about · email me · subscribe
Spurious correlation #5,100 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Kerosene used in Namibia and the second variable is Total likes of Numberphile YouTube videos.  The chart goes from 2011 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As kerosene usage in Namibia increased, so did the total likes of Numberphile YouTube videos. The glow of creativity in the videos resonated with viewers, igniting a spark of interest and leaving them all fired up for more math content. It seems the connection between kerosene and Numberphile is quite illuminating, shedding light on a new source of mathematical inspiration. Who knew that the path to numerical enlightenment was fueled by kerosene? It's a prime example of how a seemingly unrelated factor can logarithmically boost YouTube engagement.

Model: dalle-3
Prompt: Generate an image that looks like it is a scene from a Disney movie. Depict a serene Namibian village at night, with soft glowing kerosene lamps casting warm, flickering light across sandy streets. In the center of the scene, a group of villagers huddles around a smartphone. Their faces are lit up with excitement as they eagerly hit the "like" button on a Numberphile video. The flickering kerosene lamps and the growing number of likes on the video seem to be harmoniously intertwined, both sparking a sense of curiosity and inspiration in the hearts of those who encounter them. 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: Kerosene used in Namibia and Total likes of Numberphile 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: Art nouveau a funny image you would see on reddit Cutsy graphics Pop art An image that looks like it is a scene from A Disney Movie
ChatGPT: An image that looks like it is a scene from A Disney Movie

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Kerosene used in Namibia and Total likes of Numberphile YouTube videos, in the following situation: As kerosene usage in Namibia increased, so did the total likes of Numberphile YouTube videos. The glow of creativity in the videos resonated with viewers, igniting a spark of interest and leaving them all fired up for more math content. It seems the connection between kerosene and Numberphile is quite illuminating, shedding light on a new source of mathematical inspiration. Who knew that the path to numerical enlightenment was fueled by kerosene? It's a prime example of how a seemingly unrelated factor can logarithmically boost YouTube engagement.. Keep the description simple.
ChatGPT: In a small Namibian village, the night comes alive as the soft glow of kerosene lamps illuminate the humble homes, casting warm, flickering light across the sandy streets. Amidst this serene scene, a group of villagers huddles around a smartphone, their faces lit up with excitement as they eagerly hit the "like" button on a Numberphile video. The flickering kerosene lamps and the growing number of likes on the video seem to be harmoniously intertwined, both sparking a sense of curiosity and inspiration in the hearts of those who encounter them.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from A Disney Movie ] and depicting this scene: In a small Namibian village, the night comes alive as the soft glow of kerosene lamps illuminate the humble homes, casting warm, flickering light across the sandy streets. Amidst this serene scene, a group of villagers huddles around a smartphone, their faces lit up with excitement as they eagerly hit the "like" button on a Numberphile video. The flickering kerosene lamps and the growing number of likes on the video seem to be harmoniously intertwined, both sparking a sense of curiosity and inspiration in the hearts of those who encounter them. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that looks like it is a scene from a Disney movie. Depict a serene Namibian village at night, with soft glowing kerosene lamps casting warm, flickering light across sandy streets. In the center of the scene, a group of villagers huddles around a smartphone. Their faces are lit up with excitement as they eagerly hit the "like" button on a Numberphile video. The flickering kerosene lamps and the growing number of likes on the video seem to be harmoniously intertwined, both sparking a sense of curiosity and inspiration in the hearts of those who encounter them.

*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 Kerosene used in Namibia positively influenced Total likes of Numberphile YouTube videos. Include one good pun.

AI academic paper

(Because p < 0.01)
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

Journal of Internet Culture and Trends

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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. 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 Energy Information Administration and YouTube to assess this nagging question. You found a correlation coefficient of 0.9347689 and p < 0.01 for 2011 to 2021.

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]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
The relationship between seemingly unrelated variables has long intrigued researchers across various disciplines. The pursuit of uncovering connections in the most unexpected places has led to astonishing discoveries and the expansion of our understanding of the world around us. In this study, we set out to explore the uncharted territory of statistical association between the consumption of kerosene in Namibia and the total likes accumulated by Numberphile YouTube videos.

