Spurious correlation #1,629 · 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 New Hampshire and the second variable is Google searches for 'Gangnam Style'. The chart goes from 2012 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 New Hampshire and the second variable is Google searches for 'Gangnam Style'. The chart goes from 2012 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The decrease in arson in New Hampshire led to a decrease in Gangnam Style searches because firefighters were too busy perfecting the dance moves, leaving them with no time to quench the fiery trend.

^{Show image generation prompt} Model: dalle-3
Prompt: "Create a realistic image of a small New Hampshire town with a burning building in the background. A group of people is gathered in front of it, one person is holding up their phone and searching for "Gangnam Style" on Google. Capture the contrast between the chaotic scene and the lightheartedness of the musical search." 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: Arson in New Hampshire and Google searches for 'Gangnam Style'. 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: Cyber folk Art nouveau Realistic Cyber folk 3D Pixar Style
ChatGPT: Realistic

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 Arson in New Hampshire and Google searches for 'Gangnam Style' together. Keep the description simple.
ChatGPT: In a small New Hampshire town, a group of people gathers in front of a burning building. A person holds up their phone and searches for "Gangnam Style" on Google, while the catchy tune plays in the background.

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: [ Realistic ] and depicting this scene: In a small New Hampshire town, a group of people gathers in front of a burning building. A person holds up their phone and searches for "Gangnam Style" on Google, while the catchy tune plays in the background. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: "Create a realistic image of a small New Hampshire town with a burning building in the background. A group of people is gathered in front of it, one person is holding up their phone and searching for "Gangnam Style" on Google. Capture the contrast between the chaotic scene and the lightheartedness of the musical search."

*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 New Hampshire caused Gangnam Style (Google searches for 'Gangnam Style') to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

The Journal of Quirky Social Sciences

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 New Hampshire and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delved into the intriguing and perhaps unexpected relationship between instances of arson in the scenic state of New Hampshire and the worldwide phenomenon of Google searches for the iconic 'Gangnam Style'. Utilizing data from the FBI Criminal Justice Information Services and Google Trends, our research team aimed to uncover whether a connection exists between these seemingly unrelated phenomena.

The findings of our study revealed a staggering correlation coefficient of 0.9531529 and a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022. This result indicates a remarkably strong positive relationship between the occurrence of arson in New Hampshire and the frequency of Google searches for the catchy hit by Psy.

While these findings may initially seem whimsical, they serve as a vibrant reminder that patterns in human behavior can transcend the boundaries of what we expect. As the saying goes, "Where there's arson, there's fire" - but who would have thought that a fiery crime and a memorable dance craze would be intertwined in such an unexpected manner? Join us as we uncover the offbeat threads of correlation that tie these separate domains together and bring a touch of whimsy to the world of statistical analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Strap on your dancing shoes and prepare for a fiery investigation, because in this paper, we are about to shimmy and sashay through the unexpected connection between arson in New Hampshire and the global phenomenon of 'Gangnam Style'. As we unravel the enigmatic relationship between these seemingly disparate occurrences, one thing becomes clear: this study is about to set the research world ablaze – pun very much intended.
As we ignite the spark of curiosity, we aim to demonstrate that even the most seemingly unrelated phenomena can come together in an explosive display of correlation – and perhaps a bit of Dad-approved humor. Because, after all, what do you call a dancing arsonist? A fire starter, of course!
Armed with data from the FBI Criminal Justice Information Services and Google Trends, our research team sought to dig deep into the statistical trenches to uncover whether a burning desire for 'Gangnam Style' and a penchant for setting fires in the peaceful state of New Hampshire could indeed be linked. And lo and behold, the results were hotter than a trending dance move at a summer barbecue.
Hold on to your socks, because the findings of our study revealed a correlation coefficient so sizzling, it would make even the most seasoned grill master envious. With a scorching 0.9531529 and a statistically significant p-value of less than 0.01 for the period from 2012 to 2022, it's safe to say that we've set the dance floor – and the research community – ablaze with our smoking hot results.
But enough with the fiery puns, let's extinguish the flames of skepticism and take a serious look at these unexpected correlations. After all, "When there's smoke, there's fire" – but who knew that a catchy tune and a criminal act could be intertwined in such an unexpected manner? Rest assured, we are about to take a seriously lighthearted approach to uncovering the offbeat threads of correlation that connect these seemingly unrelated domains – and maybe bust a few dance moves along the way.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

As we delve into the intriguing and unexpected correlation between arson in New Hampshire and Google searches for 'Gangnam Style', we must first acknowledge the scholarly contributions that have set the stage for our fiery investigation. Smith and Doe (2015) conducted a comprehensive analysis of arson patterns in rural areas, shedding light on the complex dynamics of fire-related incidents. Little did they know, their work would ignite a spark of curiosity that would lead us to uncover the fiery correlation with a globally viral dance sensation.

In the realm of music and cultural phenomena, Jones (2013) explored the impact of internet memes on popular dance movements, offering valuable insights into the spread of viral sensations across digital platforms. While Jones may not have predicted a link between 'Gangnam Style' and a spate of arson incidents, their work paves the way for our exploration of the unexpected intersections between internet trends and criminal activities.

Speaking of intersections, let's take a moment to ponder a classic dad joke: Why did the arsonist break up with their partner? They were tired of getting burned in the relationship. Now, back to our regularly scheduled programming of scholarly inquiry.

Turning our attention to the broader cultural landscape, non-fiction works such as "The Psychology of Arson" by Firestone (2018) and "Internet Virality and Global Trends" by Trenderson (2016) provide valuable perspectives on the psychological motivations behind arson and the rapid propagation of internet phenomena, respectively. While these works may not directly address the specific combination of fiery crimes and dance-related Google searches, they lay the groundwork for understanding the complex tapestry of human behavior that forms the backdrop of our investigation.

On a lighter note, let's not overlook the whimsical influences of fiction that could offer tangential insights into our correlation conundrum. Works of fiction such as "The Arsonist's Tango" by Blaze (2014) and "Dancing through the Flames" by Heatwave (2017) may not be scholarly treatises, but they certainly add a touch of literary flair to our exploration of the unexpected connections between arson and dance crazes.

In the spirit of unexpected correlations, let's not discount the potential influence of board games on our understanding of human behavior. Games like "Fires of Desire" and "Gangnam Style: The Dance-off Edition" may not be traditional sources of scholarly insight, but they certainly invite us to ponder the whimsical interplay between fiery passions and infectious dance moves.

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 New Hampshire and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Google Trends .

For the time period 2012 to 2022, you found a correlation 0.9531529, r-squared of 0.9085005, 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]]
Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delved into the intriguing and perhaps unexpected relationship between instances of arson in the scenic state of New Hampshire and the worldwide phenomenon of Google searches for the iconic 'Gangnam Style'. Utilizing data from the FBI Criminal Justice Information Services and Google Trends, our research team aimed to uncover whether a connection exists between these seemingly unrelated phenomena.

The findings of our study revealed a staggering correlation coefficient of 0.9531529 and a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022. This result indicates a remarkably strong positive relationship between the occurrence of arson in New Hampshire and the frequency of Google searches for the catchy hit by Psy.

While these findings may initially seem whimsical, they serve as a vibrant reminder that patterns in human behavior can transcend the boundaries of what we expect. As the saying goes, "Where there's arson, there's fire" - but who would have thought that a fiery crime and a memorable dance craze would be intertwined in such an unexpected manner? Join us as we uncover the offbeat threads of correlation that tie these separate domains together and bring a touch of whimsy to the world of statistical analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Strap on your dancing shoes and prepare for a fiery investigation, because in this paper, we are about to shimmy and sashay through the unexpected connection between arson in New Hampshire and the global phenomenon of 'Gangnam Style'. As we unravel the enigmatic relationship between these seemingly disparate occurrences, one thing becomes clear: this study is about to set the research world ablaze – pun very much intended.
As we ignite the spark of curiosity, we aim to demonstrate that even the most seemingly unrelated phenomena can come together in an explosive display of correlation – and perhaps a bit of Dad-approved humor. Because, after all, what do you call a dancing arsonist? A fire starter, of course!
Armed with data from the FBI Criminal Justice Information Services and Google Trends, our research team sought to dig deep into the statistical trenches to uncover whether a burning desire for 'Gangnam Style' and a penchant for setting fires in the peaceful state of New Hampshire could indeed be linked. And lo and behold, the results were hotter than a trending dance move at a summer barbecue.
Hold on to your socks, because the findings of our study revealed a correlation coefficient so sizzling, it would make even the most seasoned grill master envious. With a scorching 0.9531529 and a statistically significant p-value of less than 0.01 for the period from 2012 to 2022, it's safe to say that we've set the dance floor – and the research community – ablaze with our smoking hot results.
But enough with the fiery puns, let's extinguish the flames of skepticism and take a serious look at these unexpected correlations. After all, "When there's smoke, there's fire" – but who knew that a catchy tune and a criminal act could be intertwined in such an unexpected manner? Rest assured, we are about to take a seriously lighthearted approach to uncovering the offbeat threads of correlation that connect these seemingly unrelated domains – and maybe bust a few dance moves along the way.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]
The statistical analysis of the data revealed a remarkably high correlation coefficient of 0.9531529 between occurrences of arson in New Hampshire and Google searches for 'Gangnam Style' from 2012 to 2022. The r-squared value of 0.9085005 further indicated that approximately 90.8% of the variability in arson incidents can be explained by the frequency of 'Gangnam Style' searches. In addition, the p-value of less than 0.01 suggested a statistically significant relationship between the two variables.

Fig. 1: Scatterplot showing the strong correlation between arson in New Hampshire and Google searches for 'Gangnam Style'.

As the data unfolded before us, it became increasingly clear that this correlation was not a mere flash in the pan, but rather a substantial and enduring association. It seems that while the New Hampshire nights were heating up with cases of arson, folks were also turning up the heat on their search engines for a little bit of Gangnam flair.

It's as if the residents of New Hampshire were so fired up that they just needed to dance it out, proving once and for all that you can't stop the beat – or the flames, apparently. One might say that these results are so hot, they could rival the scorching temperatures of a summer bonfire. But let's not get too fired up about it.

This unexpected correlation raises questions about the intricacies of human behavior and the interconnectedness of seemingly unrelated phenomena. It also prompts us to ponder if arsonists have a burning passion for K-Pop, or if K-Pop admirers have an uncontrollable urge to start fires. After all, what do you call an arsonist at a dance party? A hot stepper, of course!

But in all seriousness, these findings remind us that the world of statistical analysis is full of surprises, much like finding a disco ball in a fire station. While the connection between arson and 'Gangnam Style' may seem like a whimsical oddity, it serves as a poignant reminder that statistical correlations can lead us to uncover unexpected and intriguing patterns in human behavior.

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 New Hampshire and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delved into the intriguing and perhaps unexpected relationship between instances of arson in the scenic state of New Hampshire and the worldwide phenomenon of Google searches for the iconic 'Gangnam Style'. Utilizing data from the FBI Criminal Justice Information Services and Google Trends, our research team aimed to uncover whether a connection exists between these seemingly unrelated phenomena.

The findings of our study revealed a staggering correlation coefficient of 0.9531529 and a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022. This result indicates a remarkably strong positive relationship between the occurrence of arson in New Hampshire and the frequency of Google searches for the catchy hit by Psy.

While these findings may initially seem whimsical, they serve as a vibrant reminder that patterns in human behavior can transcend the boundaries of what we expect. As the saying goes, "Where there's arson, there's fire" - but who would have thought that a fiery crime and a memorable dance craze would be intertwined in such an unexpected manner? Join us as we uncover the offbeat threads of correlation that tie these separate domains together and bring a touch of whimsy to the world of statistical analysis.

[[LITERATURE REVIEW]]
As we delve into the intriguing and unexpected correlation between arson in New Hampshire and Google searches for 'Gangnam Style', we must first acknowledge the scholarly contributions that have set the stage for our fiery investigation. Smith and Doe (2015) conducted a comprehensive analysis of arson patterns in rural areas, shedding light on the complex dynamics of fire-related incidents. Little did they know, their work would ignite a spark of curiosity that would lead us to uncover the fiery correlation with a globally viral dance sensation.
In the realm of music and cultural phenomena, Jones (2013) explored the impact of internet memes on popular dance movements, offering valuable insights into the spread of viral sensations across digital platforms. While Jones may not have predicted a link between 'Gangnam Style' and a spate of arson incidents, their work paves the way for our exploration of the unexpected intersections between internet trends and criminal activities.
Speaking of intersections, let's take a moment to ponder a classic dad joke: Why did the arsonist break up with their partner? They were tired of getting burned in the relationship. Now, back to our regularly scheduled programming of scholarly inquiry.
Turning our attention to the broader cultural landscape, non-fiction works such as "The Psychology of Arson" by Firestone (2018) and "Internet Virality and Global Trends" by Trenderson (2016) provide valuable perspectives on the psychological motivations behind arson and the rapid propagation of internet phenomena, respectively. While these works may not directly address the specific combination of fiery crimes and dance-related Google searches, they lay the groundwork for understanding the complex tapestry of human behavior that forms the backdrop of our investigation.
On a lighter note, let's not overlook the whimsical influences of fiction that could offer tangential insights into our correlation conundrum. Works of fiction such as "The Arsonist's Tango" by Blaze (2014) and "Dancing through the Flames" by Heatwave (2017) may not be scholarly treatises, but they certainly add a touch of literary flair to our exploration of the unexpected connections between arson and dance crazes.
In the spirit of unexpected correlations, let's not discount the potential influence of board games on our understanding of human behavior. Games like "Fires of Desire" and "Gangnam Style: The Dance-off Edition" may not be traditional sources of scholarly insight, but they certainly invite us to ponder the whimsical interplay between fiery passions and infectious dance moves.

[[RESULTS]]
The statistical analysis of the data revealed a remarkably high correlation coefficient of 0.9531529 between occurrences of arson in New Hampshire and Google searches for 'Gangnam Style' from 2012 to 2022. The r-squared value of 0.9085005 further indicated that approximately 90.8% of the variability in arson incidents can be explained by the frequency of 'Gangnam Style' searches. In addition, the p-value of less than 0.01 suggested a statistically significant relationship between the two variables.
Fig. 1: Scatterplot showing the strong correlation between arson in New Hampshire and Google searches for 'Gangnam Style'.
As the data unfolded before us, it became increasingly clear that this correlation was not a mere flash in the pan, but rather a substantial and enduring association. It seems that while the New Hampshire nights were heating up with cases of arson, folks were also turning up the heat on their search engines for a little bit of Gangnam flair.
It's as if the residents of New Hampshire were so fired up that they just needed to dance it out, proving once and for all that you can't stop the beat – or the flames, apparently. One might say that these results are so hot, they could rival the scorching temperatures of a summer bonfire. But let's not get too fired up about it.
This unexpected correlation raises questions about the intricacies of human behavior and the interconnectedness of seemingly unrelated phenomena. It also prompts us to ponder if arsonists have a burning passion for K-Pop, or if K-Pop admirers have an uncontrollable urge to start fires. After all, what do you call an arsonist at a dance party? A hot stepper, of course!
But in all seriousness, these findings remind us that the world of statistical analysis is full of surprises, much like finding a disco ball in a fire station. While the connection between arson and 'Gangnam Style' may seem like a whimsical oddity, it serves as a poignant reminder that statistical correlations can lead us to uncover unexpected and intriguing patterns in human behavior.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of our study provide compelling evidence of a strong positive correlation between arson in New Hampshire and Google searches for 'Gangnam Style'. These results align with prior research by Smith and Doe (2015), who uncovered the complex dynamics of fire-related incidents in rural areas. While the connection between a viral dance sensation and a surge in arson incidents may seem like a whimsical oddity, this correlation underscores the intricate tapestry of human behavior.

It seems that the sparks of curiosity ignited by Smith and Doe have led us to a fiery dance floor of data analysis. The unexpected twist of uncovering a connection between 'Gangnam Style' and arson brings to mind the classic dad joke: Why don't firefighters ever get tired of giving YouTube tutorials? Because they have an endless supply of 'fire' content.

Furthermore, the significant correlation coefficient and r-squared value in our study echo the impact of internet memes on popular dance movements as explored by Jones (2013). Jones may not have foreseen a link between 'Gangnam Style' searches and arson, but the spread of viral sensations across digital platforms seems to have sizzled its way into the realm of criminal activities. It's almost as if the arsonists were trying to set the night on fire in more ways than one.

The statistically significant relationship between arson occurrences and 'Gangnam Style' searches also resonates with the broader cultural perspectives presented by Firestone (2018) and Trenderson (2016). It's as if the psychological motivations behind arson and the rapid propagation of internet phenomena have collided in a spectacular display of statistical pyrotechnics.

One can't help but wonder if our findings hint at an underlying passion for K-Pop within the arsonist community or a burning desire to set the dance floor ablaze amongst 'Gangnam Style' enthusiasts. It's a captivating puzzle that brings to mind another classic dad joke: Why did the music charts report the arsonist's crime? They wanted to track the 'hot' singles.

As we confront these unexpected correlations, it's important to approach the analysis with a dash of humor and a keen sense of curiosity. After all, statistical correlations have a knack for leading us down uncharted paths, not unlike stumbling upon a dance-off at a fire station. In this spirit of whimsy and wonder, our study sheds light on the nuanced and often surprising patterns that underpin human behavior, adding a touch of unexpected merriment to the world of scientific inquiry.

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 New Hampshire and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delved into the intriguing and perhaps unexpected relationship between instances of arson in the scenic state of New Hampshire and the worldwide phenomenon of Google searches for the iconic 'Gangnam Style'. Utilizing data from the FBI Criminal Justice Information Services and Google Trends, our research team aimed to uncover whether a connection exists between these seemingly unrelated phenomena.

The findings of our study revealed a staggering correlation coefficient of 0.9531529 and a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022. This result indicates a remarkably strong positive relationship between the occurrence of arson in New Hampshire and the frequency of Google searches for the catchy hit by Psy.

While these findings may initially seem whimsical, they serve as a vibrant reminder that patterns in human behavior can transcend the boundaries of what we expect. As the saying goes, "Where there's arson, there's fire" - but who would have thought that a fiery crime and a memorable dance craze would be intertwined in such an unexpected manner? Join us as we uncover the offbeat threads of correlation that tie these separate domains together and bring a touch of whimsy to the world of statistical analysis.

[[INTRDUCTION]]
Strap on your dancing shoes and prepare for a fiery investigation, because in this paper, we are about to shimmy and sashay through the unexpected connection between arson in New Hampshire and the global phenomenon of 'Gangnam Style'. As we unravel the enigmatic relationship between these seemingly disparate occurrences, one thing becomes clear: this study is about to set the research world ablaze – pun very much intended.
As we ignite the spark of curiosity, we aim to demonstrate that even the most seemingly unrelated phenomena can come together in an explosive display of correlation – and perhaps a bit of Dad-approved humor. Because, after all, what do you call a dancing arsonist? A fire starter, of course!
Armed with data from the FBI Criminal Justice Information Services and Google Trends, our research team sought to dig deep into the statistical trenches to uncover whether a burning desire for 'Gangnam Style' and a penchant for setting fires in the peaceful state of New Hampshire could indeed be linked. And lo and behold, the results were hotter than a trending dance move at a summer barbecue.
Hold on to your socks, because the findings of our study revealed a correlation coefficient so sizzling, it would make even the most seasoned grill master envious. With a scorching 0.9531529 and a statistically significant p-value of less than 0.01 for the period from 2012 to 2022, it's safe to say that we've set the dance floor – and the research community – ablaze with our smoking hot results.
But enough with the fiery puns, let's extinguish the flames of skepticism and take a serious look at these unexpected correlations. After all, "When there's smoke, there's fire" – but who knew that a catchy tune and a criminal act could be intertwined in such an unexpected manner? Rest assured, we are about to take a seriously lighthearted approach to uncovering the offbeat threads of correlation that connect these seemingly unrelated domains – and maybe bust a few dance moves along the way.

[[RESULTS]]
The statistical analysis of the data revealed a remarkably high correlation coefficient of 0.9531529 between occurrences of arson in New Hampshire and Google searches for 'Gangnam Style' from 2012 to 2022. The r-squared value of 0.9085005 further indicated that approximately 90.8% of the variability in arson incidents can be explained by the frequency of 'Gangnam Style' searches. In addition, the p-value of less than 0.01 suggested a statistically significant relationship between the two variables.
Fig. 1: Scatterplot showing the strong correlation between arson in New Hampshire and Google searches for 'Gangnam Style'.
As the data unfolded before us, it became increasingly clear that this correlation was not a mere flash in the pan, but rather a substantial and enduring association. It seems that while the New Hampshire nights were heating up with cases of arson, folks were also turning up the heat on their search engines for a little bit of Gangnam flair.
It's as if the residents of New Hampshire were so fired up that they just needed to dance it out, proving once and for all that you can't stop the beat – or the flames, apparently. One might say that these results are so hot, they could rival the scorching temperatures of a summer bonfire. But let's not get too fired up about it.
This unexpected correlation raises questions about the intricacies of human behavior and the interconnectedness of seemingly unrelated phenomena. It also prompts us to ponder if arsonists have a burning passion for K-Pop, or if K-Pop admirers have an uncontrollable urge to start fires. After all, what do you call an arsonist at a dance party? A hot stepper, of course!
But in all seriousness, these findings remind us that the world of statistical analysis is full of surprises, much like finding a disco ball in a fire station. While the connection between arson and 'Gangnam Style' may seem like a whimsical oddity, it serves as a poignant reminder that statistical correlations can lead us to uncover unexpected and intriguing patterns in human behavior.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

As we wrap up this scorching investigation, the findings of our study have not only kindled a fiery curiosity but have also sparked a renewed appreciation for the unexpected connections in our world. Who would have thought that a New Hampshire night ablaze with arson would be interwoven with the infectious beats of 'Gangnam Style'? It's as if fire and dance moves make for an unlikely duo–a real fire and ice situation, if you will!

The results of our research have unveiled a correlation coefficient so hot, it could melt even the iciest of statistical hearts. If we were to put it in layman's terms, this correlation is so strong, it's practically the statistical equivalent of a five-alarm fire. But don't worry, no fire extinguisher needed here!

In the grand tradition of dad jokes, it seems that the arsonists in New Hampshire were not just setting fires, but also setting the dance floor on fire with their unquenchable thirst for 'Gangnam Style'. Now that's what we call some hot moves!

So, where do we go from here? Well, it's safe to say that our findings have set the research community ablaze with a newfound appreciation for the unexpected. We've certainly brought some heat to the often-cool world of statistical analysis. It seems that correlation truly knows no bounds, and that you can find a fiery connection in the most unlikely places.

In conclusion, this study leaves us with a burning question: do arsonists have a secret penchant for K-Pop, or are K-Pop enthusiasts secretly harboring a fiery penchant for arson? Perhaps it's best to leave that mystery unsolved for now.

In the immortal words of a true fire safety expert, "Stop, drop, and dance!"

In the end, we can confidently declare that no further research is needed in this domain. After all, how much more fiery fun could we possibly handle?

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 Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Social Sciences

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 Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Sociological Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style' with an abstract of In this study, we delved into the intriguing and perhaps unexpected relationship between instances of arson in the scenic state of New Hampshire and the worldwide phenomenon of Google searches for the iconic 'Gangnam Style'. Utilizing data from the FBI Criminal Justice Information Services and Google Trends, our research team aimed to uncover whether a connection exists between these seemingly unrelated phenomena.
The findings of our study revealed a staggering correlation coefficient of 0.9531529 and a statistically significant p-value of less than 0.01 for the period spanning from 2012 to 2022. This result indicates a remarkably strong positive relationship between the occurrence of arson in New Hampshire and the frequency of Google searches for the catchy hit by Psy.
While these findings may initially seem whimsical, they serve as a vibrant reminder that patterns in human behavior can transcend the boundaries of what we expect. As the saying goes, "Where there's arson, there's fire" - but who would have thought that a fiery crime and a memorable dance craze would be intertwined in such an unexpected manner? Join us as we uncover the offbeat threads of correlation that tie these separate domains together and bring a touch of whimsy to the world of statistical analysis.

ChatGPT:

Gangnam Style, arson, New Hampshire, correlation, Google searches, FBI Criminal Justice Information Services, statistical analysis, data analysis, behavior patterns

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

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

Google searches for 'Gangnam Style'
Detailed data title: Relative volume of Google searches for 'Gangnam Style' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'Gangnam Style'

Correlation r = 0.9531529 (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 = 0.9085005 (Coefficient of determination)
This means 90.9% of the change in the one variable (i.e., Google searches for 'Gangnam Style') is predictable based on the change in the other (i.e., Arson in New Hampshire) over the 11 years from 2012 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.7E-6.^Show 0.0000057029056120171570000000
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 0.95 in 0.00057% of random cases. Said differently, if you correlated 175,349 random variables^Note You don't actually need 175 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 10 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.82, 0.99 ] 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.

	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Arson in New Hampshire (Arson rate)	24.6	16.9	13.8	10.5	13	9.6	8.9	9.3	11.1	8.4	8.8
Google searches for 'Gangnam Style' (Rel. search volume)	36.9	20.3333	4.66667	2.83333	1.33333	1	1	1	1	1	1

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([24.6,16.9,13.8,10.5,13,9.6,8.9,9.3,11.1,8.4,8.8,])
array_2 = np.array([36.9,20.3333,4.66667,2.83333,1.33333,1,1,1,1,1,1,])
array_1_name = "Arson in New Hampshire"
array_2_name = "Google searches for 'Gangnam Style'"

# 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 New Hampshire
Line chart for only Google searches for 'Gangnam Style'
AI-generated correlation image
The spurious research paper: Gangnam Fi(re)s: A Study on the Correlation Between Arson in New Hampshire and Google Searches for 'Gangnam Style'

View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!

Correlation ID: 1629 · Black Variable ID: 20056 · Red Variable ID: 1442


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