about · email me · subscribe
Spurious correlation #1,390 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is xkcd comics published about childhood and the second variable is The number of air traffic controllers in Minnesota.  The chart goes from 2007 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the xkcd childhood comics dwindled, fewer people were inspired to pursue careers in aviation, leading to a shortage of air traffic controllers in Minnesota. It seems the sky was no longer the limit for comic influence, and the situation really took off in a different direction.

Model: dalle-3
Prompt: Generate an image in a 3D Pixar Style of a serene park in Minnesota, where children are joyfully playing. The park is bordered by a bustling airport, with air traffic controllers skillfully guiding planes to land and take off in the background. The children look up in awe at the airplanes, reminiscing about their own childhood experiences. The scene conveys a heartwarming atmosphere of wonder and nostalgia. 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: xkcd comics published about childhood and The number of air traffic controllers in Minnesota. 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: Voxel art 3D Pixar Style Voxel art Woodblock painting Hyper-realistic
ChatGPT: 3D Pixar Style

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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota together. Keep the description simple.
ChatGPT: In an xkcd comic, a group of children are depicted playing in a park in Minnesota, surrounded by a bustling airport. The children are looking up at the air traffic controllers in awe as they skillfully guide planes to land and take off, while reminiscing about their own childhood experiences.

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: [ 3D Pixar Style ] and depicting this scene: In an xkcd comic, a group of children are depicted playing in a park in Minnesota, surrounded by a bustling airport. The children are looking up at the air traffic controllers in awe as they skillfully guide planes to land and take off, while reminiscing about their own childhood experiences. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image in a 3D Pixar Style of a serene park in Minnesota, where children are joyfully playing. The park is bordered by a bustling airport, with air traffic controllers skillfully guiding planes to land and take off in the background. The children look up in awe at the airplanes, reminiscing about their own childhood experiences. The scene conveys a heartwarming atmosphere of wonder and nostalgia.

*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 xkcd comics published about childhood caused The number of air traffic controllers in Minnesota to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota

The Journal of Comical Correlations

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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from AI analysis of xkcd comics and Bureau of Larbor Statistics to assess this nagging question. You found a correlation coefficient of 0.8975073 and p < 0.01 for 2007 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
The relationship between seemingly unrelated variables has always been a source of fascination for researchers, akin to discovering that peanut butter and chocolate actually make a fantastic combination. In this study, we delve into the unexpected and, some might say, whimsical connection between xkcd comics depicting childhood experiences and the number of air traffic controllers in the land of 10,000 lakes, also known as Minnesota. While traditional economic analyses might focus on more conventional factors influencing labor dynamics, such as productivity, wages, or technological advancements, this research presents a lighthearted exploration of the potential influence of webcomics on the labor market.

For those uninitiated with the peculiar charm of xkcd, it is a webcomic created by Randall Munroe, known for its wry humor, sarcasm, and stick figure characters. The comics cover a wide range of topics, from science and technology to the existential quandaries of everyday life. However, our focus lies specifically on the comics that touch upon the whimsy of childhood experiences, prompting us to ask, could the innocent charm of childhood portrayed in these comics have an impact on the high-stakes world of air traffic control?

While the initial idea may elicit a chuckle or two, our approach to this investigation is rooted in rigorous statistical analysis and a determination to entertain unlikely correlations. Through the adept use of AI analysis tools and the wealth of Bureau of Labor Statistics data, we have uncovered a correlation coefficient of 0.8975073, with a p-value of less than 0.01, for the time period spanning from 2007 to 2021. Yes, you read that correctly – these seemingly unrelated elements display a statistically significant relationship, much like finding out that wearing socks with sandals can surprisingly be in vogue in certain circles.

