Spurious correlation #1,220 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Arson in Arkansas and the second variable is xkcd comics published about romance. The chart goes from 2007 to 2022, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Arson in Arkansas and the second variable is xkcd comics published about romance. The chart goes from 2007 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

It turns out that as the number of arson incidents in Arkansas decreased, so did the overall fiery passion in the state. With less literal and metaphorical burning desire, there was a noticeable drop in the inspiration for romance-related xkcd comics. It seems that when it comes to creating content about love, you can't just spark it up artificially.

^{Show image generation prompt} Model: dalle-3
Prompt: Visual Prompt: Generate an image that reflects a serene scene of a small town in Arkansas. A woodblock painting illustrating a quaint town setting, where the frequency of arson incidents has declined. Include the fire department's station, with a calendar featuring xkcd comics about romance on the wall. Show fewer townspeople flipping through it. Place the firefighter's old box of fire starters gathering dust in a corner, symbolizing the decreased use due to fewer emergencies. Additionally, depict the town's bookstore with a stack of untouched xkcd comics about romance, highlighting declining sales. Capture the aroma of calm and safety in the air, and portray the peaceful twinkling of stars in the dark night sky outside. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: A decrease in Arson in Arkansas caused xkcd comics published about romance to also decrease because with fewer fires, there's less need for fire starters to ignite the flames of passion. Without the thrill of fire, people are less likely to seek out romantic escapades, leading to a decline in the demand for romance-themed comics. It seems that without the burning desire for love, the comic just doesn't have the spark it used to!. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Celtic art Woodblock painting Art nouveau Woodblock painting Cute 2D animation
ChatGPT: Woodblock painting

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. A decrease in Arson in Arkansas caused xkcd comics published about romance to also decrease because with fewer fires, there's less need for fire starters to ignite the flames of passion. Without the thrill of fire, people are less likely to seek out romantic escapades, leading to a decline in the demand for romance-themed comics. It seems that without the burning desire for love, the comic just doesn't have the spark it used to!
ChatGPT: Imagine a small town in Arkansas where the number of arson incidents has decreased. The fire department's calendar featuring xkcd comics about romance is seen hanging on the wall, but fewer people are flipping through it. The firefighter's old box of fire starters sits in the corner, gathering dust, as there are fewer emergencies that require their use. The town's bookstore has a stack of xkcd comics about romance, but the sales have decreased, and the comics sit untouched on the shelves. Outside, the air smells of calm and safety, and the stars twinkle peacefully in the dark night sky.

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: [ Woodblock painting ] and depicting this scene: Imagine a small town in Arkansas where the number of arson incidents has decreased. The fire department's calendar featuring xkcd comics about romance is seen hanging on the wall, but fewer people are flipping through it. The firefighter's old box of fire starters sits in the corner, gathering dust, as there are fewer emergencies that require their use. The town's bookstore has a stack of xkcd comics about romance, but the sales have decreased, and the comics sit untouched on the shelves. Outside, the air smells of calm and safety, and the stars twinkle peacefully in the dark night sky. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Visual Prompt: Generate an image that reflects a serene scene of a small town in Arkansas. A woodblock painting illustrating a quaint town setting, where the frequency of arson incidents has declined. Include the fire department's station, with a calendar featuring xkcd comics about romance on the wall. Show fewer townspeople flipping through it. Place the firefighter's old box of fire starters gathering dust in a corner, symbolizing the decreased use due to fewer emergencies. Additionally, depict the town's bookstore with a stack of untouched xkcd comics about romance, highlighting declining sales. Capture the aroma of calm and safety in the air, and portray the peaceful twinkling of stars in the dark night sky outside.

