about · email me · subscribe
Spurious correlation #4,501 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Total views on Computerphile YouTube videos and the second variable is Robberies in the US.  The chart goes from 2013 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of people watching Computerphile videos decreased, there was a parallel decrease in the overall superiority complex of tech-savvy individuals. This led to a reduced incidence of smug hackers trying to outsmart security systems, ultimately lowering the success rate of robberies. It seems that when it comes to crime, a little less "Ctrl+Alt+Delete" mentality can actually be a good thing!

Model: dalle-3
Prompt: Prompt: Generate an image in the style of data cyber art depicting a scene where two graphs are displayed. One graph shows the total views on Computerphile YouTube videos steadily declining, symbolizing the decrease in the tech-savvy community's confidence. The other graph shows a decrease in the number of successful robberies, indicating a correlation between the two variables. The visual should imply that as the superiority complex wanes, the boldness of smug hackers diminishes, leading to a decrease in successful robberies. The graphs should be visually distinct and convey the correlation effectively. Avoid using any words or speech bubbles in the image. 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: Total views on Computerphile YouTube videos and Robberies. 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: Glitch art Cybernetic art Data cyber art Steampunk Magic realism
ChatGPT: Data cyber art

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 Total views on Computerphile YouTube videos and Robberies, in the following situation: As the number of people watching Computerphile videos decreased, there was a parallel decrease in the overall superiority complex of tech-savvy individuals. This led to a reduced incidence of smug hackers trying to outsmart security systems, ultimately lowering the success rate of robberies. It seems that when it comes to crime, a little less "Ctrl+Alt+Delete" mentality can actually be a good thing!. Keep the description simple.
ChatGPT: In the scene, the graph showing the total views on Computerphile YouTube videos is steadily declining, symbolizing the decrease in the tech-savvy community's confidence. Simultaneously, the number of successful robberies displayed on another graph is also decreasing, indicating a correlation between the two variables. The scene implies that as the superiority complex wanes, the boldness of smug hackers diminishes, leading to a decrease in successful robberies.

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: [ Data cyber art ] and depicting this scene: In the scene, the graph showing the total views on Computerphile YouTube videos is steadily declining, symbolizing the decrease in the tech-savvy community's confidence. Simultaneously, the number of successful robberies displayed on another graph is also decreasing, indicating a correlation between the two variables. The scene implies that as the superiority complex wanes, the boldness of smug hackers diminishes, leading to a decrease in successful robberies. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image in the style of data cyber art depicting a scene where two graphs are displayed. One graph shows the total views on Computerphile YouTube videos steadily declining, symbolizing the decrease in the tech-savvy community's confidence. The other graph shows a decrease in the number of successful robberies, indicating a correlation between the two variables. The visual should imply that as the superiority complex wanes, the boldness of smug hackers diminishes, leading to a decrease in successful robberies. The graphs should be visually distinct and convey the correlation effectively. Avoid using any words or speech bubbles in the image.

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

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

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

AI academic paper

(Because p < 0.01)
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

Journal of Digital Culture and Criminology

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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from YouTube and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.9326717 and p < 0.01 for 2013 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]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The proliferation of digital media has undoubtedly revolutionized the way individuals consume information, entertainment, and yes, even crime. As the world becomes increasingly interconnected through online platforms, the potential for unexpected consequences and quirky correlations emerges. In this study, we delve into the hitherto unexplored relationship between the total views of Computerphile YouTube videos and the occurrence of robberies in the United States.

While some may dismiss the notion of a connection between YouTube views and real-world crime as mere whimsy, our findings reveal a surprisingly robust association. We posit that the captivating allure of computer science educational content on Computerphile may have unforeseen effects on the behaviors of viewers, transcending the virtual sphere and seeping into the realm of criminal activity.

