Spurious correlation #4,304 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Republican votes for Senators 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.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Republican votes for Senators 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.

AI explanation

As Republican votes for Senators in Alabama increased, it led to a rise in support for local businesses, including the beef industry. This ultimately resulted in more resources and promotion for Nathan's Famous, encouraging people to relish in their hot dogs. It seems like in this case, "voting red" really did mean a "wiener winner" for the hot dog eating competition!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a bustling city street in Alabama, with a prominent Nathan's Famous hot dog stand at the center. On the left, show a large display board with the election results, indicating a steady increase in Republican votes for Senators. Meanwhile, at the hot dog stand, visual the reigning champion joyfully devouring an impressive pile of hot dogs, surrounded by a cheering crowd. The increased support for the beef industry should be evident, with imagery symbolizing a surge in hot dog consumption and thriving local businesses. The visual should convey the sense of celebration and victory, with the champion relishing in his achievement. 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: Republican votes for Senators 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: Glitch art An image that looks like it is a scene from A Disney Movie Vaporwave A TIME magazine cover image a funny image you would see on reddit
ChatGPT: A TIME 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 Republican votes for Senators in Alabama and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion, in the following situation: As Republican votes for Senators in Alabama increased, it led to a rise in support for local businesses, including the beef industry. This ultimately resulted in more resources and promotion for Nathan's Famous, encouraging people to relish in their hot dogs. It seems like in this case, "voting red" really did mean a "wiener winner" for the hot dog eating competition!. Keep the description simple.
ChatGPT: In a bustling Alabama town, the election results show a steady increase in Republican votes for Senators. Meanwhile, at the local Nathan's Famous hot dog stand, the reigning champion joyfully devours an impressive pile of hot dogs, as the crowd cheers him on. The increased support for the beef industry has led to a surge in hot dog consumption, with the champion relishing in the victory of both the competition and the thriving local businesses.

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 TIME magazine cover image ] and depicting this scene: In a bustling Alabama town, the election results show a steady increase in Republican votes for Senators. Meanwhile, at the local Nathan's Famous hot dog stand, the reigning champion joyfully devours an impressive pile of hot dogs, as the crowd cheers him on. The increased support for the beef industry has led to a surge in hot dog consumption, with the champion relishing in the victory of both the competition and the thriving local businesses. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a bustling city street in Alabama, with a prominent Nathan's Famous hot dog stand at the center. On the left, show a large display board with the election results, indicating a steady increase in Republican votes for Senators. Meanwhile, at the hot dog stand, visual the reigning champion joyfully devouring an impressive pile of hot dogs, surrounded by a cheering crowd. The increased support for the beef industry should be evident, with imagery symbolizing a surge in hot dog consumption and thriving local businesses. The visual should convey the sense of celebration and victory, with the champion relishing in his achievement.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Republican votes for Senators 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)

All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts

The Journal of Irreverent Political Science

Jan 2024

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

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Republican votes for Senators 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts

[[ABSTRACT]]
This paper investigates the purported connection between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, this study delves into the correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8624844 and p < 0.01 for the years spanning from 1979 to 2020.

We aim to provide some much-needed levity to the field of political and culinary analysis by exploring this light-hearted relationship. With the seriousness of our academic pursuits, one might say we relish in the opportunity to bring a little humor to the table. Our research does not only weigh the evidence but also adds some flavor to the discussions. Through our data-driven analysis, we strive to mustard the mental fortitude needed to tackle such contentious and tangy topics.

Ultimately, our research highlights the unexpected connections and curiosities that exist in the world, serving as a reminder that even the most unlikely correlations can be food for thought. The results of this study could potentially inspire further investigations into the intersection of politics and competitive eating, ultimately showcasing the multifaceted nature of societal interests and tastes.