While it may seem as though kerosene usage in a small African country and the popularity of educational math and science videos on a digital platform have little in common, our preliminary analysis indicated otherwise. The initial data inspection prompted us to delve deeper into this peculiar correlation, leading to the formulation of research questions that aimed to shed light on this unexpected relationship.

Our investigation was driven by a mutual curiosity for both the energy consumption patterns in Namibia and the dynamics of digital engagement, with a light-hearted acceptance of the possibility of stumbling upon an unusual statistical phenomenon. As researchers, we are acutely aware of the inherent unpredictability of human behavior and the complex interplay of variables in any given system. It is this very unpredictability that often fuels our intrigue and propels us into uncharted intellectual territory.

The unearthing of an unlikely connection between kerosene usage and YouTube likes has sent ripples of bemusement through the research community, as this unexpected revelation challenges conventional assumptions about the nature of statistical associations. This study endeavors to unravel the intricacies of this correlation while maintaining a healthy skepticism towards drawing premature conclusions.

In the subsequent sections, we will discuss the methodology employed to rigorously analyze the data, the results derived from our statistical modeling, and the implications of this unforeseen linkage. The aim is to stimulate scientific curiosity, bridge seemingly disparate domains, and offer a whimsical yet insightful perspective on the intricate tapestry of statistical relationships.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. 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 name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between seemingly unrelated variables has long intrigued researchers across various disciplines. The pursuit of uncovering connections in the most unexpected places has led to astonishing discoveries and the expansion of our understanding of the world around us. In this study, we set out to explore the uncharted territory of statistical association between the consumption of kerosene in Namibia and the total likes accumulated by Numberphile YouTube videos.
While it may seem as though kerosene usage in a small African country and the popularity of educational math and science videos on a digital platform have little in common, our preliminary analysis indicated otherwise. The initial data inspection prompted us to delve deeper into this peculiar correlation, leading to the formulation of research questions that aimed to shed light on this unexpected relationship.
Our investigation was driven by a mutual curiosity for both the energy consumption patterns in Namibia and the dynamics of digital engagement, with a light-hearted acceptance of the possibility of stumbling upon an unusual statistical phenomenon. As researchers, we are acutely aware of the inherent unpredictability of human behavior and the complex interplay of variables in any given system. It is this very unpredictability that often fuels our intrigue and propels us into uncharted intellectual territory.
The unearthing of an unlikely connection between kerosene usage and YouTube likes has sent ripples of bemusement through the research community, as this unexpected revelation challenges conventional assumptions about the nature of statistical associations. This study endeavors to unravel the intricacies of this correlation while maintaining a healthy skepticism towards drawing premature conclusions.
In the subsequent sections, we will discuss the methodology employed to rigorously analyze the data, the results derived from our statistical modeling, and the implications of this unforeseen linkage. The aim is to stimulate scientific curiosity, bridge seemingly disparate domains, and offer a whimsical yet insightful perspective on the intricate tapestry of statistical relationships.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Several studies have been conducted to investigate the consumption of kerosene and its implications on various socio-economic and environmental factors. Smith et al. (2015) delved into the household usage of kerosene in developing countries, highlighting its pervasive influence on daily life. Similarly, Doe and Jones (2018) examined the affordability and accessibility of alternative sources of energy in regions reliant on kerosene, shedding light on the intricate web of factors shaping energy consumption patterns.

As we venture into the realm of digital engagement, the literature extensively covers the impact of online content on user interaction and preferences. In "Digital Dynamics" by Brown (2017), the author presents a comprehensive analysis of the factors driving user engagement with digital media. Moreover, the work of White (2019) offers profound insights into the psychology of online interactions, unveiling the underlying mechanisms governing user behavior in the virtual sphere.

Transitioning to a more idiosyncratic domain, fictional narratives have often teased the imagination with improbable connections and unexpected parallels. In "The Alchemist" by Paulo Coelho, the protagonist embarks on a quest for hidden truths, mirroring our own endeavor to unearth unanticipated correlations. Furthermore, the interplay of seemingly disparate elements is masterfully depicted in "Cloud Atlas" by David Mitchell, serving as a parallel to our pursuit of unveiling the cryptic relationship between kerosene usage and YouTube likes.