The rise of digital content consumption has brought forth a myriad of unforeseen societal repercussions. In this regard, the correlation between YouTube views and occurrences of robberies in the US challenges traditional paradigms and beckons for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The proliferation of digital media has undoubtedly revolutionized the way individuals consume information, entertainment, and yes, even crime. As the world becomes increasingly interconnected through online platforms, the potential for unexpected consequences and quirky correlations emerges. In this study, we delve into the hitherto unexplored relationship between the total views of Computerphile YouTube videos and the occurrence of robberies in the United States.
While some may dismiss the notion of a connection between YouTube views and real-world crime as mere whimsy, our findings reveal a surprisingly robust association. We posit that the captivating allure of computer science educational content on Computerphile may have unforeseen effects on the behaviors of viewers, transcending the virtual sphere and seeping into the realm of criminal activity.
The rise of digital content consumption has brought forth a myriad of unforeseen societal repercussions. In this regard, the correlation between YouTube views and occurrences of robberies in the US challenges traditional paradigms and beckons for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The authors first consulted serious-sounding studies by Smith, Doe, and Jones in search of precedent for quirky connections between online content consumption and real-world behaviors. However, the literature fell short in directly addressing the relationship between the total views of Computerphile YouTube videos and the incidence of robberies in the United States. Despite perusing an extensive array of academic works, none directly tackled this unconventional inquiry.

In "Digital Media and Societal Impact," the authors elucidate the pervasive influence of digital media on individuals' cognitive processes and behavioral propensities. The study, while informative, fails to delve into the specific nuances of computer science educational content and its potential impact on criminal activities. Similarly, "Cyberspace and its Ramifications" explores the broader implications of online interactions, yet remains silent on the curious correlation uncovered in our investigation.

Venturing beyond the realm of academic literature, the authors turn their attention to non-fiction works with tangential relevance. "The Shallows: What the Internet is Doing to Our Brains" by Nicholas Carr illuminates the cognitive effects of prolonged digital immersion, and "Alone Together: Why We Expect More From Technology and Less From Each Other" by Sherry Turkle delves into the societal implications of technological advancement. While these texts provide valuable insights into the broader landscape of digital influence, they too neglect to address the specific nexus between Computerphile YouTube views and real-world crime occurrences.

Turning to fictional works that may hold veiled relevance, the authors seek inspiration from narratives that touch upon the intersection of technology and societal behavior. "Neuromancer" by William Gibson and "Snow Crash" by Neal Stephenson beckon with their dystopian visions of a hyperconnected world, where the boundaries between virtual and physical realities blur. While these sci-fi masterpieces offer tantalizing glimpses into the potential ramifications of digital submersion, their illustrative value in discerning the influence of Computerphile YouTube views on criminal endeavors remains, alas, negligible.

Forging ahead into uncharted territory, the researchers expand their purview to include seemingly unrelated sources of inspiration. Upon scrutinizing an array of cartoons and children's shows, the authors uncover unexpected parallels between the zany antics of animated characters and the quirky dynamics of online viewership. From the capricious escapades of "SpongeBob SquarePants" to the whimsical charm of "Phineas and Ferb," each narrative subtly hints at the enigmatic interplay of content absorption and off-kilter behavioral manifestations. While these findings may seem lighthearted, they discreetly contribute to the contemplation of the elusive link between Computerphile YouTube views and the burgeoning world of heists in the United States.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from YouTube and FBI Criminal Justice Information Services . You used data from 2013 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]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

[[INTRODUCTION]]
The proliferation of digital media has undoubtedly revolutionized the way individuals consume information, entertainment, and yes, even crime. As the world becomes increasingly interconnected through online platforms, the potential for unexpected consequences and quirky correlations emerges. In this study, we delve into the hitherto unexplored relationship between the total views of Computerphile YouTube videos and the occurrence of robberies in the United States.
While some may dismiss the notion of a connection between YouTube views and real-world crime as mere whimsy, our findings reveal a surprisingly robust association. We posit that the captivating allure of computer science educational content on Computerphile may have unforeseen effects on the behaviors of viewers, transcending the virtual sphere and seeping into the realm of criminal activity.
The rise of digital content consumption has brought forth a myriad of unforeseen societal repercussions. In this regard, the correlation between YouTube views and occurrences of robberies in the US challenges traditional paradigms and beckons for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study was designed to rigorously examine the potential connection between the total views of Computerphile YouTube videos and the frequency of robberies in the United States from 2013 to 2022. To begin, data on the total views of Computerphile videos was collected from the YouTube platform, with a meticulous focus on content related to computer science, technology, and, surprisingly, cryptic criminal schemes. Concurrently, data on the incidence of robberies in the US was sourced from the FBI Criminal Justice Information Services, providing a comprehensive record of criminal activities throughout the specified time frame.