This intriguing discovery, while certainly unconventional, warrants consideration within the realm of labor economics. What we present here is not simply an intellectual exercise in whimsy, but a thought-provoking entry into the world of unexpected influences on the labor force. Though this peculiar correlation may seem as improbable as finding a four-leaf clover on an airport tarmac, the statistical evidence compels us to take it seriously, or at least as seriously as one can take a study involving stick figure comics and professional guardians of the skies.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between seemingly unrelated variables has always been a source of fascination for researchers, akin to discovering that peanut butter and chocolate actually make a fantastic combination. In this study, we delve into the unexpected and, some might say, whimsical connection between xkcd comics depicting childhood experiences and the number of air traffic controllers in the land of 10,000 lakes, also known as Minnesota. While traditional economic analyses might focus on more conventional factors influencing labor dynamics, such as productivity, wages, or technological advancements, this research presents a lighthearted exploration of the potential influence of webcomics on the labor market.
For those uninitiated with the peculiar charm of xkcd, it is a webcomic created by Randall Munroe, known for its wry humor, sarcasm, and stick figure characters. The comics cover a wide range of topics, from science and technology to the existential quandaries of everyday life. However, our focus lies specifically on the comics that touch upon the whimsy of childhood experiences, prompting us to ask, could the innocent charm of childhood portrayed in these comics have an impact on the high-stakes world of air traffic control?
While the initial idea may elicit a chuckle or two, our approach to this investigation is rooted in rigorous statistical analysis and a determination to entertain unlikely correlations. Through the adept use of AI analysis tools and the wealth of Bureau of Labor Statistics data, we have uncovered a correlation coefficient of 0.8975073, with a p-value of less than 0.01, for the time period spanning from 2007 to 2021. Yes, you read that correctly – these seemingly unrelated elements display a statistically significant relationship, much like finding out that wearing socks with sandals can surprisingly be in vogue in certain circles.
This intriguing discovery, while certainly unconventional, warrants consideration within the realm of labor economics. What we present here is not simply an intellectual exercise in whimsy, but a thought-provoking entry into the world of unexpected influences on the labor force. Though this peculiar correlation may seem as improbable as finding a four-leaf clover on an airport tarmac, the statistical evidence compels us to take it seriously, or at least as seriously as one can take a study involving stick figure comics and professional guardians of the skies.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Curiosity piqued, our investigation into the peculiar relationship between xkcd comics about childhood and the number of air traffic controllers in the state of Minnesota led us to review existing literature on unconventional influences on labor dynamics. Smith and Doe (2015) explored the impact of non-traditional factors, such as weather patterns and sports events, on air traffic controller productivity. Jones (2017) investigated the influence of office plant diversity on workplace satisfaction and its subsequent effect on job performance across various industries.

Moving from the serious to the less serious, "Freakonomics" by Steven Levitt and Stephen Dubner (2005) discusses unorthodox correlations in various societal phenomena, albeit not delving into the specific combination of childhood comics and air traffic control. Similarly, "Blink" by Malcolm Gladwell (2005) delves into the subtleties of decision-making processes, which may pertain to the seemingly whimsical connection under consideration. On a lighter note, "Charlie and the Chocolate Factory" by Roald Dahl (1964) provides a fictional lens through which to explore unexpected connections, though it doesn't directly address air traffic control or webcomics.

Comprehensively evaluating diverse sources, including scholarly articles, non-fiction works, and fictional narratives, we were determined to leave no stone unturned in our quest for relevant insights. Consequently, the authors decided to pivot to an unconventional information source—shampoo bottles. The informative content found on the back of these bottles, alerting users to the best method for achieving luscious locks, certainly provided an unexpected perspective on labor dynamics. However, it regrettably offered no discernible insight into the potential impact of childhood comics on the labor force, leaving us to rely on more traditional research avenues for meaningful analysis and conclusions.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of 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 AI analysis of xkcd comics and Bureau of Larbor Statistics . You used data from 2007 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

[[INTRODUCTION]]
The relationship between seemingly unrelated variables has always been a source of fascination for researchers, akin to discovering that peanut butter and chocolate actually make a fantastic combination. In this study, we delve into the unexpected and, some might say, whimsical connection between xkcd comics depicting childhood experiences and the number of air traffic controllers in the land of 10,000 lakes, also known as Minnesota. While traditional economic analyses might focus on more conventional factors influencing labor dynamics, such as productivity, wages, or technological advancements, this research presents a lighthearted exploration of the potential influence of webcomics on the labor market.
For those uninitiated with the peculiar charm of xkcd, it is a webcomic created by Randall Munroe, known for its wry humor, sarcasm, and stick figure characters. The comics cover a wide range of topics, from science and technology to the existential quandaries of everyday life. However, our focus lies specifically on the comics that touch upon the whimsy of childhood experiences, prompting us to ask, could the innocent charm of childhood portrayed in these comics have an impact on the high-stakes world of air traffic control?
While the initial idea may elicit a chuckle or two, our approach to this investigation is rooted in rigorous statistical analysis and a determination to entertain unlikely correlations. Through the adept use of AI analysis tools and the wealth of Bureau of Labor Statistics data, we have uncovered a correlation coefficient of 0.8975073, with a p-value of less than 0.01, for the time period spanning from 2007 to 2021. Yes, you read that correctly – these seemingly unrelated elements display a statistically significant relationship, much like finding out that wearing socks with sandals can surprisingly be in vogue in certain circles.
This intriguing discovery, while certainly unconventional, warrants consideration within the realm of labor economics. What we present here is not simply an intellectual exercise in whimsy, but a thought-provoking entry into the world of unexpected influences on the labor force. Though this peculiar correlation may seem as improbable as finding a four-leaf clover on an airport tarmac, the statistical evidence compels us to take it seriously, or at least as seriously as one can take a study involving stick figure comics and professional guardians of the skies.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

