about · email me · subscribe
Spurious correlation #4,336 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is American cheese consumption and the second variable is Votes for the Republican Presidential candidate in Indiana.  The chart goes from 1990 to 2020, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As American cheese consumption melted, so did the hearts of Indiana voters, leading to an increased support for the Republican Presidential candidate. The cheesier the campaign, the more it feta with the residents, ultimately swaying their votes in favor of the Republican candidate. It seems like the political race was gratefully influenced by the power of this dairy deliciousness, proving that when it comes to elections, you can never underestimate the gouda-ness of a strong cheese connection!

Model: dalle-3
Prompt: Prompt: Generate an image where a giant grilled cheese sandwich with American cheese oozes onto a plate, reflecting the shape of Indiana and the hearts of the residents warming up to a Republican Presidential candidate. Show cheese-themed banners and slogans adorning the campaign trail, with a cheesy aroma filling the air to symbolize the increasing support for the candidate in Indiana. 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: American cheese consumption and Votes for the Republican Presidential candidate in Indiana. 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: Oragami a funny image macro Vaporwave Art nouveau 3D Pixar Style
ChatGPT: a funny image macro

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 American cheese consumption and Votes for the Republican Presidential candidate in Indiana, in the following situation: As American cheese consumption melted, so did the hearts of Indiana voters, leading to an increased support for the Republican Presidential candidate. The cheesier the campaign, the more it feta with the residents, ultimately swaying their votes in favor of the Republican candidate. It seems like the political race was gratefully influenced by the power of this dairy deliciousness, proving that when it comes to elections, you can never underestimate the gouda-ness of a strong cheese connection!. Keep the description simple.
ChatGPT: In Indiana, as people dined on grilled cheese sandwiches with American cheese, a warm and gooey slice of cheese melted onto their plates, reflecting the hearts of the residents warming up to the Republican Presidential candidate. Meanwhile, the campaign trail was sprinkled with cheese-themed banners and slogans, appealing to the cheesy-loving community and swaying their votes in favor of the candidate. The savory scent of melting cheese filled the air, symbolizing the increasing support for the Republican candidate in a state where the cheesier the campaign, the stronger the connection with voters.

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 funny image macro ] and depicting this scene: In Indiana, as people dined on grilled cheese sandwiches with American cheese, a warm and gooey slice of cheese melted onto their plates, reflecting the hearts of the residents warming up to the Republican Presidential candidate. Meanwhile, the campaign trail was sprinkled with cheese-themed banners and slogans, appealing to the cheesy-loving community and swaying their votes in favor of the candidate. The savory scent of melting cheese filled the air, symbolizing the increasing support for the Republican candidate in a state where the cheesier the campaign, the stronger the connection with voters. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image where a giant grilled cheese sandwich with American cheese oozes onto a plate, reflecting the shape of Indiana and the hearts of the residents warming up to a Republican Presidential candidate. Show cheese-themed banners and slogans adorning the campaign trail, with a cheesy aroma filling the air to symbolize the increasing support for the candidate in Indiana.

*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 American cheese consumption caused Votes for the Republican Presidential candidate in Indiana to increase.

AI academic paper

(Because p < 0.01)
Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana

The Cheese Chronicle

Jan 2024

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




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns.

Make the title seem clever.

Your research team used data from USDA and MIT Election Data and Science Lab, Harvard Dataverse to assess this nagging question. You found a correlation coefficient of 0.9466628 and p < 0.01 for 1990 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]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the ever-evolving landscape of political analysis, researchers have often sought to uncover the underlying factors influencing voter behavior. From socioeconomic status to ideological affiliations, the exploration of these determinants has been as varied as the toppings on a loaded baked potato. However, a lesser explored element in this proverbial political potluck is the potential role of cheese consumption in shaping voting patterns. Thus, with a sprinkle of curiosity and a dash of skepticism, we embarked on a quest to unravel the enigmatic interaction between American cheese consumption and support for the Republican presidential candidate in the state of Indiana.

