about · email me · subscribe
Spurious correlation #5,296 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Milk consumption and the second variable is Votes for the Democratic Presidential candidate in West Virginia.  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

Fewer milk mustaches led to a decrease in political favor. Turns out, lactose dissent-tolerant voters curdled the results. The dairy-airy election platform failed to butter up the electorate. It seems the state was not in the mooo-d for democratic change.

Model: dalle-3
Prompt: Style: A funny image you would see on reddit Description: In a quaint West Virginia diner, a row of disheartened voters with "I Voted" stickers on their lapels sits sipping black coffee, as half-empty milk cartons sit untouched at their table. The TV in the corner displays the election results, showing a map of the state shaded in blue for the Democratic candidate, while the milk delivery truck outside remains unattended, with crates of curdling milk waiting to be unloaded. Image prompt: Generate an image of a group of solemn-looking people in a diner, with "I Voted" stickers on their lapels, sipping coffee. The TV in the corner of the diner is showing election results with the state map shaded in blue. Outside the diner, there is a milk delivery truck with unattended crates of curdling milk. 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: Milk consumption and Votes for the Democratic Presidential candidate in West Virginia. 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: a Polaroid photo Cyberpunk Scalar art Psychedelic a funny image you would see on reddit
ChatGPT: a funny image you would see on reddit

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 Milk consumption and Votes for the Democratic Presidential candidate in West Virginia, in the following situation: Fewer milk mustaches led to a decrease in political favor. Turns out, lactose dissent-tolerant voters curdled the results. The dairy-airy election platform failed to butter up the electorate. It seems the state was not in the mooo-d for democratic change.. Keep the description simple.
ChatGPT: In a quaint West Virginia diner, a row of disheartened voters with "I Voted" stickers on their lapels sits sipping black coffee, as half-empty milk cartons sit untouched at their table. The TV in the corner displays the election results, showing a map of the state shaded in blue for the Democratic candidate, while the milk delivery truck outside remains unattended, with crates of curdling milk waiting to be unloaded.

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 you would see on reddit ] and depicting this scene: In a quaint West Virginia diner, a row of disheartened voters with "I Voted" stickers on their lapels sits sipping black coffee, as half-empty milk cartons sit untouched at their table. The TV in the corner displays the election results, showing a map of the state shaded in blue for the Democratic candidate, while the milk delivery truck outside remains unattended, with crates of curdling milk waiting to be unloaded. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Style: A funny image you would see on reddit Description: In a quaint West Virginia diner, a row of disheartened voters with "I Voted" stickers on their lapels sits sipping black coffee, as half-empty milk cartons sit untouched at their table. The TV in the corner displays the election results, showing a map of the state shaded in blue for the Democratic candidate, while the milk delivery truck outside remains unattended, with crates of curdling milk waiting to be unloaded. Image prompt: Generate an image of a group of solemn-looking people in a diner, with "I Voted" stickers on their lapels, sipping coffee. The TV in the corner of the diner is showing election results with the state map shaded in blue. Outside the diner, there is a milk delivery truck with unattended crates of curdling milk.

*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 a decrease in Milk consumption caused Votes for the Democrat Presidential candidate in West Virginia to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

The Journal of Dairy Politics and Consumption

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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title an alliteration.

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 0.9483382 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The study of the factors influencing voters' decisions is as diverse and multifaceted as the flavors of ice cream at a dairy farm. One such factor that has captured our attention is the potential link between milk consumption and votes for the Democrat Presidential candidate in the charming state of West Virginia. This investigation aims to churn up some insight into whether a county's preference for dairy products could be associated with political preferences.

As the saying goes, "Why did the cow go to outer space? To visit the Milky Way!" Likewise, the intersection of dairy products and political leanings may seem as far-fetched as a bovine astronaut, but in the realm of statistical analysis, unexpected correlations can often arise. By analyzing data sourced from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning three decades, our study seeks to wrangle these disparate variables into a coherent narrative.

Now, onto the "moo-ving" factors at play in our research. Our initial investigation uncovered a correlation coefficient of 0.9483382 and a p-value of less than 0.01, suggesting a strong and statistically significant relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia. It appears that as the dairy flows, so do the ballots! This finding not only caught us off guard, but also left us pondering the complex interplay between dietary habits and political inclinations.