The methodology employed in this research endeavor involved a multifaceted approach to capture the elusive correlation between xkcd comics about childhood and the number of air traffic controllers in Minnesota. The first step in our quixotic quest was the identification and categorization of xkcd webcomics that specifically encapsulated the whimsical essence of childhood experiences. This involved an exhaustive review of the entire xkcd archive, showcasing a dedication to the task akin to meticulously peeling grapes at a gourmet picnic.

Utilizing advanced AI analysis tools, we then subjected the identified subset of xkcd comics to a comprehensive sentiment and thematic analysis. This process included machine learning algorithms and natural language processing techniques, designed to discern the nuanced portrayal of childhood experiences within the webcomics. The algorithms were trained on a diverse dataset of childhood themes, ranging from recess antics to tooth fairy conspiracies, in a valiant effort to encapsulate the playful spirit of youth within the digital confines of stick figure art.

Concurrently, data on the number of air traffic controllers in Minnesota from 2007 to 2021 was procured from the Bureau of Labor Statistics, providing a quantitative anchor for the labor force variable under scrutiny. This laboriously gathered dataset, akin to a treasure map leading to statistical gold, laid the foundation for the subsequent statistical analyses.

The statistical analyses, which were conducted with the solemnity befitting a whimsy-induced investigation, encompassed both descriptive and inferential procedures. A sophisticated correlation analysis between the frequency of childhood-centric xkcd comics and the number of air traffic controllers in Minnesota was undertaken, employing Pearson's correlation coefficient to quantify the strength and direction of the relationship. This was complemented by engaging in a regression analysis, allowing for the elucidation of potential causal pathways or, at the very least, meandering cobblestone pathways among the variables.

Furthermore, to fortify the credibility of the findings, a battery of robustness checks, sensitivity analyses, and diagnostic assessments of the statistical models were performed. This rigorous methodological approach, akin to donning a sturdy pair of intellectual suspenders, ensured the resilience and validity of the unorthodox correlation under scrutiny.

In summary, the methodology adopted in this investigation couples thoroughness and whimsy, blending the systematic rigor of statistical analysis with the imaginative exploration of webcomic influences. This multifaceted approach, much like a well-orchestrated symphony of statistical and thematic inquiry, underpins the validity and novelty of our findings.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of 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 AI analysis of xkcd comics and Bureau of Larbor Statistics .

For the time period 2007 to 2021, you found a correlation 0.8975073, r-squared of 0.8055194, 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between seemingly unrelated variables has always been a source of fascination for researchers, akin to discovering that peanut butter and chocolate actually make a fantastic combination. In this study, we delve into the unexpected and, some might say, whimsical connection between xkcd comics depicting childhood experiences and the number of air traffic controllers in the land of 10,000 lakes, also known as Minnesota. While traditional economic analyses might focus on more conventional factors influencing labor dynamics, such as productivity, wages, or technological advancements, this research presents a lighthearted exploration of the potential influence of webcomics on the labor market.
For those uninitiated with the peculiar charm of xkcd, it is a webcomic created by Randall Munroe, known for its wry humor, sarcasm, and stick figure characters. The comics cover a wide range of topics, from science and technology to the existential quandaries of everyday life. However, our focus lies specifically on the comics that touch upon the whimsy of childhood experiences, prompting us to ask, could the innocent charm of childhood portrayed in these comics have an impact on the high-stakes world of air traffic control?
While the initial idea may elicit a chuckle or two, our approach to this investigation is rooted in rigorous statistical analysis and a determination to entertain unlikely correlations. Through the adept use of AI analysis tools and the wealth of Bureau of Labor Statistics data, we have uncovered a correlation coefficient of 0.8975073, with a p-value of less than 0.01, for the time period spanning from 2007 to 2021. Yes, you read that correctly – these seemingly unrelated elements display a statistically significant relationship, much like finding out that wearing socks with sandals can surprisingly be in vogue in certain circles.
This intriguing discovery, while certainly unconventional, warrants consideration within the realm of labor economics. What we present here is not simply an intellectual exercise in whimsy, but a thought-provoking entry into the world of unexpected influences on the labor force. Though this peculiar correlation may seem as improbable as finding a four-leaf clover on an airport tarmac, the statistical evidence compels us to take it seriously, or at least as seriously as one can take a study involving stick figure comics and professional guardians of the skies.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a rather astonishing correlation coefficient of 0.8975073 between xkcd comics focused on childhood experiences and the number of air traffic controllers in Minnesota. This correlation suggests a remarkably strong relationship, akin to discovering that finding a penny on the ground is correlated with having good luck.

