about · email me · subscribe
Spurious correlation #4,815 · 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 Pennsylvania and the second variable is Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion.  The chart goes from 1979 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The key to Biden's success in Pennsylvania lies in his appeal to the "relish" and "mustard" base, leading to a surge in support. As the votes for the Democrat candidate sizzled, so did the competitive spirit at Nathan's. It's as if every vote cast was a bun, and the champion just couldn't resist topping it with a wiener. This correlation truly cuts the mustard when it comes to political and gastronomical ramifications!

Model: dalle-3
Prompt: Generate an image of a Discovery magazine cover featuring a jubilant scene in Pennsylvania. In the foreground, a hotdog eating competition is taking place, with the champion wearing a bib stained with mustard and joyfully devouring hot dogs. The surrounding crowd is cheering and celebrating, capturing the vibrant atmosphere. The image should convey the parallel between the excitement of the hotdog competition and the surge in support for the Democratic Presidential candidate, creating a visually compelling narrative. 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 Pennsylvania 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: Symbolism Brutalism A Discovery magazine cover image Woodblock painting Sci-fi fantacy
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Votes for the Democrat Presidential candidate in Pennsylvania and Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion, in the following situation: The key to Biden's success in Pennsylvania lies in his appeal to the "relish" and "mustard" base, leading to a surge in support. As the votes for the Democrat candidate sizzled, so did the competitive spirit at Nathan's. It's as if every vote cast was a bun, and the champion just couldn't resist topping it with a wiener. This correlation truly cuts the mustard when it comes to political and gastronomical ramifications!. Keep the description simple.
ChatGPT: In Pennsylvania, as the Votes for the Democrat Presidential candidate sizzle, a crowd gathers at Nathan's Hot Dog Eating Competition. The champion, adorned with a mustard-stained bib, joyfully devours hotdogs in a vibrant display of appetite and celebration, mirroring the surge in support for the Democratic candidate.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In Pennsylvania, as the Votes for the Democrat Presidential candidate sizzle, a crowd gathers at Nathan's Hot Dog Eating Competition. The champion, adorned with a mustard-stained bib, joyfully devours hotdogs in a vibrant display of appetite and celebration, mirroring the surge in support for the Democratic candidate. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a Discovery magazine cover featuring a jubilant scene in Pennsylvania. In the foreground, a hotdog eating competition is taking place, with the champion wearing a bib stained with mustard and joyfully devouring hot dogs. The surrounding crowd is cheering and celebrating, capturing the vibrant atmosphere. The image should convey the parallel between the excitement of the hotdog competition and the surge in support for the Democratic Presidential candidate, creating a visually compelling narrative.

*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 Pennsylvania caused Hotdogs consumed by Nathan's Hot Dog Eating Competition Champion to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption

The Journal of Electoral Hot Dog Studies

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 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 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 Pennsylvania 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, just make it sound clever.

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 0.9432053 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.


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 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 Pennsylvania 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The connection between political inclinations and culinary proclivities has been a subject of intrigue for researchers across various disciplines. As the saying goes, "You are what you eat," but could it also be an indicator of how you vote? This study delves into the intriguing relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. It aims to unravel this seemingly improbable link and uncover the underlying factors driving this unexpected connection.

The correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "wiener" of a hypothesis; rather, it is a topic of much scholarly interest with implications that extend beyond the realm of jest. By employing data from reputable sources such as the MIT Election Data and Science Lab and Harvard Dataverse, this study strives to shed light on the enigmatic relationship between political trends and competitive hotdog consumption.

The notion that political decisions and competitive hotdog devouring could be entwined may seem like a "relish"-able source of amusement, but the empirical evidence presented in this research belies any dismissive attitudes towards this intriguing phenomenon. This study's findings challenge conventional wisdom and offer a compelling case for further exploration at the intersection of gastronomic indulgences and political proclivities.

Stay tuned for a journey through statistics and sausages, where complex regression analyses and comedic condiments converge to unravel the tantalizing correlation between political preferences and the consumption of cylindrical meat products.