A little statistical humor for you: What do you call a group of dairy statisticians? The milk-shake! Jokes aside, our analysis also revealed that counties with higher milk consumption exhibited a tendency to favor the Democrat Presidential candidate. Could it be that "udder" delight leads to political insight? It may seem "cheesy," but the numbers speak for themselves!

With such compelling statistical evidence at hand, the dairy dilemma presents a political puzzle that demands further exploration. It seems that in the realm of politics, as in the production of yogurt, the bacterial culture of factors involved can yield surprisingly complex outcomes. As we delve deeper into the intricacies of this correlation, we hope to shed light on the "whey" in which dairy consumption may influence political choices.

So, the next time you sip on a glass of milk, take a moment to ponder the potential political implications. Remember, democracy is a lot like milk – it needs to be stirred up!


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The study of the factors influencing voters' decisions is as diverse and multifaceted as the flavors of ice cream at a dairy farm. One such factor that has captured our attention is the potential link between milk consumption and votes for the Democrat Presidential candidate in the charming state of West Virginia. This investigation aims to churn up some insight into whether a county's preference for dairy products could be associated with political preferences.
As the saying goes, "Why did the cow go to outer space? To visit the Milky Way!" Likewise, the intersection of dairy products and political leanings may seem as far-fetched as a bovine astronaut, but in the realm of statistical analysis, unexpected correlations can often arise. By analyzing data sourced from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning three decades, our study seeks to wrangle these disparate variables into a coherent narrative.
Now, onto the "moo-ving" factors at play in our research. Our initial investigation uncovered a correlation coefficient of 0.9483382 and a p-value of less than 0.01, suggesting a strong and statistically significant relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia. It appears that as the dairy flows, so do the ballots! This finding not only caught us off guard, but also left us pondering the complex interplay between dietary habits and political inclinations.
A little statistical humor for you: What do you call a group of dairy statisticians? The milk-shake! Jokes aside, our analysis also revealed that counties with higher milk consumption exhibited a tendency to favor the Democrat Presidential candidate. Could it be that "udder" delight leads to political insight? It may seem "cheesy," but the numbers speak for themselves!
With such compelling statistical evidence at hand, the dairy dilemma presents a political puzzle that demands further exploration. It seems that in the realm of politics, as in the production of yogurt, the bacterial culture of factors involved can yield surprisingly complex outcomes. As we delve deeper into the intricacies of this correlation, we hope to shed light on the "whey" in which dairy consumption may influence political choices.
So, the next time you sip on a glass of milk, take a moment to ponder the potential political implications. Remember, democracy is a lot like milk – it needs to be stirred up!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

While the connection between milk consumption and political preferences may initially appear as curious as a lactose-intolerant cow, our investigation expands upon previous studies to unravel the enigmatic link between these seemingly unrelated variables. Smith (2015) conducted a thorough examination of dietary patterns and voting behaviors in rural areas, revealing a tentative association between dairy consumption and political leaning. This study serves as the foundation upon which we build our research, much like a steadfast cow providing the necessary milk for a dairy enthusiast's morning cappuccino.

Lorem and Ipsum (2018) further delved into the intricate web of factors influencing voting behaviors, offering a comprehensive analysis of dairy consumption trends and their potential influence on political affiliations. The authors found a positive correlation between milk intake and favorability towards certain political candidates, yielding insightful implications for our present inquiry. This finding raises the question: does milk act as a political "moo-difier," altering voters' perceptions and inclinations?

In a similar vein, Doe (2017) explored the intersection of dietary habits and political ideology, shedding light on the potential impact of dairy preferences on voting patterns. The study unearthed subtle yet discernible shifts in political leanings corresponding to variations in milk consumption, prompting us to ponder the implications of dairy as a silent influencer in the realm of political preferences.

Taking a departure from the conventional, our study draws inspiration from non-fiction works such as "The Omnivore's Dilemma" by Michael Pollan and "Milk! A 10,000-Year Food Fracas" by Mark Kurlansky, which provide valuable insights into the cultural and societal significance of dairy consumption. The intricate interplay between dietary choices and political leanings emerges as a compelling narrative, much like the intermingling flavors of a well-crafted cheese platter.

Expanding our literary horizons to the realm of fiction, the dystopian themes of "Brave New World" by Aldous Huxley and the allegorical depth of George Orwell's "Animal Farm" offer metaphorical parallels to the interplay between dairy consumption and political allegiances. As we navigate the nuances of this correlation, the parallels between fictional narratives and our empirical findings serve as a whimsical reminder that truth can indeed be stranger than fiction.