The notion of cheese as a political influencer may initially elicit a skeptical eyebrow raise or perhaps a humorous pun, but the gravity of this inquiry is not to be underestimated. The dairy aisle, often overlooked in the annals of political analysis, may hold secrets as moldy as a forgotten block of Roquefort. With this provolone premise in mind, our study aims to turn this chuckle-inducing conjecture into a gouda-fide investigation worthy of scholarly contemplation.

Indiana, known for its bustling agriculture and thriving dairy industry, serves as an ideal backdrop for our cheddar-tinged exploration. As the saying goes, "In cheese we trust" – or was it "In God we trust"? We digress. The intricate dance between lactose love and political preference provides an enticing canvas upon which to uncover potential correlations, all while leaving room for a brie-thtaking discovery or two.

By harnessing the power of large-scale data sets and statistical analysis, we navigated through a myriad of spreadsheets and charts, with the occasional interruption for a cheesy snack break. In doing so, we hope to shed light on an aspect of voter behavior that may be as surprising as finding a slice of Swiss in a bowl of tomato soup – unexpected, yet oddly complementary.

With that in mind, our study aims to slice through the layers of ambiguity and delve into the creamy depths of American cheese consumption in relation to support for Republican presidential candidates in the state of Indiana. So, grab a cracker or two, and let's embark on this lactose-infused journey into the heart of political fromage. As we say in the world of academic inquiry, "Let us not be bleu, but instead, provolone in our pursuit of cheesy enlightenment."


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the ever-evolving landscape of political analysis, researchers have often sought to uncover the underlying factors influencing voter behavior. From socioeconomic status to ideological affiliations, the exploration of these determinants has been as varied as the toppings on a loaded baked potato. However, a lesser explored element in this proverbial political potluck is the potential role of cheese consumption in shaping voting patterns. Thus, with a sprinkle of curiosity and a dash of skepticism, we embarked on a quest to unravel the enigmatic interaction between American cheese consumption and support for the Republican presidential candidate in the state of Indiana.
The notion of cheese as a political influencer may initially elicit a skeptical eyebrow raise or perhaps a humorous pun, but the gravity of this inquiry is not to be underestimated. The dairy aisle, often overlooked in the annals of political analysis, may hold secrets as moldy as a forgotten block of Roquefort. With this provolone premise in mind, our study aims to turn this chuckle-inducing conjecture into a gouda-fide investigation worthy of scholarly contemplation.
Indiana, known for its bustling agriculture and thriving dairy industry, serves as an ideal backdrop for our cheddar-tinged exploration. As the saying goes, "In cheese we trust" – or was it "In God we trust"? We digress. The intricate dance between lactose love and political preference provides an enticing canvas upon which to uncover potential correlations, all while leaving room for a brie-thtaking discovery or two.
By harnessing the power of large-scale data sets and statistical analysis, we navigated through a myriad of spreadsheets and charts, with the occasional interruption for a cheesy snack break. In doing so, we hope to shed light on an aspect of voter behavior that may be as surprising as finding a slice of Swiss in a bowl of tomato soup – unexpected, yet oddly complementary.
With that in mind, our study aims to slice through the layers of ambiguity and delve into the creamy depths of American cheese consumption in relation to support for Republican presidential candidates in the state of Indiana. So, grab a cracker or two, and let's embark on this lactose-infused journey into the heart of political fromage. As we say in the world of academic inquiry, "Let us not be bleu, but instead, provolone in our pursuit of cheesy enlightenment."

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The literature on the influence of dietary habits on political behavior is as rich and varied as the assortment of cheese at a wine and cheese party. Smith (2015) and Doe (2018) have examined the effects of food consumption on political preferences, shedding light on the potential impact of culinary choices on voting behavior. However, the specific relationship between American cheese consumption and support for the Republican presidential candidate in Indiana remains an area largely unexplored.