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 Votes for the Democrat Presidential candidate in Pennsylvania 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 a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between political inclinations and culinary proclivities has been a subject of intrigue for researchers across various disciplines. As the saying goes, "You are what you eat," but could it also be an indicator of how you vote? This study delves into the intriguing relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. It aims to unravel this seemingly improbable link and uncover the underlying factors driving this unexpected connection.
The correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "wiener" of a hypothesis; rather, it is a topic of much scholarly interest with implications that extend beyond the realm of jest. By employing data from reputable sources such as the MIT Election Data and Science Lab and Harvard Dataverse, this study strives to shed light on the enigmatic relationship between political trends and competitive hotdog consumption.
The notion that political decisions and competitive hotdog devouring could be entwined may seem like a "relish"-able source of amusement, but the empirical evidence presented in this research belies any dismissive attitudes towards this intriguing phenomenon. This study's findings challenge conventional wisdom and offer a compelling case for further exploration at the intersection of gastronomic indulgences and political proclivities.
Stay tuned for a journey through statistics and sausages, where complex regression analyses and comedic condiments converge to unravel the tantalizing correlation between political preferences and the consumption of cylindrical meat products.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Previous studies have explored the connection between political leanings and culinary habits, but none have delved as deeply into the fascinating relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Smith (2015) observed a link between voter behavior and fast-food consumption, while Doe (2018) conducted a study on the intersection of political preferences and competitive eating. Additionally, Jones (2020) investigated the influence of regional delicacies on electoral outcomes.

Turning to non-fiction sources, "Fast Food Nation" by Eric Schlosser provides insights into the impact of fast food on American culture, while "The Tipping Point" by Malcolm Gladwell examines the tipping point in social epidemics and how small changes can lead to large effects. In the realm of fiction, novels such as "The Hunger Games" by Suzanne Collins and "The Cider House Rules" by John Irving may offer tangential perspectives on the relationship between consumables and larger societal forces.

One relevant internet meme that has gained traction in recent years is the "Hotdoge" meme, featuring a Shiba Inu dog superimposed on a hotdog, which could be interpreted as an amusing representation of the amalgamation of political preferences and hotdog consumption. Another widely popular meme, the "Distracted Boyfriend," may subtly illustrate the surprising allure of hotdogs and their potential to divert attention, much like the unexpected allure of particular political candidates.

In "Hotdogomics," the authors find that the correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "frankfurter" of a relationship, but a statistically robust phenomenon that demands further investigation. As we unravel this enthralling connection, one cannot help but appreciate the sheer "bun"-dles of humor and curiosity that come with examining the unexpected convergence of electoral votes and competitive hotdog consumption. This research contributes to a growing body of literature on the interplay of seemingly unrelated phenomena, challenging established paradigms and inviting laughter and contemplation in equal measure.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Pennsylvania 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

[[INTRODUCTION]]
The connection between political inclinations and culinary proclivities has been a subject of intrigue for researchers across various disciplines. As the saying goes, "You are what you eat," but could it also be an indicator of how you vote? This study delves into the intriguing relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. It aims to unravel this seemingly improbable link and uncover the underlying factors driving this unexpected connection.
The correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "wiener" of a hypothesis; rather, it is a topic of much scholarly interest with implications that extend beyond the realm of jest. By employing data from reputable sources such as the MIT Election Data and Science Lab and Harvard Dataverse, this study strives to shed light on the enigmatic relationship between political trends and competitive hotdog consumption.
The notion that political decisions and competitive hotdog devouring could be entwined may seem like a "relish"-able source of amusement, but the empirical evidence presented in this research belies any dismissive attitudes towards this intriguing phenomenon. This study's findings challenge conventional wisdom and offer a compelling case for further exploration at the intersection of gastronomic indulgences and political proclivities.
Stay tuned for a journey through statistics and sausages, where complex regression analyses and comedic condiments converge to unravel the tantalizing correlation between political preferences and the consumption of cylindrical meat products.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The data for this study were collected from publicly available sources, including the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia, providing a range of information on presidential votes in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition from 1979 to 2020. The datasets were prepared with as much care as one would prepare a hotdog, ensuring that all relevant variables and observations were captured, albeit with less ketchup.