*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.
^{Show prompt for explanation} 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 Arson in Arkansas caused xkcd comics published about romance to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection

The Journal of Eclectic Fire Science and Pop Culture Analysis

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You 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 Arson in Arkansas and xkcd comics published about romance. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection"

[[ABSTRACT]]
This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Arson, a crime as old as the control of fire itself, has long captivated the attention of scholars and law enforcement agencies alike. The incendiary act of setting deliberate fires, often for disturbing and dangerous purposes, has puzzled and concerned society for centuries. Meanwhile, in the realm of digital culture, xkcd, the webcomic of romance, sarcasm, math, and language, has amassed a dedicated following with its unique blend of humor and nerdy charm. What could possibly link these two disparate worlds?
In this paper, we delve into the curious and unexpected nexus between arson in Arkansas and the publication of xkcd comics about romance. The motivation for this investigation stems from a peculiar observation, one that may seem as unlikely as trying to ignite a fire with a damp match: a potential correlation between the prevalence of arson incidents in the state of Arkansas and the thematic content of xkcd webcomics exploring the complexities of love and relationships.
The concept of exploring a connection between the intentional destruction of property through fire and the lighthearted portrayal of romantic entanglements may initially appear absurd, like trying to extinguish a raging inferno with a water pistol. However, the pursuit of knowledge often leads us to unexpected and, at times, whimsical avenues of inquiry, much like stumbling upon an old, dusty tome in a neglected corner of a library.
Our study is guided by a sense of scholarly curiosity akin to that of a detective hunting for clues in a crime novel, leading us to question whether there may be more to this seemingly incongruous duo than meets the eye. As we embark on this academic quest, we remain acutely aware of the fine line between serious inquiry and whimsical speculation, lest we inadvertently fan the flames of misinformation or trivialize the complexities of arson-related criminal activities.
The unprecedented blend of criminology, digital culture, and statistical analysis in this study reflects our earnest attempt to approach this enigmatic correlation with gravity and rigor, despite the inherent peculiarity and potential for lighthearted mirth. It is our hope that the findings of this study will not only contribute to the scholarly discourse but also provide a glimmer of insight into the intricate web of human behavior, creativity, and, dare we say, comic relief.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
LITERATURE REVIEW

The investigation into the curious connection between arson in Arkansas and xkcd comics focusing on romance has led us to explore a wide range of scholarly works, non-fiction texts, and even unexpected sources. This review draws upon a diverse array of literature, ranging from seminal academic studies to popular fiction, and extends to unexpected, at times whimsical, sources that have shed light on the peculiar intersection of these seemingly unrelated phenomena.

In "Fire and Fury: A Criminological Analysis of Arson" by Smith, the authors find comprehensive insights into the motivations and typologies of arson, offering a foundational understanding of the criminal act that serves as the backdrop to our investigation. Doe's "XKCD: Volume I - A Collector's Edition" provides an in-depth examination of the early years of the celebrated webcomic and its thematic evolution, offering a contextual understanding of the romantic themes that permeate the xkcd oeuvre.

Moving beyond traditional academic studies, the works of John Grisham, particularly "The Firm" and "The Client," have offered intriguing narratives within the context of legal investigations and crime fiction, prompting contemplation on the nature of criminal activities and investigative methodologies. Not to be outdone, Agatha Christie's "Murder on the Orient Express" and "The Mysterious Affair at Styles" have provided a fictional lens through which to consider the intricate threads of motivation, deception, and unexpected correlations that often underpin criminal investigations.

As our exploration delved into more unorthodox territory, we found ourselves, in a moment of scholarly levity, poring over the backs of shampoo bottles in a bewildering attempt to uncover any hidden insights into the connection between arson in Arkansas and romance-themed xkcd comics. Though our findings in this peculiar venture were, regrettably, inconclusive, it nonetheless served as a poignant reminder of the twists and turns that academic inquiry can often take, much like navigating through a labyrinth of bubblegum-scented prose and cryptic ingredient lists.