In "The Big Cheese: An Exploration of American Dairy Culture" (Johnson, 2007), the author delves into the historical, social, and cultural significance of American cheese, but no direct link to political preferences is established. Similarly, "Cheese and Politics: A Comparative Analysis" (Lee, 2012) provides insights into the intersection of cheese consumption and political ideologies across different countries, yet the focus on specific presidential candidate support in a U.S. state is absent.

Turning to fiction for potential clues, the novels "Cheese It Up" (Williams, 2004) and "The Gouda Conspiracy" (Patterson, 2016) playfully weave narratives that hint at the clandestine influence of cheese on political machinations, but their relevance to our study remains purely speculative.

In an unconventional approach to literature review, we also perused a diverse array of sources, including grocery store receipts, food blog comments, and even the discarded napkins of cheese aficionados. While these unconventional sources offered limited scholarly value, they did instigate bouts of uncontrollable laughter and a newfound appreciation for the peculiar abundance of cheese-related puns.

As we slice through the vast expanse of scholarly works and whimsical musings, the dearth of direct empirical evidence linking American cheese consumption to support for the Republican presidential candidate in Indiana is unmistakable. Therefore, our study aims to bridge this gap and serve up a platter of empirical findings that can finally lay this cheesy enigma to rest.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from USDA and MIT Election Data and Science Lab, Harvard Dataverse . You used data from 1990 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]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

[[INTRODUCTION]]
In the ever-evolving landscape of political analysis, researchers have often sought to uncover the underlying factors influencing voter behavior. From socioeconomic status to ideological affiliations, the exploration of these determinants has been as varied as the toppings on a loaded baked potato. However, a lesser explored element in this proverbial political potluck is the potential role of cheese consumption in shaping voting patterns. Thus, with a sprinkle of curiosity and a dash of skepticism, we embarked on a quest to unravel the enigmatic interaction between American cheese consumption and support for the Republican presidential candidate in the state of Indiana.
The notion of cheese as a political influencer may initially elicit a skeptical eyebrow raise or perhaps a humorous pun, but the gravity of this inquiry is not to be underestimated. The dairy aisle, often overlooked in the annals of political analysis, may hold secrets as moldy as a forgotten block of Roquefort. With this provolone premise in mind, our study aims to turn this chuckle-inducing conjecture into a gouda-fide investigation worthy of scholarly contemplation.
Indiana, known for its bustling agriculture and thriving dairy industry, serves as an ideal backdrop for our cheddar-tinged exploration. As the saying goes, "In cheese we trust" – or was it "In God we trust"? We digress. The intricate dance between lactose love and political preference provides an enticing canvas upon which to uncover potential correlations, all while leaving room for a brie-thtaking discovery or two.
By harnessing the power of large-scale data sets and statistical analysis, we navigated through a myriad of spreadsheets and charts, with the occasional interruption for a cheesy snack break. In doing so, we hope to shed light on an aspect of voter behavior that may be as surprising as finding a slice of Swiss in a bowl of tomato soup – unexpected, yet oddly complementary.
With that in mind, our study aims to slice through the layers of ambiguity and delve into the creamy depths of American cheese consumption in relation to support for Republican presidential candidates in the state of Indiana. So, grab a cracker or two, and let's embark on this lactose-infused journey into the heart of political fromage. As we say in the world of academic inquiry, "Let us not be bleu, but instead, provolone in our pursuit of cheesy enlightenment."

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To begin our dairy-filled expedition into the political wilderness, we harnessed the raw power of data collection and statistical analysis to unearth the potential nexus between American cheese consumption and support for the Republican presidential candidate in Indiana. Our research team employed a multifaceted approach that involved both quantitative and qualitative methodologies, resembling the intricate process of selecting the perfect pairing for a robust red wine or a pungent blue cheese.

Data on American cheese consumption was collated from the USDA, where we perused through an array of reports and spreadsheets to identify the cheese consumption patterns across the Hoosier state from 1990 to 2020. We also scoured the MIT Election Data and Science Lab and the Harvard Dataverse for comprehensive records of Republican presidential candidate votes in Indiana over the same timeframe, navigating through the electoral labyrinth much like a mouse in search of a delectable piece of cheese – or in this case, an intriguing statistical correlation.

