about · email me · subscribe
Spurious correlation #5,371 · 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 Democratic Senators in Mississippi.  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 increased, so did the level of cheesiness in political ads. This inadvertently led to an upswell of support for Democrat Senators in Mississippi as the ads resonated with voters on a subconscious, dairy-induced level. Remember, when it comes to politics, it's all about the havarti of the people.

Model: dalle-3
Prompt: An image that looks like it is a scene from A Disney Movie where in a Mississippi living room, a TV blares with a political ad featuring a senatorial candidate amidst a flood of American cheese. A family gathers around, enjoying grilled cheese sandwiches, as the orange-hued commercial plays on the screen. The ad's amplified cheesiness is reflected in the increasing consumption of American cheese. As the family bites into their sandwiches, the Democratic candidate's message seems to resonate with them, leading to an increase in votes for Democratic Senators in Mississippi. This should be depicted in a warm and inviting living room setting with an enchanted, almost whimsical mood, showcasing animated characters and a magical glow emanating from the TV as the cheesy ad plays. 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 Democratic Senators in Mississippi. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: inspired by bauhaus Charcoal Futuristic Cyber folk An image that looks like it is a scene from A Disney Movie
ChatGPT: An image that looks like it is a scene from A Disney Movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both American cheese consumption and Votes for Democratic Senators in Mississippi, in the following situation: As American cheese consumption increased, so did the level of cheesiness in political ads. This inadvertently led to an upswell of support for Democrat Senators in Mississippi as the ads resonated with voters on a subconscious, dairy-induced level. Remember, when it comes to politics, it's all about the havarti of the people.. Keep the description simple.
ChatGPT: In a Mississippi living room, a TV blares with a political ad featuring a senatorial candidate amidst a flood of American cheese. A family gathers around, enjoying grilled cheese sandwiches, as the orange-hued commercial plays on the screen. The ad's amplified cheesiness is reflected in the increasing consumption of American cheese. As the family bites into their sandwiches, the Democratic candidate's message seems to resonate with them, leading to an increase in votes for Democratic Senators in Mississippi.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from A Disney Movie ] and depicting this scene: In a Mississippi living room, a TV blares with a political ad featuring a senatorial candidate amidst a flood of American cheese. A family gathers around, enjoying grilled cheese sandwiches, as the orange-hued commercial plays on the screen. The ad's amplified cheesiness is reflected in the increasing consumption of American cheese. As the family bites into their sandwiches, the Democratic candidate's message seems to resonate with them, leading to an increase in votes for Democratic Senators in Mississippi. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: An image that looks like it is a scene from A Disney Movie where in a Mississippi living room, a TV blares with a political ad featuring a senatorial candidate amidst a flood of American cheese. A family gathers around, enjoying grilled cheese sandwiches, as the orange-hued commercial plays on the screen. The ad's amplified cheesiness is reflected in the increasing consumption of American cheese. As the family bites into their sandwiches, the Democratic candidate's message seems to resonate with them, leading to an increase in votes for Democratic Senators in Mississippi. This should be depicted in a warm and inviting living room setting with an enchanted, almost whimsical mood, showcasing animated characters and a magical glow emanating from the TV as the cheesy ad plays.

*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 Democrat votes for Senators in Mississippi to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

The Journal of Dairy Political Science

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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title a clever pun.

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 0.8120008 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]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."


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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

When it comes to understanding the intricate dance of political preferences, researchers have long sought out unique and often unorthodox variables to unearth the complex dynamics at play. In our case, we couldn't resist diving into the delightful world of cheese to investigate its potential link to political leanings. As the saying goes, "Why did the cheese go to the museum? Because it's a-mature." With this in mind, our study aims to unravel the curious connection between American cheese consumption and Democrat votes for Senators in Mississippi.

One might question the validity of such an investigation, but as scientists, we are firm believers in the power of data to reveal unexpected patterns. After all, as researchers, we know that even the humblest of variables, such as cheese consumption, can churn out significant correlations. Speaking of which, did you hear about the scientific study on dairy products? Apparently, they've got a lot of whey to go.

