about · email me · subscribe
Spurious correlation #5,600 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Votes for the Democratic Presidential candidate in Hawaii and the second variable is New York Times Fiction Best Sellers.  The chart goes from 1976 to 2014, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Perhaps Hawaii's overwhelming support for the Democratic candidate created a ripple effect in the literary world, inspiring a surge in fictional storytelling and imaginative narratives. It's as if the Democratic candidate's popularity cast a spell on Hawaii, sparking a wave of creativity that spread all the way to the New York Times Best Sellers list. It's a tale of political influence shaping the literary landscape, where every vote for the Democratic candidate becomes a plot twist in the story of book sales.

Model: dalle-3
Prompt: An image that looks like it is a scene from a Pixar movie: In this image, a colorful and bustling Hawaiian scene unfolds as a sea of animated voters casts their ballots for the Democratic Presidential candidate under a sunny sky. The voters are depicted in joyful and diverse animated forms, each proudly participating in their civic duty. In the background, the iconic New York Times Fiction Best Sellers list looms tall and majestic, displaying a collection of whimsical and vibrant novels with fantastical cover art. The ballots being cast transform into tiny fluttering pages of a book, which gracefully sweep across the ocean towards New York City, where they are eagerly received by a bustling metropolis of animated characters. The image captures the seamless connection between political support in Hawaii and the surge of creativity that influences the literary world on the other side of the country. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Votes for the Democratic Presidential candidate in Hawaii and New York Times Fiction Best Sellers. 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: Photorealism An image that looks like it is a scene from a Pixar movie An image that looks like it is a scene from A Disney Movie Brutalism Glitch art
ChatGPT: An image that looks like it is a scene from a Pixar 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 Votes for the Democratic Presidential candidate in Hawaii and New York Times Fiction Best Sellers, in the following situation: Perhaps Hawaii's overwhelming support for the Democratic candidate created a ripple effect in the literary world, inspiring a surge in fictional storytelling and imaginative narratives. It's as if the Democratic candidate's popularity cast a spell on Hawaii, sparking a wave of creativity that spread all the way to the New York Times Best Sellers list. It's a tale of political influence shaping the literary landscape, where every vote for the Democratic candidate becomes a plot twist in the story of book sales.. Keep the description simple.
ChatGPT: In a vibrant scene, a sea of voters in Hawaii proudly cast their ballots for the Democratic Presidential candidate, while in the background, the New York Times Fiction Best Sellers list displays a flurry of captivating novels with imaginative narratives and colorful cover art. The ballots seem to transform into tiny pages of a book fluttering towards New York, illustrating how political support in Hawaii ignites a surge of creativity that influences the literary world on the other side of the country.

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 Pixar movie ] and depicting this scene: In a vibrant scene, a sea of voters in Hawaii proudly cast their ballots for the Democratic Presidential candidate, while in the background, the New York Times Fiction Best Sellers list displays a flurry of captivating novels with imaginative narratives and colorful cover art. The ballots seem to transform into tiny pages of a book fluttering towards New York, illustrating how political support in Hawaii ignites a surge of creativity that influences the literary world on the other side of the country. 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 Pixar movie: In this image, a colorful and bustling Hawaiian scene unfolds as a sea of animated voters casts their ballots for the Democratic Presidential candidate under a sunny sky. The voters are depicted in joyful and diverse animated forms, each proudly participating in their civic duty. In the background, the iconic New York Times Fiction Best Sellers list looms tall and majestic, displaying a collection of whimsical and vibrant novels with fantastical cover art. The ballots being cast transform into tiny fluttering pages of a book, which gracefully sweep across the ocean towards New York City, where they are eagerly received by a bustling metropolis of animated characters. The image captures the seamless connection between political support in Hawaii and the surge of creativity that influences the literary world on the other side of the country.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in Votes for the Democrat Presidential candidate in Hawaii caused New York Times Fiction Best Sellers to increase.

AI academic paper

(Because p < 0.01)
The Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

The Journal of Political Literature

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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from MIT Election Data and Science Lab, Harvard Dataverse and Hawes to assess this nagging question. You found a correlation coefficient of 0.9189783 and p < 0.01 for 1976 to 2014.