To investigate the relationship between the two variables, a sophisticated statistical analysis was employed, utilizing a custom-built algorithm that we like to refer to as the "Regressio-nit's Hot Dog" model. This model was designed specifically for this study, as there is no pre-existing statistical technique for analyzing the intersection of political voting behavior and competitive hotdog consumption. The algorithm, carefully seasoned with meticulous coding, processed the data through a series of complex regression analyses, which we affectionately call "linear links" and "hot dogmatic regressions" in the spirit of scholarly punnery.

The "Regressio-nit's Hot Dog" model was specifically tailored to account for various potential confounding variables, such as regional differences in hotdog preferences and fluctuations in political sentiments over time. The algorithm was trained using a mix of Bayesian statistics and hotdog-related humor to ensure that it produced rigorous and reliable results without letting the seriousness of the analysis go "bun"-noticed.

In addition to the regression analyses, a time series analysis was conducted to examine the temporal dynamics of the relationship between votes for the Democratic candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion. This analysis involved a careful examination of historical patterns and trends, with a particular focus on identifying any cyclical movements mirroring the electoral cycles and competitive eating seasons.

Furthermore, to validate the robustness of the findings, a sensitivity analysis was performed to assess the stability of the correlation coefficient across different subperiods. This involved examining the relationship between votes and hotdog consumption in subperiods such as election years, leap years, and dog years (don't worry, no hotdogs were actually consumed during this phase of the analysis).

The data analysis was conducted using a statistical software package that was not only statistically efficient but also had a good sense of humor, a rare characteristic in statistical software. The significance level for all analyses was set at α = 0.01, reflecting the level of confidence required to assert a meaningful connection between political voting behavior and competitive hotdog consumption.

This methodological approach, while quirky in its application, was selected to ensure a rigorous and comprehensive investigation of the correlation between votes for the Democrat presidential candidate in Pennsylvania and the consumption of hotdogs by the Nathan's Hot Dog Eating Competition champion. The combination of bespoke statistical modeling, historical analysis, and sensitivity testing allowed for a thorough exploration of this unexpected and inherently humorous relationship.

In the immortal words of Oscar Mayer, "Oh, I'd love to be an Oscar Mayer Wiener, that is what I'd truly like to be..." And in the noble pursuit of knowledge, we embark on this methodological journey to uncover the tantalizing truth behind electoral outcomes 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 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 Pennsylvania 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 0.9432053, r-squared of 0.8896363, 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The connection between political inclinations and culinary proclivities has been a subject of intrigue for researchers across various disciplines. As the saying goes, "You are what you eat," but could it also be an indicator of how you vote? This study delves into the intriguing relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. It aims to unravel this seemingly improbable link and uncover the underlying factors driving this unexpected connection.
The correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "wiener" of a hypothesis; rather, it is a topic of much scholarly interest with implications that extend beyond the realm of jest. By employing data from reputable sources such as the MIT Election Data and Science Lab and Harvard Dataverse, this study strives to shed light on the enigmatic relationship between political trends and competitive hotdog consumption.
The notion that political decisions and competitive hotdog devouring could be entwined may seem like a "relish"-able source of amusement, but the empirical evidence presented in this research belies any dismissive attitudes towards this intriguing phenomenon. This study's findings challenge conventional wisdom and offer a compelling case for further exploration at the intersection of gastronomic indulgences and political proclivities.
Stay tuned for a journey through statistics and sausages, where complex regression analyses and comedic condiments converge to unravel the tantalizing correlation between political preferences and the consumption of cylindrical meat products.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of data spanning the years 1979 to 2020 revealed a remarkably strong correlation between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.9432053 exudes a level of statistical significance that would make even the most seasoned researcher pause to relish the findings. It seems that as the votes for the Democrat candidate increased, so did the number of hotdogs gobbled by the competitive eater.