Furthermore, our team delved into the annals of academic literature and scholarly publications to gain a deeper understanding of the potential psychosocial and cultural implications of cheese consumption, seeking to encompass the broader context of dairy habits within the political landscape. This endeavor allowed us to craft a more holistic framework for analyzing the cheese-voting relationship, much like the craft of an artisanal cheesemaker refining the intricate flavors of a well-aged Gouda.

With data in hand, our statistical analysis commenced, akin to the meticulous process of eyeing the perfect cheese wheel for a high-profile event – attention to detail was paramount. We employed a robust correlation analysis to unveil the potential ties between American cheese consumption and Republican presidential candidate votes in Indiana, utilizing advanced statistical software to slice through the data like a sharp cheese knife through a block of aged cheddar.

To account for potential confounding variables that could skew our findings faster than a slice of Gruyère at a summer picnic, we performed a series of multivariate regression analyses, incorporating factors such as demographic characteristics, economic indicators, and historical voting patterns. This multifaceted approach was akin to the art of crafting a perfectly balanced cheese board – diverse, complex, and ultimately delectable.

At each stage of our methodology, we remained ever vigilant for any potential biases that could crumble our findings like a poorly aged Parmesan, ensuring that our research maintained the integrity and rigor expected of scholarly inquiry. In doing so, we aimed to present a comprehensive analysis of the cheese-voting interplay that would be as robust and satisfying as a well-paired wine and cheese soirée.

In summary, our methodology sought to blend the precision of statistical analysis with the nuanced exploration of cheese consumption patterns and political preferences, much like the harmonious fusion of flavors in a meticulously crafted fondue. Armed with data, analytics, and a dash of humor, we endeavored to navigate through the complexities of this culinary-political intersection, emerging with findings that would tantalize the academic palate and potentially transform the way we view the dairy-laden tapestry of political allegiance.


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

Please make up the results section of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from USDA and MIT Election Data and Science Lab, Harvard Dataverse .

For the time period 1990 to 2020, you found a correlation 0.9466628, r-squared of 0.8961705, 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]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the ever-evolving landscape of political analysis, researchers have often sought to uncover the underlying factors influencing voter behavior. From socioeconomic status to ideological affiliations, the exploration of these determinants has been as varied as the toppings on a loaded baked potato. However, a lesser explored element in this proverbial political potluck is the potential role of cheese consumption in shaping voting patterns. Thus, with a sprinkle of curiosity and a dash of skepticism, we embarked on a quest to unravel the enigmatic interaction between American cheese consumption and support for the Republican presidential candidate in the state of Indiana.
The notion of cheese as a political influencer may initially elicit a skeptical eyebrow raise or perhaps a humorous pun, but the gravity of this inquiry is not to be underestimated. The dairy aisle, often overlooked in the annals of political analysis, may hold secrets as moldy as a forgotten block of Roquefort. With this provolone premise in mind, our study aims to turn this chuckle-inducing conjecture into a gouda-fide investigation worthy of scholarly contemplation.
Indiana, known for its bustling agriculture and thriving dairy industry, serves as an ideal backdrop for our cheddar-tinged exploration. As the saying goes, "In cheese we trust" – or was it "In God we trust"? We digress. The intricate dance between lactose love and political preference provides an enticing canvas upon which to uncover potential correlations, all while leaving room for a brie-thtaking discovery or two.
By harnessing the power of large-scale data sets and statistical analysis, we navigated through a myriad of spreadsheets and charts, with the occasional interruption for a cheesy snack break. In doing so, we hope to shed light on an aspect of voter behavior that may be as surprising as finding a slice of Swiss in a bowl of tomato soup – unexpected, yet oddly complementary.
With that in mind, our study aims to slice through the layers of ambiguity and delve into the creamy depths of American cheese consumption in relation to support for Republican presidential candidates in the state of Indiana. So, grab a cracker or two, and let's embark on this lactose-infused journey into the heart of political fromage. As we say in the world of academic inquiry, "Let us not be bleu, but instead, provolone in our pursuit of cheesy enlightenment."

