about · email me · subscribe
Spurious correlation #4,845 · 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 South Dakota and the second variable is Total comments on Vihart's YouTube videos.  The chart goes from 2009 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The rise in arson in South Dakota led to an unexpected surplus in burnt out trees, which in turn sparked a renewed interest in fractal patterns and mathematical beauty, consequently prompting people to engage more with ViHart's thought-provoking content, thus leading to the increase in total comments on her YouTube videos.

Model: dalle-3
Prompt: Generate an image of the Black Hills of South Dakota with charred trees standing against a clear blue sky, incorporating vibrant vaporwave colors. The burnt out trees should display intricate fractal patterns, symbolizing the newfound interest in mathematical beauty. Perhaps add a subtle nod to ViHart's content, such as an icon representing her YouTube channel, enriching the visual narrative. 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 South Dakota and Total comments on Vihart YouTube videos. 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: Vaporwave An image that looks like it is a scene from A Disney Movie Voxel art Surrealism Vaporwave
ChatGPT: Vaporwave

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 South Dakota and Total comments on Vihart YouTube videos, in the following situation: The rise in arson in South Dakota led to an unexpected surplus in burnt out trees, which in turn sparked a renewed interest in fractal patterns and mathematical beauty, consequently prompting people to engage more with ViHart's thought-provoking content, thus leading to the increase in total comments on her YouTube videos.. Keep the description simple.
ChatGPT: In the Black Hills of South Dakota, where the recent rise in arson has left charred trees standing in stark contrast against the clear blue sky. However, from the aftermath, a captivating sight emerges - the burnt out trees take on intricate fractal patterns, sparking a renewed interest in mathematical beauty. This newfound fascination prompts people to engage more with ViHart's thought-provoking content on YouTube, leading to an increase in the total comments on her videos.

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: [ Vaporwave ] and depicting this scene: In the Black Hills of South Dakota, where the recent rise in arson has left charred trees standing in stark contrast against the clear blue sky. However, from the aftermath, a captivating sight emerges - the burnt out trees take on intricate fractal patterns, sparking a renewed interest in mathematical beauty. This newfound fascination prompts people to engage more with ViHart's thought-provoking content on YouTube, leading to an increase in the total comments on her videos. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of the Black Hills of South Dakota with charred trees standing against a clear blue sky, incorporating vibrant vaporwave colors. The burnt out trees should display intricate fractal patterns, symbolizing the newfound interest in mathematical beauty. Perhaps add a subtle nod to ViHart's content, such as an icon representing her YouTube channel, enriching the visual narrative.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in Arson in South Dakota positively influenced Total comments on Vihart YouTube videos.

AI academic paper

(Because p < 0.01)
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

The Journal of Experimental Pyrokinetics

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Make the title a clever pun.

Your research team used data from FBI Criminal Justice Information Services and YouTube to assess this nagging question. You found a correlation coefficient of 0.9214508 and p < 0.01 for 2009 to 2022.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As the saying goes, "Where there's smoke, there's fire." But who would have thought that the same principle would apply to the world of statistical analysis? In this study, we embark on a fiery journey to explore the unlikely association between arson rates in South Dakota and the total comments on Vihart's YouTube videos. It's a bit like trying to reconcile the compatibility of water and fire – a conundrum worthy of sparking both intrigue and amusement for researchers and readers alike.

Now, I must say that delving into the relationship between arson and YouTube comments has been quite an enlightening experience – pun intended. The proverbial lightbulb above our heads illuminated the need to investigate whether there exists a connection that would set the statistical world ablaze. As we set forth on this inferno-inducing adventure, we couldn't help but wonder if our findings would ignite a new wave of interdisciplinary research or simply go up in smoke.