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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
The Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

In the ever-expanding realm of political science and literary analysis, an unexpected and somewhat whimsical correlation has come to light. As researchers seek to uncover the intricate connections between voting patterns and consumer behavior, our study delves into the intriguing relationship between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. While the intersection of politics and fiction may seem as unlikely as a reality TV star becoming President, the data speaks for itself—loud and clear, like a poorly written political thriller.

It is a truth universally acknowledged, that a single presidential election in a particular state can have an impact on the literary pursuits of its inhabitants. As our research unfolds, we embark on a journey to unravel the enigmatic bond between an individual's political inclinations and their choice of fictional escapism. This correlation, as serendipitous as stumbling upon a rare first edition in a used bookstore, has raised eyebrows and piqued the curiosity of scholars and non-scholars alike.

As with any unexpected correlation, the first question that springs to mind is undoubtedly, "Is this just a fluke, or do we have a real plot twist on our hands?" To tackle this question, we meticulously scrutinize the data obtained from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and Hawes, a treasure trove of literary data. Through rigorous statistical analysis, we reveal a correlation coefficient that would make even the most stoic academic crack a smile—0.9189783, with a p-value of less than 0.01. This eyebrow-raising coefficient suggests a connection more robust than the bond between a detective and their trusty sidekick.

The implications of this correlation, if proven to be more than a mere fluke of statistical probability, are as bewildering as a mystery novel's final plot twist. What could possibly tie the political leanings of a state's populace to their choice of fiction? Are we witnessing the influence of political rhetoric on literary tastes, or could it be that the narrative devices used in popular fiction hold the power to sway political allegiances? These questions, as intriguing as a locked-room murder, propel our investigation into uncharted territories of interdisciplinary connection.

As we venture further into this peculiar confluence of political drama and fictional narratives, we invite our esteemed colleagues and curious observers to join us in unraveling the captivating patterns and peculiar curiosities that have emerged from our study. By embracing the quirkier side of academic investigation, we strive to shed light on this mesmerizing correlation and the delightful oddities it unveils—because in the world of research, as in life, sometimes truth is indeed stranger than fiction.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then 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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
In the ever-expanding realm of political science and literary analysis, an unexpected and somewhat whimsical correlation has come to light. As researchers seek to uncover the intricate connections between voting patterns and consumer behavior, our study delves into the intriguing relationship between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. While the intersection of politics and fiction may seem as unlikely as a reality TV star becoming President, the data speaks for itself—loud and clear, like a poorly written political thriller.
It is a truth universally acknowledged, that a single presidential election in a particular state can have an impact on the literary pursuits of its inhabitants. As our research unfolds, we embark on a journey to unravel the enigmatic bond between an individual's political inclinations and their choice of fictional escapism. This correlation, as serendipitous as stumbling upon a rare first edition in a used bookstore, has raised eyebrows and piqued the curiosity of scholars and non-scholars alike.
As with any unexpected correlation, the first question that springs to mind is undoubtedly, "Is this just a fluke, or do we have a real plot twist on our hands?" To tackle this question, we meticulously scrutinize the data obtained from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and Hawes, a treasure trove of literary data. Through rigorous statistical analysis, we reveal a correlation coefficient that would make even the most stoic academic crack a smile—0.9189783, with a p-value of less than 0.01. This eyebrow-raising coefficient suggests a connection more robust than the bond between a detective and their trusty sidekick.
The implications of this correlation, if proven to be more than a mere fluke of statistical probability, are as bewildering as a mystery novel's final plot twist. What could possibly tie the political leanings of a state's populace to their choice of fiction? Are we witnessing the influence of political rhetoric on literary tastes, or could it be that the narrative devices used in popular fiction hold the power to sway political allegiances? These questions, as intriguing as a locked-room murder, propel our investigation into uncharted territories of interdisciplinary connection.
As we venture further into this peculiar confluence of political drama and fictional narratives, we invite our esteemed colleagues and curious observers to join us in unraveling the captivating patterns and peculiar curiosities that have emerged from our study. By embracing the quirkier side of academic investigation, we strive to shed light on this mesmerizing correlation and the delightful oddities it unveils—because in the world of research, as in life, sometimes truth is indeed stranger than fiction.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

To understand the surprising correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers, we must first take a closer look at the existing literature. Several studies have examined the intersection of politics and literature, shedding light on the societal dynamics at play. Smith (2010) delved into the relationship between political ideology and reading preferences, while Doe (2015) explored the impact of electoral outcomes on consumer behavior, albeit in less whimsical domains. However, this body of work has yet to unravel the peculiar connection our study seeks to illuminate.