In our earnest pursuit of understanding this enigmatic junction of arson and romance, we have drawn upon an eclectic array of sources, recognizing that the unexpected intersections of human behavior, creativity, and criminal activities may often lead us to scholarly destinations as surprising and unpredictable as the plot twists in a crime novel.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Arson in Arkansas and xkcd comics published about romance. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 FBI Criminal Justice Information Services and AI analysis of xkcd comics . You used data from 2007 to 2022

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]]
"Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection"

[[ABSTRACT]]
This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

[[INTRODUCTION]]
Arson, a crime as old as the control of fire itself, has long captivated the attention of scholars and law enforcement agencies alike. The incendiary act of setting deliberate fires, often for disturbing and dangerous purposes, has puzzled and concerned society for centuries. Meanwhile, in the realm of digital culture, xkcd, the webcomic of romance, sarcasm, math, and language, has amassed a dedicated following with its unique blend of humor and nerdy charm. What could possibly link these two disparate worlds?
In this paper, we delve into the curious and unexpected nexus between arson in Arkansas and the publication of xkcd comics about romance. The motivation for this investigation stems from a peculiar observation, one that may seem as unlikely as trying to ignite a fire with a damp match: a potential correlation between the prevalence of arson incidents in the state of Arkansas and the thematic content of xkcd webcomics exploring the complexities of love and relationships.
The concept of exploring a connection between the intentional destruction of property through fire and the lighthearted portrayal of romantic entanglements may initially appear absurd, like trying to extinguish a raging inferno with a water pistol. However, the pursuit of knowledge often leads us to unexpected and, at times, whimsical avenues of inquiry, much like stumbling upon an old, dusty tome in a neglected corner of a library.
Our study is guided by a sense of scholarly curiosity akin to that of a detective hunting for clues in a crime novel, leading us to question whether there may be more to this seemingly incongruous duo than meets the eye. As we embark on this academic quest, we remain acutely aware of the fine line between serious inquiry and whimsical speculation, lest we inadvertently fan the flames of misinformation or trivialize the complexities of arson-related criminal activities.
The unprecedented blend of criminology, digital culture, and statistical analysis in this study reflects our earnest attempt to approach this enigmatic correlation with gravity and rigor, despite the inherent peculiarity and potential for lighthearted mirth. It is our hope that the findings of this study will not only contribute to the scholarly discourse but also provide a glimmer of insight into the intricate web of human behavior, creativity, and, dare we say, comic relief.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To unravel the mysterious connection between arson in Arkansas and the thematic content of xkcd webcomics, our research team employed a methodological approach that can be likened to untangling a knotty plotline in a detective novel – equal parts methodical investigation and whimsical curiosity.

Data Collection:
Our first step in this peculiar quest was to gather information on arson incidents in Arkansas from the FBI Criminal Justice Information Services. We meticulously combed through reports, incident data, and historical records, akin to scrutinizing a crime scene for elusive clues. To balance this rather somber pursuit, we turned our attention to obtaining a comprehensive dataset of xkcd comics that revolved around themes of romance and relationships from 2007 to 2022. This involved a deep dive into the whimsical world of webcomics, where the search for romantic humor was not so much a chore as it was a delightful excursion into digital storytelling.

AI Analysis:
Armed with our dual troves of data – one steeped in the complexities of criminal activities and the other in the wry humor of digital comic artistry – we called upon the assistance of advanced Artificial Intelligence (AI) algorithms. These sophisticated digital sleuths were tasked with scrutinizing each xkcd comic related to romance, seeking patterns, motifs, and thematic undercurrents that may have eluded the naked eye. This process was both intellectually rigorous and, dare we say, a touch whimsical, akin to inviting a serious detective to a whimsical tea party.

Correlation Calculations:
Upon obtaining the results of AI analysis, we ventured into the realm of statistical calculations, where we assessed the correlation between the frequency of arson incidents in Arkansas and the publication of xkcd romance comics. Like an archeologist carefully piecing together fragments of an ancient artifact, we meticulously examined the statistical parameters to uncover any potential links, all the while maintaining a scientific composure that belied the inherently whimsical nature of our inquiry.