Before diving into the cheesy details, it's crucial to acknowledge the inherent absurdity of our research question. However, as we venture into this uncharted territory, we can't help but appreciate the humorous aspect of our investigation. They say that laughter is the best medicine, but it's also a great way to cope with questionable research ideas. Besides, who doesn't love a good gouda dad joke every now and then?

Navigating through the sea of statistical analyses and political theories, we embarked on our quest armed with data from reputable sources, including the USDA, MIT Election Data and Science Lab, and Harvard Dataverse. As we waded through spreadsheets and graphs, the age-old question lingered in our minds: What do you call cheese that isn't yours? Nacho cheese! Oh, the perils of cheesy humor in academia.

Our findings, as we shall elucidate in the subsequent sections, unearthed a surprising correlation coefficient of 0.8120008 and a p-value less than 0.01. These numbers may seem bland at first, but they signify a statistically significant relationship between American cheese consumption and Democrat votes for Senators in Mississippi. It appears that the love for American cheese and political affiliations may share a more profound connection than meets the eye.

So, as we delve into our findings, let's embrace the quirkiness of our research and savor the 'gouda' moments it brings. After all, who knew that cheese could pack such a political punch in the heart of Mississippi?


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 Democrat votes for Senators in Mississippi. 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 few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
When it comes to understanding the intricate dance of political preferences, researchers have long sought out unique and often unorthodox variables to unearth the complex dynamics at play. In our case, we couldn't resist diving into the delightful world of cheese to investigate its potential link to political leanings. As the saying goes, "Why did the cheese go to the museum? Because it's a-mature." With this in mind, our study aims to unravel the curious connection between American cheese consumption and Democrat votes for Senators in Mississippi.
One might question the validity of such an investigation, but as scientists, we are firm believers in the power of data to reveal unexpected patterns. After all, as researchers, we know that even the humblest of variables, such as cheese consumption, can churn out significant correlations. Speaking of which, did you hear about the scientific study on dairy products? Apparently, they've got a lot of whey to go.
Before diving into the cheesy details, it's crucial to acknowledge the inherent absurdity of our research question. However, as we venture into this uncharted territory, we can't help but appreciate the humorous aspect of our investigation. They say that laughter is the best medicine, but it's also a great way to cope with questionable research ideas. Besides, who doesn't love a good gouda dad joke every now and then?
Navigating through the sea of statistical analyses and political theories, we embarked on our quest armed with data from reputable sources, including the USDA, MIT Election Data and Science Lab, and Harvard Dataverse. As we waded through spreadsheets and graphs, the age-old question lingered in our minds: What do you call cheese that isn't yours? Nacho cheese! Oh, the perils of cheesy humor in academia.
Our findings, as we shall elucidate in the subsequent sections, unearthed a surprising correlation coefficient of 0.8120008 and a p-value less than 0.01. These numbers may seem bland at first, but they signify a statistically significant relationship between American cheese consumption and Democrat votes for Senators in Mississippi. It appears that the love for American cheese and political affiliations may share a more profound connection than meets the eye.
So, as we delve into our findings, let's embrace the quirkiness of our research and savor the 'gouda' moments it brings. After all, who knew that cheese could pack such a political punch in the heart of Mississippi?

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
**[[LITERATURE REVIEW]]**

In their seminal work, Smith et al. (2015) examined the dietary habits and political inclinations of residents in southeastern states, laying the groundwork for our investigation into the peculiar nexus of American cheese consumption and Democrat votes for Senators in Mississippi. The authors discovered a nuanced relationship between food preferences and electoral behavior, opening the door to the tantalizing prospect of cheese-based political analysis. Speaking of cheese-based analysis, why did the cheese lover refuse to share? Because he was too gouda at it!

Doe and Jones (2017) conducted an exhaustive study on voting patterns in Mississippi, delving into demographic factors and historical trends to decipher the complex tapestry of political allegiances. While their research did not directly touch upon cheese consumption, their findings underscored the multifaceted nature of electoral dynamics in the state. It's like they say, researching political preferences is like a wheel of cheese - it's full of holes but still holds together.

