about · email me · subscribe
Spurious correlation #4,414 · 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 Democratic Presidential candidate in Alabama 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

As Democratic votes in Alabama rose, so did the competitive spirit in the political arena. This surge in competition ignited a hunger for success, mirroring the insatiable appetite of a hot dog eating champion. As the political race heated up, it created a veritable 'frank-furter' frenzy, leading to a 'bundling' of support for the Democratic candidate and a parallel surge in hot dog consumption. It seems that in the race for victory, both in politics and competitive eating, the stakes have truly become 'link-ed'!

Model: dalle-3
Prompt: Generate an image that looks like it is a scene from a Pixar movie. Depict a vibrant Alabama town square, where citizens are gathering in spirited debate as the democratic votes tally climbs higher on a large digital board. Picture the reigning Nathan's Hot Dog Eating Competition champion devouring hot dogs at an astonishing pace, with the crowd cheering with each impressive bite. Capture the aroma of sizzling hot dogs filling the air, blending with the fervent political energy. Encapsulate the intertwined fervor of political and competitive eating fervor, with the surrounding excitement fueling an intense appetite, creating a delightful chaos of cheering, voting, and feasting. 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 Democrat Presidential candidate in Alabama 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: inspired by bauhaus A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s An image that looks like it is a scene from a Pixar movie High-tech A scene from Skyrim
ChatGPT: An image that looks like it is a scene from a Pixar movie

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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion, in the following situation: As Democratic votes in Alabama rose, so did the competitive spirit in the political arena. This surge in competition ignited a hunger for success, mirroring the insatiable appetite of a hot dog eating champion. As the political race heated up, it created a veritable 'frank-furter' frenzy, leading to a 'bundling' of support for the Democratic candidate and a parallel surge in hot dog consumption. It seems that in the race for victory, both in politics and competitive eating, the stakes have truly become 'link-ed'!. Keep the description simple.
ChatGPT: In a vibrant Alabama town square, the democratic votes tally climbed higher on a large digital board, as citizens gathered in spirited debate. Nearby, the reigning Nathan's Hot Dog Eating Competition champion devoured hot dogs at an astonishing pace, the crowd cheering with each impressive bite. The aroma of sizzling hot dogs filled the air, blending with the fervent political energy. As the Democratic candidate gained support, the surrounding excitement fueled an intense appetite, creating a delightful chaos of cheering, voting, and feasting, truly encapsulating the intertwined fervor of political and competitive eating fervor.

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: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In a vibrant Alabama town square, the democratic votes tally climbed higher on a large digital board, as citizens gathered in spirited debate. Nearby, the reigning Nathan's Hot Dog Eating Competition champion devoured hot dogs at an astonishing pace, the crowd cheering with each impressive bite. The aroma of sizzling hot dogs filled the air, blending with the fervent political energy. As the Democratic candidate gained support, the surrounding excitement fueled an intense appetite, creating a delightful chaos of cheering, voting, and feasting, truly encapsulating the intertwined fervor of political and competitive eating fervor. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that looks like it is a scene from a Pixar movie. Depict a vibrant Alabama town square, where citizens are gathering in spirited debate as the democratic votes tally climbs higher on a large digital board. Picture the reigning Nathan's Hot Dog Eating Competition champion devouring hot dogs at an astonishing pace, with the crowd cheering with each impressive bite. Capture the aroma of sizzling hot dogs filling the air, blending with the fervent political energy. Encapsulate the intertwined fervor of political and competitive eating fervor, with the surrounding excitement fueling an intense appetite, creating a delightful chaos of cheering, voting, and feasting.

*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 Democrat Presidential candidate in Alabama caused Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama 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 researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 0.8715312 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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Here is the title and abstract of the paper:
[[TITLE]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the realm of data analysis, unexpected correlations often leave researchers 'frankfurter'ing their brows in perplexity. One such surprising relationship we stumbled upon is the uncanny link between the amount of hot dogs consumed at Nathan's Hot Dog Eating Competition and the voting trends for the Democrat Presidential candidate in Alabama. It seems that these two unrelated entities may indeed be closer than we initially thought – akin to the bond between hot dogs and their faithful companions in a bun.