In the digital realm, where memes reign supreme, we cannot overlook the cultural impact of internet phenomena. The "Distracted Boyfriend" meme, depicting an individual torn between loyalty and allure, echoes the conflict between conventional energy sources and the draw of captivating digital content. Moreover, the "This is Fine" dog meme humorously captures the essence of our research endeavor as we navigate through the surprising correlation with an air of nonchalant acceptance.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Energy Information Administration and YouTube . You used data from 2011 to 2021

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]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

[[INTRODUCTION]]
The relationship between seemingly unrelated variables has long intrigued researchers across various disciplines. The pursuit of uncovering connections in the most unexpected places has led to astonishing discoveries and the expansion of our understanding of the world around us. In this study, we set out to explore the uncharted territory of statistical association between the consumption of kerosene in Namibia and the total likes accumulated by Numberphile YouTube videos.
While it may seem as though kerosene usage in a small African country and the popularity of educational math and science videos on a digital platform have little in common, our preliminary analysis indicated otherwise. The initial data inspection prompted us to delve deeper into this peculiar correlation, leading to the formulation of research questions that aimed to shed light on this unexpected relationship.
Our investigation was driven by a mutual curiosity for both the energy consumption patterns in Namibia and the dynamics of digital engagement, with a light-hearted acceptance of the possibility of stumbling upon an unusual statistical phenomenon. As researchers, we are acutely aware of the inherent unpredictability of human behavior and the complex interplay of variables in any given system. It is this very unpredictability that often fuels our intrigue and propels us into uncharted intellectual territory.
The unearthing of an unlikely connection between kerosene usage and YouTube likes has sent ripples of bemusement through the research community, as this unexpected revelation challenges conventional assumptions about the nature of statistical associations. This study endeavors to unravel the intricacies of this correlation while maintaining a healthy skepticism towards drawing premature conclusions.
In the subsequent sections, we will discuss the methodology employed to rigorously analyze the data, the results derived from our statistical modeling, and the implications of this unforeseen linkage. The aim is to stimulate scientific curiosity, bridge seemingly disparate domains, and offer a whimsical yet insightful perspective on the intricate tapestry of statistical relationships.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The initial step in this whimsical journey of statistical exploration involved the arduous task of gathering data from the Energy Information Administration and YouTube. We scoured the depths of the internet, employing a combination of advanced search algorithms and some good old-fashioned dedication to amass a comprehensive dataset spanning the years 2011 to 2021. The acquisition process was not without its perils, as navigating the labyrinthine corridors of online information required a touch of derring-do and a keen eye for relevant data points.

Data Preprocessing:
Once the treasure trove of data was secured, the subsequent stage demanded an intricate dance of data preprocessing. We meticulously cleaned and wrangled the datasets, ensuring that each observation was polished to statistical perfection. Outlying data points were gently coaxed into conformity, and missing values were delicately imputed with the utmost precision. The data transformation process was conducted with the finesse of a maestro orchestrating a symphony, harmonizing the disparate elements into a coherent and analyzable ensemble.

Statistical Analysis:
With our refined datasets in hand, we embarked on the exhilarating expedition of statistical analysis. Employing a menagerie of statistical techniques, including correlation analysis, regression modeling, and hypothesis testing, we unfurled the mathematical canvas upon which the enigmatic relationship between kerosene consumption in Namibia and the allure of Numberphile's educational expositions would be painted. Every statistical model and test was executed with the exacting precision of an artisan crafting a masterpiece, mindful of the intricate interplay between our variables and the subtleties of statistical inference.

Model Validation:
In the pursuit of scientific rigor, our investigations were subjected to the rigors of model validation. The veracity of our findings was put to the test, as the statistical models underwent the crucible of validation metrics and diagnostic checks. We scrutinized the models with a discerning gaze, ensuring that the conclusions drawn from our analyses possessed the robustness and reliability befitting a scholarly endeavor.