The utilization of such disparate data sources posed a unique challenge, akin to attempting to blend the complexity of quantum cryptography with the unyielding nature of criminal intent. However, through a series of carefully crafted algorithms and statistical maneuvers, the research team harmonized these distinct datasets, much like coaxing a reluctant harmonica into performing alongside a grand piano.

Subsequently, to elucidate the potential relationship between YouTube views and real-world robberies, a series of sophisticated statistical analyses were performed. The data was subjected to regression modeling, time-series analysis, and propensity score matching, employing an arsenal of statistical tools that would make even the most prudent data analyst tremble with a mix of trepidation and curiosity.

In particular, the Pearson correlation coefficient was calculated to quantify the strength and direction of the association between YouTube views and robbery occurrences, yielding surprising results that would make even the most hardened statistician raise an intrigued eyebrow. Moreover, a series of sensitivity analyses were conducted to ensure the robustness of the findings, an endeavor akin to performing a delicate high-wire act while juggling boulders of data.

Furthermore, covariates such as socioeconomic indicators, regional variations, and, of course, the phases of the moon, were meticulously incorporated into the analytical framework to account for potential confounding factors that could skew the findings, navigating through a maze of variables like a cartographer charting unexplored territories.

Taken together, the methodology employed in this study transcended the conventional boundaries of statistical analysis, delving into the realm of online content consumption and its potential influence on real-world behaviors, all while maintaining a sense of bemused wonderment at the unexpected connections revealed through the labyrinthine paths of data analysis.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 2013 to 2022, you found a correlation 0.9326717, r-squared of 0.8698765, 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]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The proliferation of digital media has undoubtedly revolutionized the way individuals consume information, entertainment, and yes, even crime. As the world becomes increasingly interconnected through online platforms, the potential for unexpected consequences and quirky correlations emerges. In this study, we delve into the hitherto unexplored relationship between the total views of Computerphile YouTube videos and the occurrence of robberies in the United States.
While some may dismiss the notion of a connection between YouTube views and real-world crime as mere whimsy, our findings reveal a surprisingly robust association. We posit that the captivating allure of computer science educational content on Computerphile may have unforeseen effects on the behaviors of viewers, transcending the virtual sphere and seeping into the realm of criminal activity.
The rise of digital content consumption has brought forth a myriad of unforeseen societal repercussions. In this regard, the correlation between YouTube views and occurrences of robberies in the US challenges traditional paradigms and beckons for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a remarkably high correlation coefficient (r) of 0.9326717 between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. This robust correlation, with an r-squared value of 0.8698765, exceeded our initial expectations and hints at the existence of a potential relationship between online content consumption and criminal behavior. The p-value of less than 0.01 further solidifies the strength of this association, indicating a statistically significant link between the two variables.

The Figure 1 depicts a scatterplot illustrating the strong positive correlation between the total views of Computerphile YouTube videos and the number of robberies in the US. As the views of Computerphile videos increased, so did the occurrences of robberies, painting a compelling picture of the potential influence of online content on real-world criminal activities.

These findings present a quirky departure from conventional research inquiries into social phenomena, shedding light on the peculiar ways in which seemingly unrelated factors may intersect and exert influence. While the precise mechanisms underlying this correlation remain shrouded in mystery, the unexpected strength of the association prompts us to consider the quirky possibility of computer science education inadvertently inspiring real-world heists. This peculiar connection goes against the notion of "crime and punishment," suggesting that perhaps, in the age of digital convergence, it is "code and commission" that are shaping criminal behaviors.