As researchers, we often find ourselves chasing correlations like a hot dog vendor in a marathon. Sometimes we find buns of intriguing patterns, and other times we encounter a sausage of statistical noise. Yet, what we discovered in this study – a startling correlation coefficient of 0.8715312 between hot dog consumption and Democrat votes – indeed begs the question of whether there's more to this link than mere statistical serendipity.

One could argue that the findings of this research lead to the idea that when it comes to voter preferences, perhaps the recipe for success involves more than just condiments – a sprinkle of hot dog consumption might just be the missing ingredient. After all, in the grand American culinary tradition, perhaps hot dogs and political elections go together like mustard and ketchup.

Intrigued by the undeniably tight bond between voting habits and hot dog consumption, we delved deeper into the data to 'ketchup' with any potential explanations, especially since we didn't want to 'relish' the opportunity to uncover new knowledge. Our approach was meticulous - pouring over the MIT Election Data and Science Lab records, sifting through Harvard Dataverse, and, of course, perusing Wikipedia to ensure our understanding of the phenomena was thorough enough to 'meat' our high academic standards.

As we navigate through the mustard and relish of this unexpected correlation, it's crucial to consider the broader implications of our findings. One cannot help but wonder if our results shed light on new ways to predict voting behaviors, or if we've simply stumbled upon an amusing anecdote in the annals of political data analysis.

In the spirit of academic inquiry, let us mull over the conundrum at hand: When it comes to predicting political leanings, is this a case of 'democracy with relish'? And furthermore, could hot dog consumption be a 'weenie' bit more telling than we've ever given it credit for? These are the burning questions we aim to address in this 'politic-ly' charged investigation.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of data analysis, unexpected correlations often leave researchers 'frankfurter'ing their brows in perplexity. One such surprising relationship we stumbled upon is the uncanny link between the amount of hot dogs consumed at Nathan's Hot Dog Eating Competition and the voting trends for the Democrat Presidential candidate in Alabama. It seems that these two unrelated entities may indeed be closer than we initially thought – akin to the bond between hot dogs and their faithful companions in a bun.
As researchers, we often find ourselves chasing correlations like a hot dog vendor in a marathon. Sometimes we find buns of intriguing patterns, and other times we encounter a sausage of statistical noise. Yet, what we discovered in this study – a startling correlation coefficient of 0.8715312 between hot dog consumption and Democrat votes – indeed begs the question of whether there's more to this link than mere statistical serendipity.
One could argue that the findings of this research lead to the idea that when it comes to voter preferences, perhaps the recipe for success involves more than just condiments – a sprinkle of hot dog consumption might just be the missing ingredient. After all, in the grand American culinary tradition, perhaps hot dogs and political elections go together like mustard and ketchup.
Intrigued by the undeniably tight bond between voting habits and hot dog consumption, we delved deeper into the data to 'ketchup' with any potential explanations, especially since we didn't want to 'relish' the opportunity to uncover new knowledge. Our approach was meticulous - pouring over the MIT Election Data and Science Lab records, sifting through Harvard Dataverse, and, of course, perusing Wikipedia to ensure our understanding of the phenomena was thorough enough to 'meat' our high academic standards.
As we navigate through the mustard and relish of this unexpected correlation, it's crucial to consider the broader implications of our findings. One cannot help but wonder if our results shed light on new ways to predict voting behaviors, or if we've simply stumbled upon an amusing anecdote in the annals of political data analysis.
In the spirit of academic inquiry, let us mull over the conundrum at hand: When it comes to predicting political leanings, is this a case of 'democracy with relish'? And furthermore, could hot dog consumption be a 'weenie' bit more telling than we've ever given it credit for? These are the burning questions we aim to address in this 'politic-ly' charged investigation.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Smith and Doe (2014) explore the complexities of political behaviors and decision-making processes in their seminal work "Voting Patterns in the Deep South." Their analysis provides valuable insights into the intricate interplay of historical, cultural, and socioeconomic factors that shape the voting preferences of Alabamians. As they untangle the intricate web of political choices, one cannot help but ponder – did they use a condiment to spice up their research?

Moving on to a more appetizing line of inquiry, Jones (2017) examines the gastronomic phenomena in "The World of Competitive Eating: From Records to Reckonings." This comprehensive study delves into the world of competitive eating, shedding light on the extraordinary feats of consumption at events such as Nathan's Hot Dog Eating Competition. The sheer volume of hot dogs devoured raises the question - are these 'wiener' take all competitions?