Picture this: conducting statistical analysis on arson data is like playing with fire, both figuratively and statistically. Our data exploration is akin to navigating through a statistical forest where every correlation coefficient is a potential spark waiting to ignite a scientific revelation – or at least a dashing pun or two. So, without further ado, let's heat things up as we untangle the smoldering relationship between arson in South Dakota and the comments section of Vihart's YouTube videos.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the saying goes, "Where there's smoke, there's fire." But who would have thought that the same principle would apply to the world of statistical analysis? In this study, we embark on a fiery journey to explore the unlikely association between arson rates in South Dakota and the total comments on Vihart's YouTube videos. It's a bit like trying to reconcile the compatibility of water and fire – a conundrum worthy of sparking both intrigue and amusement for researchers and readers alike.
Now, I must say that delving into the relationship between arson and YouTube comments has been quite an enlightening experience – pun intended. The proverbial lightbulb above our heads illuminated the need to investigate whether there exists a connection that would set the statistical world ablaze. As we set forth on this inferno-inducing adventure, we couldn't help but wonder if our findings would ignite a new wave of interdisciplinary research or simply go up in smoke.
Picture this: conducting statistical analysis on arson data is like playing with fire, both figuratively and statistically. Our data exploration is akin to navigating through a statistical forest where every correlation coefficient is a potential spark waiting to ignite a scientific revelation – or at least a dashing pun or two. So, without further ado, let's heat things up as we untangle the smoldering relationship between arson in South Dakota and the comments section of Vihart's YouTube videos.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The investigation into the correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos has sparked the interest of scholars across various disciplines. In "Smith et al.'s study," the authors find a direct association between arson and increased social media activity, shedding light on the combustible nature of online engagement. Similarly, Doe and Jones' research reveals a positive correlation between arson rates and digital interactions, igniting discussions on the interconnectedness of fire-related incidents and virtual communication.

Now, let's turn the page and examine some seminal non-fiction works relevant to our incendiary inquiry. "The Psychology of Arson" by John Doe provides valuable insights into the motivation behind arson, illuminating the psychological tinder that may fuel this destructive behavior. Moreover, "The YouTube Phenomenon" by Jane Smith delves into the impact of online content on viewer engagement, casting a radiant spotlight on the dynamics of digital interactions.

On a more fictitious note, the novel "The Firestarter's Dilemma" by A. Blaze offers a fantastical exploration of arson-related mysteries, adding a touch of whimsy to our scorching topic. Additionally, "The Algorithm of Engagement" by S. Vihart (no relation to the YouTube personality) presents a fictional account of a mathematical discovery that unlocks the secrets of digital engagement, sparking the imagination and quite possibly a few fires of curiosity.

And now for a touch of internet culture, it would be remiss not to mention the "This is Fine" meme, which, much like our unexpected research findings, captures the essence of maintaining composure in the face of unforeseen circumstances. Additionally, the "Fire up the Grill" meme aptly captures the theme of igniting enthusiasm and conversation, much like the surge in YouTube comments observed in our study.

In summary, the diverse array of literature and cultural references surrounding the correlation between arson in South Dakota and the total comments on Vihart's YouTube videos underscores the multifaceted nature of this research endeavor. As we continue to stoke the figurative flames of inquiry, it becomes clear that there is much yet to be illuminated in this fiery fusion of statistical analysis and online engagement.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and YouTube . You used data from 2009 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]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

[[INTRODUCTION]]
As the saying goes, "Where there's smoke, there's fire." But who would have thought that the same principle would apply to the world of statistical analysis? In this study, we embark on a fiery journey to explore the unlikely association between arson rates in South Dakota and the total comments on Vihart's YouTube videos. It's a bit like trying to reconcile the compatibility of water and fire – a conundrum worthy of sparking both intrigue and amusement for researchers and readers alike.
Now, I must say that delving into the relationship between arson and YouTube comments has been quite an enlightening experience – pun intended. The proverbial lightbulb above our heads illuminated the need to investigate whether there exists a connection that would set the statistical world ablaze. As we set forth on this inferno-inducing adventure, we couldn't help but wonder if our findings would ignite a new wave of interdisciplinary research or simply go up in smoke.
Picture this: conducting statistical analysis on arson data is like playing with fire, both figuratively and statistically. Our data exploration is akin to navigating through a statistical forest where every correlation coefficient is a potential spark waiting to ignite a scientific revelation – or at least a dashing pun or two. So, without further ado, let's heat things up as we untangle the smoldering relationship between arson in South Dakota and the comments section of Vihart's YouTube videos.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the incendiary link between arson in South Dakota and the total comments on Vihart's YouTube videos, we crafted a research methodology that was as meticulous as a fire investigator sifting through charred remains. First, we gathered arson data from the FBI Criminal Justice Information Services, carefully selecting records from 2009 to 2022 – because as they say, our research was really heating up by then. Then, we ventured into the boundless expanse of YouTube to retrieve the total number of comments on Vihart's videos during the same time frame, as counting comments seemed more illuminating than counting fireflies.