Moving beyond the conventional, let us delve into non-fiction books that attempt to bridge the gap between politics and literary tastes. From “Fire and Fury” by Michael Wolff to “What Happened” by Hillary Rodham Clinton, these publications provide a narrative backdrop to the electoral upheavals that have marked recent history. While these titles offer insights into the political realm, they do not directly address the curious correlation we are investigating. Nonetheless, as we pivot to the realm of fiction, the plot thickens.

In “The Plot Against America” by Philip Roth and “The 19th Wife” by David Ebershoff, we encounter imaginative narratives that intertwine fictional characters with real-world political scenarios, offering a unique lens through which to examine the impact of politics on literature. As we immerse ourselves in these fictitious realms, our quest for understanding leads us to unexpected destinations, where the boundaries between reality and imagination blur.

In addition to delving into literary works, we expand our investigation to popular culture, seeking clues in unexpected places. Through arduous research involving copious consumption of TV shows (strictly for academic purposes, of course), we uncover shows like "The West Wing" and "House of Cards," whose gripping political dramas mesmerize audiences. These shows provide a tantalizing glimpse into the political psyche of viewers, but alas, they do not directly illuminate our curious correlation.

As we navigate through these various narratives and cultural reflections, it becomes abundantly clear that our study occupies a peculiar and whimsical niche. Through this literature review, we lay the groundwork for our exploration into the delightful oddities and unexpected connections that await us, embracing the quirkier side of academic investigation with gusto and enthusiasm.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from MIT Election Data and Science Lab, Harvard Dataverse and Hawes . You used data from 1976 to 2014

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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

[[INTRODUCTION]]
INTRODUCTION
In the ever-expanding realm of political science and literary analysis, an unexpected and somewhat whimsical correlation has come to light. As researchers seek to uncover the intricate connections between voting patterns and consumer behavior, our study delves into the intriguing relationship between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. While the intersection of politics and fiction may seem as unlikely as a reality TV star becoming President, the data speaks for itself—loud and clear, like a poorly written political thriller.
It is a truth universally acknowledged, that a single presidential election in a particular state can have an impact on the literary pursuits of its inhabitants. As our research unfolds, we embark on a journey to unravel the enigmatic bond between an individual's political inclinations and their choice of fictional escapism. This correlation, as serendipitous as stumbling upon a rare first edition in a used bookstore, has raised eyebrows and piqued the curiosity of scholars and non-scholars alike.
As with any unexpected correlation, the first question that springs to mind is undoubtedly, "Is this just a fluke, or do we have a real plot twist on our hands?" To tackle this question, we meticulously scrutinize the data obtained from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and Hawes, a treasure trove of literary data. Through rigorous statistical analysis, we reveal a correlation coefficient that would make even the most stoic academic crack a smile—0.9189783, with a p-value of less than 0.01. This eyebrow-raising coefficient suggests a connection more robust than the bond between a detective and their trusty sidekick.
The implications of this correlation, if proven to be more than a mere fluke of statistical probability, are as bewildering as a mystery novel's final plot twist. What could possibly tie the political leanings of a state's populace to their choice of fiction? Are we witnessing the influence of political rhetoric on literary tastes, or could it be that the narrative devices used in popular fiction hold the power to sway political allegiances? These questions, as intriguing as a locked-room murder, propel our investigation into uncharted territories of interdisciplinary connection.
As we venture further into this peculiar confluence of political drama and fictional narratives, we invite our esteemed colleagues and curious observers to join us in unraveling the captivating patterns and peculiar curiosities that have emerged from our study. By embracing the quirkier side of academic investigation, we strive to shed light on this mesmerizing correlation and the delightful oddities it unveils—because in the world of research, as in life, sometimes truth is indeed stranger than fiction.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on this whimsical and unexpected journey into the intriguing correlation between votes for Democrat presidential candidates in Hawaii and New York Times Fiction Best Sellers, our research team devised a meticulous and, dare I say, quite novel methodology. We sought to unearth the veritable treasure trove of data from various reputable sources, including the MIT Election Data and Science Lab, the Harvard Dataverse, and the Hawes database, with the same enthusiasm a treasure hunter feels when stumbling upon buried riches.

Our first step was to wrangle the electoral data from Hawaii and the national New York Times Fiction Best Sellers from the years 1976 to 2014—a task as daunting as herding cats during a political debate. We then meticulously cleaned and curated the datasets, ensuring that only the finest and most accurate data points made their way into our analysis, much like a discerning editor plucking the choicest manuscripts for publication.

With our datasets in hand, we waded into the uncharted waters of statistical analysis, armed with an assortment of analytical tools sharper than Sherlock Holmes' deductive reasoning. Utilizing robust statistical techniques such as Pearson correlation coefficient and multiple regression analysis, we set out to unveil the hidden patterns and correlations, akin to a detective disentangling a web of deception.

As with any daring adventure, we encountered our fair share of challenges along the way. Wrestling with the idiosyncrasies of electoral data and navigating the labyrinthine landscape of fiction best sellers required the tenacity of a political campaign and the creativity of a bestselling author. Yet, undeterred by the obstacles, we forged ahead, driven by the promise of uncovering an enigmatic and outlandish connection that would rival the plot twists of a gripping political thriller.

In addition to the quantitative analysis, we augmented our investigation with qualitative inquiries, engaging in interviews with avid readers and politically-inclined individuals to gain a deeper understanding of their preferences and proclivities. These candid conversations, peppered with anecdotes and insights, added a touch of colorful storytelling to our otherwise scholarly pursuit, much like a splash of vibrant paint on a canvas.

Our methodology, while imbued with whimsy and levity, adhered to the rigorous standards of scientific inquiry, ensuring that our findings withstood the scrutiny of peer review with the same resilience as a well-crafted argument. Through this multidimensional approach, we endeavored to capture the essence of this unexpected correlation, offering a glimpse into the delightful confluence of political fervor and literary indulgence—because, in the world of academia, as in any good story, sometimes the most extraordinary discoveries unfold in the most unconventional of ways.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1976 to 2014, you found a correlation 0.9189783, r-squared of 0.8445211, 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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
In the ever-expanding realm of political science and literary analysis, an unexpected and somewhat whimsical correlation has come to light. As researchers seek to uncover the intricate connections between voting patterns and consumer behavior, our study delves into the intriguing relationship between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. While the intersection of politics and fiction may seem as unlikely as a reality TV star becoming President, the data speaks for itself—loud and clear, like a poorly written political thriller.
It is a truth universally acknowledged, that a single presidential election in a particular state can have an impact on the literary pursuits of its inhabitants. As our research unfolds, we embark on a journey to unravel the enigmatic bond between an individual's political inclinations and their choice of fictional escapism. This correlation, as serendipitous as stumbling upon a rare first edition in a used bookstore, has raised eyebrows and piqued the curiosity of scholars and non-scholars alike.
As with any unexpected correlation, the first question that springs to mind is undoubtedly, "Is this just a fluke, or do we have a real plot twist on our hands?" To tackle this question, we meticulously scrutinize the data obtained from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and Hawes, a treasure trove of literary data. Through rigorous statistical analysis, we reveal a correlation coefficient that would make even the most stoic academic crack a smile—0.9189783, with a p-value of less than 0.01. This eyebrow-raising coefficient suggests a connection more robust than the bond between a detective and their trusty sidekick.
The implications of this correlation, if proven to be more than a mere fluke of statistical probability, are as bewildering as a mystery novel's final plot twist. What could possibly tie the political leanings of a state's populace to their choice of fiction? Are we witnessing the influence of political rhetoric on literary tastes, or could it be that the narrative devices used in popular fiction hold the power to sway political allegiances? These questions, as intriguing as a locked-room murder, propel our investigation into uncharted territories of interdisciplinary connection.
As we venture further into this peculiar confluence of political drama and fictional narratives, we invite our esteemed colleagues and curious observers to join us in unraveling the captivating patterns and peculiar curiosities that have emerged from our study. By embracing the quirkier side of academic investigation, we strive to shed light on this mesmerizing correlation and the delightful oddities it unveils—because in the world of research, as in life, sometimes truth is indeed stranger than fiction.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the data acquired from the MIT Election Data and Science Lab, Harvard Dataverse, and Hawes has unearthed a bewilderingly strong correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. The correlation coefficient of 0.9189783, accompanied by an r-squared value of 0.8445211 and a p-value less than 0.01, holds sway over our findings, much like a leading character captivates readers in a best-selling novel.

As depicted in Figure 1, the scatterplot emphasizes the robust and unexpected relationship between these two seemingly disparate variables. The alignment of the data points is as uncanny as stumbling upon a plot hole in a well-written mystery, leaving no room for doubt regarding the strength of this correlation.

This striking correlation, akin to an unexpected plot twist, prompts contemplation of the potential underlying factors contributing to this peculiar connection. One cannot help but wonder whether the political climate of a state influences the literary preferences of its populace, or if the narrative elements within popular fiction exert a subtle yet undeniable influence on political inclinations. The confluence of these seemingly incongruous spheres redefines the term "political fiction," akin to an unexpected crossover event in the literary universe.

The robustness of this correlation impels us to consider unconventional theories of influence and alignment between politics and storytelling. The intersection of these two domains, seemingly as distant as the poles, invites us to ponder whether the narrative arc of a best-selling novel could mirror the political trajectory of a state, each chapter revealing a surprising turn of events. The whimsy of this discovery exposes a fascinating realm of inquiry where the boundaries between politics and literature blur, much like a poorly drawn map of a fictional world.

The high correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers bolsters the intrigue and astonishment surrounding this unlikely association. The scholarly community and enthusiasts of esoteric correlations alike are beckoned to partake in the captivating enigma uncovered by our study. This research serves as a reminder that within the realm of statistical analysis, as in life, serendipitous findings and unexpected correlations can add a touch of whimsy to the otherwise predictable landscape of academic inquiry.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

[[LITERATURE REVIEW]]
To understand the surprising correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers, we must first take a closer look at the existing literature. Several studies have examined the intersection of politics and literature, shedding light on the societal dynamics at play. Smith (2010) delved into the relationship between political ideology and reading preferences, while Doe (2015) explored the impact of electoral outcomes on consumer behavior, albeit in less whimsical domains. However, this body of work has yet to unravel the peculiar connection our study seeks to illuminate.
Moving beyond the conventional, let us delve into non-fiction books that attempt to bridge the gap between politics and literary tastes. From “Fire and Fury” by Michael Wolff to “What Happened” by Hillary Rodham Clinton, these publications provide a narrative backdrop to the electoral upheavals that have marked recent history. While these titles offer insights into the political realm, they do not directly address the curious correlation we are investigating. Nonetheless, as we pivot to the realm of fiction, the plot thickens.
In “The Plot Against America” by Philip Roth and “The 19th Wife” by David Ebershoff, we encounter imaginative narratives that intertwine fictional characters with real-world political scenarios, offering a unique lens through which to examine the impact of politics on literature. As we immerse ourselves in these fictitious realms, our quest for understanding leads us to unexpected destinations, where the boundaries between reality and imagination blur.
In addition to delving into literary works, we expand our investigation to popular culture, seeking clues in unexpected places. Through arduous research involving copious consumption of TV shows (strictly for academic purposes, of course), we uncover shows like "The West Wing" and "House of Cards," whose gripping political dramas mesmerize audiences. These shows provide a tantalizing glimpse into the political psyche of viewers, but alas, they do not directly illuminate our curious correlation.
As we navigate through these various narratives and cultural reflections, it becomes abundantly clear that our study occupies a peculiar and whimsical niche. Through this literature review, we lay the groundwork for our exploration into the delightful oddities and unexpected connections that await us, embracing the quirkier side of academic investigation with gusto and enthusiasm.

[[RESULTS]]
Our analysis of the data acquired from the MIT Election Data and Science Lab, Harvard Dataverse, and Hawes has unearthed a bewilderingly strong correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. The correlation coefficient of 0.9189783, accompanied by an r-squared value of 0.8445211 and a p-value less than 0.01, holds sway over our findings, much like a leading character captivates readers in a best-selling novel.
As depicted in Figure 1, the scatterplot emphasizes the robust and unexpected relationship between these two seemingly disparate variables. The alignment of the data points is as uncanny as stumbling upon a plot hole in a well-written mystery, leaving no room for doubt regarding the strength of this correlation.
This striking correlation, akin to an unexpected plot twist, prompts contemplation of the potential underlying factors contributing to this peculiar connection. One cannot help but wonder whether the political climate of a state influences the literary preferences of its populace, or if the narrative elements within popular fiction exert a subtle yet undeniable influence on political inclinations. The confluence of these seemingly incongruous spheres redefines the term "political fiction," akin to an unexpected crossover event in the literary universe.
The robustness of this correlation impels us to consider unconventional theories of influence and alignment between politics and storytelling. The intersection of these two domains, seemingly as distant as the poles, invites us to ponder whether the narrative arc of a best-selling novel could mirror the political trajectory of a state, each chapter revealing a surprising turn of events. The whimsy of this discovery exposes a fascinating realm of inquiry where the boundaries between politics and literature blur, much like a poorly drawn map of a fictional world.
The high correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers bolsters the intrigue and astonishment surrounding this unlikely association. The scholarly community and enthusiasts of esoteric correlations alike are beckoned to partake in the captivating enigma uncovered by our study. This research serves as a reminder that within the realm of statistical analysis, as in life, serendipitous findings and unexpected correlations can add a touch of whimsy to the otherwise predictable landscape of academic inquiry.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our perplexing findings have woven a tapestry of intrigue, reminiscent of a gripping fictional narrative, with the captivating correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers at its core. This discovery not only substantiates prior research that delves into the relationship between political inclinations and literary tastes but also adds a dash of whimsy to the scholarly conversation.

To begin with, the unexpected correlation we uncovered aligns with the work of Smith (2010), who ventured into the relationship between political ideology and reading preferences. While our study may initially appear to tread on whimsical terrain, the robust correlation coefficient of 0.9189783 serves as a testament to the underlying influence of political climate on literary preferences, echoing Smith's findings in a remarkably delightful manner.

Moreover, our results resonate with the earlier exploration by Doe (2015) on the impact of electoral outcomes on consumer behavior. The uncanny alignment between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers adds a layer of peculiarity to Doe's area of inquiry, as if the characters in a political drama have unexpectedly crept into the pages of a best-selling novel.

As our findings intertwine with prior research, the plot thickens, mirroring the tension and anticipation of a thrilling cliffhanger. The narrative backdrop we have uncovered not only broadens our understanding of the intersections between politics and literature but also injects a jolt of whimsy into the scholarly discourse, akin to an unexpected punchline in an otherwise conventional narrative.

In essence, our study, much like a well-crafted piece of fiction, challenges the boundaries of convention and offers a tantalizing glimpse into the delightful oddities and unexpected correlations that enrich the academic landscape. The robustness of the correlation we have unveiled invites further exploration into the unconventional theories of influence and alignment between politics and storytelling, lending an air of whimsy to the realm of statistical analysis.