Ethical Considerations:
Amidst the clatter of statistical analyses and algorithmic scrutiny, we remained attuned to the ethical considerations inherent in our investigation. It was imperative to approach the intersection of criminal behavior and digital culture with a somber reverence, akin to a detective navigating a complex case with an ethical compass. We strived to ensure that our scholarly pursuit neither trivialized the gravity of arson-related criminal activities nor detracted from the nuance of digital storytelling, all while injecting a hint of scholarly whimsy in our quest for unexpected correlations.

In undertaking this methodological odyssey, our research team remained keenly aware of the unique blend of gravity and lighthearted inquiry that permeated our investigation. Our approach may have been unconventional, akin to embarking on a quest for hidden treasure beneath the veneer of everyday life, but it allowed us to uncover a correlation as unexpected as discovering a punchline in the midst of a seemingly serious conversation.

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

Please make up the results section of an academic research paper presenting the findings of the connection between Arson in Arkansas and xkcd comics published about romance. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 FBI Criminal Justice Information Services and AI analysis of xkcd comics .

For the time period 2007 to 2022, you found a correlation 0.9051802, r-squared of 0.8193513, 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]]
"Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection"

[[ABSTRACT]]
This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Arson, a crime as old as the control of fire itself, has long captivated the attention of scholars and law enforcement agencies alike. The incendiary act of setting deliberate fires, often for disturbing and dangerous purposes, has puzzled and concerned society for centuries. Meanwhile, in the realm of digital culture, xkcd, the webcomic of romance, sarcasm, math, and language, has amassed a dedicated following with its unique blend of humor and nerdy charm. What could possibly link these two disparate worlds?
In this paper, we delve into the curious and unexpected nexus between arson in Arkansas and the publication of xkcd comics about romance. The motivation for this investigation stems from a peculiar observation, one that may seem as unlikely as trying to ignite a fire with a damp match: a potential correlation between the prevalence of arson incidents in the state of Arkansas and the thematic content of xkcd webcomics exploring the complexities of love and relationships.
The concept of exploring a connection between the intentional destruction of property through fire and the lighthearted portrayal of romantic entanglements may initially appear absurd, like trying to extinguish a raging inferno with a water pistol. However, the pursuit of knowledge often leads us to unexpected and, at times, whimsical avenues of inquiry, much like stumbling upon an old, dusty tome in a neglected corner of a library.
Our study is guided by a sense of scholarly curiosity akin to that of a detective hunting for clues in a crime novel, leading us to question whether there may be more to this seemingly incongruous duo than meets the eye. As we embark on this academic quest, we remain acutely aware of the fine line between serious inquiry and whimsical speculation, lest we inadvertently fan the flames of misinformation or trivialize the complexities of arson-related criminal activities.
The unprecedented blend of criminology, digital culture, and statistical analysis in this study reflects our earnest attempt to approach this enigmatic correlation with gravity and rigor, despite the inherent peculiarity and potential for lighthearted mirth. It is our hope that the findings of this study will not only contribute to the scholarly discourse but also provide a glimmer of insight into the intricate web of human behavior, creativity, and, dare we say, comic relief.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data collected from a myriad of sources, including the FBI Criminal Justice Information Services and advanced AI analysis of xkcd comics, yielded unexpected and thought-provoking results. Our investigation into the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance revealed a remarkably high correlation coefficient of 0.9051802, with an r-squared value of 0.8193513 and a p-value of less than 0.01 for the period spanning from 2007 to 2022. This statistically significant correlation represents a substantial finding, akin to stumbling upon a hidden ember in a vast field of data.

The correlation can be visually appreciated in Figure 1, a scatterplot showcasing the robust relationship between the two seemingly unrelated variables. The strong linear trend depicted in the scatterplot illustrates the striking affinity between the frequency of arson incidents and the thematic content of xkcd romance comics. It's almost as if the data points are engaged in a duet, harmoniously dancing across the plot, much like protagonists in a romantic comedy – albeit with a slightly more incendiary twist.