Ethical Considerations:
Amidst the fervor of our empirical odyssey, ethical considerations were held in the highest regard. The principles of data privacy, integrity, and respect for diverse perspectives were woven into the fabric of our research practices. Our endeavor upheld the noble standards of ethical conduct, affirming our commitment to the responsible pursuit of knowledge and the conscientious dissemination of our findings.

Innovation in Analysis:
Recognizing the unconventional nature of our research endeavor, we embraced a spirit of innovation in our analytical approach. Drawing inspiration from the unorthodox juxtaposition of kerosene and YouTube likes, we ventured into uncharted methodological territory, experimenting with novel techniques and emerging paradigms in statistical analysis. The pursuit of scientific novelty infused our methodology with a dash of daring and a sprinkle of audacity, echoing the whimsical nature of our research inquiry.

The meticulous orchestration of data collection, preprocessing, statistical analysis, and ethical considerations underpinned our methodology, paving the way for the revelation of an unexpected statistical liaison between the consumption of kerosene in Namibia and the digital adoration garnered by Numberphile's intellectual vignettes. The subsequent section will unveil the captivating tapestry of results woven from our methodological craftsmanship.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Energy Information Administration and YouTube .

For the time period 2011 to 2021, you found a correlation 0.9347689, r-squared of 0.8737928, 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]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between seemingly unrelated variables has long intrigued researchers across various disciplines. The pursuit of uncovering connections in the most unexpected places has led to astonishing discoveries and the expansion of our understanding of the world around us. In this study, we set out to explore the uncharted territory of statistical association between the consumption of kerosene in Namibia and the total likes accumulated by Numberphile YouTube videos.
While it may seem as though kerosene usage in a small African country and the popularity of educational math and science videos on a digital platform have little in common, our preliminary analysis indicated otherwise. The initial data inspection prompted us to delve deeper into this peculiar correlation, leading to the formulation of research questions that aimed to shed light on this unexpected relationship.
Our investigation was driven by a mutual curiosity for both the energy consumption patterns in Namibia and the dynamics of digital engagement, with a light-hearted acceptance of the possibility of stumbling upon an unusual statistical phenomenon. As researchers, we are acutely aware of the inherent unpredictability of human behavior and the complex interplay of variables in any given system. It is this very unpredictability that often fuels our intrigue and propels us into uncharted intellectual territory.
The unearthing of an unlikely connection between kerosene usage and YouTube likes has sent ripples of bemusement through the research community, as this unexpected revelation challenges conventional assumptions about the nature of statistical associations. This study endeavors to unravel the intricacies of this correlation while maintaining a healthy skepticism towards drawing premature conclusions.
In the subsequent sections, we will discuss the methodology employed to rigorously analyze the data, the results derived from our statistical modeling, and the implications of this unforeseen linkage. The aim is to stimulate scientific curiosity, bridge seemingly disparate domains, and offer a whimsical yet insightful perspective on the intricate tapestry of statistical relationships.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our statistical analysis revealed a remarkably robust correlation between kerosene consumption in Namibia and the total likes garnered by Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9347689, indicating a strong positive relationship between these seemingly unrelated variables. The coefficient of determination (r-squared) further solidified this finding, standing at a respectable 0.8737928, suggesting that approximately 87.4% of the variation in YouTube likes can be explained by the variation in kerosene usage.

Our analysis also yielded a p-value of less than 0.01, signifying a statistically significant relationship between kerosene consumption and YouTube likes. This provides compelling evidence that the observed association is not merely a fortuitous alignment of numerical values, but rather a meaningful and potentially meaningful linkage between the energy habits of a nation and the digital appreciation for Numberphile's mathematical musings.

Furthermore, the scatterplot depicted in Figure 1 (not included here for suspense and dramatic effect) visually illustrates the tight clustering of data points around a positively sloped regression line, affirming the strength of the correlation and the unlikelihood of this connection being a mere statistical fluke.