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis unveiled a curdled correlation between American cheese consumption and support for the Republican presidential candidate in Indiana during the years 1990 to 2020. Our statistical analysis yielded a strikingly high correlation coefficient of 0.9466628, an r-squared value of 0.8961705, and a p-value less than 0.01. These findings suggest a robust and significant relationship between these variables, complementing the body of research on the multifaceted factors influencing political preferences.

To visually capture this intriguing relationship, we present Figure 1, a scatterplot showcasing the positively sloping trend between American cheese consumption and votes for the Republican presidential candidate in Indiana. The data points are as tightly packed as a wedge of aged cheddar, solidifying the strength of this connection. Our findings indicate that as American cheese consumption increases, so does the support for the Republican presidential candidate, emphasizing a cheesily compelling association that deserves further attention.

This robust relationship, with a correlation nearing 1.0, possesses a weightiness comparable to a hefty wheel of Wisconsin cheese. While correlation does not imply causation, the magnitude of this correlation sure does cause a stir in the queso of political inquiry. The implications of this discovery prompt us to ponder whether there's more to American cheese than meets the eye – or should we say taste bud?

In light of these findings, one cannot help but wonder if the phrase "cheesehead" takes on a whole new political significance in the state of Indiana. It seems that the cheesy satisfaction provided by American cheese may indeed be intertwined with political leanings, eliciting a smile as broad as the holes in a slice of Swiss cheese.

So, as we wrap up this piece of research, let us savor the gouda news of this correlation, recognizing that truth can be stranger than fiction, and sometimes cheesier too.

Next up, the discussion section, where we will feta out the implications of these findings and explore avenues for further research in the thrill-a-dairy field of political cheesemongering.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

[[LITERATURE REVIEW]]
The literature on the influence of dietary habits on political behavior is as rich and varied as the assortment of cheese at a wine and cheese party. Smith (2015) and Doe (2018) have examined the effects of food consumption on political preferences, shedding light on the potential impact of culinary choices on voting behavior. However, the specific relationship between American cheese consumption and support for the Republican presidential candidate in Indiana remains an area largely unexplored.
In "The Big Cheese: An Exploration of American Dairy Culture" (Johnson, 2007), the author delves into the historical, social, and cultural significance of American cheese, but no direct link to political preferences is established. Similarly, "Cheese and Politics: A Comparative Analysis" (Lee, 2012) provides insights into the intersection of cheese consumption and political ideologies across different countries, yet the focus on specific presidential candidate support in a U.S. state is absent.
Turning to fiction for potential clues, the novels "Cheese It Up" (Williams, 2004) and "The Gouda Conspiracy" (Patterson, 2016) playfully weave narratives that hint at the clandestine influence of cheese on political machinations, but their relevance to our study remains purely speculative.
In an unconventional approach to literature review, we also perused a diverse array of sources, including grocery store receipts, food blog comments, and even the discarded napkins of cheese aficionados. While these unconventional sources offered limited scholarly value, they did instigate bouts of uncontrollable laughter and a newfound appreciation for the peculiar abundance of cheese-related puns.
As we slice through the vast expanse of scholarly works and whimsical musings, the dearth of direct empirical evidence linking American cheese consumption to support for the Republican presidential candidate in Indiana is unmistakable. Therefore, our study aims to bridge this gap and serve up a platter of empirical findings that can finally lay this cheesy enigma to rest.

[[RESULTS]]
The results of our analysis unveiled a curdled correlation between American cheese consumption and support for the Republican presidential candidate in Indiana during the years 1990 to 2020. Our statistical analysis yielded a strikingly high correlation coefficient of 0.9466628, an r-squared value of 0.8961705, and a p-value less than 0.01. These findings suggest a robust and significant relationship between these variables, complementing the body of research on the multifaceted factors influencing political preferences.
To visually capture this intriguing relationship, we present Figure 1, a scatterplot showcasing the positively sloping trend between American cheese consumption and votes for the Republican presidential candidate in Indiana. The data points are as tightly packed as a wedge of aged cheddar, solidifying the strength of this connection. Our findings indicate that as American cheese consumption increases, so does the support for the Republican presidential candidate, emphasizing a cheesily compelling association that deserves further attention.
This robust relationship, with a correlation nearing 1.0, possesses a weightiness comparable to a hefty wheel of Wisconsin cheese. While correlation does not imply causation, the magnitude of this correlation sure does cause a stir in the queso of political inquiry. The implications of this discovery prompt us to ponder whether there's more to American cheese than meets the eye – or should we say taste bud?
In light of these findings, one cannot help but wonder if the phrase "cheesehead" takes on a whole new political significance in the state of Indiana. It seems that the cheesy satisfaction provided by American cheese may indeed be intertwined with political leanings, eliciting a smile as broad as the holes in a slice of Swiss cheese.
So, as we wrap up this piece of research, let us savor the gouda news of this correlation, recognizing that truth can be stranger than fiction, and sometimes cheesier too.
Next up, the discussion section, where we will feta out the implications of these findings and explore avenues for further research in the thrill-a-dairy field of political cheesemongering.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

In the delightful dish of political science, our study serves up a hefty slice of cheese-laden insight, demonstrating a robust and eye-opening correlation between American cheese consumption and support for the Republican presidential candidate in Indiana. Our findings add a substantial layer of provolone to the existing literature, cheese-paring away at the enigmatic relationship between dietary preferences and political ideology.

Our results lend credence to prior research by Smith (2015) and Doe (2018), who hinted at the potential impact of food consumption on political behavior. While they dabbled in the realm of culinary influence on voting patterns, our study matures into a pungent wheel of evidence, supporting and building upon their findings. The tangy taste of empirical validation adds a zesty twist to the fondue of political inquiry.

Furthermore, our study's unconventional homage to the literary musings of Williams (2004) and Patterson (2016), often dismissed as mere flights of fancy, now takes center stage as we witness reality out-cheesing fiction. The clandestine influence of cheese on political machinations, playfully hinted at in these novels, appears to have melted into the empirical fabric of our findings. Who knew that cracking open a wedge of imagination could lead us to the ripest research outcomes?

As we bask in the glow of our statistical revelation, it's hard not to exclaim, "That's nacho average correlation!" The tantalizingly high correlation coefficient reinforces the notion that there's more to American cheese than meets the palate. While correlation cannot be mistaken for causation, the magnitude of our result stands brie-tly as a standalone artifact, stirring up a gouda deal of intrigue and potential avenues for future investigational fondue-ries.

Our study also poses an intriguing question: Could the state of Indiana be a land where the "cheesehead" moniker takes on a whole new political significance? The cheesy satisfaction provided by American cheese may indeed be intertwined with political leanings, adding a velvety richness to our understanding of the political palates of Hoosiers.

So, as we gratefully savor the fromage-forward implications of our findings, let us not wallow in cheesy puns but instead look ahead to future explorations in the thrill-a-dairy field of political cheesemongering. After all, in the realm of American cheese and political preferences, it's always a gouda time for further research and cheddar-ing new insights.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between American cheese consumption and Votes for the Republican Presidential candidate in Indiana. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
"Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana"

[[ABSTRACT]]
In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.

Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

[[INTRDUCTION]]
In the ever-evolving landscape of political analysis, researchers have often sought to uncover the underlying factors influencing voter behavior. From socioeconomic status to ideological affiliations, the exploration of these determinants has been as varied as the toppings on a loaded baked potato. However, a lesser explored element in this proverbial political potluck is the potential role of cheese consumption in shaping voting patterns. Thus, with a sprinkle of curiosity and a dash of skepticism, we embarked on a quest to unravel the enigmatic interaction between American cheese consumption and support for the Republican presidential candidate in the state of Indiana.
The notion of cheese as a political influencer may initially elicit a skeptical eyebrow raise or perhaps a humorous pun, but the gravity of this inquiry is not to be underestimated. The dairy aisle, often overlooked in the annals of political analysis, may hold secrets as moldy as a forgotten block of Roquefort. With this provolone premise in mind, our study aims to turn this chuckle-inducing conjecture into a gouda-fide investigation worthy of scholarly contemplation.
Indiana, known for its bustling agriculture and thriving dairy industry, serves as an ideal backdrop for our cheddar-tinged exploration. As the saying goes, "In cheese we trust" – or was it "In God we trust"? We digress. The intricate dance between lactose love and political preference provides an enticing canvas upon which to uncover potential correlations, all while leaving room for a brie-thtaking discovery or two.
By harnessing the power of large-scale data sets and statistical analysis, we navigated through a myriad of spreadsheets and charts, with the occasional interruption for a cheesy snack break. In doing so, we hope to shed light on an aspect of voter behavior that may be as surprising as finding a slice of Swiss in a bowl of tomato soup – unexpected, yet oddly complementary.
With that in mind, our study aims to slice through the layers of ambiguity and delve into the creamy depths of American cheese consumption in relation to support for Republican presidential candidates in the state of Indiana. So, grab a cracker or two, and let's embark on this lactose-infused journey into the heart of political fromage. As we say in the world of academic inquiry, "Let us not be bleu, but instead, provolone in our pursuit of cheesy enlightenment."

[[RESULTS]]
The results of our analysis unveiled a curdled correlation between American cheese consumption and support for the Republican presidential candidate in Indiana during the years 1990 to 2020. Our statistical analysis yielded a strikingly high correlation coefficient of 0.9466628, an r-squared value of 0.8961705, and a p-value less than 0.01. These findings suggest a robust and significant relationship between these variables, complementing the body of research on the multifaceted factors influencing political preferences.
To visually capture this intriguing relationship, we present Figure 1, a scatterplot showcasing the positively sloping trend between American cheese consumption and votes for the Republican presidential candidate in Indiana. The data points are as tightly packed as a wedge of aged cheddar, solidifying the strength of this connection. Our findings indicate that as American cheese consumption increases, so does the support for the Republican presidential candidate, emphasizing a cheesily compelling association that deserves further attention.
This robust relationship, with a correlation nearing 1.0, possesses a weightiness comparable to a hefty wheel of Wisconsin cheese. While correlation does not imply causation, the magnitude of this correlation sure does cause a stir in the queso of political inquiry. The implications of this discovery prompt us to ponder whether there's more to American cheese than meets the eye – or should we say taste bud?
In light of these findings, one cannot help but wonder if the phrase "cheesehead" takes on a whole new political significance in the state of Indiana. It seems that the cheesy satisfaction provided by American cheese may indeed be intertwined with political leanings, eliciting a smile as broad as the holes in a slice of Swiss cheese.
So, as we wrap up this piece of research, let us savor the gouda news of this correlation, recognizing that truth can be stranger than fiction, and sometimes cheesier too.
Next up, the discussion section, where we will feta out the implications of these findings and explore avenues for further research in the thrill-a-dairy field of political cheesemongering.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shown a gouda-strong correlation between American cheese consumption and votes for the Republican presidential candidate in Indiana. The statistically significant relationship suggests that there might be more to this fromage-focused phenomenon than meets the eye – or the palate. It appears that Hoosiers have a penchant for both cheddar and conservative candidates, leading us to ponder whether the key to political victory truly lies in the dairy aisle.

The implications of these findings are grater than one might think. The cheesy satisfaction provided by American cheese seems to be intricately intertwined with political leanings, raising questions about the role of gastronomical preferences in shaping electoral outcomes. Could it be that a well-timed cheese tasting event could sway voter sentiments, or perhaps a campaign promise of free grilled cheese sandwiches for all?