The implications of this unexpected correlation extend beyond the realms of statistical analysis and into the nuanced intersections of human behavior, cultural expressions, and criminal activities. Like a surprising plot twist in a detective novel, the discovery of this correlation challenges conventional wisdom and sets the stage for further exploration of the quirky, and perhaps enigmatic, relationship between humor, sentiment, and fire-related criminal behavior.

This finding not only enriches the academic literature on criminology and popular culture but also serves as a delightful reminder that, in the vast landscape of research, unexpected connections can spark illuminating insights, much like a well-crafted punchline in a comedy routine. The results of our investigation have kindled a flame of curiosity and subtle amusement, underscoring the enduring allure of uncovering unexpected patterns in the multifaceted tapestry of human endeavors.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Arson in Arkansas and xkcd comics published about romance. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection"

[[ABSTRACT]]
This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

[[LITERATURE REVIEW]]
LITERATURE REVIEW
The investigation into the curious connection between arson in Arkansas and xkcd comics focusing on romance has led us to explore a wide range of scholarly works, non-fiction texts, and even unexpected sources. This review draws upon a diverse array of literature, ranging from seminal academic studies to popular fiction, and extends to unexpected, at times whimsical, sources that have shed light on the peculiar intersection of these seemingly unrelated phenomena.
In "Fire and Fury: A Criminological Analysis of Arson" by Smith, the authors find comprehensive insights into the motivations and typologies of arson, offering a foundational understanding of the criminal act that serves as the backdrop to our investigation. Doe's "XKCD: Volume I - A Collector's Edition" provides an in-depth examination of the early years of the celebrated webcomic and its thematic evolution, offering a contextual understanding of the romantic themes that permeate the xkcd oeuvre.
Moving beyond traditional academic studies, the works of John Grisham, particularly "The Firm" and "The Client," have offered intriguing narratives within the context of legal investigations and crime fiction, prompting contemplation on the nature of criminal activities and investigative methodologies. Not to be outdone, Agatha Christie's "Murder on the Orient Express" and "The Mysterious Affair at Styles" have provided a fictional lens through which to consider the intricate threads of motivation, deception, and unexpected correlations that often underpin criminal investigations.
As our exploration delved into more unorthodox territory, we found ourselves, in a moment of scholarly levity, poring over the backs of shampoo bottles in a bewildering attempt to uncover any hidden insights into the connection between arson in Arkansas and romance-themed xkcd comics. Though our findings in this peculiar venture were, regrettably, inconclusive, it nonetheless served as a poignant reminder of the twists and turns that academic inquiry can often take, much like navigating through a labyrinth of bubblegum-scented prose and cryptic ingredient lists.
In our earnest pursuit of understanding this enigmatic junction of arson and romance, we have drawn upon an eclectic array of sources, recognizing that the unexpected intersections of human behavior, creativity, and criminal activities may often lead us to scholarly destinations as surprising and unpredictable as the plot twists in a crime novel.