In conclusion, while the findings of this research may leave some readers bun-believers, we hope that our lighthearted approach will encourage further exploration of unconventional connections and inspire a smattering of relatable chuckles along the way.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of politics and culinary indulgence has long been a subject of curiosity, with controversies such as "Is a hotdog a sandwich?" continually sparking heated debates. However, our investigation delves into a somewhat less contentious, yet equally intriguing question: What is the relationship, if any, between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion? We assure the reader that our inquiry is much more than a mere sausage fest of statistical analysis.
This study takes an earnest yet light-hearted approach to uncovering any potential connection between these two seemingly unrelated variables. As we leap into the realm of data analysis, one might say we're relishing the chance to add some zing to the often-mundane corridors of academia. After all, who says academic research can't have a little mustard on top?
The aim of this research is not only to uncover any patterns or correlations but also to inject a dose of mirth into the otherwise stoic world of statistical analysis. With this approach, we hope to ketchup with our readers' interests and ensure that our findings are not just a blend of raw data but also a humorous, yet informative, serving. It is with this saucy outlook that we begin our exploration of the peculiar ties that bind political preferences and competitive hotdog consumption.
As we delve into the statistical relationships between Republican votes and hotdog gobbling, we are reminded of the old adage: "You can't make an omelet without breaking eggs." Similarly, one might argue, "You can't conduct statistical analysis without making a few puns along the way." And so, armed with data and a sprinkle of humor, we embark on this scholarly escapade, eager to present our findings to an audience that might appreciate a research paper spiced with a dash of levity.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith and Doe (2005) assert that the consumption of hotdogs has been a long-standing tradition in American culture, often associated with outdoor barbecues and baseball games. Similarly, Jones (2010) emphasizes the historical significance of political elections in shaping the socio-cultural landscape of a nation. However, what these studies fail to address is the potential interplay between these seemingly distinct areas of interest.

In "Hot Dogs: A Global History," Bruce Kraig traces the cultural significance of hotdogs in various societies, shedding light on their enduring appeal. Meanwhile, "The Power and the Glory" by Graham Greene delves into the intricate dynamics of power struggles, albeit in a context far removed from the realm of culinary competitions.

In the realm of cinema, the striking parallels between the political arena and the competitive eating circuit are poignantly depicted in "The American President" and "The Great Outdoors." While these films do not directly address the specific connection between Republican votes in Alabama and the consumption of hotdogs by competitive eaters, they offer valuable insights into the complexities of human behavior and societal norms.

Evidently, the literature on this subject matter is sorely lacking, much like a hotdog without its condiments. Our study aims to bridge this gap by unraveling the enigmatic correlation between Republican votes for Senators in Alabama and the hotdog consumption habits of Nathan's Hot Dog Eating Competition Champion. One might say we're on a roll with this endeavor, hoping to add some relish to the scholarly discourse.

In "The Guinness Book of World Records," researchers highlight the astonishing feats accomplished by individuals, including record-breaking hotdog consumption. Despite its focus on records of various kinds, the book fails to delve into the potential political ramifications of competitive eating achievements.

Moreover, "The Da Vinci Code" by Dan Brown offers a riveting exploration of cryptic connections and hidden truths, albeit in a completely different context. While the novel does not directly address the correlation under investigation, its themes of unraveling mysteries are certainly apropos to our research aims.

The cinematic masterpiece "Forrest Gump" charmingly captures the ethos of American culture and history, featuring scenes of Gump's unwitting involvement in major events. Although the film does not explicitly touch upon the nexus of political votes and competitive eating, its portrayal of serendipitous occurrences certainly resonates with the unexpected nature of our research subject.

In "The Silence of the Lambs," the complex relationship between individuals and their consumption choices is explored in a riveting thriller, albeit in a considerably darker context. While the novel's focus is distinct from the lighthearted nature of our inquiry, its examination of human appetites may offer intriguing parallels to our study's exploration of consumption patterns.

Our research endeavors to add a dash of humor to the often staid world of scholarly investigation, spotlighting the whimsical connections that lie beneath the surface. In defiance of conventional academic rigor, we embark on this scholarly escapade with a dollop of jest, inviting readers to join us in unraveling the peculiar ties that bind political preferences and competitive hotdog consumption.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Republican votes for Senators 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts

[[ABSTRACT]]
This paper investigates the purported connection between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, this study delves into the correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8624844 and p < 0.01 for the years spanning from 1979 to 2020.

We aim to provide some much-needed levity to the field of political and culinary analysis by exploring this light-hearted relationship. With the seriousness of our academic pursuits, one might say we relish in the opportunity to bring a little humor to the table. Our research does not only weigh the evidence but also adds some flavor to the discussions. Through our data-driven analysis, we strive to mustard the mental fortitude needed to tackle such contentious and tangy topics.

Ultimately, our research highlights the unexpected connections and curiosities that exist in the world, serving as a reminder that even the most unlikely correlations can be food for thought. The results of this study could potentially inspire further investigations into the intersection of politics and competitive eating, ultimately showcasing the multifaceted nature of societal interests and tastes.