These findings invite us to ponder the whimsical ways in which seemingly unrelated elements of our world can interlace and influence one another. While the precise mechanisms behind this correlation remain elusive, the implications are tantalizing and open the door to quirky conjectures about the interplay between household energy choices and online engagement. Indeed, the fusion of kerosene scenes and YouTube dreams beckons a rethinking of the ways in which disparate domains of human activity may harmonize, providing fodder for both statistical amusement and contemplation.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

[[LITERATURE REVIEW]]
Several studies have been conducted to investigate the consumption of kerosene and its implications on various socio-economic and environmental factors. Smith et al. (2015) delved into the household usage of kerosene in developing countries, highlighting its pervasive influence on daily life. Similarly, Doe and Jones (2018) examined the affordability and accessibility of alternative sources of energy in regions reliant on kerosene, shedding light on the intricate web of factors shaping energy consumption patterns.
As we venture into the realm of digital engagement, the literature extensively covers the impact of online content on user interaction and preferences. In "Digital Dynamics" by Brown (2017), the author presents a comprehensive analysis of the factors driving user engagement with digital media. Moreover, the work of White (2019) offers profound insights into the psychology of online interactions, unveiling the underlying mechanisms governing user behavior in the virtual sphere.
Transitioning to a more idiosyncratic domain, fictional narratives have often teased the imagination with improbable connections and unexpected parallels. In "The Alchemist" by Paulo Coelho, the protagonist embarks on a quest for hidden truths, mirroring our own endeavor to unearth unanticipated correlations. Furthermore, the interplay of seemingly disparate elements is masterfully depicted in "Cloud Atlas" by David Mitchell, serving as a parallel to our pursuit of unveiling the cryptic relationship between kerosene usage and YouTube likes.
In the digital realm, where memes reign supreme, we cannot overlook the cultural impact of internet phenomena. The "Distracted Boyfriend" meme, depicting an individual torn between loyalty and allure, echoes the conflict between conventional energy sources and the draw of captivating digital content. Moreover, the "This is Fine" dog meme humorously captures the essence of our research endeavor as we navigate through the surprising correlation with an air of nonchalant acceptance.

[[RESULTS]]
The results of our statistical analysis revealed a remarkably robust correlation between kerosene consumption in Namibia and the total likes garnered by Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9347689, indicating a strong positive relationship between these seemingly unrelated variables. The coefficient of determination (r-squared) further solidified this finding, standing at a respectable 0.8737928, suggesting that approximately 87.4% of the variation in YouTube likes can be explained by the variation in kerosene usage.
Our analysis also yielded a p-value of less than 0.01, signifying a statistically significant relationship between kerosene consumption and YouTube likes. This provides compelling evidence that the observed association is not merely a fortuitous alignment of numerical values, but rather a meaningful and potentially meaningful linkage between the energy habits of a nation and the digital appreciation for Numberphile's mathematical musings.
Furthermore, the scatterplot depicted in Figure 1 (not included here for suspense and dramatic effect) visually illustrates the tight clustering of data points around a positively sloped regression line, affirming the strength of the correlation and the unlikelihood of this connection being a mere statistical fluke.
These findings invite us to ponder the whimsical ways in which seemingly unrelated elements of our world can interlace and influence one another. While the precise mechanisms behind this correlation remain elusive, the implications are tantalizing and open the door to quirky conjectures about the interplay between household energy choices and online engagement. Indeed, the fusion of kerosene scenes and YouTube dreams beckons a rethinking of the ways in which disparate domains of human activity may harmonize, providing fodder for both statistical amusement and contemplation.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of this study not only corroborate prior literature positing the influence of kerosene on socio-economic and environmental factors but also shed light on the unexpected interconnectedness of digital engagement. While the relationship between kerosene consumption in Namibia and the total likes garnered by Numberphile YouTube videos may initially seem whimsical, the robust correlation coefficient and statistically significant p-value fortify the legitimacy of this unlikely bond.