The scatterplot (Fig. 1) visually encapsulates this robust relationship, displaying a trend so striking that one could say it "ketchup" the attention of anyone perusing our findings. The points on the plot align with an almost sausage-like precision, pointing to a correlation that is not to be taken lightly.

The statistically significant p-value of less than 0.01 further solidifies the compelling nature of this correlation. It seems that the political landscape and competitive hot dog consumption are entwined in ways that defy conventional wisdom, leaving us with a moral dilemma – should we now say "cast a vote, not a bun" when discussing election strategies?

This correlation may seem like a whimsical interplay between political fervor and culinary feats, but its implications reach deeper than the bottom of a hot dog bun. The findings offer a tantalizing glimpse into the multi-faceted influences that shape human behavior, suggesting that the path to electoral success might indeed "rely on the consumption of cylindrical meat products" – a realization that will surely have politicians pondering their campaign strategies in a new light.


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 Votes for the Democrat Presidential candidate in Pennsylvania 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

[[LITERATURE REVIEW]]
Previous studies have explored the connection between political leanings and culinary habits, but none have delved as deeply into the fascinating relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. Smith (2015) observed a link between voter behavior and fast-food consumption, while Doe (2018) conducted a study on the intersection of political preferences and competitive eating. Additionally, Jones (2020) investigated the influence of regional delicacies on electoral outcomes.
Turning to non-fiction sources, "Fast Food Nation" by Eric Schlosser provides insights into the impact of fast food on American culture, while "The Tipping Point" by Malcolm Gladwell examines the tipping point in social epidemics and how small changes can lead to large effects. In the realm of fiction, novels such as "The Hunger Games" by Suzanne Collins and "The Cider House Rules" by John Irving may offer tangential perspectives on the relationship between consumables and larger societal forces.
One relevant internet meme that has gained traction in recent years is the "Hotdoge" meme, featuring a Shiba Inu dog superimposed on a hotdog, which could be interpreted as an amusing representation of the amalgamation of political preferences and hotdog consumption. Another widely popular meme, the "Distracted Boyfriend," may subtly illustrate the surprising allure of hotdogs and their potential to divert attention, much like the unexpected allure of particular political candidates.
In "Hotdogomics," the authors find that the correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "frankfurter" of a relationship, but a statistically robust phenomenon that demands further investigation. As we unravel this enthralling connection, one cannot help but appreciate the sheer "bun"-dles of humor and curiosity that come with examining the unexpected convergence of electoral votes and competitive hotdog consumption. This research contributes to a growing body of literature on the interplay of seemingly unrelated phenomena, challenging established paradigms and inviting laughter and contemplation in equal measure.

[[RESULTS]]
The analysis of data spanning the years 1979 to 2020 revealed a remarkably strong correlation between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.9432053 exudes a level of statistical significance that would make even the most seasoned researcher pause to relish the findings. It seems that as the votes for the Democrat candidate increased, so did the number of hotdogs gobbled by the competitive eater.
The scatterplot (Fig. 1) visually encapsulates this robust relationship, displaying a trend so striking that one could say it "ketchup" the attention of anyone perusing our findings. The points on the plot align with an almost sausage-like precision, pointing to a correlation that is not to be taken lightly.
The statistically significant p-value of less than 0.01 further solidifies the compelling nature of this correlation. It seems that the political landscape and competitive hot dog consumption are entwined in ways that defy conventional wisdom, leaving us with a moral dilemma – should we now say "cast a vote, not a bun" when discussing election strategies?
This correlation may seem like a whimsical interplay between political fervor and culinary feats, but its implications reach deeper than the bottom of a hot dog bun. The findings offer a tantalizing glimpse into the multi-faceted influences that shape human behavior, suggesting that the path to electoral success might indeed "rely on the consumption of cylindrical meat products" – a realization that will surely have politicians pondering their campaign strategies in a new light.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study shed light on an unexpected yet robust correlation between votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. The findings are consistent with previous research suggesting that political leanings and gastronomic preferences may be intertwined in ways that defy traditional expectations.

The strong correlation coefficient of 0.9432053, along with a statistically significant p-value of less than 0.01, supports the notion that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the competitive eater. This suggests a potentially deeper relationship between political engagement and culinary indulgence, challenging conventional wisdom and serving as a reminder that sometimes, correlations can be as surprising as finding a hotdog in a box of donuts.

Our findings build upon the work of Smith (2015) and Doe (2018), who hinted at the connection between political behavior and fast-food consumption, albeit not specifically focused on competitive hotdog eating. The sustained nature of the correlation over a lengthy period from 1979 to 2020 underlines the robustness of this association, inviting a long-overdue analysis of the societal implications of partisan voting and hotdog consumption.

The unexpected relationship between electoral outcomes and competitive hot dog consumption could even be considered a "bun-derful" avenue for further exploration in the domains of human behavior and societal trends. The significant correlation observed in this study may prompt future research into the psychological and sociological factors that underpin this unlikely relationship, eliciting responses from scholars and laypersons alike that range from "That's a lot to relish" to "I never sausage a correlation before."

Our results add empirical weight to the seemingly humorous meme of "Hotdogomics," highlighting the need to acknowledge that sometimes, statistical significance can be as unexpected as an invitation to a hotdog eating contest at a vegetarian convention. This research demonstrates the potential of seemingly disparate phenomena to converge in ways that challenge traditional boundaries, inviting a reconsideration of the factors that shape human behavior and electoral outcomes.

In conclusion, the findings from this study encourage a reevaluation of the relationship between political preferences and culinary habits, reminding us that sometimes, the most "bunderful" discoveries can be found in the unlikeliest places – even in the statistical analysis of hotdogs and political elections. This unexpected correlation opens the door for deeper investigations into the nuanced connections between seemingly unrelated domains, daring us to embrace the whimsical and the surprising in our quest for understanding human behavior and societal trends.


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 Votes for the Democrat Presidential candidate in Pennsylvania 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]]
"Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption"

[[ABSTRACT]]
The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.

Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.

One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

[[INTRDUCTION]]
The connection between political inclinations and culinary proclivities has been a subject of intrigue for researchers across various disciplines. As the saying goes, "You are what you eat," but could it also be an indicator of how you vote? This study delves into the intriguing relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. It aims to unravel this seemingly improbable link and uncover the underlying factors driving this unexpected connection.
The correlation between votes for the Democrat candidate in Pennsylvania and hotdog consumption by the Nathan's Hot Dog Eating Competition champion is no mere "wiener" of a hypothesis; rather, it is a topic of much scholarly interest with implications that extend beyond the realm of jest. By employing data from reputable sources such as the MIT Election Data and Science Lab and Harvard Dataverse, this study strives to shed light on the enigmatic relationship between political trends and competitive hotdog consumption.
The notion that political decisions and competitive hotdog devouring could be entwined may seem like a "relish"-able source of amusement, but the empirical evidence presented in this research belies any dismissive attitudes towards this intriguing phenomenon. This study's findings challenge conventional wisdom and offer a compelling case for further exploration at the intersection of gastronomic indulgences and political proclivities.
Stay tuned for a journey through statistics and sausages, where complex regression analyses and comedic condiments converge to unravel the tantalizing correlation between political preferences and the consumption of cylindrical meat products.

[[RESULTS]]
The analysis of data spanning the years 1979 to 2020 revealed a remarkably strong correlation between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. The correlation coefficient of 0.9432053 exudes a level of statistical significance that would make even the most seasoned researcher pause to relish the findings. It seems that as the votes for the Democrat candidate increased, so did the number of hotdogs gobbled by the competitive eater.
The scatterplot (Fig. 1) visually encapsulates this robust relationship, displaying a trend so striking that one could say it "ketchup" the attention of anyone perusing our findings. The points on the plot align with an almost sausage-like precision, pointing to a correlation that is not to be taken lightly.
The statistically significant p-value of less than 0.01 further solidifies the compelling nature of this correlation. It seems that the political landscape and competitive hot dog consumption are entwined in ways that defy conventional wisdom, leaving us with a moral dilemma – should we now say "cast a vote, not a bun" when discussing election strategies?
This correlation may seem like a whimsical interplay between political fervor and culinary feats, but its implications reach deeper than the bottom of a hot dog bun. The findings offer a tantalizing glimpse into the multi-faceted influences that shape human behavior, suggesting that the path to electoral success might indeed "rely on the consumption of cylindrical meat products" – a realization that will surely have politicians pondering their campaign strategies in a new light.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a remarkably robust correlation between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition. As the votes for the Democrat candidate increased, so did the number of hotdogs devoured, leaving us with a statistical relationship that's harder to swallow than an overcooked hotdog at a barbecue.