Ultimately, our findings stand as a testament to the delightful and often surprising connections that await within the uncharted territories of academic inquiry, adding a touch of whimsy and intrigue to the otherwise predictable landscape of scholarly exploration. As we turn the page to the next chapter of this captivating saga, we are reminded that within the world of academic research, as in the realm of fiction, unexpected plot twists and whimsical discoveries await those who dare to venture beyond the confines of conventional wisdom.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Votes for the Democrat Presidential candidate in Hawaii and New York Times Fiction Best Sellers. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers

[[ABSTRACT]]
This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

[[INTRDUCTION]]
INTRODUCTION
In the ever-expanding realm of political science and literary analysis, an unexpected and somewhat whimsical correlation has come to light. As researchers seek to uncover the intricate connections between voting patterns and consumer behavior, our study delves into the intriguing relationship between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. While the intersection of politics and fiction may seem as unlikely as a reality TV star becoming President, the data speaks for itself—loud and clear, like a poorly written political thriller.
It is a truth universally acknowledged, that a single presidential election in a particular state can have an impact on the literary pursuits of its inhabitants. As our research unfolds, we embark on a journey to unravel the enigmatic bond between an individual's political inclinations and their choice of fictional escapism. This correlation, as serendipitous as stumbling upon a rare first edition in a used bookstore, has raised eyebrows and piqued the curiosity of scholars and non-scholars alike.
As with any unexpected correlation, the first question that springs to mind is undoubtedly, "Is this just a fluke, or do we have a real plot twist on our hands?" To tackle this question, we meticulously scrutinize the data obtained from reputable sources such as the MIT Election Data and Science Lab, the Harvard Dataverse, and Hawes, a treasure trove of literary data. Through rigorous statistical analysis, we reveal a correlation coefficient that would make even the most stoic academic crack a smile—0.9189783, with a p-value of less than 0.01. This eyebrow-raising coefficient suggests a connection more robust than the bond between a detective and their trusty sidekick.
The implications of this correlation, if proven to be more than a mere fluke of statistical probability, are as bewildering as a mystery novel's final plot twist. What could possibly tie the political leanings of a state's populace to their choice of fiction? Are we witnessing the influence of political rhetoric on literary tastes, or could it be that the narrative devices used in popular fiction hold the power to sway political allegiances? These questions, as intriguing as a locked-room murder, propel our investigation into uncharted territories of interdisciplinary connection.
As we venture further into this peculiar confluence of political drama and fictional narratives, we invite our esteemed colleagues and curious observers to join us in unraveling the captivating patterns and peculiar curiosities that have emerged from our study. By embracing the quirkier side of academic investigation, we strive to shed light on this mesmerizing correlation and the delightful oddities it unveils—because in the world of research, as in life, sometimes truth is indeed stranger than fiction.

[[RESULTS]]
Our analysis of the data acquired from the MIT Election Data and Science Lab, Harvard Dataverse, and Hawes has unearthed a bewilderingly strong correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers. The correlation coefficient of 0.9189783, accompanied by an r-squared value of 0.8445211 and a p-value less than 0.01, holds sway over our findings, much like a leading character captivates readers in a best-selling novel.
As depicted in Figure 1, the scatterplot emphasizes the robust and unexpected relationship between these two seemingly disparate variables. The alignment of the data points is as uncanny as stumbling upon a plot hole in a well-written mystery, leaving no room for doubt regarding the strength of this correlation.
This striking correlation, akin to an unexpected plot twist, prompts contemplation of the potential underlying factors contributing to this peculiar connection. One cannot help but wonder whether the political climate of a state influences the literary preferences of its populace, or if the narrative elements within popular fiction exert a subtle yet undeniable influence on political inclinations. The confluence of these seemingly incongruous spheres redefines the term "political fiction," akin to an unexpected crossover event in the literary universe.
The robustness of this correlation impels us to consider unconventional theories of influence and alignment between politics and storytelling. The intersection of these two domains, seemingly as distant as the poles, invites us to ponder whether the narrative arc of a best-selling novel could mirror the political trajectory of a state, each chapter revealing a surprising turn of events. The whimsy of this discovery exposes a fascinating realm of inquiry where the boundaries between politics and literature blur, much like a poorly drawn map of a fictional world.
The high correlation between votes for Democrat presidential candidates in Hawaii and the New York Times Fiction Best Sellers bolsters the intrigue and astonishment surrounding this unlikely association. The scholarly community and enthusiasts of esoteric correlations alike are beckoned to partake in the captivating enigma uncovered by our study. This research serves as a reminder that within the realm of statistical analysis, as in life, serendipitous findings and unexpected correlations can add a touch of whimsy to the otherwise predictable landscape of academic inquiry.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unravelled a correlation so robust it could rival the most captivating plot twists in fiction. The unexpected connection between votes for Democrat presidential candidates in Hawaii and New York Times Fiction Best Sellers reflects the whimsical and often perplexing nature of human behavioral trends. The remarkably high correlation coefficient of 0.9189783 (p < 0.01) not only piques scholarly curiosity but also prompts a wry smile akin to stumbling upon a well-concealed Easter egg in a novel.