Delving into the world of television, as diligent researchers, we couldn't resist the enlightening allure of "The Great British Baking Show," where the interplay of dairy products and culinary expertise captures the essence of our inquiry. The quirky charm of "Parks and Recreation" offers a lighthearted glimpse into the political landscape, reminding us to approach our research with a hint of humor and a dash of optimism.

As we venture into uncharted territories of statistical analysis and dairy-based puns, our exploration of the relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia takes on a distinct flavor – much like a metaphorical milkshake of inquiry and insight.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

[[INTRODUCTION]]
The study of the factors influencing voters' decisions is as diverse and multifaceted as the flavors of ice cream at a dairy farm. One such factor that has captured our attention is the potential link between milk consumption and votes for the Democrat Presidential candidate in the charming state of West Virginia. This investigation aims to churn up some insight into whether a county's preference for dairy products could be associated with political preferences.
As the saying goes, "Why did the cow go to outer space? To visit the Milky Way!" Likewise, the intersection of dairy products and political leanings may seem as far-fetched as a bovine astronaut, but in the realm of statistical analysis, unexpected correlations can often arise. By analyzing data sourced from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning three decades, our study seeks to wrangle these disparate variables into a coherent narrative.
Now, onto the "moo-ving" factors at play in our research. Our initial investigation uncovered a correlation coefficient of 0.9483382 and a p-value of less than 0.01, suggesting a strong and statistically significant relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia. It appears that as the dairy flows, so do the ballots! This finding not only caught us off guard, but also left us pondering the complex interplay between dietary habits and political inclinations.
A little statistical humor for you: What do you call a group of dairy statisticians? The milk-shake! Jokes aside, our analysis also revealed that counties with higher milk consumption exhibited a tendency to favor the Democrat Presidential candidate. Could it be that "udder" delight leads to political insight? It may seem "cheesy," but the numbers speak for themselves!
With such compelling statistical evidence at hand, the dairy dilemma presents a political puzzle that demands further exploration. It seems that in the realm of politics, as in the production of yogurt, the bacterial culture of factors involved can yield surprisingly complex outcomes. As we delve deeper into the intricacies of this correlation, we hope to shed light on the "whey" in which dairy consumption may influence political choices.
So, the next time you sip on a glass of milk, take a moment to ponder the potential political implications. Remember, democracy is a lot like milk – it needs to be stirred up!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

We embarked on this research endeavor with a trove of data collected from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning the years 1990 to 2020. Our intrepid team milked these sources for all they were worth, leaving no pasture unexplored in our quest for the most comprehensive and dairy-licious dataset.

To wrangle the vast expanse of data and extract meaningful insights, we employed a combination of sophisticated statistical techniques and a fair amount of cow-pondering. Our first step involved calculating the per capita milk consumption in each county of West Virginia across the three decades. This involved some rather "moo-ving" data manipulation, as we meticulously combed through records to ensure an udderly accurate portrayal of dairy consumption trends.

Once we had milked the data for all it was worth, we compared these consumption figures with the corresponding votes for the Democrat Presidential candidate in each county. We employed a bountiful array of statistical methods, including linear regression analysis and correlation tests, to examine the relationship between dairy consumption and voting patterns. It was no small feat, but we were determined to leave no "stone-cow" unturned in our pursuit of understanding the dairy dilemma.

Now, a little research humor to lighten the mood: Why don't statisticians like to go camping? Because it's "in-tents"! But I digress. After conducting rigorous analyses, we arrived at a compelling correlation coefficient of 0.9483382 and a p-value less than 0.01. This indicated a robust and statistically significant association between milk consumption and votes for the Democrat Presidential candidate in West Virginia.

To ensure the reliability and validity of our findings, we also performed sensitivity analyses and employed robust statistical controls to account for potential confounding variables. This rigorous approach allowed us to separate the wheat from the chaff and confidently affirm the significance of the dairy-dilemma in the context of political preferences.