The implications of our findings reach beyond the realm of statistical analysis, offering an opportunity to inject a dose of unexpected humor and quirkiness into the traditionally staid landscape of academic research. These results beckon for further exploration, inciting a blend of curiosity and amusement as we unravel the quirky mysteries that underpin the interplay between online content consumption and real-world behaviors.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

[[LITERATURE REVIEW]]
The authors first consulted serious-sounding studies by Smith, Doe, and Jones in search of precedent for quirky connections between online content consumption and real-world behaviors. However, the literature fell short in directly addressing the relationship between the total views of Computerphile YouTube videos and the incidence of robberies in the United States. Despite perusing an extensive array of academic works, none directly tackled this unconventional inquiry.
In "Digital Media and Societal Impact," the authors elucidate the pervasive influence of digital media on individuals' cognitive processes and behavioral propensities. The study, while informative, fails to delve into the specific nuances of computer science educational content and its potential impact on criminal activities. Similarly, "Cyberspace and its Ramifications" explores the broader implications of online interactions, yet remains silent on the curious correlation uncovered in our investigation.
Venturing beyond the realm of academic literature, the authors turn their attention to non-fiction works with tangential relevance. "The Shallows: What the Internet is Doing to Our Brains" by Nicholas Carr illuminates the cognitive effects of prolonged digital immersion, and "Alone Together: Why We Expect More From Technology and Less From Each Other" by Sherry Turkle delves into the societal implications of technological advancement. While these texts provide valuable insights into the broader landscape of digital influence, they too neglect to address the specific nexus between Computerphile YouTube views and real-world crime occurrences.
Turning to fictional works that may hold veiled relevance, the authors seek inspiration from narratives that touch upon the intersection of technology and societal behavior. "Neuromancer" by William Gibson and "Snow Crash" by Neal Stephenson beckon with their dystopian visions of a hyperconnected world, where the boundaries between virtual and physical realities blur. While these sci-fi masterpieces offer tantalizing glimpses into the potential ramifications of digital submersion, their illustrative value in discerning the influence of Computerphile YouTube views on criminal endeavors remains, alas, negligible.
Forging ahead into uncharted territory, the researchers expand their purview to include seemingly unrelated sources of inspiration. Upon scrutinizing an array of cartoons and children's shows, the authors uncover unexpected parallels between the zany antics of animated characters and the quirky dynamics of online viewership. From the capricious escapades of "SpongeBob SquarePants" to the whimsical charm of "Phineas and Ferb," each narrative subtly hints at the enigmatic interplay of content absorption and off-kilter behavioral manifestations. While these findings may seem lighthearted, they discreetly contribute to the contemplation of the elusive link between Computerphile YouTube views and the burgeoning world of heists in the United States.

[[RESULTS]]
The statistical analysis revealed a remarkably high correlation coefficient (r) of 0.9326717 between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. This robust correlation, with an r-squared value of 0.8698765, exceeded our initial expectations and hints at the existence of a potential relationship between online content consumption and criminal behavior. The p-value of less than 0.01 further solidifies the strength of this association, indicating a statistically significant link between the two variables.
The Figure 1 depicts a scatterplot illustrating the strong positive correlation between the total views of Computerphile YouTube videos and the number of robberies in the US. As the views of Computerphile videos increased, so did the occurrences of robberies, painting a compelling picture of the potential influence of online content on real-world criminal activities.
These findings present a quirky departure from conventional research inquiries into social phenomena, shedding light on the peculiar ways in which seemingly unrelated factors may intersect and exert influence. While the precise mechanisms underlying this correlation remain shrouded in mystery, the unexpected strength of the association prompts us to consider the quirky possibility of computer science education inadvertently inspiring real-world heists. This peculiar connection goes against the notion of "crime and punishment," suggesting that perhaps, in the age of digital convergence, it is "code and commission" that are shaping criminal behaviors.
The implications of our findings reach beyond the realm of statistical analysis, offering an opportunity to inject a dose of unexpected humor and quirkiness into the traditionally staid landscape of academic research. These results beckon for further exploration, inciting a blend of curiosity and amusement as we unravel the quirky mysteries that underpin the interplay between online content consumption and real-world behaviors.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study yielded a remarkably robust correlation between the total views of Computerphile YouTube videos and the incidence of robberies in the United States. Such a strong relationship begs the consideration of potential causality, albeit in a thoroughly tongue-in-cheek manner. Building upon the literature review's lighthearted foray into seemingly unrelated sources of inspiration, the results of our analysis unexpectedly supported the offhand observation of the zany antics of animated characters mirroring the quirky dynamics of online viewership. Perhaps there is a subtle, yet discernible, influence of computer science education through YouTube videos on the real-world evolution of criminal endeavors. This contemplation amuses the mind, offering a whimsical perspective on the typically staid pursuit of statistical inference.