Transitioning to a more literary exploration of the subject matter, Orwell's "Animal Farm" offers a poignant allegory of political power and revolution. While the animals may not have had a hankering for hot dogs, their struggle for autonomy and governance resonates with the complexities of voting behaviors. One might say that the pigs in the story were trying to avoid being "roasted," but we digress.

In a strikingly similar vein, Lewis Carroll's "Alice's Adventures in Wonderland" presents a whimsical tale filled with curious characters and fantastical events. Although there are no explicit references to hot dog consumption or political allegiances, one cannot overlook the potential for a hidden message in the Mad Hatter's tea party – perhaps a sausage fest of political discourse?

Moving away from traditional literature, a recent tweet from @HotDogChamp1985 caught our attention with the astute observation, "Eating hot dogs at the speed of light, voting for Democrats with all my might #SausageParty2020." This simple yet poignant message seems to encapsulate the essence of our research - a delicious fusion of political advocacy and hot dog appreciation.

In the spirit of academic rigor, we acknowledge the unusual and seemingly absurd nature of our inquiry. However, as researchers, we must not shy away from exploring uncharted territories, even if they lead us to the bewildering intersection of hot dogs and political predilections. As we embark on this quirky expedition, we are reminded that sometimes, truth truly is 'stranger than fiction.'

With these diverse perspectives in mind, we approach our study with a blend of scholarly contemplation and a dash of humor, recognizing that the unexpected correlations in data can often serve as a source of intellectual delight.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

[[INTRODUCTION]]
In the realm of data analysis, unexpected correlations often leave researchers 'frankfurter'ing their brows in perplexity. One such surprising relationship we stumbled upon is the uncanny link between the amount of hot dogs consumed at Nathan's Hot Dog Eating Competition and the voting trends for the Democrat Presidential candidate in Alabama. It seems that these two unrelated entities may indeed be closer than we initially thought – akin to the bond between hot dogs and their faithful companions in a bun.
As researchers, we often find ourselves chasing correlations like a hot dog vendor in a marathon. Sometimes we find buns of intriguing patterns, and other times we encounter a sausage of statistical noise. Yet, what we discovered in this study – a startling correlation coefficient of 0.8715312 between hot dog consumption and Democrat votes – indeed begs the question of whether there's more to this link than mere statistical serendipity.
One could argue that the findings of this research lead to the idea that when it comes to voter preferences, perhaps the recipe for success involves more than just condiments – a sprinkle of hot dog consumption might just be the missing ingredient. After all, in the grand American culinary tradition, perhaps hot dogs and political elections go together like mustard and ketchup.
Intrigued by the undeniably tight bond between voting habits and hot dog consumption, we delved deeper into the data to 'ketchup' with any potential explanations, especially since we didn't want to 'relish' the opportunity to uncover new knowledge. Our approach was meticulous - pouring over the MIT Election Data and Science Lab records, sifting through Harvard Dataverse, and, of course, perusing Wikipedia to ensure our understanding of the phenomena was thorough enough to 'meat' our high academic standards.
As we navigate through the mustard and relish of this unexpected correlation, it's crucial to consider the broader implications of our findings. One cannot help but wonder if our results shed light on new ways to predict voting behaviors, or if we've simply stumbled upon an amusing anecdote in the annals of political data analysis.
In the spirit of academic inquiry, let us mull over the conundrum at hand: When it comes to predicting political leanings, is this a case of 'democracy with relish'? And furthermore, could hot dog consumption be a 'weenie' bit more telling than we've ever given it credit for? These are the burning questions we aim to address in this 'politic-ly' charged investigation.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between Democrat Presidential votes in Alabama and the consumption of Nathan's hot dogs, our research team embarked on a comical, yet rigorously thorough, data-gathering escapade. We conjured up a deviously clever plan that involved sifting through troves of internet archives, peeking behind the curtains of the MIT Election Data and Science Lab, teasing through the Harvard Dataverse, and gallivanting around Wikipedia to round up historical data from 1979 to 2020.

Armed with spreadsheets, calculators, and a comically oversized magnifying glass, we meticulously documented the voting patterns in Alabama for the Democrat Presidential candidate and the number of hot dogs ingested by the champions of the renowned Nathan's Hot Dog Eating Competition. Not to mention, we also shamelessly sampled a few hot dogs in the name of quality control – all in the pursuit of scientific excellence, of course.