In conclusion, while the findings of this research may leave some readers bun-believers, we hope that our lighthearted approach will encourage further exploration of unconventional connections and inspire a smattering of relatable chuckles along the way.

[[LITERATURE REVIEW]]
Smith and Doe (2005) assert that the consumption of hotdogs has been a long-standing tradition in American culture, often associated with outdoor barbecues and baseball games. Similarly, Jones (2010) emphasizes the historical significance of political elections in shaping the socio-cultural landscape of a nation. However, what these studies fail to address is the potential interplay between these seemingly distinct areas of interest.
In "Hot Dogs: A Global History," Bruce Kraig traces the cultural significance of hotdogs in various societies, shedding light on their enduring appeal. Meanwhile, "The Power and the Glory" by Graham Greene delves into the intricate dynamics of power struggles, albeit in a context far removed from the realm of culinary competitions.
In the realm of cinema, the striking parallels between the political arena and the competitive eating circuit are poignantly depicted in "The American President" and "The Great Outdoors." While these films do not directly address the specific connection between Republican votes in Alabama and the consumption of hotdogs by competitive eaters, they offer valuable insights into the complexities of human behavior and societal norms.
Evidently, the literature on this subject matter is sorely lacking, much like a hotdog without its condiments. Our study aims to bridge this gap by unraveling the enigmatic correlation between Republican votes for Senators in Alabama and the hotdog consumption habits of Nathan's Hot Dog Eating Competition Champion. One might say we're on a roll with this endeavor, hoping to add some relish to the scholarly discourse.
In "The Guinness Book of World Records," researchers highlight the astonishing feats accomplished by individuals, including record-breaking hotdog consumption. Despite its focus on records of various kinds, the book fails to delve into the potential political ramifications of competitive eating achievements.
Moreover, "The Da Vinci Code" by Dan Brown offers a riveting exploration of cryptic connections and hidden truths, albeit in a completely different context. While the novel does not directly address the correlation under investigation, its themes of unraveling mysteries are certainly apropos to our research aims.
The cinematic masterpiece "Forrest Gump" charmingly captures the ethos of American culture and history, featuring scenes of Gump's unwitting involvement in major events. Although the film does not explicitly touch upon the nexus of political votes and competitive eating, its portrayal of serendipitous occurrences certainly resonates with the unexpected nature of our research subject.
In "The Silence of the Lambs," the complex relationship between individuals and their consumption choices is explored in a riveting thriller, albeit in a considerably darker context. While the novel's focus is distinct from the lighthearted nature of our inquiry, its examination of human appetites may offer intriguing parallels to our study's exploration of consumption patterns.
Our research endeavors to add a dash of humor to the often staid world of scholarly investigation, spotlighting the whimsical connections that lie beneath the surface. In defiance of conventional academic rigor, we embark on this scholarly escapade with a dollop of jest, inviting readers to join us in unraveling the peculiar ties that bind political preferences and competitive hotdog consumption.

[[RESULTS]]
The analysis of the data collected from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia revealed a significant correlation between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. The correlation coefficient was found to be 0.8624844, indicating a strong positive relationship between the two variables. One might say these findings are nothing to "relish," as the strength of the correlation lends credence to the notion that political leanings may indeed impact the consumption of competitive quantities of hotdogs.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.7438794. This value suggests that approximately 74.39% of the variability in hotdog consumption can be explained by the number of Republican votes for Senators in Alabama. Put simply, this means that the political landscape in Alabama appears to have a notable influence on the hotdog-eating tendencies of the champion at Nathan's annual competition. Who would have thought that political allegiances could leave such a "stomach-churning" impression on competitive eating habits?
The p-value obtained from the analysis was less than 0.01, signifying that the observed correlation is statistically significant. It appears that the relationship between political voting patterns and competitive hotdog consumption is not just a fluke, but rather a meaningful and persistent phenomenon. One could argue that these results are not just a "frank" observation, but a tantalizing insight into the uncharted territory of political-culinary correlations.
The aforementioned results are succinctly visualized in the scatterplot presented in Figure 1. The scatterplot illustrates the strong positive correlation between Republican votes for Senators in Alabama and the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition Champion over the years. The data points are clustered in a notably linear fashion, further bolstering the assertion that these two variables are intimately connected. It seems that in the realm of competitive hotdog consumption, the political climate plays a significant role—a correlation worth "relishing," indeed.
One may be tempted to brush off these findings as mere coincidence, but as the saying goes, "When there's smoke, there's fire"—or in this case, "Where there are votes, there are hotdogs." These results prompt a reconsideration of the seemingly disparate realms of politics and indulgent eating, underscoring the need for further research into the unexpected ties that bind them. After all, who wouldn't relish the opportunity to explore the broad spectrum of societal and gustatory influences on competitive eating habits?
In conclusion, our findings not only shed light on the peculiar correlation between Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion but also serve as a testament to the delightful surprises that await in the intersection of political and culinary spheres. It is our hope that these results serve as a springboard for future investigations into the uncharted territory of unconventional correlations and inspire an appetite for statistical research that is both informative and peppered with a dash of humor. After all, in the world of academia, a little levity can go a long way in making data-driven discoveries more palatable and engaging.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our investigation has yielded intriguing insights into the seemingly whimsical yet surprisingly robust relationship between Republican votes for Senators in Alabama and the consumption of hotdogs by the illustrious champion of the Nathan's Hot Dog Eating Competition. Our findings not only support, but also tangibly bolster, prior research that has hinted at the potential interplay between sociopolitical preferences and prodigious hotdog ingestion. Who would have thought that the southern political climate could have such a significant impact on the competitive consumption of everyone's favorite encased meat product?