Moreover, the unexpected strength of the correlation raises intriguing questions regarding the potential impact of online educational content on behavioral propensities. While conventional wisdom might attribute criminal activities to a myriad of socioeconomic factors, our findings prompt the consideration of a parallel narrative: one where computer science tutorials unwittingly incite an enigmatic wave of heists across the nation. Indeed, the age-old adage "knowledge is power" takes on a peculiar twist, where knowledge may, in fact, be a peculiar catalyst for mischievous exploits.

The quirky possibility of computer science education inadvertently inspiring real-world heists, though initially far-fetched, finds support in our statistically significant findings. As we navigate the uncharted territory of online content's influence on societal behaviors, these results invite a blend of mirth and contemplation, evoking a resonance with the whimsical charm of "Phineas and Ferb." While our discussion remains rooted in the rigorous examination of statistical outcomes, the unexpectedly quirky nature of our findings imbues the academic arena with a hint of playful curiosity, challenging the conventional tenets of scholarly discourse.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Total views on Computerphile YouTube videos and Robberies in the US. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?

[[ABSTRACT]]
This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

[[INTRDUCTION]]
The proliferation of digital media has undoubtedly revolutionized the way individuals consume information, entertainment, and yes, even crime. As the world becomes increasingly interconnected through online platforms, the potential for unexpected consequences and quirky correlations emerges. In this study, we delve into the hitherto unexplored relationship between the total views of Computerphile YouTube videos and the occurrence of robberies in the United States.
While some may dismiss the notion of a connection between YouTube views and real-world crime as mere whimsy, our findings reveal a surprisingly robust association. We posit that the captivating allure of computer science educational content on Computerphile may have unforeseen effects on the behaviors of viewers, transcending the virtual sphere and seeping into the realm of criminal activity.
The rise of digital content consumption has brought forth a myriad of unforeseen societal repercussions. In this regard, the correlation between YouTube views and occurrences of robberies in the US challenges traditional paradigms and beckons for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.

[[RESULTS]]
The statistical analysis revealed a remarkably high correlation coefficient (r) of 0.9326717 between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. This robust correlation, with an r-squared value of 0.8698765, exceeded our initial expectations and hints at the existence of a potential relationship between online content consumption and criminal behavior. The p-value of less than 0.01 further solidifies the strength of this association, indicating a statistically significant link between the two variables.
The Figure 1 depicts a scatterplot illustrating the strong positive correlation between the total views of Computerphile YouTube videos and the number of robberies in the US. As the views of Computerphile videos increased, so did the occurrences of robberies, painting a compelling picture of the potential influence of online content on real-world criminal activities.
These findings present a quirky departure from conventional research inquiries into social phenomena, shedding light on the peculiar ways in which seemingly unrelated factors may intersect and exert influence. While the precise mechanisms underlying this correlation remain shrouded in mystery, the unexpected strength of the association prompts us to consider the quirky possibility of computer science education inadvertently inspiring real-world heists. This peculiar connection goes against the notion of "crime and punishment," suggesting that perhaps, in the age of digital convergence, it is "code and commission" that are shaping criminal behaviors.
The implications of our findings reach beyond the realm of statistical analysis, offering an opportunity to inject a dose of unexpected humor and quirkiness into the traditionally staid landscape of academic research. These results beckon for further exploration, inciting a blend of curiosity and amusement as we unravel the quirky mysteries that underpin the interplay between online content consumption and real-world behaviors.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, the unanticipated correlation between the total views of Computerphile YouTube videos and the incidence of robberies in the United States presents a quirky and intriguing avenue for further inquiry. The strikingly high correlation coefficient and statistically significant p-value underscore the need for continued exploration into the whimsical realm of online content's potential influence on real-world criminal activities. Our findings challenge traditional paradigms and beckon for further examination, offering a unique opportunity to inject a dash of unexpected humor into the otherwise solemn world of statistical inquiry.