In conclusion, our methodology employed a blend of meticulous data collection, comprehensive statistical analyses, and a healthy dose of tongue-in-cheek humor to peel back the layers of the dairy-driven political puzzle. Our methods were as thorough as a cow's cud-chewing, leaving no room for statistical bull-"moo"-nkey business.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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 0.9483382, r-squared of 0.8993453, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The study of the factors influencing voters' decisions is as diverse and multifaceted as the flavors of ice cream at a dairy farm. One such factor that has captured our attention is the potential link between milk consumption and votes for the Democrat Presidential candidate in the charming state of West Virginia. This investigation aims to churn up some insight into whether a county's preference for dairy products could be associated with political preferences.
As the saying goes, "Why did the cow go to outer space? To visit the Milky Way!" Likewise, the intersection of dairy products and political leanings may seem as far-fetched as a bovine astronaut, but in the realm of statistical analysis, unexpected correlations can often arise. By analyzing data sourced from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning three decades, our study seeks to wrangle these disparate variables into a coherent narrative.
Now, onto the "moo-ving" factors at play in our research. Our initial investigation uncovered a correlation coefficient of 0.9483382 and a p-value of less than 0.01, suggesting a strong and statistically significant relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia. It appears that as the dairy flows, so do the ballots! This finding not only caught us off guard, but also left us pondering the complex interplay between dietary habits and political inclinations.
A little statistical humor for you: What do you call a group of dairy statisticians? The milk-shake! Jokes aside, our analysis also revealed that counties with higher milk consumption exhibited a tendency to favor the Democrat Presidential candidate. Could it be that "udder" delight leads to political insight? It may seem "cheesy," but the numbers speak for themselves!
With such compelling statistical evidence at hand, the dairy dilemma presents a political puzzle that demands further exploration. It seems that in the realm of politics, as in the production of yogurt, the bacterial culture of factors involved can yield surprisingly complex outcomes. As we delve deeper into the intricacies of this correlation, we hope to shed light on the "whey" in which dairy consumption may influence political choices.
So, the next time you sip on a glass of milk, take a moment to ponder the potential political implications. Remember, democracy is a lot like milk – it needs to be stirred up!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The correlation analysis revealed a strong, positive correlation between milk consumption and votes for the Democrat Presidential candidate in West Virginia over the period of 1990 to 2020. The correlation coefficient was found to be a remarkably high 0.9483382, indicating a close relationship between these two variables. This finding suggests that perhaps the phrase should be "got milk, got Democrat votes" in the context of West Virginia politics! Who knew that the dairy aisle and the voting booth could have so much in common?

The r-squared value of 0.8993453 indicates that a substantial proportion of the variance in Democrat votes can be explained by milk consumption. It seems that the dairy dilemma is not just a curdled mystery but a potent predictor of political preference in the hills of West Virginia.

Our analysis further unveiled a p-value of less than 0.01, signifying an extremely low probability that the observed relationship between milk consumption and Democrat votes is due to random chance. It seems that not everything in statistical analysis is as random as a dairy pun - there's no whey this relationship occurred by mere coincidence!

As for the scatterplot (Fig. 1), well, it tells a thousand words! The figure vividly illustrates the robust positive linear association between milk consumption and votes for the Democrat Presidential candidate in West Virginia. One could say it's a picture-perfect representation of the milk-voting connection, a real dairy delight for statistical enthusiasts!

In the immortal words of Winston Churchill, "I am easily satisfied with the very best". Indeed, our statistical findings pertain to this quip, demonstrating an overwhelming association between milk consumption and Democrat votes in West Virginia. It's a statistical bonanza wrapped in a dairy wrapper!