The substantial correlation coefficient of 0.8624844, evident across the years from 1979 to 2020, emphatically underscores the tight link between these ostensibly incongruous variables. It's safe to say that when it comes to political leanings and competitive hotdog consumption, there's no "wiener" in doubt about the observable connection. Furthermore, our analysis also revealed a coefficient of determination (r-squared) of 0.7438794, indicating that a staggering 74.39% of the variance in hotdog consumption can be attributed to Republican voting patterns. It seems the political landscape in Alabama is a key condiment in shaping the colossal hotdog consumption behavior of the competition's champion.

The statistically significant p-value, less than 0.01, further solidifies the legitimacy of the relationship between these variables, quelling any "dogged" skepticism about the meaningfulness of our findings. It's not just a fluke—the interplay of political ideologies and competitive hotdog chomping is a real, statistically verifiable phenomenon. These results undoubtedly leave a "relishable" taste in the mouth of academic inquiry and provide a hearty chuckle to those tickled by the unexpected whims of human behavior and statistical correlations.

Our study's findings align with the seminal work of Smith and Doe (2005), who highlighted the enduring cultural tradition of hotdog consumption, and Jones (2010), who underscored the societal implications of political elections. The connection we've uncovered serves as a light-hearted yet impactful addition to the scholarly discourse, painting a vivid picture of the quirky connections that underlie human interests and behaviors. One might say that our findings have "ketchupped" with the existing literature, adding a fun twist to the serious world of scholarly investigation.

As we delve deeper into the multilayered nexus of political landscapes and gustatory extravaganzas, it becomes increasingly apparent that the "hotdog-eat-hotdog" world of competitive consumption is not immune to the flavorful influences of political leanings. Our study's affirmation of this connection urges further exploration into the unconventional correlations that shape societal interests and tastes. It's a reminder that in the hallowed halls of academia, there's always room for a dash of humor and surprise amidst the serious pursuit of knowledge.

In essence, our research sets the stage for a smorgasbord of future inquiries into the unexpected links that bind political inclinations and culinary feats, leaving a lingering aftertaste of amusement and intellectual curiosity. After all, in the grand feast of statistical discovery, a little humor and levity can be the seasoning that makes the most stimulating findings easier to digest.

It's a "bunderful" world out there, where even the most unexpected connections can serve as fodder for scholarly merriment. One might say that our study has masterfully combined the art of tasteful research with the science of tongue-in-cheek exploration, leaving a "bunned" impression on the terrain of academic investigation.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Republican votes for Senators 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts

[[ABSTRACT]]
This paper investigates the purported connection between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, this study delves into the correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8624844 and p < 0.01 for the years spanning from 1979 to 2020.

We aim to provide some much-needed levity to the field of political and culinary analysis by exploring this light-hearted relationship. With the seriousness of our academic pursuits, one might say we relish in the opportunity to bring a little humor to the table. Our research does not only weigh the evidence but also adds some flavor to the discussions. Through our data-driven analysis, we strive to mustard the mental fortitude needed to tackle such contentious and tangy topics.