The strength and significance of this correlation would make even the most hardened cynic exclaim, "What in ketchupation is going on here?" It seems that the political landscape and competitive hot dog consumption are indeed intertwined, prompting us to ponder whether the phrase "as American as apple pie" should be updated to "as American as hot dogs and elections."

Our findings compel us to reconsider the old adage, "You can't put all your eggs in one basket," and instead suggest, "You can't put all your sausages in one bun – unless you want to win an election." The implications of this research extend beyond the realm of jest and into the realm of nuanced understanding of human behavior and societal trends, proving that sometimes, the most unexpected connections yield the most tantalizing insights.

In the wise words of a hot dog enthusiast, "When life gives you hotdogs, don't just make hotdogs – make statistical inferences about electoral behavior." With that being said, we assert that no further research is needed in this area, as we have truly relished uncovering this statistical delicacy.


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 Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Electoral Hot Dog Studies


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 Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption. Respond only with the name of a fictional organization.

ChatGPT:

The League of Culinary Statistics and Political Analysis


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 Hot Diggity Democrat: A Correlation Analysis of Pennsylvania's Presidential Votes and Nathan's Hot Dog Consumption with an abstract of The connection between political preferences and gastronomic indulgences has long piqued the interest of researchers in various disciplines. In this study, we use data from the MIT Election Data and Science Lab, Harvard Dataverse, and Wikipedia to explore the relationship between the votes for the Democratic presidential candidate in Pennsylvania and the consumption of hotdogs by the champion of Nathan's Hot Dog Eating Competition.
Our analysis revealed a striking correlation coefficient of 0.9432053 and a statistically significant p-value of less than 0.01 for the period spanning from 1979 to 2020. This finding suggests that as the votes for the Democrat candidate increase, so does the number of hotdogs consumed by the Nathan's Hot Dog Eating Competition champion. It seems that the political landscape and competitive hot dog consumption are linked in ways that defy conventional wisdom.
One might even say that the relationship between electoral outcomes and competitive hot dog consumption is no mere "bun-dle of joy," but a statistically robust phenomenon with tantalizing implications for understanding human behavior and societal trends. Our findings contribute to the intersection of political science and culinary studies, challenging traditional notions of cause and effect.

ChatGPT:

Pennsylvania, presidential votes, Democratic candidate, hot dog consumption, Nathan's Hot Dog Eating Competition, correlation analysis, MIT Election Data and Science Lab, Harvard Dataverse, Wikipedia, gastronomic indulgences, political preferences, electoral outcomes, societal trends, human behavior

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

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 = 0.9432053 (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 = 0.8896363 (Coefficient of determination)
This means 89% 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 Pennsylvania) over the 11 years from 1979 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.3E-5. 0.0000133691039020066460000000
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 0.94 in 0.0013% of random cases. Said differently, if you correlated 74,799 random variables You don't actually need 74 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.79, 0.99 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19801984198819921996200020042008201220162020
Votes for the Democratic Presidential candidate in Pennsylvania (Total votes)19375402228130219494022391602215820248597029381003276360299027029264403458230
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([1937540,2228130,2194940,2239160,2215820,2485970,2938100,3276360,2990270,2926440,3458230,])
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 Pennsylvania"
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 rating is stellar!


Correlation ID: 4815 · Black Variable ID: 26024 · Red Variable ID: 500
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0