With these datasets in hand, we then unleashed the power of statistical analysis to tease out any glimmers of correlation between these seemingly incongruous variables. Much like a fireman using a hose to douse a flame, we employed Pearson's correlation coefficient to quantify the strength and direction of the relationship between arson rates and Vihart's video comments. We also wielded the menacing p-value to determine the statistical significance of our findings, hoping to stop any smoke and mirrors acts in their tracks.

As we stepped back to observe the statistical bonfire we had ignited, we couldn't help but marvel at the smoking-hot correlation coefficient of 0.9214508 and the statistically significant p-value of less than 0.01 that emerged from our analysis. Yes, our results were as striking as discovering a match in a dark room – with a side of statistical significance.

In addition, we meticulously controlled for potential confounding variables, ensuring that our findings weren't engulfed in a statistical inferno. We also employed advanced time-series analysis methods to capture the dynamic nature of both arson rates and YouTube comments, because as any seasoned fire dancer knows, timing is everything.

Overall, our methodology served as the proverbial firefighter in this research endeavor, swiftly extinguishing doubts and illuminating the unexpected relationship between arson in South Dakota and the comments section of Vihart's YouTube videos. It's safe to say that our methodology not only fanned the flames of curiosity but also kindled a new appreciation for the fiery world of statistical analysis - pun fire-ly intended.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2009 to 2022, you found a correlation 0.9214508, r-squared of 0.8490717, 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]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the saying goes, "Where there's smoke, there's fire." But who would have thought that the same principle would apply to the world of statistical analysis? In this study, we embark on a fiery journey to explore the unlikely association between arson rates in South Dakota and the total comments on Vihart's YouTube videos. It's a bit like trying to reconcile the compatibility of water and fire – a conundrum worthy of sparking both intrigue and amusement for researchers and readers alike.
Now, I must say that delving into the relationship between arson and YouTube comments has been quite an enlightening experience – pun intended. The proverbial lightbulb above our heads illuminated the need to investigate whether there exists a connection that would set the statistical world ablaze. As we set forth on this inferno-inducing adventure, we couldn't help but wonder if our findings would ignite a new wave of interdisciplinary research or simply go up in smoke.
Picture this: conducting statistical analysis on arson data is like playing with fire, both figuratively and statistically. Our data exploration is akin to navigating through a statistical forest where every correlation coefficient is a potential spark waiting to ignite a scientific revelation – or at least a dashing pun or two. So, without further ado, let's heat things up as we untangle the smoldering relationship between arson in South Dakota and the comments section of Vihart's YouTube videos.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a notably strong correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos. With a correlation coefficient of 0.9214508 and an r-squared value of 0.8490717, the connection between these seemingly disparate variables blazes with significance. It's almost as if these variables were caught in a fiery embrace, much like the way a father embraces his questionable puns – with great reluctance and yet undeniable warmth.

The p-value of less than 0.01 further fuels the validity of this correlation, indicating that the likelihood of such a relationship occurring by random chance is about as likely as finding a fire extinguisher at a bonfire – highly improbable.

Fig. 1 showcases a scatterplot that visually captures the potent correlation between the two variables. This relationship is as clear as day, leaving little room for doubt or debate. It's almost like the statistical software couldn't resist playing with fire and decided to showcase its scorching findings through an illuminating visual representation.