The r-squared value of 0.8055194 indicates that approximately 80.55% of the variation in the number of air traffic controllers in Minnesota can be explained by the whimsical representations of childhood in xkcd comics. This finding highlights the unexpected influence of seemingly unrelated factors on labor market dynamics, much like realizing that carrying an umbrella might lead to a sunny day.

The p-value of less than 0.01 further emphasizes the robustness of this correlation, reinforcing the notion that the relationship between xkcd childhood comics and air traffic controller numbers in Minnesota is not merely a fluke, but a statistically significant phenomenon. This discovery challenges conventional wisdom about labor market influences and presents a quirky dimension to labor force dynamics, not unlike discovering a secret compartment in an airplane.

The strong correlation is visually depicted in Figure 1, where a scatterplot illustrates the compelling association between xkcd childhood comics and air traffic controller numbers in Minnesota. The plot showcases the whimsical yet remarkably influential nature of this relationship, akin to finding a treasure map in a childhood comic and realizing it leads to actual treasure.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

[[LITERATURE REVIEW]]
Curiosity piqued, our investigation into the peculiar relationship between xkcd comics about childhood and the number of air traffic controllers in the state of Minnesota led us to review existing literature on unconventional influences on labor dynamics. Smith and Doe (2015) explored the impact of non-traditional factors, such as weather patterns and sports events, on air traffic controller productivity. Jones (2017) investigated the influence of office plant diversity on workplace satisfaction and its subsequent effect on job performance across various industries.
Moving from the serious to the less serious, "Freakonomics" by Steven Levitt and Stephen Dubner (2005) discusses unorthodox correlations in various societal phenomena, albeit not delving into the specific combination of childhood comics and air traffic control. Similarly, "Blink" by Malcolm Gladwell (2005) delves into the subtleties of decision-making processes, which may pertain to the seemingly whimsical connection under consideration. On a lighter note, "Charlie and the Chocolate Factory" by Roald Dahl (1964) provides a fictional lens through which to explore unexpected connections, though it doesn't directly address air traffic control or webcomics.
Comprehensively evaluating diverse sources, including scholarly articles, non-fiction works, and fictional narratives, we were determined to leave no stone unturned in our quest for relevant insights. Consequently, the authors decided to pivot to an unconventional information source—shampoo bottles. The informative content found on the back of these bottles, alerting users to the best method for achieving luscious locks, certainly provided an unexpected perspective on labor dynamics. However, it regrettably offered no discernible insight into the potential impact of childhood comics on the labor force, leaving us to rely on more traditional research avenues for meaningful analysis and conclusions.

[[RESULTS]]
The statistical analysis revealed a rather astonishing correlation coefficient of 0.8975073 between xkcd comics focused on childhood experiences and the number of air traffic controllers in Minnesota. This correlation suggests a remarkably strong relationship, akin to discovering that finding a penny on the ground is correlated with having good luck.
The r-squared value of 0.8055194 indicates that approximately 80.55% of the variation in the number of air traffic controllers in Minnesota can be explained by the whimsical representations of childhood in xkcd comics. This finding highlights the unexpected influence of seemingly unrelated factors on labor market dynamics, much like realizing that carrying an umbrella might lead to a sunny day.
The p-value of less than 0.01 further emphasizes the robustness of this correlation, reinforcing the notion that the relationship between xkcd childhood comics and air traffic controller numbers in Minnesota is not merely a fluke, but a statistically significant phenomenon. This discovery challenges conventional wisdom about labor market influences and presents a quirky dimension to labor force dynamics, not unlike discovering a secret compartment in an airplane.
The strong correlation is visually depicted in Figure 1, where a scatterplot illustrates the compelling association between xkcd childhood comics and air traffic controller numbers in Minnesota. The plot showcases the whimsical yet remarkably influential nature of this relationship, akin to finding a treasure map in a childhood comic and realizing it leads to actual treasure.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The striking correlation uncovered in this study aligns with prior research investigating unconventional influences on labor dynamics, such as the influence of weather patterns and office plant diversity on workplace satisfaction and job performance. Smith and Doe's (2015) exploration of non-traditional factors affecting air traffic controller productivity may find resonance in our findings, as our study suggests that whimsical childhood representations in xkcd comics have a substantial impact on the number of air traffic controllers in Minnesota. Similarly, Jones's (2017) investigation into the effect of office plant diversity on workplace satisfaction and subsequent job performance across various industries may offer a parallel to our unexpected correlation, albeit in a more lighthearted and unconventional manner.

Furthermore, the robust correlation coefficient and p-value validate the unconventional yet impactful connection between xkcd childhood comics and air traffic controller numbers in Minnesota. The strong statistical significance of this relationship challenges traditional assumptions about labor market dynamics and prompts a reevaluation of the potential influences that may shape the labor force in specific geographic regions, not unlike stumbling upon a hidden gem in an unexpected place.

This study sheds light on a whimsical yet compelling aspect of labor market dynamics and underscores the need for further exploration into the quirky underpinnings of labor force developments. While the specific mechanisms through which xkcd childhood comics influence air traffic controller numbers remain open to interpretation, the findings of this research introduce a novel lens through which to perceive the interplay of seemingly disparate elements, evoking the delight of unexpectedly finding a pot of gold at the end of a rainbow.

In conclusion, the correlation uncovered between xkcd childhood comics and air traffic controller numbers in Minnesota presents a peculiar yet thought-provoking avenue for future research. This unexpected connection invites further inquiry into the potential impact of whimsical representations on labor market dynamics and highlights the need for continued exploration of unconventional influences on the labor force, much like embarking on a whimsical adventure with an unpredictable yet fascinating destination.


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 xkcd comics published about childhood and The number of air traffic controllers in Minnesota. Make lots of 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]]
"The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota"

[[ABSTRACT]]
This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

[[INTRDUCTION]]
The relationship between seemingly unrelated variables has always been a source of fascination for researchers, akin to discovering that peanut butter and chocolate actually make a fantastic combination. In this study, we delve into the unexpected and, some might say, whimsical connection between xkcd comics depicting childhood experiences and the number of air traffic controllers in the land of 10,000 lakes, also known as Minnesota. While traditional economic analyses might focus on more conventional factors influencing labor dynamics, such as productivity, wages, or technological advancements, this research presents a lighthearted exploration of the potential influence of webcomics on the labor market.
For those uninitiated with the peculiar charm of xkcd, it is a webcomic created by Randall Munroe, known for its wry humor, sarcasm, and stick figure characters. The comics cover a wide range of topics, from science and technology to the existential quandaries of everyday life. However, our focus lies specifically on the comics that touch upon the whimsy of childhood experiences, prompting us to ask, could the innocent charm of childhood portrayed in these comics have an impact on the high-stakes world of air traffic control?
While the initial idea may elicit a chuckle or two, our approach to this investigation is rooted in rigorous statistical analysis and a determination to entertain unlikely correlations. Through the adept use of AI analysis tools and the wealth of Bureau of Labor Statistics data, we have uncovered a correlation coefficient of 0.8975073, with a p-value of less than 0.01, for the time period spanning from 2007 to 2021. Yes, you read that correctly – these seemingly unrelated elements display a statistically significant relationship, much like finding out that wearing socks with sandals can surprisingly be in vogue in certain circles.
This intriguing discovery, while certainly unconventional, warrants consideration within the realm of labor economics. What we present here is not simply an intellectual exercise in whimsy, but a thought-provoking entry into the world of unexpected influences on the labor force. Though this peculiar correlation may seem as improbable as finding a four-leaf clover on an airport tarmac, the statistical evidence compels us to take it seriously, or at least as seriously as one can take a study involving stick figure comics and professional guardians of the skies.

[[RESULTS]]
The statistical analysis revealed a rather astonishing correlation coefficient of 0.8975073 between xkcd comics focused on childhood experiences and the number of air traffic controllers in Minnesota. This correlation suggests a remarkably strong relationship, akin to discovering that finding a penny on the ground is correlated with having good luck.
The r-squared value of 0.8055194 indicates that approximately 80.55% of the variation in the number of air traffic controllers in Minnesota can be explained by the whimsical representations of childhood in xkcd comics. This finding highlights the unexpected influence of seemingly unrelated factors on labor market dynamics, much like realizing that carrying an umbrella might lead to a sunny day.
The p-value of less than 0.01 further emphasizes the robustness of this correlation, reinforcing the notion that the relationship between xkcd childhood comics and air traffic controller numbers in Minnesota is not merely a fluke, but a statistically significant phenomenon. This discovery challenges conventional wisdom about labor market influences and presents a quirky dimension to labor force dynamics, not unlike discovering a secret compartment in an airplane.
The strong correlation is visually depicted in Figure 1, where a scatterplot illustrates the compelling association between xkcd childhood comics and air traffic controller numbers in Minnesota. The plot showcases the whimsical yet remarkably influential nature of this relationship, akin to finding a treasure map in a childhood comic and realizing it leads to actual treasure.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation into the unexpected correlation between xkcd comics about childhood and the number of air traffic controllers in Minnesota has uncovered a statistically significant and, dare we say, whimsical connection. This study has provided a delightful foray into the world of unlikely correlations, akin to stumbling upon a hidden surprise at the bottom of a cereal box.

The robust correlation coefficient and p-value serve as a compelling reminder that the world of labor dynamics can be influenced by the most unexpected of sources, much like finding a pearl in a random oyster. While traditional economic analyses may raise an eyebrow at our findings, we stand by the statistical evidence and the undeniable charm of this peculiar relationship.

However, as tempting as it may be to dive deeper into the realm of whimsical influences on labor dynamics, we must assert that no further research is needed in this area. We have reached the pinnacle of whimsy, where statistical significance meets stick figure comics, and to delve any further into this domain may risk shattering the delicate equilibrium of statistical absurdity.

In the spirit of xkcd comics, we leave you with this parting thought: sometimes, the most astonishing correlations can be found in the unlikeliest of places. It is true what they say - truth is indeed stranger than fiction, and in our case, statistically stranger than stick figure comics.


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 The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Comical Correlations


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 The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Comic Strip Studies and Social Trends


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 The Xciting Correlation: A Statistical Analysis of xkcd Comics About Childhood and its Impact on Air Traffic Controller Numbers in Minnesota with an abstract of This study presents a peculiar yet compelling investigation into the potential influence of xkcd comics depicting childhood experiences on the number of air traffic controllers in the state of Minnesota. Through the utilization of AI analysis of xkcd comics and Bureau of Labor Statistics data, a correlation coefficient of 0.8975073 was established with a p-value of less than 0.01 for the time period spanning from 2007 to 2021. This unexpected correlation raises intriguing questions about the potential impact of whimsical childhood representations on the labor force in a specific geographical area. The findings of this research provide a whimsical perspective on the intersection of unconventional influences on labor dynamics and prompt further exploration into the quirky dynamics that may underpin labor market developments.

ChatGPT:

xkcd comics, childhood experiences, air traffic controllers, Minnesota, statistical analysis, Bureau of Labor Statistics, AI analysis, correlation coefficient, labor force, geographical area, whimsical, labor dynamics, labor market developments

*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

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

See what else correlates with xkcd comics published about childhood

The number of air traffic controllers in Minnesota
Detailed data title: BLS estimate of air traffic controllers in Minnesota
Source: Bureau of Larbor Statistics
See what else correlates with The number of air traffic controllers in Minnesota

Correlation r = 0.8975073 (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 = 0.8055194 (Coefficient of determination)
This means 80.6% of the change in the one variable (i.e., The number of air traffic controllers in Minnesota) is predictable based on the change in the other (i.e., xkcd comics published about childhood) over the 15 years from 2007 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.7E-6. 0.0000056822525527865290000000
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 0.9 in 0.00057% of random cases. Said differently, if you correlated 175,987 random variables You don't actually need 175 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 14 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 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.

[ 0.71, 0.97 ] 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.
200720082009201020112012201320142015201620172018201920202021
xkcd comics published about childhood (xkcd comics)10111310764141011242
The number of air traffic controllers in Minnesota (Air Traffic Controllers)680700690680650630610590590620600580580590550




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([10,11,13,10,7,6,4,1,4,10,1,1,2,4,2,])
array_2 = np.array([680,700,690,680,650,630,610,590,590,620,600,580,580,590,550,])
array_1_name = "xkcd comics published about childhood"
array_2_name = "The number of air traffic controllers in Minnesota"

# 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 a rater extraordinaire!


Correlation ID: 1390 · Black Variable ID: 20025 · Red Variable ID: 10115
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0