Moving beyond scholarly articles, the world of non-fiction literature offers valuable insights into the cultural and culinary significance of cheese in American society. In "The Oxford Companion to Cheese," the authors expound upon the diverse range of cheese varieties adored by the American populace, cementing the place of cheese as a beloved culinary staple across the nation. It's no wonder cheese plays such a crucial role in shaping public opinion; after all, it's always mature enough to sway our preferences.

On the fictional front, works like "Cheese and Politics: A Tale of Two Obsessions" by Fictional Author emphasize the symbolic weight of cheese as a metaphor for power struggles and social dynamics. While purely fictitious, such literary explorations provide an imaginative lens through which to view the intersection of food and politics. It's almost like they're saying, "All's fair in love and war, but especially when it comes to cheese."

Television has also offered its share of illuminating content, with shows like "The Great Cheese Debate" amplifying the cultural significance of cheese consumption and its potential influence on decision-making processes. Through our extensive and totally academic binge-watching sessions, we've gleaned invaluable insights into the art of cheese appreciation and its resonance with societal norms. Whether it's string cheese pulling people together or blue cheese dividing them, the impact of cheese is undeniable.

As we wade through this smorgasbord of literary and media influences, it becomes evident that the study of American cheese consumption and its correlation with Democrat votes for Senators in Mississippi is not just a matter of statistical analysis, but an exploration of the quirky, enchanting, and occasionally absurd dimensions of human behavior. So, let's fondue deeper into the cheesy abyss, shall we?


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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

[[INTRODUCTION]]
When it comes to understanding the intricate dance of political preferences, researchers have long sought out unique and often unorthodox variables to unearth the complex dynamics at play. In our case, we couldn't resist diving into the delightful world of cheese to investigate its potential link to political leanings. As the saying goes, "Why did the cheese go to the museum? Because it's a-mature." With this in mind, our study aims to unravel the curious connection between American cheese consumption and Democrat votes for Senators in Mississippi.
One might question the validity of such an investigation, but as scientists, we are firm believers in the power of data to reveal unexpected patterns. After all, as researchers, we know that even the humblest of variables, such as cheese consumption, can churn out significant correlations. Speaking of which, did you hear about the scientific study on dairy products? Apparently, they've got a lot of whey to go.
Before diving into the cheesy details, it's crucial to acknowledge the inherent absurdity of our research question. However, as we venture into this uncharted territory, we can't help but appreciate the humorous aspect of our investigation. They say that laughter is the best medicine, but it's also a great way to cope with questionable research ideas. Besides, who doesn't love a good gouda dad joke every now and then?
Navigating through the sea of statistical analyses and political theories, we embarked on our quest armed with data from reputable sources, including the USDA, MIT Election Data and Science Lab, and Harvard Dataverse. As we waded through spreadsheets and graphs, the age-old question lingered in our minds: What do you call cheese that isn't yours? Nacho cheese! Oh, the perils of cheesy humor in academia.
Our findings, as we shall elucidate in the subsequent sections, unearthed a surprising correlation coefficient of 0.8120008 and a p-value less than 0.01. These numbers may seem bland at first, but they signify a statistically significant relationship between American cheese consumption and Democrat votes for Senators in Mississippi. It appears that the love for American cheese and political affiliations may share a more profound connection than meets the eye.
So, as we delve into our findings, let's embrace the quirkiness of our research and savor the 'gouda' moments it brings. After all, who knew that cheese could pack such a political punch in the heart of Mississippi?

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To establish a robust foundation for our investigation, we ventured into the labyrinth of research methods with the curiosity of a mouse in a cheese factory (although we promise to exercise more restraint than the said mouse). Our data collection process, akin to carefully selecting the finest cheese for a charcuterie board, involved procuring information from various sources, primarily the USDA, MIT Election Data and Science Lab, and the Harvard Dataverse. We gathered data spanning from 1990 to 2020, ensuring a chunky sample size that would melt away any doubts about the rigor of our study.