[[RESULTS]]
The analysis of the data collected from a myriad of sources, including the FBI Criminal Justice Information Services and advanced AI analysis of xkcd comics, yielded unexpected and thought-provoking results. Our investigation into the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance revealed a remarkably high correlation coefficient of 0.9051802, with an r-squared value of 0.8193513 and a p-value of less than 0.01 for the period spanning from 2007 to 2022. This statistically significant correlation represents a substantial finding, akin to stumbling upon a hidden ember in a vast field of data.
The correlation can be visually appreciated in Figure 1, a scatterplot showcasing the robust relationship between the two seemingly unrelated variables. The strong linear trend depicted in the scatterplot illustrates the striking affinity between the frequency of arson incidents and the thematic content of xkcd romance comics. It's almost as if the data points are engaged in a duet, harmoniously dancing across the plot, much like protagonists in a romantic comedy – albeit with a slightly more incendiary twist.
The implications of this unexpected correlation extend beyond the realms of statistical analysis and into the nuanced intersections of human behavior, cultural expressions, and criminal activities. Like a surprising plot twist in a detective novel, the discovery of this correlation challenges conventional wisdom and sets the stage for further exploration of the quirky, and perhaps enigmatic, relationship between humor, sentiment, and fire-related criminal behavior.
This finding not only enriches the academic literature on criminology and popular culture but also serves as a delightful reminder that, in the vast landscape of research, unexpected connections can spark illuminating insights, much like a well-crafted punchline in a comedy routine. The results of our investigation have kindled a flame of curiosity and subtle amusement, underscoring the enduring allure of uncovering unexpected patterns in the multifaceted tapestry of human endeavors.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study support and extend prior research in intriguing ways, providing compelling evidence for the unforeseen yet potent connection between arson incidents in Arkansas and the themes of romance portrayed in xkcd comics. This unexpected correlation between two seemingly disparate phenomena, reminiscent of a serendipitous pairing in a romantic comedy, serves as a testament to the intricate intertwining of human behaviors, popular culture, and criminal activities.

Our findings confirm and build upon the seminal work of Smith (2010), who expounded upon the motivations and typologies of arson. As our results suggest, the thematic content of xkcd romance comics appears to resonate with certain individuals to the point of manifesting in criminal acts, akin to the grand gestures of affection depicted in classic romantic narratives – albeit with significantly more dire consequences. This alignment with Smith's typologies of arson motivations showcases the multifaceted nature of criminal behavior and its unexpected intersections with cultural expressions.

Furthermore, Doe's (2015) comprehensive analysis of xkcd comics provides a contextual understanding of the thematic evolution within the webcomic. Our study sheds light on the potential influence of these evolving themes on the manifestation of criminal behavior, reminiscent of the unfolding plot twists in a suspenseful crime novel. The statistical significance of the correlation observed in our study underscores the need to further investigate the influence of cultural content on criminal activities, offering a sobering reminder of the profound impact of artistic representations on human behavior.

In a particularly captivating fashion, our findings mirror the intricate threads of motivation, deception, and unexpected correlations depicted in the works of crime fiction authors such as Grisham and Christie. This unexpected parallel underscores the enthralling nature of these findings, echoing the exhilarating revelations that often arise from unraveling enigmatic narratives akin to conducting a detective investigation.

It is worth noting that while our research did not yield conclusive findings from perusing the backs of shampoo bottles, the unexpected correlation uncovered between arson and romance-themed xkcd comics serves as a compelling metaphor for the unpredictability of academic inquiry – not unlike navigating a labyrinth of bubblegum-scented prose to uncover hidden insights.

In conclusion, the startling correlation between arson in Arkansas and romance-centric xkcd comics represents a captivating confluence of human behavior, cultural expressions, and criminal activities. This unexpected finding not only contributes to the scholarly discourse on criminology and popular culture but also serves as a testament to the enduring allure of uncovering unexpected patterns and hidden connections, much like a well-crafted punchline in a comedy routine.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Arson in Arkansas and xkcd comics published about romance. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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]]
"Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection"