Ultimately, our research highlights the unexpected connections and curiosities that exist in the world, serving as a reminder that even the most unlikely correlations can be food for thought. The results of this study could potentially inspire further investigations into the intersection of politics and competitive eating, ultimately showcasing the multifaceted nature of societal interests and tastes.

In conclusion, while the findings of this research may leave some readers bun-believers, we hope that our lighthearted approach will encourage further exploration of unconventional connections and inspire a smattering of relatable chuckles along the way.

[[INTRDUCTION]]
The intersection of politics and culinary indulgence has long been a subject of curiosity, with controversies such as "Is a hotdog a sandwich?" continually sparking heated debates. However, our investigation delves into a somewhat less contentious, yet equally intriguing question: What is the relationship, if any, between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion? We assure the reader that our inquiry is much more than a mere sausage fest of statistical analysis.
This study takes an earnest yet light-hearted approach to uncovering any potential connection between these two seemingly unrelated variables. As we leap into the realm of data analysis, one might say we're relishing the chance to add some zing to the often-mundane corridors of academia. After all, who says academic research can't have a little mustard on top?
The aim of this research is not only to uncover any patterns or correlations but also to inject a dose of mirth into the otherwise stoic world of statistical analysis. With this approach, we hope to ketchup with our readers' interests and ensure that our findings are not just a blend of raw data but also a humorous, yet informative, serving. It is with this saucy outlook that we begin our exploration of the peculiar ties that bind political preferences and competitive hotdog consumption.
As we delve into the statistical relationships between Republican votes and hotdog gobbling, we are reminded of the old adage: "You can't make an omelet without breaking eggs." Similarly, one might argue, "You can't conduct statistical analysis without making a few puns along the way." And so, armed with data and a sprinkle of humor, we embark on this scholarly escapade, eager to present our findings to an audience that might appreciate a research paper spiced with a dash of levity.

[[RESULTS]]
The analysis of the data collected from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia revealed a significant correlation between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. The correlation coefficient was found to be 0.8624844, indicating a strong positive relationship between the two variables. One might say these findings are nothing to "relish," as the strength of the correlation lends credence to the notion that political leanings may indeed impact the consumption of competitive quantities of hotdogs.
Furthermore, the coefficient of determination (r-squared) was calculated to be 0.7438794. This value suggests that approximately 74.39% of the variability in hotdog consumption can be explained by the number of Republican votes for Senators in Alabama. Put simply, this means that the political landscape in Alabama appears to have a notable influence on the hotdog-eating tendencies of the champion at Nathan's annual competition. Who would have thought that political allegiances could leave such a "stomach-churning" impression on competitive eating habits?
The p-value obtained from the analysis was less than 0.01, signifying that the observed correlation is statistically significant. It appears that the relationship between political voting patterns and competitive hotdog consumption is not just a fluke, but rather a meaningful and persistent phenomenon. One could argue that these results are not just a "frank" observation, but a tantalizing insight into the uncharted territory of political-culinary correlations.
The aforementioned results are succinctly visualized in the scatterplot presented in Figure 1. The scatterplot illustrates the strong positive correlation between Republican votes for Senators in Alabama and the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition Champion over the years. The data points are clustered in a notably linear fashion, further bolstering the assertion that these two variables are intimately connected. It seems that in the realm of competitive hotdog consumption, the political climate plays a significant role—a correlation worth "relishing," indeed.
One may be tempted to brush off these findings as mere coincidence, but as the saying goes, "When there's smoke, there's fire"—or in this case, "Where there are votes, there are hotdogs." These results prompt a reconsideration of the seemingly disparate realms of politics and indulgent eating, underscoring the need for further research into the unexpected ties that bind them. After all, who wouldn't relish the opportunity to explore the broad spectrum of societal and gustatory influences on competitive eating habits?
In conclusion, our findings not only shed light on the peculiar correlation between Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion but also serve as a testament to the delightful surprises that await in the intersection of political and culinary spheres. It is our hope that these results serve as a springboard for future investigations into the uncharted territory of unconventional correlations and inspire an appetite for statistical research that is both informative and peppered with a dash of humor. After all, in the world of academia, a little levity can go a long way in making data-driven discoveries more palatable and engaging.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In wrapping up our study, we find ourselves in a bit of a pickle - albeit a very tangy and statistically significant one. Our research has demonstrated a compelling correlation between Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion, with a correlation coefficient that is nothing to "relish" and a p-value that is statistically significant. These findings serve as a robust reminder that when it comes to political leanings and hotdog indulgence, there's more than just "mustard" at play.