Before we could sink our teeth into the analysis, we had to ensure that the data we selected was as fresh as a block of newly aged cheddar. Our team meticulously combed through an assortment of datasets, making sure to slice away any outliers that could potentially skew our results. This process demanded a level of precision akin to separating curds from whey – a task not for the faint of heart or the lactose intolerant!

Given the nature of our research question, we incorporated an array of statistical methods that would typically make even the most seasoned analysts crumble like a dry biscuit. Our toolkit included a multi-variant regression analysis, a chi-squared test, and a few other statistical tools that we won't bore you with - after all, we wouldn't want to sound too cheesy. These analyses allowed us to slice and dice the data, serving up a platter of insights into the savory relationship between American cheese consumption and Democrat votes for Senators in Mississippi.

To ensure the robustness of our findings, we also conducted a sensitivity analysis, akin to tasting the same cheese in different pairings to gauge its flavor profile. This process involved tweaking various parameters within our models to ascertain the stability of our results, guarding against any unexpected stinkers that could sour the credibility of our study.

In addition to the quantitative analyses, we also delved into qualitative research by conducting interviews with Mississippi residents. These interviews not only provided a human touch to our study but also allowed us to delve deeper into the nuanced reasons behind their cheese preferences and political affiliations. Plus, it offered a delightful break from the monotony of crunching numbers – a welcome reprieve, much like a cheese platter in the midst of a bland scientific symposium.

With our methodology as sharp as a freshly honed grater, we proceeded to carve through the data with the precision of a cheese sculptor, unearthing the intriguing relationship between American cheese consumption and Democrat votes for senators in Mississippi.

Oh, and speaking of cheese, did you hear about the explosion at the cheese factory? All that was left was de Brie!


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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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 0.8120008, r-squared of 0.6593453, 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]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
When it comes to understanding the intricate dance of political preferences, researchers have long sought out unique and often unorthodox variables to unearth the complex dynamics at play. In our case, we couldn't resist diving into the delightful world of cheese to investigate its potential link to political leanings. As the saying goes, "Why did the cheese go to the museum? Because it's a-mature." With this in mind, our study aims to unravel the curious connection between American cheese consumption and Democrat votes for Senators in Mississippi.
One might question the validity of such an investigation, but as scientists, we are firm believers in the power of data to reveal unexpected patterns. After all, as researchers, we know that even the humblest of variables, such as cheese consumption, can churn out significant correlations. Speaking of which, did you hear about the scientific study on dairy products? Apparently, they've got a lot of whey to go.
Before diving into the cheesy details, it's crucial to acknowledge the inherent absurdity of our research question. However, as we venture into this uncharted territory, we can't help but appreciate the humorous aspect of our investigation. They say that laughter is the best medicine, but it's also a great way to cope with questionable research ideas. Besides, who doesn't love a good gouda dad joke every now and then?
Navigating through the sea of statistical analyses and political theories, we embarked on our quest armed with data from reputable sources, including the USDA, MIT Election Data and Science Lab, and Harvard Dataverse. As we waded through spreadsheets and graphs, the age-old question lingered in our minds: What do you call cheese that isn't yours? Nacho cheese! Oh, the perils of cheesy humor in academia.
Our findings, as we shall elucidate in the subsequent sections, unearthed a surprising correlation coefficient of 0.8120008 and a p-value less than 0.01. These numbers may seem bland at first, but they signify a statistically significant relationship between American cheese consumption and Democrat votes for Senators in Mississippi. It appears that the love for American cheese and political affiliations may share a more profound connection than meets the eye.
So, as we delve into our findings, let's embrace the quirkiness of our research and savor the 'gouda' moments it brings. After all, who knew that cheese could pack such a political punch in the heart of Mississippi?

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon analyzing the data collected from the USDA, MIT Election Data and Science Lab, and Harvard Dataverse, we found a strong positive correlation between American cheese consumption and Democrat votes for Senators in Mississippi during the period of 1990 to 2020. The correlation coefficient of 0.8120008 and an r-squared value of 0.6593453 indicated a robust relationship between the variables, with a p-value of less than 0.01.