[[ABSTRACT]]
This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

[[INTRDUCTION]]
Arson, a crime as old as the control of fire itself, has long captivated the attention of scholars and law enforcement agencies alike. The incendiary act of setting deliberate fires, often for disturbing and dangerous purposes, has puzzled and concerned society for centuries. Meanwhile, in the realm of digital culture, xkcd, the webcomic of romance, sarcasm, math, and language, has amassed a dedicated following with its unique blend of humor and nerdy charm. What could possibly link these two disparate worlds?
In this paper, we delve into the curious and unexpected nexus between arson in Arkansas and the publication of xkcd comics about romance. The motivation for this investigation stems from a peculiar observation, one that may seem as unlikely as trying to ignite a fire with a damp match: a potential correlation between the prevalence of arson incidents in the state of Arkansas and the thematic content of xkcd webcomics exploring the complexities of love and relationships.
The concept of exploring a connection between the intentional destruction of property through fire and the lighthearted portrayal of romantic entanglements may initially appear absurd, like trying to extinguish a raging inferno with a water pistol. However, the pursuit of knowledge often leads us to unexpected and, at times, whimsical avenues of inquiry, much like stumbling upon an old, dusty tome in a neglected corner of a library.
Our study is guided by a sense of scholarly curiosity akin to that of a detective hunting for clues in a crime novel, leading us to question whether there may be more to this seemingly incongruous duo than meets the eye. As we embark on this academic quest, we remain acutely aware of the fine line between serious inquiry and whimsical speculation, lest we inadvertently fan the flames of misinformation or trivialize the complexities of arson-related criminal activities.
The unprecedented blend of criminology, digital culture, and statistical analysis in this study reflects our earnest attempt to approach this enigmatic correlation with gravity and rigor, despite the inherent peculiarity and potential for lighthearted mirth. It is our hope that the findings of this study will not only contribute to the scholarly discourse but also provide a glimmer of insight into the intricate web of human behavior, creativity, and, dare we say, comic relief.

[[RESULTS]]
The analysis of the data collected from a myriad of sources, including the FBI Criminal Justice Information Services and advanced AI analysis of xkcd comics, yielded unexpected and thought-provoking results. Our investigation into the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance revealed a remarkably high correlation coefficient of 0.9051802, with an r-squared value of 0.8193513 and a p-value of less than 0.01 for the period spanning from 2007 to 2022. This statistically significant correlation represents a substantial finding, akin to stumbling upon a hidden ember in a vast field of data.
The correlation can be visually appreciated in Figure 1, a scatterplot showcasing the robust relationship between the two seemingly unrelated variables. The strong linear trend depicted in the scatterplot illustrates the striking affinity between the frequency of arson incidents and the thematic content of xkcd romance comics. It's almost as if the data points are engaged in a duet, harmoniously dancing across the plot, much like protagonists in a romantic comedy – albeit with a slightly more incendiary twist.
The implications of this unexpected correlation extend beyond the realms of statistical analysis and into the nuanced intersections of human behavior, cultural expressions, and criminal activities. Like a surprising plot twist in a detective novel, the discovery of this correlation challenges conventional wisdom and sets the stage for further exploration of the quirky, and perhaps enigmatic, relationship between humor, sentiment, and fire-related criminal behavior.
This finding not only enriches the academic literature on criminology and popular culture but also serves as a delightful reminder that, in the vast landscape of research, unexpected connections can spark illuminating insights, much like a well-crafted punchline in a comedy routine. The results of our investigation have kindled a flame of curiosity and subtle amusement, underscoring the enduring allure of uncovering unexpected patterns in the multifaceted tapestry of human endeavors.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has illuminated a surprisingly robust correlation between arson incidents in Arkansas and the thematic content of xkcd romance comics. This unexpected finding underscores the enigmatic interplay between humor, human behavior, and fire-related criminal activities, akin to a whimsical dance between unlikely partners. The statistical significance of the correlation coefficient, r-squared value, and p-value emphasizes the resonance of this peculiar relationship, much like a romantic sonnet composed in the flickering glow of a firelit evening.

The implications of this correlation permeate the realms of criminology and popular culture, adding a dash of quirky intrigue to the scholarly discourse. As we reflect on the unanticipated affinity between arson and romance comics, it becomes evident that the pursuit of knowledge often leads us down unconventional paths, not unlike stumbling upon an unexpected punchline in a serious conversation.

While our findings provide a captivating glimpse into the intersection of human behavior and creative expression, it is essential to acknowledge the inherent novelty and potential for lighthearted amusement in this correlation. Far from extinguishing the flames of curiosity, our investigation has kindled a spark of whimsy and contemplation, inviting further exploration of the idiosyncratic connections that permeate our world.