The idiosyncratic nature of our findings can be paralleled with the quest for hidden truths in "The Alchemist" and the interplay of seemingly disparate elements in "Cloud Atlas." Just as the Alchemist pursues enigmatic connections that transcend conventional wisdom, our statistical analysis unraveled an intricate link between two seemingly unrelated realms. Additionally, the juxtaposition of memes, such as the "Distracted Boyfriend" and "This is Fine" dog, aptly captures the blend of amusement and curiosity evoked by our unanticipated discovery.

The statistically significant relationship between kerosene usage and YouTube likes suggests a profound intertwining of offline energy consumption habits and online digital interactions. This unanticipated correlation invites contemplation on the peculiar ways in which human activities across different domains may influentially intertwine, providing fodder for both statistical amusement and thoughtful rumination.

Ultimately, the fusion of kerosene scenes and YouTube dreams prompts a reconsideration of the intricate ways in which seemingly unrelated facets of human existence may harmonize. While the exact mechanisms underlying this connection may remain elusive, the statistical evidence is undeniable, opening the door to further whimsical conjectures and profound insights into the intricacies of human behavior in both the physical and virtual realms.


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 Kerosene used in Namibia and Total likes of Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation

[[ABSTRACT]]
This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

[[INTRDUCTION]]
The relationship between seemingly unrelated variables has long intrigued researchers across various disciplines. The pursuit of uncovering connections in the most unexpected places has led to astonishing discoveries and the expansion of our understanding of the world around us. In this study, we set out to explore the uncharted territory of statistical association between the consumption of kerosene in Namibia and the total likes accumulated by Numberphile YouTube videos.
While it may seem as though kerosene usage in a small African country and the popularity of educational math and science videos on a digital platform have little in common, our preliminary analysis indicated otherwise. The initial data inspection prompted us to delve deeper into this peculiar correlation, leading to the formulation of research questions that aimed to shed light on this unexpected relationship.
Our investigation was driven by a mutual curiosity for both the energy consumption patterns in Namibia and the dynamics of digital engagement, with a light-hearted acceptance of the possibility of stumbling upon an unusual statistical phenomenon. As researchers, we are acutely aware of the inherent unpredictability of human behavior and the complex interplay of variables in any given system. It is this very unpredictability that often fuels our intrigue and propels us into uncharted intellectual territory.
The unearthing of an unlikely connection between kerosene usage and YouTube likes has sent ripples of bemusement through the research community, as this unexpected revelation challenges conventional assumptions about the nature of statistical associations. This study endeavors to unravel the intricacies of this correlation while maintaining a healthy skepticism towards drawing premature conclusions.
In the subsequent sections, we will discuss the methodology employed to rigorously analyze the data, the results derived from our statistical modeling, and the implications of this unforeseen linkage. The aim is to stimulate scientific curiosity, bridge seemingly disparate domains, and offer a whimsical yet insightful perspective on the intricate tapestry of statistical relationships.

[[RESULTS]]
The results of our statistical analysis revealed a remarkably robust correlation between kerosene consumption in Namibia and the total likes garnered by Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9347689, indicating a strong positive relationship between these seemingly unrelated variables. The coefficient of determination (r-squared) further solidified this finding, standing at a respectable 0.8737928, suggesting that approximately 87.4% of the variation in YouTube likes can be explained by the variation in kerosene usage.
Our analysis also yielded a p-value of less than 0.01, signifying a statistically significant relationship between kerosene consumption and YouTube likes. This provides compelling evidence that the observed association is not merely a fortuitous alignment of numerical values, but rather a meaningful and potentially meaningful linkage between the energy habits of a nation and the digital appreciation for Numberphile's mathematical musings.
Furthermore, the scatterplot depicted in Figure 1 (not included here for suspense and dramatic effect) visually illustrates the tight clustering of data points around a positively sloped regression line, affirming the strength of the correlation and the unlikelihood of this connection being a mere statistical fluke.
These findings invite us to ponder the whimsical ways in which seemingly unrelated elements of our world can interlace and influence one another. While the precise mechanisms behind this correlation remain elusive, the implications are tantalizing and open the door to quirky conjectures about the interplay between household energy choices and online engagement. Indeed, the fusion of kerosene scenes and YouTube dreams beckons a rethinking of the ways in which disparate domains of human activity may harmonize, providing fodder for both statistical amusement and contemplation.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the correlation between kerosene consumption in Namibia and the total likes garnered by Numberphile YouTube videos has revealed a remarkably robust and statistically significant relationship. The tight clustering of data points around the regression line, akin to supportive fans gathering around a popular YouTuber, underscores the strength of this unexpected connection. This serendipitous uncovering prompts us to reflect on the whimsical ways in which numerical values can intertwine and lead to intriguing statistical revelations. As researchers, we are acutely aware of the unpredictable nature of human behavior and the intricate dance of variables in any given system, but this discovery certainly takes the cake in terms of unlikely pairings.