Fig. 1 displays a scatterplot revealing the striking association between American cheese consumption and Democrat votes for Senators in Mississippi. It's quite a gouda sight, if I do say so myself!

It's fascinating to think that something as seemingly unrelated as cheese consumption might have an impact on political leanings. Who would have thought that the humble slice of American cheese could hold such political sway? It's almost as surprising as finding a hidden cheese stash in the lab fridge!

Our results provide compelling evidence of a noteworthy connection between these variables. Even the most ardent skeptics will have to admit that this correlation is no mere coincidence; it's as real as the holes in a slice of Swiss cheese.

Our findings lay the groundwork for future research endeavors exploring the mechanisms underpinning this unexpected correlation. Perhaps we'll uncover the "wheys" in which cheese preferences intertwine with political consciousness, or the "cheddar" that binds them together. This discovery opens the door to a multitude of "gouda" research opportunities.

In the realm of scientific inquiry, it's essential to embrace the unexpected and sometimes unconventional findings. Who knows what other surprising correlations may emerge from the depths of data analysis? With enough determination and a good sense of humor, we might just find ourselves knee-deep in the cheese-filled world of unlikely statistical relationships. After all, in the words of Thomas Edison, "To invent, you need a good imagination and a pile of junk."

The results of our research not only illuminate the political nuances of Mississippi but also serve as a lighthearted reminder of the somewhat whimsical nature of scientific exploration. Who says research can't be both enlightening and a little bit "cheesy"?


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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

[[LITERATURE REVIEW]]
In their seminal work, Smith et al. (2015) examined the dietary habits and political inclinations of residents in southeastern states, laying the groundwork for our investigation into the peculiar nexus of American cheese consumption and Democrat votes for Senators in Mississippi. The authors discovered a nuanced relationship between food preferences and electoral behavior, opening the door to the tantalizing prospect of cheese-based political analysis. Speaking of cheese-based analysis, why did the cheese lover refuse to share? Because he was too gouda at it!
Doe and Jones (2017) conducted an exhaustive study on voting patterns in Mississippi, delving into demographic factors and historical trends to decipher the complex tapestry of political allegiances. While their research did not directly touch upon cheese consumption, their findings underscored the multifaceted nature of electoral dynamics in the state. It's like they say, researching political preferences is like a wheel of cheese - it's full of holes but still holds together.
Moving beyond scholarly articles, the world of non-fiction literature offers valuable insights into the cultural and culinary significance of cheese in American society. In "The Oxford Companion to Cheese," the authors expound upon the diverse range of cheese varieties adored by the American populace, cementing the place of cheese as a beloved culinary staple across the nation. It's no wonder cheese plays such a crucial role in shaping public opinion; after all, it's always mature enough to sway our preferences.
On the fictional front, works like "Cheese and Politics: A Tale of Two Obsessions" by Fictional Author emphasize the symbolic weight of cheese as a metaphor for power struggles and social dynamics. While purely fictitious, such literary explorations provide an imaginative lens through which to view the intersection of food and politics. It's almost like they're saying, "All's fair in love and war, but especially when it comes to cheese."
Television has also offered its share of illuminating content, with shows like "The Great Cheese Debate" amplifying the cultural significance of cheese consumption and its potential influence on decision-making processes. Through our extensive and totally academic binge-watching sessions, we've gleaned invaluable insights into the art of cheese appreciation and its resonance with societal norms. Whether it's string cheese pulling people together or blue cheese dividing them, the impact of cheese is undeniable.
As we wade through this smorgasbord of literary and media influences, it becomes evident that the study of American cheese consumption and its correlation with Democrat votes for Senators in Mississippi is not just a matter of statistical analysis, but an exploration of the quirky, enchanting, and occasionally absurd dimensions of human behavior. So, let's fondue deeper into the cheesy abyss, shall we?

[[RESULTS]]
Upon analyzing the data collected from the USDA, MIT Election Data and Science Lab, and Harvard Dataverse, we found a strong positive correlation between American cheese consumption and Democrat votes for Senators in Mississippi during the period of 1990 to 2020. The correlation coefficient of 0.8120008 and an r-squared value of 0.6593453 indicated a robust relationship between the variables, with a p-value of less than 0.01.
Fig. 1 displays a scatterplot revealing the striking association between American cheese consumption and Democrat votes for Senators in Mississippi. It's quite a gouda sight, if I do say so myself!
It's fascinating to think that something as seemingly unrelated as cheese consumption might have an impact on political leanings. Who would have thought that the humble slice of American cheese could hold such political sway? It's almost as surprising as finding a hidden cheese stash in the lab fridge!
Our results provide compelling evidence of a noteworthy connection between these variables. Even the most ardent skeptics will have to admit that this correlation is no mere coincidence; it's as real as the holes in a slice of Swiss cheese.
Our findings lay the groundwork for future research endeavors exploring the mechanisms underpinning this unexpected correlation. Perhaps we'll uncover the "wheys" in which cheese preferences intertwine with political consciousness, or the "cheddar" that binds them together. This discovery opens the door to a multitude of "gouda" research opportunities.
In the realm of scientific inquiry, it's essential to embrace the unexpected and sometimes unconventional findings. Who knows what other surprising correlations may emerge from the depths of data analysis? With enough determination and a good sense of humor, we might just find ourselves knee-deep in the cheese-filled world of unlikely statistical relationships. After all, in the words of Thomas Edison, "To invent, you need a good imagination and a pile of junk."
The results of our research not only illuminate the political nuances of Mississippi but also serve as a lighthearted reminder of the somewhat whimsical nature of scientific exploration. Who says research can't be both enlightening and a little bit "cheesy"?

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our study ventured into uncharted territory, exploring the entwined realms of American cheese consumption and Democrat votes for Senators in Mississippi. The correlation coefficient of 0.8120008 and a p-value less than 0.01 paint a compelling picture of the surprising relationship between these variables. Now, before we get too "grated" away by these statistics, let's delve into the potential implications and avenues for further research.

Our results coalesce with the foundational work of Smith et al. (2015), who first broached the uncharted territory of cheese-based political analysis. The "wheys" in which dietary habits interlace with political allegiances are no longer a mere "brie"-f hypothesis but a tangible reality. Speaking of which, did you hear about the cheesemonger who fell off his delivery truck? He de-brie-ed.

Additionally, our findings align with the comprehensive work of Doe and Jones (2017), despite their lack of direct emphasis on cheese consumption. The multifaceted nature of electoral dynamics in Mississippi has finally been "aged" like a fine cheese, unveiling the intricate layers of influence shaping voter behavior. It's like a scientific "wheel" of fortune punctuated with holes of insight.

Our investigation syncs with the broader cultural and culinary significance of cheese in American society, as expounded upon in "The Oxford Companion to Cheese." The impact of cheese on public opinion is not just a matter of conjecture; it's as "mature" as a well-aged cheddar, influencing tastes and preferences in unforeseen ways. Just as a slice of cheese has the power to elevate the humdrum sandwich, so too does it seem to elevate political leanings.

The unexpected correlation between American cheese consumption and Democrat votes for Senators in Mississippi unveils a "gouda" research opportunity. By peeling back the layers of statistical cheese, we may uncover the "cheddar" that binds these variables or the "wheys" in which they intertwine. This unlikely nexus opens the door to "gouda" research opportunities, and who knows what other surprising correlations may "emerge" from the depths of data analysis?

In closing this discussion, we cannot help but emphasize the playful nature of our findings. As we navigate the intricate landscape of science and research, it's important to embrace the unexpected with a good sense of humor. After all, who says a lighthearted investigation can't be as enlightening as it is "cheesy"? As the great Benjamin Disraeli once said, "Change is inevitable, except from a vending machine."

Now, I'll leave you with a final one: Why did the cheese go to the art exhibit? Because it wanted to get cultured!


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 Democrat votes for Senators in Mississippi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi

[[ABSTRACT]]
In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.

As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.

Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine."

[[INTRDUCTION]]
When it comes to understanding the intricate dance of political preferences, researchers have long sought out unique and often unorthodox variables to unearth the complex dynamics at play. In our case, we couldn't resist diving into the delightful world of cheese to investigate its potential link to political leanings. As the saying goes, "Why did the cheese go to the museum? Because it's a-mature." With this in mind, our study aims to unravel the curious connection between American cheese consumption and Democrat votes for Senators in Mississippi.
One might question the validity of such an investigation, but as scientists, we are firm believers in the power of data to reveal unexpected patterns. After all, as researchers, we know that even the humblest of variables, such as cheese consumption, can churn out significant correlations. Speaking of which, did you hear about the scientific study on dairy products? Apparently, they've got a lot of whey to go.
Before diving into the cheesy details, it's crucial to acknowledge the inherent absurdity of our research question. However, as we venture into this uncharted territory, we can't help but appreciate the humorous aspect of our investigation. They say that laughter is the best medicine, but it's also a great way to cope with questionable research ideas. Besides, who doesn't love a good gouda dad joke every now and then?
Navigating through the sea of statistical analyses and political theories, we embarked on our quest armed with data from reputable sources, including the USDA, MIT Election Data and Science Lab, and Harvard Dataverse. As we waded through spreadsheets and graphs, the age-old question lingered in our minds: What do you call cheese that isn't yours? Nacho cheese! Oh, the perils of cheesy humor in academia.
Our findings, as we shall elucidate in the subsequent sections, unearthed a surprising correlation coefficient of 0.8120008 and a p-value less than 0.01. These numbers may seem bland at first, but they signify a statistically significant relationship between American cheese consumption and Democrat votes for Senators in Mississippi. It appears that the love for American cheese and political affiliations may share a more profound connection than meets the eye.
So, as we delve into our findings, let's embrace the quirkiness of our research and savor the 'gouda' moments it brings. After all, who knew that cheese could pack such a political punch in the heart of Mississippi?

[[RESULTS]]
Upon analyzing the data collected from the USDA, MIT Election Data and Science Lab, and Harvard Dataverse, we found a strong positive correlation between American cheese consumption and Democrat votes for Senators in Mississippi during the period of 1990 to 2020. The correlation coefficient of 0.8120008 and an r-squared value of 0.6593453 indicated a robust relationship between the variables, with a p-value of less than 0.01.
Fig. 1 displays a scatterplot revealing the striking association between American cheese consumption and Democrat votes for Senators in Mississippi. It's quite a gouda sight, if I do say so myself!
It's fascinating to think that something as seemingly unrelated as cheese consumption might have an impact on political leanings. Who would have thought that the humble slice of American cheese could hold such political sway? It's almost as surprising as finding a hidden cheese stash in the lab fridge!
Our results provide compelling evidence of a noteworthy connection between these variables. Even the most ardent skeptics will have to admit that this correlation is no mere coincidence; it's as real as the holes in a slice of Swiss cheese.
Our findings lay the groundwork for future research endeavors exploring the mechanisms underpinning this unexpected correlation. Perhaps we'll uncover the "wheys" in which cheese preferences intertwine with political consciousness, or the "cheddar" that binds them together. This discovery opens the door to a multitude of "gouda" research opportunities.
In the realm of scientific inquiry, it's essential to embrace the unexpected and sometimes unconventional findings. Who knows what other surprising correlations may emerge from the depths of data analysis? With enough determination and a good sense of humor, we might just find ourselves knee-deep in the cheese-filled world of unlikely statistical relationships. After all, in the words of Thomas Edison, "To invent, you need a good imagination and a pile of junk."
The results of our research not only illuminate the political nuances of Mississippi but also serve as a lighthearted reminder of the somewhat whimsical nature of scientific exploration. Who says research can't be both enlightening and a little bit "cheesy"?

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has demonstrated a statistically significant correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Who would have thought that political leanings could be intertwined with the love for a good old slice of American cheese? It's a gouda surprise, indeed! Perhaps we should start referring to political allegiances as "bleupartisan" to capture this cheesy connection.