It appears that the political landscape in Alabama has an undeniable influence on the champion's voracious appetite for competitive hotdog consumption, to the tune of approximately 74.39% of the variability being explained by the number of Republican votes. One might say that these results are enough to make one exclaim, "Hot diggity dog!" It's clear that this seemingly whimsical connection is no mere "frank" observation, but a compelling insight into the intersection of political preferences and culinary feats.

As we consider the possibilities for further research in this area, one thing is undeniably clear: this study marks the beginning and, notably, the end of our investigation into the unexpectedly delectable marriage of political sentiments and competitive eating habits. After all, have you ever heard of someone saying, "I relish the idea of additional research on the correlation between political votes and hotdog consumption"? We think not.

In conclusion, this research not only provides food for thought but also serves as a flavorful reminder that even the most unexpected correlations can be worth investigating. As such, we assert that no further research is needed in this area. It's time to "ketchup" on other pressing matters - perhaps some equally spicy research into the connection between Democratic votes and ice cream consumption. After all, in the world of academic pursuits, there's always room for another scoop of statistical curiosity!

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 All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Political Science

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 All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Gastronomic Political 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 All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts with an abstract of This paper investigates the purported connection between the number of Republican votes for Senators in Alabama and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition Champion. Utilizing data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, this study delves into the correlation between these seemingly disparate phenomena. Our findings reveal a striking correlation coefficient of 0.8624844 and p < 0.01 for the years spanning from 1979 to 2020.
We aim to provide some much-needed levity to the field of political and culinary analysis by exploring this light-hearted relationship. With the seriousness of our academic pursuits, one might say we relish in the opportunity to bring a little humor to the table. Our research does not only weigh the evidence but also adds some flavor to the discussions. Through our data-driven analysis, we strive to mustard the mental fortitude needed to tackle such contentious and tangy topics.
Ultimately, our research highlights the unexpected connections and curiosities that exist in the world, serving as a reminder that even the most unlikely correlations can be food for thought. The results of this study could potentially inspire further investigations into the intersection of politics and competitive eating, ultimately showcasing the multifaceted nature of societal interests and tastes.
In conclusion, while the findings of this research may leave some readers bun-believers, we hope that our lighthearted approach will encourage further exploration of unconventional connections and inspire a smattering of relatable chuckles along the way.

ChatGPT:

Nathan's Hot Dog Eating Competition, Senators, Republican votes, Alabama, correlation, MIT Election Data and Science Lab, Harvard Dataverse, Wikipedia, hotdog consumption, correlation coefficient, political analysis, culinary analysis, lighthearted relationship, unexpected connections, societal interests, competitive eating, unconventional connections, humor in research

*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

Republican votes for Senators in Alabama
Detailed data title: Total number of votes cast for Federal Republican Senate candidates in Alabama
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Republican votes for Senators 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 = 0.8624844 (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 = 0.7438794 (Coefficient of determination)
This means 74.4% of the change in the one variable (i.e., Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion) is predictable based on the change in the other (i.e., Republican votes for Senators in Alabama) over the 14 years from 1979 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.2E-5.^Show 0.0000721206984813758100000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.86 in 0.0072% of random cases. Said differently, if you correlated 13,866 random variables^Note Which I absolutely did.
with the same 13 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.61, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

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

	1980	1984	1986	1990	1992	1996	1998	2002	2004	2008	2010	2014	2016	2020
Republican votes for Senators in Alabama (Total votes)	650362	498508	602537	467190	522015	786436	817973	792561	1242200	1305380	968181	795606	1335100	1392080
Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion (Hotdogs eaten)	9.5	9.5	15.5	16	19	22.25	19	50.5	53.33	59	54	61	70	75

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([650362,498508,602537,467190,522015,786436,817973,792561,1242200,1305380,968181,795606,1335100,1392080,])
array_2 = np.array([9.5,9.5,15.5,16,19,22.25,19,50.5,53.33,59,54,61,70,75,])
array_1_name = "Republican votes for Senators 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. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Republican votes for Senators in Alabama
Line chart for only Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion
AI-generated correlation image
The spurious research paper: All in Jest? Senatorial Votes in East and Nathan's Hot Dog Feasts

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 4304 · Black Variable ID: 26197 · Red Variable ID: 500


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