It is abundantly clear that no more research is needed in this area. The findings of this study, akin to a well-crafted punchline, have delivered their delightful twist, leaving us with a satisfying conclusion worth cherishing. As we bid adieu to this peculiar correlation, we do so with a smile and a nod to the whimsy of academic inquiry, embracing the unexpected insights that add a touch of mirth to the pursuit of knowledge.

And with that, our odd but intriguing journey comes to a close, leaving us with the knowledge that sometimes, in the peculiar dance of academia, even arson and romance can share a wry, unexpected connection.

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 Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Fire Science and Pop Culture Analysis

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 Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Arson Studies

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 Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection with an abstract of This paper aims to investigate the potential relationship between arson incidents in Arkansas and the publication of xkcd comics focusing on romance. By utilizing data from the FBI Criminal Justice Information Services and applying advanced AI analysis to xkcd comics, our research team sought to uncover any hidden connections between these seemingly disparate phenomena. Our analysis revealed a surprisingly high correlation coefficient of 0.9051802 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2022. The implications of this unexpected correlation are both intriguing and potentially illuminating, shedding light on the intersections of humor, human behavior, and fire-related criminal activities. The results of our study not only contribute to the literature on criminology and popular culture but also serve as a poignant reminder that even in the world of academia, correlations can sometimes spark unexpected insights, igniting a flame of curiosity in the pursuit of knowledge.

ChatGPT:

arson in Arkansas, xkcd romance comics, correlation analysis, FBI Criminal Justice Information Services, AI analysis, criminology, popular culture, humor, human behavior, fire-related criminal activities, correlation coefficient, p-value, literature review, academia, research study

*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

Arson in Arkansas
Detailed data title: The arson rate per 100,000 residents in Arkansas
Source: FBI Criminal Justice Information Services
See what else correlates with Arson in Arkansas

xkcd comics published about romance
Detailed data title: The number of xkcd comics published each year about romance
Source: AI analysis of xkcd comics
Additional Info: ^{See full details} I designed a Python workflow to perform OCR on every xkcd comic, feed that text into a large language model, and ask the model whether this comic was about the category named in the title.

See what else correlates with xkcd comics published about romance

Correlation r = 0.9051802 (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 = 0.8193513 (Coefficient of determination)
This means 81.9% of the change in the one variable (i.e., xkcd comics published about romance) is predictable based on the change in the other (i.e., Arson in Arkansas) over the 16 years from 2007 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.4E-6.^Show 0.0000014335804033879220000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.91 in 0.00014% of random cases. Said differently, if you correlated 697,554 random variables^Note You don't actually need 697 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 15 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.74, 0.97 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Arson in Arkansas (Arson rate)	24.1	24.7	21.2	21.8	20.8	19	17.5	15.3	16.4	18.1	18	17.6	14.4	18.9	18.6	16.1
xkcd comics published about romance (xkcd comics)	38	35	21	28	11	18	3	4	3	2	3	1	1	5	6	3

Why this works

Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
Lack of causal connection: There is probably^Note 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.
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^Note 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.
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. ^Note 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. ^{Show the steps to do this.} 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([24.1,24.7,21.2,21.8,20.8,19,17.5,15.3,16.4,18.1,18,17.6,14.4,18.9,18.6,16.1,])
array_2 = np.array([38,35,21,28,11,18,3,4,3,2,3,1,1,5,6,3,])
array_1_name = "Arson in Arkansas"
array_2_name = "xkcd comics published about romance"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Arson in Arkansas
Line chart for only xkcd comics published about romance
The spurious research paper: Burning Love: Exploring the Arson in Arkansas and XKCD Romance Comics Connection

View another random correlation

How fun was this correlation?

Hats off to you for rating!

Correlation ID: 1220 · Black Variable ID: 20060 · Red Variable ID: 20013


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: