining a suitably serious countenance, also whisper a playful invitation to consider the tantalizing possibility of a connection between political allegiances and culinary prowess.

In our pursuit of understanding the enigmatic web of human behavior, we invite our esteemed readers to join us on this intellectual romp through the ballot box and the bun. Together, let us savor the delicious and sometimes absurd correlations that underpin our everyday existence. After all, what could be more academically fulfilling than unraveling the inexplicably interwoven threads of political leanings and competitive hotdog consumption, all while eliciting a chuckle or two along the way?


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
The Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of politics and food consumption has been a source of both fascination and levity in academic circles. While the correlation between voting patterns and culinary preferences may not seem immediately apparent, it is a topic worthy of investigation for its potential societal implications – and its potential for sparking laughter at academic conferences. In this paper, we delve into the curious relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.
Amidst the sea of serious scholarly inquiries, we embark on an exploration that embraces the lighthearted and offbeat. As we burrow through the data gathered from esteemed sources such as MIT Election Data and Science Lab and the Harvard Dataverse, we are met with an unexpectedly tantalizing aroma of statistical significance. The resulting findings, much like a well-cooked sausage, are bound to leave an indelible impression on our understanding of human behavior and, hopefully, invoke an appetite for academic inquiry.
On the surface, one may harbor skepticism about the relevance of these two seemingly disparate domains. Nevertheless, as we peel back the layers of statistical analysis, we uncover a correlation coefficient of 0.9607301 with a p-value that gleams like a freshly polished condiment stand – lingering below the 0.01 threshold. These figures, while maintaining a suitably serious countenance, also whisper a playful invitation to consider the tantalizing possibility of a connection between political allegiances and culinary prowess.
In our pursuit of understanding the enigmatic web of human behavior, we invite our esteemed readers to join us on this intellectual romp through the ballot box and the bun. Together, let us savor the delicious and sometimes absurd correlations that underpin our everyday existence. After all, what could be more academically fulfilling than unraveling the inexplicably interwoven threads of political leanings and competitive hotdog consumption, all while eliciting a chuckle or two along the way?

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The correlation between political behaviors and food consumption has been a topic of growing interest in the academic community, with a particular emphasis on uncovering unexpected and often whimsical associations. Smith et al. (2015) examined the link between voting patterns and gastronomic inclinations in their study, "Political Palates: A Statistical Analysis of Culinary Preferences and Partisan Loyalties," presenting a thought-provoking exploration of the quirky interplay between civic engagement and dietary choices. Building upon this foundation, Doe and Jones (2018) further delved into the realm of competitive eating and political affiliations in their publication, "Red, White, and Wieners: Investigating the Nexus Between Competitive Eating Champions and Political Leanings," offering intriguing insights into the intersection of voracious appetites and partisan allegiances.

As we venture into this unexpected territory, we cannot overlook the contributions of works such as "The Hotdog in History" by Smith (2009) and "Sausage Politics: A Cultural Analysis of Culinary Symbolism in Electoral Campaigns" by Doe (2012). While delving into non-fiction literature, we also find inspiration in fictional works that offer a whimsical lens through which to view the intricate connections between politics and culinary culture, including "The Hunger Games" by Collins (2008) and "A Feast for Crows" by Martin (2005). In the realm of board games, "Food Fight: The Congressional Edition" emerges as a satirical yet strangely relatable depiction of the political maneuvering that often surrounds culinary decision-making.

The infusion of humor and levity into academic discourse is both refreshing and enlightening, providing a momentarily delightful diversion from the typical scholarly rigor. In this spirit, we should embrace the opportunity to unearth unexpected correlations and indulge in the lighthearted exploration of the ballot box and the bun. After all, in the vast banquet of scholarly pursuits, there is ample room to savor the amusing and the bizarre, particularly when it comes to unraveling the peculiar nexus between Republican votes in North Carolina and the consumption of hotdogs by Nathan's Hot Dog Eating Competition Champion.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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 MIT Election Data and Science Lab, Harvard Dataverse and Wikipedia . You used data from 1979 to 2020

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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

[[INTRODUCTION]]
The intersection of politics and food consumption has been a source of both fascination and levity in academic circles. While the correlation between voting patterns and culinary preferences may not seem immediately apparent, it is a topic worthy of investigation for its potential societal implications – and its potential for sparking laughter at academic conferences. In this paper, we delve into the curious relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.
Amidst the sea of serious scholarly inquiries, we embark on an exploration that embraces the lighthearted and offbeat. As we burrow through the data gathered from esteemed sources such as MIT Election Data and Science Lab and the Harvard Dataverse, we are met with an unexpectedly tantalizing aroma of statistical significance. The resulting findings, much like a well-cooked sausage, are bound to leave an indelible impression on our understanding of human behavior and, hopefully, invoke an appetite for academic inquiry.
On the surface, one may harbor skepticism about the relevance of these two seemingly disparate domains. Nevertheless, as we peel back the layers of statistical analysis, we uncover a correlation coefficient of 0.9607301 with a p-value that gleams like a freshly polished condiment stand – lingering below the 0.01 threshold. These figures, while maintaining a suitably serious countenance, also whisper a playful invitation to consider the tantalizing possibility of a connection between political allegiances and culinary prowess.
In our pursuit of understanding the enigmatic web of human behavior, we invite our esteemed readers to join us on this intellectual romp through the ballot box and the bun. Together, let us savor the delicious and sometimes absurd correlations that underpin our everyday existence. After all, what could be more academically fulfilling than unraveling the inexplicably interwoven threads of political leanings and competitive hotdog consumption, all while eliciting a chuckle or two along the way?

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In order to explore the ostensible connection between votes for the Republican presidential candidate in North Carolina and the consumption of frankfurters by the victor of the Nathan's Hot Dog Eating Competition, a series of methodological maneuvers were concocted to extract and scrutinize the pertinent data.

First and foremost, data on electoral outcomes in North Carolina from 1979 to 2020 was culled from the MIT Election Data and Science Lab. This dataset was then lovingly massaged and tenderly seasoned to ensure its palatability for statistical analysis. The delectable morsels of information regarding the consumption of hot dogs by the illustrious champion of Nathan's Hot Dog Eating Competition were sourced largely from the unofficially official font of knowledge, Wikipedia. While some may raise an eyebrow at this choice, it is worth noting that Wikipedia has become a surprisingly reliable repository of quirky facts and figures, much like the odd assortment of condiments one might find at a hot dog stand.

Once the ingredients were gathered, a heaping serving of statistical analysis was prepared. Various correlation tests, including the Pearson correlation coefficient and its accompanying p-value, were employed to discern any discernible patterns between the two seemingly incongruous sets of data. The application of these statistical tools allowed for the detection of potential associations that might have otherwise slipped through the cracks, not unlike a particularly elusive dollop of relish.

Moreover, to ensure the robustness of our findings and to validate the validity of our suppositions, alternative statistical techniques were considered. Sensitivity analyses and permutation tests were toyed with like condiment choices at a hot dog stand, each offering a different flavor of assurance regarding the strength of the observed correlation.

In the spirit of full disclosure, it is imperative to acknowledge the inherent limitations of such an investigation. Causality, much like the elusive quest for the perfect hot dog topping, remains a complex and understudied issue in this context. Therefore, while we present our findings with the enthusiasm of a connoisseur introducing their favorite hot dog joint, we urge readers to savor this study with a pinch of scholarly skepticism.

In the end, the seasoned stew of election data and hot dog consumption statistics yielded a surprising aroma of statistical significance, driving us closer to unraveling the enigmatic tapestry of human behavior and culinary idiosyncrasies. While the road to understanding the nexus of politics and competitive eating may at times be as winding as a strand of sauerkraut, our methodological approach sought to navigate this convoluted terrain with a blend of rigorous analysis and lighthearted curiosity.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
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 results section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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 MIT Election Data and Science Lab, Harvard Dataverse and Wikipedia .

For the time period 1979 to 2020, you found a correlation 0.9607301, r-squared of 0.9230023, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of politics and food consumption has been a source of both fascination and levity in academic circles. While the correlation between voting patterns and culinary preferences may not seem immediately apparent, it is a topic worthy of investigation for its potential societal implications – and its potential for sparking laughter at academic conferences. In this paper, we delve into the curious relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.
Amidst the sea of serious scholarly inquiries, we embark on an exploration that embraces the lighthearted and offbeat. As we burrow through the data gathered from esteemed sources such as MIT Election Data and Science Lab and the Harvard Dataverse, we are met with an unexpectedly tantalizing aroma of statistical significance. The resulting findings, much like a well-cooked sausage, are bound to leave an indelible impression on our understanding of human behavior and, hopefully, invoke an appetite for academic inquiry.
On the surface, one may harbor skepticism about the relevance of these two seemingly disparate domains. Nevertheless, as we peel back the layers of statistical analysis, we uncover a correlation coefficient of 0.9607301 with a p-value that gleams like a freshly polished condiment stand – lingering below the 0.01 threshold. These figures, while maintaining a suitably serious countenance, also whisper a playful invitation to consider the tantalizing possibility of a connection between political allegiances and culinary prowess.
In our pursuit of understanding the enigmatic web of human behavior, we invite our esteemed readers to join us on this intellectual romp through the ballot box and the bun. Together, let us savor the delicious and sometimes absurd correlations that underpin our everyday existence. After all, what could be more academically fulfilling than unraveling the inexplicably interwoven threads of political leanings and competitive hotdog consumption, all while eliciting a chuckle or two along the way?

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis unveiled a remarkably robust correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Over the period from 1979 to 2020, a correlation coefficient of 0.9607301 emerged from the statistical crucible, reflecting a strong positive relationship between these seemingly unrelated variables.

We were delighted to observe an r-squared value of 0.9230023, indicating that approximately 92.3% of the variation in hotdog consumption by the Nathan's Hot Dog Eating Competition champion could be explained by the variation in Republican votes in North Carolina. This finding, much like a perfectly crafted hotdog, was both surprising and satisfying.

Furthermore, the p-value of less than 0.01 suggested a level of statistical significance that would make even the most discerning hotdog connoisseur nod in approval. The relationship between these variables stood firm under rigorous scrutiny, beckoning us to ponder the uncanny alignment of political persuasion and competitive hotdog consumption with a mixture of amusement and scholarly intrigue.

In Fig. 1, the scatterplot lays bare the compelling correlation we uncovered. The data points, akin to a smorgasbord of political and gastronomic inclinations, coalesce into a visual representation of the unmistakable association between Republican votes and hotdog ingestion prowess. The figure stands as a testament to the unexpected entanglement of civic engagement and gustatory feats, inviting both appreciation for its scientific value and a chuckle at the whimsical nature of human behavior.

These findings proffer an insightful glimpse into the capricious dance of political allegiances and culinary proclivities, underscoring the delightful eccentricities that permeate our societal tapestry. The correlation identified in this study, while initially cloaked in the mundane garb of statistical analysis, reveals a compelling narrative of human behavior that transcends the confines of conventional research inquiries.

These results, much like a perfectly grilled hotdog, leave a lingering impression that is both intellectually nourishing and humorously whimsical, underscoring the intricate connections that abound in our world – and reminding us that academia can indeed be a place of serious inquiry and joyous revelry, sometimes at the same time.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

[[LITERATURE REVIEW]]
The correlation between political behaviors and food consumption has been a topic of growing interest in the academic community, with a particular emphasis on uncovering unexpected and often whimsical associations. Smith et al. (2015) examined the link between voting patterns and gastronomic inclinations in their study, "Political Palates: A Statistical Analysis of Culinary Preferences and Partisan Loyalties," presenting a thought-provoking exploration of the quirky interplay between civic engagement and dietary choices. Building upon this foundation, Doe and Jones (2018) further delved into the realm of competitive eating and political affiliations in their publication, "Red, White, and Wieners: Investigating the Nexus Between Competitive Eating Champions and Political Leanings," offering intriguing insights into the intersection of voracious appetites and partisan allegiances.
As we venture into this unexpected territory, we cannot overlook the contributions of works such as "The Hotdog in History" by Smith (2009) and "Sausage Politics: A Cultural Analysis of Culinary Symbolism in Electoral Campaigns" by Doe (2012). While delving into non-fiction literature, we also find inspiration in fictional works that offer a whimsical lens through which to view the intricate connections between politics and culinary culture, including "The Hunger Games" by Collins (2008) and "A Feast for Crows" by Martin (2005). In the realm of board games, "Food Fight: The Congressional Edition" emerges as a satirical yet strangely relatable depiction of the political maneuvering that often surrounds culinary decision-making.
The infusion of humor and levity into academic discourse is both refreshing and enlightening, providing a momentarily delightful diversion from the typical scholarly rigor. In this spirit, we should embrace the opportunity to unearth unexpected correlations and indulge in the lighthearted exploration of the ballot box and the bun. After all, in the vast banquet of scholarly pursuits, there is ample room to savor the amusing and the bizarre, particularly when it comes to unraveling the peculiar nexus between Republican votes in North Carolina and the consumption of hotdogs by Nathan's Hot Dog Eating Competition Champion.

[[RESULTS]]
The results of our analysis unveiled a remarkably robust correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Over the period from 1979 to 2020, a correlation coefficient of 0.9607301 emerged from the statistical crucible, reflecting a strong positive relationship between these seemingly unrelated variables.
We were delighted to observe an r-squared value of 0.9230023, indicating that approximately 92.3% of the variation in hotdog consumption by the Nathan's Hot Dog Eating Competition champion could be explained by the variation in Republican votes in North Carolina. This finding, much like a perfectly crafted hotdog, was both surprising and satisfying.
Furthermore, the p-value of less than 0.01 suggested a level of statistical significance that would make even the most discerning hotdog connoisseur nod in approval. The relationship between these variables stood firm under rigorous scrutiny, beckoning us to ponder the uncanny alignment of political persuasion and competitive hotdog consumption with a mixture of amusement and scholarly intrigue.
In Fig. 1, the scatterplot lays bare the compelling correlation we uncovered. The data points, akin to a smorgasbord of political and gastronomic inclinations, coalesce into a visual representation of the unmistakable association between Republican votes and hotdog ingestion prowess. The figure stands as a testament to the unexpected entanglement of civic engagement and gustatory feats, inviting both appreciation for its scientific value and a chuckle at the whimsical nature of human behavior.
These findings proffer an insightful glimpse into the capricious dance of political allegiances and culinary proclivities, underscoring the delightful eccentricities that permeate our societal tapestry. The correlation identified in this study, while initially cloaked in the mundane garb of statistical analysis, reveals a compelling narrative of human behavior that transcends the confines of conventional research inquiries.
These results, much like a perfectly grilled hotdog, leave a lingering impression that is both intellectually nourishing and humorously whimsical, underscoring the intricate connections that abound in our world – and reminding us that academia can indeed be a place of serious inquiry and joyous revelry, sometimes at the same time.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings have unearthed a captivating relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. With a correlation coefficient of 0.9607301, the alignment between these apparently distinctive phenomena is as compelling as it is eyebrow-raising. Our results not only echo the work of Smith et al. (2015) and Doe and Jones (2018) but also reinforce the notion that the ballot box and the bun may be more closely entwined than previously envisaged.

The robustness of our correlation, akin to the smoky flavor of a well-grilled hotdog, is supported by the notion that approximately 92.3% of the variation in hotdog consumption by the Nathan's Hot Dog Eating Competition champion can be elucidated by the variation in Republican votes in North Carolina. This lends credence to the whimsical yet meaningful musings of Smith (2009) and Doe (2012) regarding the nuanced interplay of culinary symbolism in electoral campaigns. As we digest these results, it becomes clear that the synergistic relationship between political allegiances and competitive hotdog consumption is not merely a flavor of the month but a recurring motif in the culinary theater of American politics.

The statistical significance of our findings, with a p-value of less than 0.01, serves as a firm nod to the alignment of these variables, reminiscent of the nod of approval one might give to a perfectly constructed hotdog. Our study not only underscores the inherent peculiarity of human behavior but also highlights the delightful interconnectedness of seemingly disparate facets of our societal fabric.

The scatterplot, much like a visual feast for the scholarly eye, offers a compelling portrayal of the unanticipated association between Republican votes and hotdog prowess. It stands as a testament to the veritable confluence of civic engagement and gastronomic feats, urging us to marvel at the whimsical nature of human proclivities while appreciating the scholarly rigor underpinning this discovery. Our results, like a well-spiced hotdog, elicit a simultaneous appreciation for the quirkiness of human behavior and the scholarly pursuit of meaningful insights.

In conclusion, our study nuances the intricate web of connections between political behaviors and culinary indulgences. As we savor the interplay of statistical robustness and whimsical revelations, we are reminded that even in the serious domain of academic research, there is always room for a dash of humor and the unexpected – much like finding pickles in unexpected places.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Republican Presidential candidate in North Carolina and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. 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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

[[INTRDUCTION]]
The intersection of politics and food consumption has been a source of both fascination and levity in academic circles. While the correlation between voting patterns and culinary preferences may not seem immediately apparent, it is a topic worthy of investigation for its potential societal implications – and its potential for sparking laughter at academic conferences. In this paper, we delve into the curious relationship between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.
Amidst the sea of serious scholarly inquiries, we embark on an exploration that embraces the lighthearted and offbeat. As we burrow through the data gathered from esteemed sources such as MIT Election Data and Science Lab and the Harvard Dataverse, we are met with an unexpectedly tantalizing aroma of statistical significance. The resulting findings, much like a well-cooked sausage, are bound to leave an indelible impression on our understanding of human behavior and, hopefully, invoke an appetite for academic inquiry.
On the surface, one may harbor skepticism about the relevance of these two seemingly disparate domains. Nevertheless, as we peel back the layers of statistical analysis, we uncover a correlation coefficient of 0.9607301 with a p-value that gleams like a freshly polished condiment stand – lingering below the 0.01 threshold. These figures, while maintaining a suitably serious countenance, also whisper a playful invitation to consider the tantalizing possibility of a connection between political allegiances and culinary prowess.
In our pursuit of understanding the enigmatic web of human behavior, we invite our esteemed readers to join us on this intellectual romp through the ballot box and the bun. Together, let us savor the delicious and sometimes absurd correlations that underpin our everyday existence. After all, what could be more academically fulfilling than unraveling the inexplicably interwoven threads of political leanings and competitive hotdog consumption, all while eliciting a chuckle or two along the way?

[[RESULTS]]
The results of our analysis unveiled a remarkably robust correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Over the period from 1979 to 2020, a correlation coefficient of 0.9607301 emerged from the statistical crucible, reflecting a strong positive relationship between these seemingly unrelated variables.
We were delighted to observe an r-squared value of 0.9230023, indicating that approximately 92.3% of the variation in hotdog consumption by the Nathan's Hot Dog Eating Competition champion could be explained by the variation in Republican votes in North Carolina. This finding, much like a perfectly crafted hotdog, was both surprising and satisfying.
Furthermore, the p-value of less than 0.01 suggested a level of statistical significance that would make even the most discerning hotdog connoisseur nod in approval. The relationship between these variables stood firm under rigorous scrutiny, beckoning us to ponder the uncanny alignment of political persuasion and competitive hotdog consumption with a mixture of amusement and scholarly intrigue.
In Fig. 1, the scatterplot lays bare the compelling correlation we uncovered. The data points, akin to a smorgasbord of political and gastronomic inclinations, coalesce into a visual representation of the unmistakable association between Republican votes and hotdog ingestion prowess. The figure stands as a testament to the unexpected entanglement of civic engagement and gustatory feats, inviting both appreciation for its scientific value and a chuckle at the whimsical nature of human behavior.
These findings proffer an insightful glimpse into the capricious dance of political allegiances and culinary proclivities, underscoring the delightful eccentricities that permeate our societal tapestry. The correlation identified in this study, while initially cloaked in the mundane garb of statistical analysis, reveals a compelling narrative of human behavior that transcends the confines of conventional research inquiries.
These results, much like a perfectly grilled hotdog, leave a lingering impression that is both intellectually nourishing and humorously whimsical, underscoring the intricate connections that abound in our world – and reminding us that academia can indeed be a place of serious inquiry and joyous revelry, sometimes at the same time.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has brought to light the surprisingly strong correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. The compelling correlation coefficient of 0.9607301, reminiscent of a perfectly twisted sausage, has intrigued us and left us craving more insights into this delightfully quirky association.

While our findings emphasize the statistical significance of the relationship between political leanings and competitive hotdog consumption, it also beckons us to ponder the deeper connections that transcend the world of numbers and p-values. As we reflect on the whimsical nature of these intertwined realms, we can't help but wonder about the potential societal implications of this correlation. Who would have thought that political preferences and hotdog-eating prowess would share such an intriguing connection? It's as if every ballot cast and every bite taken contribute to a grand symphony of unexpected harmonies.

As we close the lid on this particular chapter of inquiry, we are left with a profound appreciation for the delightful idiosyncrasies that permeate our world. This study serves as a gentle reminder that even the most peculiar correlations can offer valuable insights, not to mention a hearty chuckle or two. After all, every statistical analysis can benefit from a dash of humor and a sprinkling of levity!

In the spirit of academic inquiry and perhaps an unabashed love of puns, we assert that no more research is needed in this area. It's safe to say that we've relished this investigation to the fullest, and it's time to pass the mustard onto new research endeavors. Cheers to uncovering the unexpected, even if it involves a few hotdogs along the way.


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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Gastronomic Politics


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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Gastronomic Politics and Electoral 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 Ballot Box and the Bun: A Correlative Study of Republican Votes in North Carolina and Nathan's Hot Dog Consumption with an abstract of The impact of political affiliations on culinary choices has been a topic of interest across various disciplines. In this study, we present a comprehensive analysis of the correlation between votes for the Republican presidential candidate in North Carolina and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we unearth a striking correlation coefficient of 0.9607301 with a p-value of less than 0.01, spanning from 1979 to 2020. Our findings unravel an intricate association between political leanings and competitive eating, shedding light on a curious interplay between civic engagement and gastronomic inclinations. This study provides an amusing yet compelling insight into the nexus of political allegiances and the savory world of competitive hotdog consumption.

ChatGPT:

Republican votes, North Carolina, Nathan's Hot Dog Consumption, correlation, political affiliations, culinary choices, MIT Election Data and Science Lab, Harvard Dataverse, Republican presidential candidate, correlation coefficient, p-value, competitive eating, civic engagement, gastronomic inclinations, political allegiances, hotdog consumption, Nathan's Hot Dog Eating Competition, correlation analysis, savory world, voting patterns

*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

Votes for the Republican Presidential candidate in North Carolina
Detailed data title: Total votes cast for the Republican Presidential candidate in North Carolina
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Republican Presidential candidate in North Carolina

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 = 0.9607301 (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 = 0.9230023 (Coefficient of determination)
This means 92.3% 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., Votes for the Republican Presidential candidate in North Carolina) over the 11 years from 1979 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.61E-6. 0.0000026066657276862550000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. 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 0.96 in 0.000261% of random cases. Said differently, if you correlated 383,632 random variables You don't actually need 383 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 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
19801984198819921996200020042008201220162020
Votes for the Republican Presidential candidate in North Carolina (Total votes)9150181346480123726011346601225940163116019611702128470227040023626302758770
Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion (Hotdogs eaten)9.59.5101922.252553.3359687075




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([915018,1346480,1237260,1134660,1225940,1631160,1961170,2128470,2270400,2362630,2758770,])
array_2 = np.array([9.5,9.5,10,19,22.25,25,53.33,59,68,70,75,])
array_1_name = "Votes for the Republican Presidential candidate in North Carolina"
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. 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:


View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!


Correlation ID: 4523 · Black Variable ID: 26015 · Red Variable ID: 500
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0