The implications of this unanticipated linkage extend beyond the realms of statistical analysis, delving into the curious interplay of energy consumption patterns in a nation and digital engagement with educational content. It invites contemplation on the quirky ways in which seemingly disparate domains of human activity may intertwine, providing fodder for both statistical amusement and intellectual curiosity.

While this study has shed light on an unexpected statistical phenomenon, further investigations could explore the underlying mechanisms driving this correlation. Nevertheless, at present, it is evident that the fusion of kerosene scenes and YouTube dreams has captured our intrigue and tickled our statistical fancies. In light of these findings, it is our firm belief that no further research is needed in this peculiar domain, as the blend of kerosene and YouTube already serves as a delightful reminder of the delightful whimsy enmeshed in statistical exploration.


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 Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Internet Culture and Trends


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 Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Internet Imagination 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 Kerosene Scenes and YouTube Dreams: A Statistical Analysis of Their Correlation with an abstract of This study delves into the fascinating relationship between the consumption of kerosene in Namibia and the total likes garnered by Numberphile YouTube videos. Leveraging data from the Energy Information Administration and YouTube, our research team conducted a rigorous statistical analysis to investigate this seemingly unrelated pair. The findings unveiled a striking correlation coefficient of 0.9347689 and a significant p-value of less than 0.01 for the period spanning from 2011 to 2021. The implications of this unexpected association are explored, paving the way for further inquiries into the enigmatic world of energy consumption and digital engagement.

ChatGPT:

kerosene consumption, Namibia, YouTube videos, correlation analysis, statistical analysis, Energy Information Administration, YouTube likes, correlation coefficient, p-value, energy consumption, digital engagement, Numberphile videos, Namibia energy consumption

*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

Kerosene used in Namibia
Detailed data title: Volume of kerosene used consumed in Namibia in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Namibia

Total likes of Numberphile YouTube videos
Detailed data title: Total likes of Numberphile YouTube videos.
Source: Numberphile YouTube
See what else correlates with Total likes of Numberphile YouTube videos

Correlation r = 0.9347689 (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 = 0.8737928 (Coefficient of determination)
This means 87.4% of the change in the one variable (i.e., Total likes of Numberphile YouTube videos) is predictable based on the change in the other (i.e., Kerosene used in Namibia) over the 11 years from 2011 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.5E-5. 0.0000246261941531312330000000
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 0.0025% of random cases. Said differently, if you correlated 40,607 random variables You don't actually need 40 thousand variables to find a correlation like this one. 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.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.76, 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.
20112012201320142015201620172018201920202021
Kerosene used in Namibia (Million Barrels/Day)0.04235620.06336070.04235620.04235620.0423560.042240.04235620.04235620.04345210.04153550.043827
Total likes of Numberphile YouTube videos (Total likes)159754552434016286301366330155447016099801220150868813884640679589671821




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([0.0423562,0.0633607,0.0423562,0.0423562,0.042356,0.04224,0.0423562,0.0423562,0.0434521,0.0415355,0.043827,])
array_2 = np.array([159754,5524340,1628630,1366330,1554470,1609980,1220150,868813,884640,679589,671821,])
array_1_name = "Kerosene used in Namibia"
array_2_name = "Total likes of Numberphile 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?

You're the rating guru we've been waiting for!


Correlation ID: 5100 · Black Variable ID: 24725 · Red Variable ID: 25487
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0