The unexpected strength of the association prompts us to consider the quirky possibility of computer science education inadvertently inspiring real-world heists. This peculiar connection challenges conventional expectations and hints at the curious ways in which seemingly unrelated factors may intersect and exert influence. While the precise mechanisms underlying this correlation remain shrouded in mystery, the quirky possibility of "code and commission" shaping criminal behaviors certainly leads to a novel perspective on the age-old adage.

In light of these intriguing results, it is our assertion that no further research in this area is needed. After all, we have already established that watching Computerphile videos might just be the catalyst for a sudden interest in heisting. Case closed.


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 YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Digital Culture and Criminology


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 YouTube Views and Crime News: Do Computerphile Hits Affect US Heists?. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Advanced Technological Research and Exploration (SATRE)


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 YouTube Views and Crime News: Do Computerphile Hits Affect US Heists? with an abstract of This study investigates the potential link between the total views of Computerphile YouTube videos and the incidence of robberies in the United States from 2013 to 2022. Utilizing data from YouTube and the FBI Criminal Justice Information Services, a thorough analysis was conducted. The findings revealed a remarkably high correlation coefficient of 0.9326717 and a p-value < 0.01, indicating a strong association between the two variables during the specified time period. This unexpectedly robust correlation prompts further inquiry into the influence of online content consumption on real-world criminal behaviors, adding a quirky twist to the otherwise mundane realm of statistical analysis.

ChatGPT:

YouTube views, crime news, Computerphile, US heists, correlation analysis, online content consumption, criminal behaviors, FBI crime statistics, YouTube data, statistical analysis

*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

Total views on Computerphile YouTube videos
Detailed data title: Total views on Computerphile YouTube videos.
Source: YouTube
Additional Info: Current total views of videos released that year.

See what else correlates with Total views on Computerphile YouTube videos

Robberies in the US
Detailed data title: The robbery rate per 100,000 residents in United States
Source: FBI Criminal Justice Information Services
See what else correlates with Robberies in the US

Correlation r = 0.9326717 (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 = 0.8698765 (Coefficient of determination)
This means 87% of the change in the one variable (i.e., Robberies in the US) is predictable based on the change in the other (i.e., Total views on Computerphile YouTube videos) over the 10 years from 2013 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.3E-5. 0.0000828402514899321900000000
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 0.93 in 0.0083% of random cases. Said differently, if you correlated 12,071 random variables Which I absolutely did.
with the same 9 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 9 because we have two variables measured over a period of 10 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.73, 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.
2013201420152016201720182019202020212022
Total views on Computerphile YouTube videos (Total views)274562002931090024277300332531003106050014377800144568001011620093891406810510
Robberies in the US (Robbery rate)109101.3102.2102.998.686.181.873.965.566.1




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.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([27456200,29310900,24277300,33253100,31060500,14377800,14456800,10116200,9389140,6810510,])
array_2 = np.array([109,101.3,102.2,102.9,98.6,86.1,81.8,73.9,65.5,66.1,])
array_1_name = "Total views on Computerphile YouTube videos"
array_2_name = "Robberies in the US"

# 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?

You're the correlation whisperer we needed!


Correlation ID: 4501 · Black Variable ID: 25923 · Red Variable ID: 20182
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0