Our findings bolster the argument that even the most unexpected variables can reveal intriguing patterns. It's proof that in the realm of statistical analysis, one can't simply brush off seemingly unrelated factors as mere coincidences. After all, there's a reason they say, "It's all gouda."

Our research, while lighthearted in nature, has not only unveiled an enthralling correlation but also opened the door to a world of possibilities for future investigations. Who knows what other unexpected relationships lie hidden beneath the veneer of mundane variables? The world of research is as full of surprises as a camembert cheese platter at a wine and cheese party!

So, as we wrap up this study, we can confidently assert that our findings present a compelling case for the intersection of American cheese consumption and political leaning. It's a fascinating notion that adds a dash of peppery jack to the already spicy realm of political research.

In the words of Benjamin Franklin, "In this world, nothing can be said to be certain, except death, taxes, and the unexpected correlations in statistical analysis." With that in mind, it is clear that no more research is needed in this area. After all, we've already milked this topic for all its worth!

And remember, always approach statistical research with a sense of humor. After all, as researchers, we know that sometimes the "whey" forward is through a "gouda" pun or two.

So, there you have it! Our research has indeed been as enlightening as it has been "cheesy." With that, it's time to bid adieu to this gouda adventure in statistical exploration.


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 Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Political Science


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Dairy Policy and Political Science


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 Gouda Democrats: The Cheddar Connection between American Cheese Consumption and Democrat Votes for Senators in Mississippi with an abstract of In this paper, we tackle the age-old question of whether there is a correlation between American cheese consumption and Democrat votes for Senators in Mississippi. Our team gathered and analyzed data from the USDA and MIT Election Data and Science Lab, and Harvard Dataverse, covering a period from 1990 to 2020. To our surprise (and delight, of course), we uncovered a correlation coefficient of 0.8120008 and a p-value less than 0.01, indicating a statistically significant relationship between these seemingly unrelated variables.
As we delved into the data, we couldn't help but crack a few cheesy jokes. Speaking of which, did you hear about the cheese factory that exploded in France? There was nothing left but de Brie! Anyway, the findings of our research not only shed light on the political landscape of Mississippi but also provide an avenue for some 'grate' discussions on the broader impact of cheese preferences on voting behavior.
Our results may prompt further investigations into the underlying mechanisms driving this correlation, but for now, we hope our study adds a slice of levity to the often-serious realm of political research. After all, in the words of Benjamin Disraeli, "Change is inevitable. Except from a vending machine.

ChatGPT:

American cheese consumption, Democrat votes, Senators in Mississippi, correlation analysis, USDA data, MIT Election Data and Science Lab, Harvard Dataverse, cheese preferences, voting behavior, political landscape Mississippi, correlation coefficient, statistical significance, cheese jokes, voting behavior mechanisms

*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 Democratic Senators in Mississippi
Detailed data title: Total number of votes cast for Federal Democrat Senate candidates in Mississippi
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for Democratic Senators in Mississippi

Correlation r = 0.8120008 (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 = 0.6593453 (Coefficient of determination)
This means 65.9% of the change in the one variable (i.e., Votes for Democratic Senators in Mississippi) is predictable based on the change in the other (i.e., American cheese consumption) over the 9 years from 1990 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0079. 0.0078508439919694870000000000
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 0.81 in 0.79% of random cases. Said differently, if you correlated 127 random variables Which I absolutely did.
with the same 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 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.

[ 0.32, 0.96 ] 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.
199419962000200620082012201420182020
American cheese consumption (Pounds per person)11.423711.808712.683913.065613.130613.256913.665615.402715.5
Votes for Democratic Senators in Mississippi (Total votes)189752240647314090213000480915503467239439790386578691




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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. 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.
  5. 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([11.4237,11.8087,12.6839,13.0656,13.1306,13.2569,13.6656,15.4027,15.5,])
array_2 = np.array([189752,240647,314090,213000,480915,503467,239439,790386,578691,])
array_1_name = "American cheese consumption"
array_2_name = "Votes for Democratic Senators in Mississippi"

# 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 shining a light on this correlation!


Correlation ID: 5371 · Black Variable ID: 553 · Red Variable ID: 26263
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0