While our findings do not provide a definitive causal explanation, they do raise thought-provoking questions that are as curious as a metaphysical mystery and as delightful as a perfectly-timed comedy. Could the political climate of a state subtly influence the literary inclinations of its residents, or do the narrative elements within popular fiction engage in a carefully choreographed dance with political allegiances? The intersection of these realms presents a captivating puzzle, much like a literary whodunit that defies conventions and expectations.

As we close this chapter on the unexpected correlation between politics and literature, it becomes evident that the human psyche is as enigmatic and whimsical as the most intricate of fictional characters. While this study unveils a correlation worth its weight in comedic plot devices, we assert that no further research is needed in this area. After all, some correlations are best left to resonate as charming anomalies, adding a touch of intrigue to the otherwise predictable landscape of academic inquiry.


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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Political Literature


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 Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Literary Political Analysis


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Dem(ocrat) and the Best Seller: Analyzing the Correlation Between Votes for Democrat Presidential Candidates in Hawaii and New York Times Fiction Best Sellers with an abstract of This research paper investigates the surprising connection between the votes for Democrat presidential candidates in Hawaii and the national best-selling fiction titles showcased in the New York Times. Through rigorous data analysis from MIT Election Data and Science Lab, Harvard Dataverse, and Hawes, our findings reveal an astonishingly high correlation coefficient of 0.9189783 (p < 0.01) for the period spanning from 1976 to 2014. We explore the potential factors contributing to this connection, including the influence of political climate on literary preferences, and the impact of storytelling elements on political inclinations. The unexpected correlations and whimsical patterns unearthed in this study promise to intrigue both the academic community and aficionados of eccentric trivia.

ChatGPT:

Democrat presidential candidates, Hawaii, New York Times, fiction best sellers, correlation analysis, MIT Election Data and Science Lab, Harvard Dataverse, political climate, literary preferences, storytelling elements, political inclinations

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

New York Times Fiction Best Sellers
Detailed data title: Number of unique fictional books on the New York Times Best Seller List (counting repeat books only once)
Source: Hawes
See what else correlates with New York Times Fiction Best Sellers

Correlation r = 0.9189783 (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 = 0.8445211 (Coefficient of determination)
This means 84.5% of the change in the one variable (i.e., New York Times Fiction Best Sellers) is predictable based on the change in the other (i.e., Votes for the Democratic Presidential candidate in Hawaii) over the 10 years from 1976 through 2014.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.000171. 0.0001708129144379488000000000
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 0.92 in 0.0171% of random cases. Said differently, if you correlated 5,854 random variables Which I absolutely did.
with the same 9 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 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.

[ 0.69, 0.98 ] 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.
1976198019841988199219962000200420082012
Votes for the Democratic Presidential candidate in Hawaii (Percentage of votes)50.59244.802143.815954.269448.092856.928855.791754.009671.452970.1479
New York Times Fiction Best Sellers (NYT Best Sellers)3777101214143435




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. 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([50.592,44.8021,43.8159,54.2694,48.0928,56.9288,55.7917,54.0096,71.4529,70.1479,])
array_2 = np.array([3,7,7,7,10,12,14,14,34,35,])
array_1_name = "Votes for the Democratic Presidential candidate in Hawaii"
array_2_name = "New York Times Fiction Best Sellers"

# 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?

I'm genuinely thankful for your rating!


Correlation ID: 5600 · Black Variable ID: 26082 · Red Variable ID: 96
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0