The significance of this correlation could rival even the most mature of Parmigiano-Reggianos. This lactose-laden revelation prompts us to reevaluate the phrase "say cheese" in the realms of political strategy. It seems that the power of American cheese extends beyond its meltability and flavor – it may hold the potential to sway the hearts and stomachs of voters alike.

However, as much as we relish these findings, it's important to remember that correlation does not imply causation. While we can't attribute political leanings solely to a penchant for creamy, melty goodness, we can't help but brie curious about the underlying mechanisms at play.

In light of these curdled revelations, it's safe to say that the political landscape may be more cheesy than we initially thought – and we're not just talking about the campaign ads. But for now, we can confidently declare that the connection between American cheese consumption and political preferences in Indiana has been thoroughly investigated. So let's cut the cheese on further research in this area – it's been a gouda ride, but it's time to move on to less dairy-centric investigations. After all, there's no need to milk this topic dry.


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 Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana. Respond only with the name of a fictional academic journal.

ChatGPT:

The Cheese Chronicle


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 Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Dairy Politics and Culinary Research


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 Say Cheese: The Gouda, the Bad, and the Ugly - Exploring the Relationship between American Cheese Consumption and Votes for the Republican Presidential Candidate in Indiana with an abstract of In the pursuit of dairy derring-do, our study delves into the curdled connection between American cheese consumption and voting behavior in the Hoosier state. With a cheesy grin and a hint of political intrigue, we harnessed the power of USDA and MIT Election Data and Science Lab, Harvard Dataverse to unravel the enigmatic link between cheese intake and Republican presidential candidate support from 1990 to 2020.
Our findings paint a picture sharper than cheddar, as a correlation coefficient of 0.9466628 and p < 0.01 left us graterly surprised. This titillating tidbit suggests that there might indeed be something more than just a fondue of fantasy at play. The implications of our fromage-forward research could be a game-changer in understanding the fromage politique of the American electorate. So, grab a slice of cheese, and let's delve into the gooey complexities of political palates and dairy delights.

ChatGPT:

American cheese consumption, Republican presidential candidate support, Indiana voting behavior, correlation between cheese intake and political affiliation, USDA cheese consumption data, MIT Election Data and Science Lab, Harvard Dataverse, dairy consumption and voting behavior, relationship between food preferences and political affiliation

*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

American cheese consumption
Detailed data title: Per capita consumption of American cheese in the US
Source: USDA
See what else correlates with American cheese consumption

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

Correlation r = 0.9466628 (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 = 0.8961705 (Coefficient of determination)
This means 89.6% of the change in the one variable (i.e., Votes for the Republican Presidential candidate in Indiana) is predictable based on the change in the other (i.e., American cheese consumption) over the 8 years from 1990 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00036. 0.0003643280145253126000000000
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 0.95 in 0.036% of random cases. Said differently, if you correlated 2,745 random variables Which I absolutely did.
with the same 7 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 7 because we have two variables measured over a period of 8 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.

[ 0.73, 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.
19921996200020042008201220162020
American cheese consumption (Pounds per person)11.255911.808712.683912.861213.130613.256914.362115.5
Votes for the Republican Presidential candidate in Indiana (Total votes)9893751006690124584014794401345650142054015572901729520




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. Confounding variable: 2020 is particularly different from the other years on this graph. Confounding variables (like global pandemics) will cause two variables to look connected when in fact a "sneaky third" variable is influencing both of them behind the scenes.
  5. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.




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([11.2559,11.8087,12.6839,12.8612,13.1306,13.2569,14.3621,15.5,])
array_2 = np.array([989375,1006690,1245840,1479440,1345650,1420540,1557290,1729520,])
array_1_name = "American cheese consumption"
array_2_name = "Votes for the Republican Presidential candidate in Indiana"

# 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?

Thanks for being the explorer we needed!


Correlation ID: 4336 · Black Variable ID: 553 · Red Variable ID: 25977
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0