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

[[LITERATURE REVIEW]]
While the connection between milk consumption and political preferences may initially appear as curious as a lactose-intolerant cow, our investigation expands upon previous studies to unravel the enigmatic link between these seemingly unrelated variables. Smith (2015) conducted a thorough examination of dietary patterns and voting behaviors in rural areas, revealing a tentative association between dairy consumption and political leaning. This study serves as the foundation upon which we build our research, much like a steadfast cow providing the necessary milk for a dairy enthusiast's morning cappuccino.
Lorem and Ipsum (2018) further delved into the intricate web of factors influencing voting behaviors, offering a comprehensive analysis of dairy consumption trends and their potential influence on political affiliations. The authors found a positive correlation between milk intake and favorability towards certain political candidates, yielding insightful implications for our present inquiry. This finding raises the question: does milk act as a political "moo-difier," altering voters' perceptions and inclinations?
In a similar vein, Doe (2017) explored the intersection of dietary habits and political ideology, shedding light on the potential impact of dairy preferences on voting patterns. The study unearthed subtle yet discernible shifts in political leanings corresponding to variations in milk consumption, prompting us to ponder the implications of dairy as a silent influencer in the realm of political preferences.
Taking a departure from the conventional, our study draws inspiration from non-fiction works such as "The Omnivore's Dilemma" by Michael Pollan and "Milk! A 10,000-Year Food Fracas" by Mark Kurlansky, which provide valuable insights into the cultural and societal significance of dairy consumption. The intricate interplay between dietary choices and political leanings emerges as a compelling narrative, much like the intermingling flavors of a well-crafted cheese platter.
Expanding our literary horizons to the realm of fiction, the dystopian themes of "Brave New World" by Aldous Huxley and the allegorical depth of George Orwell's "Animal Farm" offer metaphorical parallels to the interplay between dairy consumption and political allegiances. As we navigate the nuances of this correlation, the parallels between fictional narratives and our empirical findings serve as a whimsical reminder that truth can indeed be stranger than fiction.
Delving into the world of television, as diligent researchers, we couldn't resist the enlightening allure of "The Great British Baking Show," where the interplay of dairy products and culinary expertise captures the essence of our inquiry. The quirky charm of "Parks and Recreation" offers a lighthearted glimpse into the political landscape, reminding us to approach our research with a hint of humor and a dash of optimism.
As we venture into uncharted territories of statistical analysis and dairy-based puns, our exploration of the relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia takes on a distinct flavor – much like a metaphorical milkshake of inquiry and insight.

[[RESULTS]]
The correlation analysis revealed a strong, positive correlation between milk consumption and votes for the Democrat Presidential candidate in West Virginia over the period of 1990 to 2020. The correlation coefficient was found to be a remarkably high 0.9483382, indicating a close relationship between these two variables. This finding suggests that perhaps the phrase should be "got milk, got Democrat votes" in the context of West Virginia politics! Who knew that the dairy aisle and the voting booth could have so much in common?
The r-squared value of 0.8993453 indicates that a substantial proportion of the variance in Democrat votes can be explained by milk consumption. It seems that the dairy dilemma is not just a curdled mystery but a potent predictor of political preference in the hills of West Virginia.
Our analysis further unveiled a p-value of less than 0.01, signifying an extremely low probability that the observed relationship between milk consumption and Democrat votes is due to random chance. It seems that not everything in statistical analysis is as random as a dairy pun - there's no whey this relationship occurred by mere coincidence!
As for the scatterplot (Fig. 1), well, it tells a thousand words! The figure vividly illustrates the robust positive linear association between milk consumption and votes for the Democrat Presidential candidate in West Virginia. One could say it's a picture-perfect representation of the milk-voting connection, a real dairy delight for statistical enthusiasts!
In the immortal words of Winston Churchill, "I am easily satisfied with the very best". Indeed, our statistical findings pertain to this quip, demonstrating an overwhelming association between milk consumption and Democrat votes in West Virginia. It's a statistical bonanza wrapped in a dairy wrapper!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings provide compelling evidence for the intriguing relationship between milk consumption and votes for the Democrat Presidential candidate in the convoluted landscape of West Virginia politics. The prodigious correlation coefficient of 0.9483382 indicates a remarkably strong positive correlation, affirming the results of previous studies and emphasizing the significance of dairy intake in shaping political preference. It seems that the classic childhood query, "Got milk?" now extends beyond mere nutritional inquiry to delving into political inclinations - an utterly "punny" realization indeed!

Supporting the work of Smith (2015) and Lorem and Ipsum (2018), our study corroborates their earlier observations by elucidating the profound impact of milk consumption on political voting patterns. While the idea of dairy products influencing political sentiments may seem as unlikely as spotting a lactose-tolerant cat, our results unequivocally validate the "moo-difier" effect of milk on political perceptions and preferences. It’s no "accidairy" that these findings have churned up the interest of researchers and enthusiasts alike in the science of political preferences.

The strikingly low p-value further reinforces the robustness of our findings, firmly establishing the statistically significant relationship between dairy consumption and Democrat votes. It's safe to say that in this statistical saga, there's "no whey" that these results are a fluke - they are as solid as a chunk of aged cheddar. Our study serves as a testament to the power of empirical research, reminding us that beneath the veneer of whimsy and dairy puns lies a truly impactful exploration of political discourse.

With empirical evidence as compelling as a creamy blue cheese, our findings lend credence to the notion that dietary choices, particularly dairy consumption, play a pivotal role in shaping political affiliations. As we mull over the seemingly improbable connection between milk and democracy, it becomes increasingly apparent that the cultural significance of dietary habits cannot be trivialized. After all, isn't it "moo-re" than a mere coincidence that dairy consumption and political leanings share such a formidable bond?

In essence, our study adds depth to the scholarly discourse surrounding the multifaceted interplay between dietary preferences and political allegiances. As we unravel the intricate web of influences on voter behavior, the "dairy dilemma" emerges as a compelling metaphor for the nuanced complexities of democracy. Indeed, the electoral process is not merely black and white but a "milky white" blend of various factors, each adding its own unique flavor to the political landscape.

As we grapple with the implications of dairy consumption on voting behavior, our inquiry takes on the semblance of an intellectually stimulating cheese platter, enticing researchers to partake in the rich tapestry of dairy-based inquiry. Our endeavor serves as a friendly reminder that even in the scholarly pursuit of statistical rigor and empirical evidence, there's always "moo-re" room for a touch of levity and a sprinkle of dairy-related humor.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Milk consumption and Votes for the Democrat Presidential candidate in West Virginia. 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]]
The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia

[[ABSTRACT]]
In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.

Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!

To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!

With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

[[INTRDUCTION]]
The study of the factors influencing voters' decisions is as diverse and multifaceted as the flavors of ice cream at a dairy farm. One such factor that has captured our attention is the potential link between milk consumption and votes for the Democrat Presidential candidate in the charming state of West Virginia. This investigation aims to churn up some insight into whether a county's preference for dairy products could be associated with political preferences.
As the saying goes, "Why did the cow go to outer space? To visit the Milky Way!" Likewise, the intersection of dairy products and political leanings may seem as far-fetched as a bovine astronaut, but in the realm of statistical analysis, unexpected correlations can often arise. By analyzing data sourced from the USDA and MIT Election Data and Science Lab, Harvard Dataverse spanning three decades, our study seeks to wrangle these disparate variables into a coherent narrative.
Now, onto the "moo-ving" factors at play in our research. Our initial investigation uncovered a correlation coefficient of 0.9483382 and a p-value of less than 0.01, suggesting a strong and statistically significant relationship between milk consumption and votes for the Democrat Presidential candidate in West Virginia. It appears that as the dairy flows, so do the ballots! This finding not only caught us off guard, but also left us pondering the complex interplay between dietary habits and political inclinations.
A little statistical humor for you: What do you call a group of dairy statisticians? The milk-shake! Jokes aside, our analysis also revealed that counties with higher milk consumption exhibited a tendency to favor the Democrat Presidential candidate. Could it be that "udder" delight leads to political insight? It may seem "cheesy," but the numbers speak for themselves!
With such compelling statistical evidence at hand, the dairy dilemma presents a political puzzle that demands further exploration. It seems that in the realm of politics, as in the production of yogurt, the bacterial culture of factors involved can yield surprisingly complex outcomes. As we delve deeper into the intricacies of this correlation, we hope to shed light on the "whey" in which dairy consumption may influence political choices.
So, the next time you sip on a glass of milk, take a moment to ponder the potential political implications. Remember, democracy is a lot like milk – it needs to be stirred up!

[[RESULTS]]
The correlation analysis revealed a strong, positive correlation between milk consumption and votes for the Democrat Presidential candidate in West Virginia over the period of 1990 to 2020. The correlation coefficient was found to be a remarkably high 0.9483382, indicating a close relationship between these two variables. This finding suggests that perhaps the phrase should be "got milk, got Democrat votes" in the context of West Virginia politics! Who knew that the dairy aisle and the voting booth could have so much in common?
The r-squared value of 0.8993453 indicates that a substantial proportion of the variance in Democrat votes can be explained by milk consumption. It seems that the dairy dilemma is not just a curdled mystery but a potent predictor of political preference in the hills of West Virginia.
Our analysis further unveiled a p-value of less than 0.01, signifying an extremely low probability that the observed relationship between milk consumption and Democrat votes is due to random chance. It seems that not everything in statistical analysis is as random as a dairy pun - there's no whey this relationship occurred by mere coincidence!
As for the scatterplot (Fig. 1), well, it tells a thousand words! The figure vividly illustrates the robust positive linear association between milk consumption and votes for the Democrat Presidential candidate in West Virginia. One could say it's a picture-perfect representation of the milk-voting connection, a real dairy delight for statistical enthusiasts!
In the immortal words of Winston Churchill, "I am easily satisfied with the very best". Indeed, our statistical findings pertain to this quip, demonstrating an overwhelming association between milk consumption and Democrat votes in West Virginia. It's a statistical bonanza wrapped in a dairy wrapper!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]
In conclusion, our study has uncorked a veritable cornucopia of findings regarding the intriguing relationship between milk consumption and votes for the Democrat Presidential candidate in vibrant West Virginia. The statistical evidence overwhelmingly supports a compelling link between dairy intake and political preference in this region. It seems that in the land of milk and ballots, the two are not just curds and whey.

Our results suggest that the phrase "got milk, got Democrat votes" may hold more truth than we originally thought! It's as if the dairy industry has been quietly churning out political influence alongside all those gallons of milk. Could it be that there's more to democracy than meets the eye? Perhaps it's all a matter of lactose and ballots!

This study has certainly left us feeling more enthused than a cow in a pasture! The statistical analysis not only provides a milk-filled window into political behavior but also underscores the rich potential for unexpected correlations in sociopolitical research. It seems that even in the realm of voter preferences, there's always room for a little dairy surprise.

After delving into the "moo-ving" world of statistics and politics, it's clear that further research in this area may not be needed. We've milked this study for all it's worth, and the evidence stands as strong as a dairy farmer's handshake – there's no need to cry over unspilled milk here! It's time to tip our hats and bid adieu to the dairy dilemma, leaving it as a "got milk, got votes" story for the ages.


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Politics and Consumption


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Appalachian Agricultural Analysis (CAAA)


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Dairy Dilemma: Democrat Presidential Votes and Dairy Consumption in West Virginia with an abstract of In this study, we tackle the titillating question of the potential relationship between milk consumption and votes for the Democrat Presidential candidate in the wonderful state of West Virginia. Our research team utilized data obtained from the USDA and MIT Election Data and Science Lab, Harvard Dataverse for the years 1990 to 2020 to delve into this udderly intriguing subject.
Our analysis revealed a striking correlation coefficient of 0.9483382 and a p-value less than 0.01, indicating a statistically significant relationship between milk consumption and Democrat votes in West Virginia. It seems that as the dairy flows, so do the ballots!
To milk this study for all it's worth, we discovered that counties with higher milk consumption tended to lean towards voting for the Democrat Presidential candidate. Could it be that dairy delight leads to political insight? It may seem "udderly" ridiculous, but the numbers don't lie!
With such strong statistical evidence, it's clear that the dairy dilemma is a political puzzle worth exploring further. So next time you're pondering West Virginia's voting trends, just remember, it's all about the milk - after all, democracy is a lot like milk, it needs to be stirred up!

ChatGPT:

Dairy consumption, Democrat votes, Presidential election, West Virginia, correlation analysis, USDA data, MIT Election Data and Science Lab, Harvard Dataverse, milk consumption, political voting trends, statistical relationship, county data, correlation coefficient, p-value, political insight, democracy, voting patterns.

*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

Milk consumption
Detailed data title: Per capita consumption of Fluid beverage milk in the US
Source: USDA
See what else correlates with Milk consumption

Votes for the Democratic Presidential candidate in West Virginia
Detailed data title: Percentage of all votes cast for the Democrat Presidential candidate in West Virginia
Source: MIT Election Data and Science Lab, Harvard Dataverse
See what else correlates with Votes for the Democratic Presidential candidate in West Virginia

Correlation r = 0.9483382 (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 = 0.8993453 (Coefficient of determination)
This means 89.9% of the change in the one variable (i.e., Votes for the Democratic Presidential candidate in West Virginia) is predictable based on the change in the other (i.e., Milk consumption) over the 8 years from 1990 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00033. 0.0003314884594645248700000000
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 0.033% of random cases. Said differently, if you correlated 3,017 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
Milk consumption (Pounds per person)215205196185181169153141
Votes for the Democratic Presidential candidate in West Virginia (Percentage of votes)48.414851.505645.592743.205142.589835.539326.476929.6965




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.




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([215,205,196,185,181,169,153,141,])
array_2 = np.array([48.4148,51.5056,45.5927,43.2051,42.5898,35.5393,26.4769,29.6965,])
array_1_name = "Milk consumption"
array_2_name = "Votes for the Democratic Presidential candidate in West Virginia"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!


Correlation ID: 5296 · Black Variable ID: 554 · Red Variable ID: 26187
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0