As we interpret these results, it's clear that the flames of curiosity have been stoked, setting ablaze a new avenue for further inquiry into the unanticipated connection between arson in South Dakota and the comment section of Vihart's YouTube videos. This correlation ignites a sense of intrigue and marvel, much like a well-crafted dad joke that leaves one simultaneously amused and perplexed.

This investigation not only sheds light on the capricious nature of statistical analysis but also kindles a flame of curiosity in the interdisciplinary exploration of seemingly unrelated phenomena. It's as though the statistical universe has thrown us a curveball that's akin to a fiery dad joke – unexpected, amusing, and remarkably thought-provoking.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

[[LITERATURE REVIEW]]
The investigation into the correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos has sparked the interest of scholars across various disciplines. In "Smith et al.'s study," the authors find a direct association between arson and increased social media activity, shedding light on the combustible nature of online engagement. Similarly, Doe and Jones' research reveals a positive correlation between arson rates and digital interactions, igniting discussions on the interconnectedness of fire-related incidents and virtual communication.
Now, let's turn the page and examine some seminal non-fiction works relevant to our incendiary inquiry. "The Psychology of Arson" by John Doe provides valuable insights into the motivation behind arson, illuminating the psychological tinder that may fuel this destructive behavior. Moreover, "The YouTube Phenomenon" by Jane Smith delves into the impact of online content on viewer engagement, casting a radiant spotlight on the dynamics of digital interactions.
On a more fictitious note, the novel "The Firestarter's Dilemma" by A. Blaze offers a fantastical exploration of arson-related mysteries, adding a touch of whimsy to our scorching topic. Additionally, "The Algorithm of Engagement" by S. Vihart (no relation to the YouTube personality) presents a fictional account of a mathematical discovery that unlocks the secrets of digital engagement, sparking the imagination and quite possibly a few fires of curiosity.
And now for a touch of internet culture, it would be remiss not to mention the "This is Fine" meme, which, much like our unexpected research findings, captures the essence of maintaining composure in the face of unforeseen circumstances. Additionally, the "Fire up the Grill" meme aptly captures the theme of igniting enthusiasm and conversation, much like the surge in YouTube comments observed in our study.
In summary, the diverse array of literature and cultural references surrounding the correlation between arson in South Dakota and the total comments on Vihart's YouTube videos underscores the multifaceted nature of this research endeavor. As we continue to stoke the figurative flames of inquiry, it becomes clear that there is much yet to be illuminated in this fiery fusion of statistical analysis and online engagement.

[[RESULTS]]
The statistical analysis revealed a notably strong correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos. With a correlation coefficient of 0.9214508 and an r-squared value of 0.8490717, the connection between these seemingly disparate variables blazes with significance. It's almost as if these variables were caught in a fiery embrace, much like the way a father embraces his questionable puns – with great reluctance and yet undeniable warmth.
The p-value of less than 0.01 further fuels the validity of this correlation, indicating that the likelihood of such a relationship occurring by random chance is about as likely as finding a fire extinguisher at a bonfire – highly improbable.
Fig. 1 showcases a scatterplot that visually captures the potent correlation between the two variables. This relationship is as clear as day, leaving little room for doubt or debate. It's almost like the statistical software couldn't resist playing with fire and decided to showcase its scorching findings through an illuminating visual representation.
As we interpret these results, it's clear that the flames of curiosity have been stoked, setting ablaze a new avenue for further inquiry into the unanticipated connection between arson in South Dakota and the comment section of Vihart's YouTube videos. This correlation ignites a sense of intrigue and marvel, much like a well-crafted dad joke that leaves one simultaneously amused and perplexed.
This investigation not only sheds light on the capricious nature of statistical analysis but also kindles a flame of curiosity in the interdisciplinary exploration of seemingly unrelated phenomena. It's as though the statistical universe has thrown us a curveball that's akin to a fiery dad joke – unexpected, amusing, and remarkably thought-provoking.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings have undoubtedly set the research world ablaze with curiosity and bemusement, akin to stumbling upon a fiery pun hidden within dense statistical analysis. The strong correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos lends credence to the notion that these seemingly unrelated variables are, in fact, as entwined as a pair of smoldering embers. It's almost as if these variables were meant to spark our interest, much like a well-timed dad joke at a particularly dry academic conference.

The alignment of our results with prior research, such as Smith et al.'s and Doe and Jones' studies, further ignites the flame of confidence in the validity of our findings. Like a seasoned firefighter, the literature review not only laid the groundwork for our investigation but also fanned the flames of speculation, preparing us to face the unexpected inferno of correlation that ultimately emerged from our statistical analysis.

Our unexpected discovery also sheds light on the interconnectedness of otherwise disparate phenomena, bringing to mind the apt comparison to the "This is Fine" meme – an emblem of maintaining composure in the face of unexpected circumstances, much like our own unexpected findings of harmony between arson and YouTube comments. Furthermore, the novel "The Firestarter's Dilemma" and "The Algorithm of Engagement" fictionally mirror our statistically illuminated connection, imparting a whimsical touch to our fiery intellectual inquiry.

In summary, our research not only confirms the extraordinary nature of statistical analysis but also underscores the potential for unconventional connections to emerge, much like the unexpected humor counterpart to a dad joke. It's as if the statistical universe conspired to play a riveting and somewhat enigmatic practical joke on us, leaving us both bemused and fascinated by the intricate interplay of statistics and seemingly unrelated phenomena.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Arson in South Dakota and Total comments on Vihart YouTube videos. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos

[[ABSTRACT]]
This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.

It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

[[INTRDUCTION]]
As the saying goes, "Where there's smoke, there's fire." But who would have thought that the same principle would apply to the world of statistical analysis? In this study, we embark on a fiery journey to explore the unlikely association between arson rates in South Dakota and the total comments on Vihart's YouTube videos. It's a bit like trying to reconcile the compatibility of water and fire – a conundrum worthy of sparking both intrigue and amusement for researchers and readers alike.
Now, I must say that delving into the relationship between arson and YouTube comments has been quite an enlightening experience – pun intended. The proverbial lightbulb above our heads illuminated the need to investigate whether there exists a connection that would set the statistical world ablaze. As we set forth on this inferno-inducing adventure, we couldn't help but wonder if our findings would ignite a new wave of interdisciplinary research or simply go up in smoke.
Picture this: conducting statistical analysis on arson data is like playing with fire, both figuratively and statistically. Our data exploration is akin to navigating through a statistical forest where every correlation coefficient is a potential spark waiting to ignite a scientific revelation – or at least a dashing pun or two. So, without further ado, let's heat things up as we untangle the smoldering relationship between arson in South Dakota and the comments section of Vihart's YouTube videos.

[[RESULTS]]
The statistical analysis revealed a notably strong correlation between arson rates in South Dakota and the total comments on Vihart's YouTube videos. With a correlation coefficient of 0.9214508 and an r-squared value of 0.8490717, the connection between these seemingly disparate variables blazes with significance. It's almost as if these variables were caught in a fiery embrace, much like the way a father embraces his questionable puns – with great reluctance and yet undeniable warmth.
The p-value of less than 0.01 further fuels the validity of this correlation, indicating that the likelihood of such a relationship occurring by random chance is about as likely as finding a fire extinguisher at a bonfire – highly improbable.
Fig. 1 showcases a scatterplot that visually captures the potent correlation between the two variables. This relationship is as clear as day, leaving little room for doubt or debate. It's almost like the statistical software couldn't resist playing with fire and decided to showcase its scorching findings through an illuminating visual representation.
As we interpret these results, it's clear that the flames of curiosity have been stoked, setting ablaze a new avenue for further inquiry into the unanticipated connection between arson in South Dakota and the comment section of Vihart's YouTube videos. This correlation ignites a sense of intrigue and marvel, much like a well-crafted dad joke that leaves one simultaneously amused and perplexed.
This investigation not only sheds light on the capricious nature of statistical analysis but also kindles a flame of curiosity in the interdisciplinary exploration of seemingly unrelated phenomena. It's as though the statistical universe has thrown us a curveball that's akin to a fiery dad joke – unexpected, amusing, and remarkably thought-provoking.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

After setting the statistical world ablaze with our findings, it's safe to say that the connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos is indeed no mere smokescreen. The scorching correlation coefficient of 0.9214508 and the sizzling p-value of less than 0.01 have unequivocally sparked new interest in the interplay between these fiery variables.

In the realm of statistical analysis, uncovering such a relationship is akin to finding out that you can't have your arson and not ignite YouTube comments too - a real plot twist, if you will. Our results suggest that as arson rates rise, so does the burning desire to comment on Vihart's videos, leaving us to ponder whether there's a lurking arsonist in the YouTube comment section or if Vihart's content is simply highly flammable - talk about setting the internet ablaze!

As the puns and correlations come together like a well-orchestrated comedy act, it's clear that this unexpected correlation not only adds fuel to the fire of interdisciplinary research but also blazes a trail for future investigations into the enigmatic connection between seemingly unrelated phenomena, much like a dad joke that's both inexplicably funny and peculiarly thought-provoking.

In conclusion, it's evident that further research in this area is as unnecessary as bringing a fire extinguisher to a water park - in other words, simply not needed. With this fiery uncovering, it's time to extinguish the flames of curiosity and let this puzzling correlation smolder in the annals of statistical enigmas.


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 Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Experimental Pyrokinetics


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 Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Forensic Social Media 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 Playing with Fire: Exploring the Fiery Connection Between Arson in South Dakota and Total Comments on Vihart YouTube Videos with an abstract of This study delves into the unexpected and seemingly unrelated connection between arson rates in South Dakota and the total comments on Vihart's YouTube videos. Utilizing data from the FBI Criminal Justice Information Services and YouTube, we scrutinized the intriguing relationship between these divergent variables. Surprisingly, we uncovered a correlation coefficient of 0.9214508 and a statistically significant p-value of less than 0.01 for the time period spanning from 2009 to 2022.
It appears that as arson rates in South Dakota rise, so do the total comments on Vihart's YouTube videos – a correlation that is as surprising as the sudden appearance of a flaming punchline at a dad joke convention. While the exact mechanism underlying this correlation remains enigmatic, this research opens new avenues for interdisciplinary exploration and sparks peculiar new insights into the interconnectedness of seemingly unrelated phenomena.

ChatGPT:

arson rates South Dakota, Vihart YouTube videos comments, correlation, FBI CJIS data, YouTube data analysis, interdisciplinary exploration, interconnectedness of phenomena

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

Total comments on Vihart's YouTube videos
Detailed data title: Total comments on Vihart YouTube videos.
Source: YouTube
See what else correlates with Total comments on Vihart's YouTube videos

Correlation r = 0.9214508 (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 = 0.8490717 (Coefficient of determination)
This means 84.9% of the change in the one variable (i.e., Total comments on Vihart's YouTube videos) is predictable based on the change in the other (i.e., Arson in South Dakota) over the 14 years from 2009 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.9E-6. 0.0000028582006487379434000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.92 in 0.00029% of random cases. Said differently, if you correlated 349,870 random variables You don't actually need 349 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 13 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.76, 0.98 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
20092010201120122013201420152016201720182019202020212022
Arson in South Dakota (Arson rate)10.310.317.227.917.510.510.414.615.78.97.311.18.17.4
Total comments on Vihart's YouTube videos (Total comments)180028490550971252676140815028141871544315950139023583241847854823




Why this works

  1. 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.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([10.3,10.3,17.2,27.9,17.5,10.5,10.4,14.6,15.7,8.9,7.3,11.1,8.1,7.4,])
array_2 = np.array([1800,28490,55097,125267,61408,15028,14187,15443,15950,13902,3583,2418,4785,4823,])
array_1_name = "Arson in South Dakota"
array_2_name = "Total comments on Vihart's YouTube videos"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

I'm genuinely thankful for your rating!


Correlation ID: 4845 · Black Variable ID: 20069 · Red Variable ID: 25564
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0