Once we had assembled our prodigious pile of data, we concocted a convoluted yet surprisingly effective analysis that involved integrating polynomial regressions, Gaussian mixture models, and a complex algorithm that may or may not have been inspired by the competitive eating techniques of the esteemed hot dog devourers. It's safe to say that our methodology was as meticulously crafted as a hot dog bun, and as packed with flavor as the juiciest sausage.

In line with our overarching mission to uncover the hidden gems of unexplored correlations, we wielded statistical tools with the precision of a hot dog eating contest judge, carefully ferreting out insights and patterns that would have gone unnoticed by the untrained eye. We wanted to ensure that our findings were as solid as a well-cooked hot dog, with just the right amount of snap.

And, much like the surprising burst of flavor that awaits in every bite of a meticulously crafted hot dog, our methodology bore fruit in the form of a standout correlation coefficient and a p-value that, much like a well-dressed hot dog, was less than 0.01. With these statistical gems in our grasp, we confidently present our findings on the tantalizing connection between Democrat votes in Alabama and the hot dog consumption at Nathan's – because, as the old adage goes, the proof is in the pudding, or in this case, the hot dog.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 0.8715312, r-squared of 0.7595666, 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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of data analysis, unexpected correlations often leave researchers 'frankfurter'ing their brows in perplexity. One such surprising relationship we stumbled upon is the uncanny link between the amount of hot dogs consumed at Nathan's Hot Dog Eating Competition and the voting trends for the Democrat Presidential candidate in Alabama. It seems that these two unrelated entities may indeed be closer than we initially thought – akin to the bond between hot dogs and their faithful companions in a bun.
As researchers, we often find ourselves chasing correlations like a hot dog vendor in a marathon. Sometimes we find buns of intriguing patterns, and other times we encounter a sausage of statistical noise. Yet, what we discovered in this study – a startling correlation coefficient of 0.8715312 between hot dog consumption and Democrat votes – indeed begs the question of whether there's more to this link than mere statistical serendipity.
One could argue that the findings of this research lead to the idea that when it comes to voter preferences, perhaps the recipe for success involves more than just condiments – a sprinkle of hot dog consumption might just be the missing ingredient. After all, in the grand American culinary tradition, perhaps hot dogs and political elections go together like mustard and ketchup.
Intrigued by the undeniably tight bond between voting habits and hot dog consumption, we delved deeper into the data to 'ketchup' with any potential explanations, especially since we didn't want to 'relish' the opportunity to uncover new knowledge. Our approach was meticulous - pouring over the MIT Election Data and Science Lab records, sifting through Harvard Dataverse, and, of course, perusing Wikipedia to ensure our understanding of the phenomena was thorough enough to 'meat' our high academic standards.
As we navigate through the mustard and relish of this unexpected correlation, it's crucial to consider the broader implications of our findings. One cannot help but wonder if our results shed light on new ways to predict voting behaviors, or if we've simply stumbled upon an amusing anecdote in the annals of political data analysis.
In the spirit of academic inquiry, let us mull over the conundrum at hand: When it comes to predicting political leanings, is this a case of 'democracy with relish'? And furthermore, could hot dog consumption be a 'weenie' bit more telling than we've ever given it credit for? These are the burning questions we aim to address in this 'politic-ly' charged investigation.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a strong positive correlation between the number of votes for the Democrat Presidential candidate in Alabama and the amount of hot dogs consumed by the champions of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.8715312 suggests a substantial and statistically significant relationship between these two variables. This finding implies that as the consumption of hot dogs at the esteemed competition increases, so does the support for the Democratic candidate in Alabama.

It seems that the Red and Blue of the political spectrum may be best represented by ketchup and mustard after all! It appears that when it comes to the culinary delight of hot dogs, these sausages are not confined to just the picnic table, but may also have a role to play on the political plate.

Our scatterplot (Fig. 1) visually conveys the strength of this correlation, depicting the upward trend between hot dog consumption and Democrat votes over the years. One cannot help but be reminded of the words of Thomas Jefferson, who famously stated, "Life, liberty, and the pursuit of hot dogs."

In conclusion, this research highlights a surprising relationship between hot dog consumption and political preferences, raising intriguing questions about the potential influence of food on voting behaviors. Our findings may add a new dimension to the age-old question of whether "you are what you eat," or rather, "you vote as you eat."

These results beckon further investigation and discussions surrounding the intersection of food, culture, and politics, urging researchers to ponder the possibilities of predicting political leanings that transcend the traditional realm of surveys and interviews.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

[[LITERATURE REVIEW]]
Smith and Doe (2014) explore the complexities of political behaviors and decision-making processes in their seminal work "Voting Patterns in the Deep South." Their analysis provides valuable insights into the intricate interplay of historical, cultural, and socioeconomic factors that shape the voting preferences of Alabamians. As they untangle the intricate web of political choices, one cannot help but ponder – did they use a condiment to spice up their research?
Moving on to a more appetizing line of inquiry, Jones (2017) examines the gastronomic phenomena in "The World of Competitive Eating: From Records to Reckonings." This comprehensive study delves into the world of competitive eating, shedding light on the extraordinary feats of consumption at events such as Nathan's Hot Dog Eating Competition. The sheer volume of hot dogs devoured raises the question - are these 'wiener' take all competitions?
Transitioning to a more literary exploration of the subject matter, Orwell's "Animal Farm" offers a poignant allegory of political power and revolution. While the animals may not have had a hankering for hot dogs, their struggle for autonomy and governance resonates with the complexities of voting behaviors. One might say that the pigs in the story were trying to avoid being "roasted," but we digress.
In a strikingly similar vein, Lewis Carroll's "Alice's Adventures in Wonderland" presents a whimsical tale filled with curious characters and fantastical events. Although there are no explicit references to hot dog consumption or political allegiances, one cannot overlook the potential for a hidden message in the Mad Hatter's tea party – perhaps a sausage fest of political discourse?
Moving away from traditional literature, a recent tweet from @HotDogChamp1985 caught our attention with the astute observation, "Eating hot dogs at the speed of light, voting for Democrats with all my might #SausageParty2020." This simple yet poignant message seems to encapsulate the essence of our research - a delicious fusion of political advocacy and hot dog appreciation.
In the spirit of academic rigor, we acknowledge the unusual and seemingly absurd nature of our inquiry. However, as researchers, we must not shy away from exploring uncharted territories, even if they lead us to the bewildering intersection of hot dogs and political predilections. As we embark on this quirky expedition, we are reminded that sometimes, truth truly is 'stranger than fiction.'
With these diverse perspectives in mind, we approach our study with a blend of scholarly contemplation and a dash of humor, recognizing that the unexpected correlations in data can often serve as a source of intellectual delight.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between the number of votes for the Democrat Presidential candidate in Alabama and the amount of hot dogs consumed by the champions of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.8715312 suggests a substantial and statistically significant relationship between these two variables. This finding implies that as the consumption of hot dogs at the esteemed competition increases, so does the support for the Democratic candidate in Alabama.
It seems that the Red and Blue of the political spectrum may be best represented by ketchup and mustard after all! It appears that when it comes to the culinary delight of hot dogs, these sausages are not confined to just the picnic table, but may also have a role to play on the political plate.
Our scatterplot (Fig. 1) visually conveys the strength of this correlation, depicting the upward trend between hot dog consumption and Democrat votes over the years. One cannot help but be reminded of the words of Thomas Jefferson, who famously stated, "Life, liberty, and the pursuit of hot dogs."
In conclusion, this research highlights a surprising relationship between hot dog consumption and political preferences, raising intriguing questions about the potential influence of food on voting behaviors. Our findings may add a new dimension to the age-old question of whether "you are what you eat," or rather, "you vote as you eat."
These results beckon further investigation and discussions surrounding the intersection of food, culture, and politics, urging researchers to ponder the possibilities of predicting political leanings that transcend the traditional realm of surveys and interviews.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The journey of unearthing the intriguing correlation between the number of votes for the Democrat Presidential candidate in Alabama and the amount of hot dogs consumed by the champions of Nathan's Hot Dog Eating Competition has been both enlightening and, dare we say, delicious. Our results not only substantiate the prior research findings in this domain but also propel us into uncharted territories of culinary-political confluence. With a correlation coefficient of 0.8715312 – a statistical relationship strong enough to make a hearty "bacon" of an argument – our study supports the notion that these seemingly disconnected variables may, in fact, have a tangible influence on each other.

Harkening back to the appetizing literature review, the work of Smith and Doe (2014) on the voting patterns in the Deep South offers valuable groundwork for understanding the political behaviors of Alabamians. It is as if the historical, cultural, and socioeconomic factors served as the buns to our hot dog of a correlation. Similarly, Jones’ (2017) exploration of the world of competitive eating, coupled with the literary whimsy of Orwell and Carroll's texts, has provided the necessary seasoning to understand the complexities and nuances of our findings.

The unexpected robustness of our correlation may indeed prompt some skeptics to exclaim, "That's a bunch of baloney!" However, like the resilience of a well-grilled sausage, our findings have withstood rigorous statistical scrutiny and emerged as a tantalizing revelation in the realm of political science research.

In drawing a link between hot dog consumption and political preferences, our study opens a can of 'wurst' for discussion – one that transcends the mundane confines of typical electoral analyses. Is it possible that hot dogs serve as more than just a culinary delight? Could they be indicating a larger societal phenomenon, pointing towards a "bunderful" predictor of political inclinations?

As we reflect on the 'wiener'takes all competitive eating events, we can't help but marvel at the 'relish'sh potential for further lines of inquiry. Beyond the statistical realm, our findings beckon us to embark on a quest to untangle the intricate web of food culture, tradition, and their potential influences on political choices. We might even declare that in such a 'bundant' world, perhaps the phrase "you are what you eat" isn't so far-fetched after all.

With this in mind, we invite you to ponder, in the spirit of both intellectual curiosity and gastronomic delight, whether our findings indicate a spicy revelation in the realm of voting behaviors or merely illustrate a lighthearted "sausage party" of statistical chance.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Democrat Presidential candidate in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

[[ABSTRACT]]
The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption

In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.

Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.

As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

[[INTRDUCTION]]
In the realm of data analysis, unexpected correlations often leave researchers 'frankfurter'ing their brows in perplexity. One such surprising relationship we stumbled upon is the uncanny link between the amount of hot dogs consumed at Nathan's Hot Dog Eating Competition and the voting trends for the Democrat Presidential candidate in Alabama. It seems that these two unrelated entities may indeed be closer than we initially thought – akin to the bond between hot dogs and their faithful companions in a bun.
As researchers, we often find ourselves chasing correlations like a hot dog vendor in a marathon. Sometimes we find buns of intriguing patterns, and other times we encounter a sausage of statistical noise. Yet, what we discovered in this study – a startling correlation coefficient of 0.8715312 between hot dog consumption and Democrat votes – indeed begs the question of whether there's more to this link than mere statistical serendipity.
One could argue that the findings of this research lead to the idea that when it comes to voter preferences, perhaps the recipe for success involves more than just condiments – a sprinkle of hot dog consumption might just be the missing ingredient. After all, in the grand American culinary tradition, perhaps hot dogs and political elections go together like mustard and ketchup.
Intrigued by the undeniably tight bond between voting habits and hot dog consumption, we delved deeper into the data to 'ketchup' with any potential explanations, especially since we didn't want to 'relish' the opportunity to uncover new knowledge. Our approach was meticulous - pouring over the MIT Election Data and Science Lab records, sifting through Harvard Dataverse, and, of course, perusing Wikipedia to ensure our understanding of the phenomena was thorough enough to 'meat' our high academic standards.
As we navigate through the mustard and relish of this unexpected correlation, it's crucial to consider the broader implications of our findings. One cannot help but wonder if our results shed light on new ways to predict voting behaviors, or if we've simply stumbled upon an amusing anecdote in the annals of political data analysis.
In the spirit of academic inquiry, let us mull over the conundrum at hand: When it comes to predicting political leanings, is this a case of 'democracy with relish'? And furthermore, could hot dog consumption be a 'weenie' bit more telling than we've ever given it credit for? These are the burning questions we aim to address in this 'politic-ly' charged investigation.

[[RESULTS]]
The analysis of the data revealed a strong positive correlation between the number of votes for the Democrat Presidential candidate in Alabama and the amount of hot dogs consumed by the champions of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.8715312 suggests a substantial and statistically significant relationship between these two variables. This finding implies that as the consumption of hot dogs at the esteemed competition increases, so does the support for the Democratic candidate in Alabama.
It seems that the Red and Blue of the political spectrum may be best represented by ketchup and mustard after all! It appears that when it comes to the culinary delight of hot dogs, these sausages are not confined to just the picnic table, but may also have a role to play on the political plate.
Our scatterplot (Fig. 1) visually conveys the strength of this correlation, depicting the upward trend between hot dog consumption and Democrat votes over the years. One cannot help but be reminded of the words of Thomas Jefferson, who famously stated, "Life, liberty, and the pursuit of hot dogs."
In conclusion, this research highlights a surprising relationship between hot dog consumption and political preferences, raising intriguing questions about the potential influence of food on voting behaviors. Our findings may add a new dimension to the age-old question of whether "you are what you eat," or rather, "you vote as you eat."
These results beckon further investigation and discussions surrounding the intersection of food, culture, and politics, urging researchers to ponder the possibilities of predicting political leanings that transcend the traditional realm of surveys and interviews.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

As we wrap up our findings, it's time to relish in the unusual and intriguing correlation we've uncovered. The "frankly" strong relationship between hot dog consumption at Nathan's Hot Dog Eating Competition and the support for the Democrat Presidential candidate in Alabama has raised some "bundamental" questions about the link between culinary habits and political preferences.

Our results may serve as a reminder that when it comes to predicting voting behaviors, sometimes it's not just about "ketchup" polls and surveys, but also about understanding the "mustard" of unexpected influencers. It seems that hot dogs and democracy have more in common than meets the "bun" – they both involve a lot of "relish" and can leave a lasting "impression"!

In the grand scheme of things, it's clear that our research has "cut the mustard," providing a flavorful addition to the tapestry of political analysis. And as we consider the implications of our findings, perhaps it's time to ponder the deeper question: does the path to political victory truly run through a hot dog stand?

In light of these fascinating results, it seems that more research in this area would just be a bunch of "baloney"! Perhaps it's time we all "beef" up our understanding of the unorthodox connections between food and political inclinations and "relish" the unexpected insights that may emerge. As we move forward, let's not "sausage" any more time on this topic but rather savor the flavors of knowledge that our findings have brought to the table.


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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama 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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Gastronomic Research and Public Policy


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 Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption with an abstract of The Sausage Party: An Examination of the Correlation Between Democrat Presidential Votes in Alabama and Nathan's Hot Dog Consumption
In this paper, we delve into the unexpected connection between the political preferences of Alabamians and the consumption of hot dogs by the legendary eaters at Nathan's Hot Dog Eating Competition. Utilizing data from MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, we painstakingly analyzed the voting patterns for the Democrat Presidential candidate in Alabama and the number of hot dogs devoured by the champions of Nathan's contest from 1979 to 2020.
Surprisingly, our research uncovered a remarkably strong correlation coefficient of 0.8715312 with a p-value less than 0.01, illustrating a striking relationship between these seemingly unrelated variables. It seems that as Nathan's hot dog consumption rises, so too does the support for the Democratic candidate in Alabama.
As a poignant nod to our findings, we can't help but wonder if this correlation points to a "frankly" good predictor of political leanings. And in the spirit of our results, we humbly submit the question: is this a case of "democracy with relish"?

ChatGPT:

Nathan's Hot Dog Eating Competition, Democrat Presidential Votes, Alabama, correlation, hot dog consumption, MIT Election Data and Science Lab, Harvard Dataverse, Wikipedia, voting patterns, Nathan's contest champions, political preferences, Alabamians, correlation coefficient, p-value, political leanings, "democracy with relish"

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

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 = 0.8715312 (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 = 0.7595666 (Coefficient of determination)
This means 76% 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 Democratic Presidential candidate in Alabama) over the 11 years from 1979 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00047. 0.0004733078786103535400000000
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 0.87 in 0.047% of random cases. Said differently, if you correlated 2,113 random variables Which I absolutely did.
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.

[ 0.57, 0.97 ] 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 Democratic Presidential candidate in Alabama (Total votes)636730551899549506690080662165692611693933813479795696729547849624
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.
  4. 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. 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. 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([636730,551899,549506,690080,662165,692611,693933,813479,795696,729547,849624,])
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 Democratic Presidential candidate in Alabama"
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 correlation rating is out of this world!


Correlation ID: 4414 · Black Variable ID: 25946 · Red Variable ID: 500
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0