about · email me · subscribe
Spurious correlation #3,690 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Pittsburgh and the second variable is US birth rates of triplets or more.  The chart goes from 2002 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Because the decrease in air pollution in Pittsburgh led to a decrease in the number of children playing the "Hold Your Breath the Longest" game, resulting in less suffocation-induced temporary triplet formation.

Model: dalle-3
Prompt: Create an image showing a vibrant and dynamic TIME magazine cover image with a depiction of a clear, blue sky over Pittsburgh. In the foreground, children are seen laughing and playing outdoors without any respiratory concerns. In the background, multiple families with triplets or more are joyfully walking together, immersed in the improved air quality. The scene should convey a sense of relief and joy as the community enjoys the pollution-free environment. 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: Air pollution in Pittsburgh and US birth rates of triplets or more. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Cyber folk A TIME magazine cover image Realistic a funny image macro a Polaroid photo
ChatGPT: A TIME magazine cover image

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 Air pollution in Pittsburgh and US birth rates of triplets or more, in the following situation: Because the decrease in air pollution in Pittsburgh led to a decrease in the number of children playing the "Hold Your Breath the Longest" game, resulting in less suffocation-induced temporary triplet formation.. Keep the description simple.
ChatGPT: In a clean and clear sky over Pittsburgh, children happily play outdoors without holding their breath. In the background, a few families with triplets or more are seen walking together, enjoying the improved air quality.

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: [ A TIME magazine cover image ] and depicting this scene: In a clean and clear sky over Pittsburgh, children happily play outdoors without holding their breath. In the background, a few families with triplets or more are seen walking together, enjoying the improved air quality. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image showing a vibrant and dynamic TIME magazine cover image with a depiction of a clear, blue sky over Pittsburgh. In the foreground, children are seen laughing and playing outdoors without any respiratory concerns. In the background, multiple families with triplets or more are joyfully walking together, immersed in the improved air quality. The scene should convey a sense of relief and joy as the community enjoys the pollution-free environment.

*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
System prompt: You provide humerus 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. Your responses should be able to be used as the title for a funny post, or the top comment on a thread explaining the connection.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in Pittsburgh caused US birth rates of triplets or more to decrease. Make the causal connection creative and unexpected. Keep it to ~50 tokens. Do not start with 'well' or 'you see' or similar statements. Do not restate the variables; lead with the answer (what comes after 'because...')

AI academic paper

(Because p < 0.01)
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

The Journal of Quirky Atmospheric Studies

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 Air pollution in Pittsburgh and US birth rates of triplets or more. 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 Environmental Protection Agency and CDC to assess this nagging question. You found a correlation coefficient of 0.8250760 and p < 0.01 for 2002 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.


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 Air pollution in Pittsburgh and US birth rates of triplets or more. Make lots of 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

The atmosphere, like a nosy neighbor, has been eavesdropping on Pittsburgh's air quality, and the findings will take your breath away! While the Steel City is renowned for its industrial prowess, its notoriety for air pollution has sparked curiosity about its potential impact on human fertility. Our study delved into this intriguing intersection of air quality and reproductive outcomes, specifically focusing on the incidence of triplet or higher-order births in the United States.

As we embarked on this research journey, the initial reaction from our colleagues was one of bemusement. After all, pondering the potential link between Pittsburgh's smoky skies and the birth of three (or more!) infants simultaneously seemed like traversing uncharted territory. However, armed with a passion for unraveling scientific mysteries and a penchant for wordplay, we set out to explore this unusual yet captivating relationship.

Armed with data from the Environmental Protection Agency and the Centers for Disease Control and Prevention, we sought to unmask the hidden connection between air pollution levels in Pittsburgh and the birth rates of triplets or more across the United States. Our statistical analysis unfurled an eyebrow-raising correlation coefficient of 0.8250760, complete with a p-value less than 0.01! A statistically significant finding, indeed - and one that prompted us to take a deep breath and dissect the implications with scholarly rigor.

Through this investigation, we aim not only to shed light on the atmospheric impact on triplet totals but also to inject a breath of fresh air into the discourse surrounding air quality and its unforeseen repercussions on human fertility. So, dear reader, fasten your seatbelts, as we embark on a scholarly journey that will challenge your preconceptions and, dare we say, leave you breathless with fascination!


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 Air pollution in Pittsburgh and US birth rates of triplets or more. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The atmosphere, like a nosy neighbor, has been eavesdropping on Pittsburgh's air quality, and the findings will take your breath away! While the Steel City is renowned for its industrial prowess, its notoriety for air pollution has sparked curiosity about its potential impact on human fertility. Our study delved into this intriguing intersection of air quality and reproductive outcomes, specifically focusing on the incidence of triplet or higher-order births in the United States.
As we embarked on this research journey, the initial reaction from our colleagues was one of bemusement. After all, pondering the potential link between Pittsburgh's smoky skies and the birth of three (or more!) infants simultaneously seemed like traversing uncharted territory. However, armed with a passion for unraveling scientific mysteries and a penchant for wordplay, we set out to explore this unusual yet captivating relationship.
Armed with data from the Environmental Protection Agency and the Centers for Disease Control and Prevention, we sought to unmask the hidden connection between air pollution levels in Pittsburgh and the birth rates of triplets or more across the United States. Our statistical analysis unfurled an eyebrow-raising correlation coefficient of 0.8250760, complete with a p-value less than 0.01! A statistically significant finding, indeed - and one that prompted us to take a deep breath and dissect the implications with scholarly rigor.
Through this investigation, we aim not only to shed light on the atmospheric impact on triplet totals but also to inject a breath of fresh air into the discourse surrounding air quality and its unforeseen repercussions on human fertility. So, dear reader, fasten your seatbelts, as we embark on a scholarly journey that will challenge your preconceptions and, dare we say, leave you breathless with fascination!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Numerous studies have documented the adverse effects of air pollution on human health, with a special focus on respiratory ailments and cardiovascular complications (Smith, 2015; Doe, 2018; Jones, 2020). However, the research has largely circumvented the enchanting realm of reproductive outcomes, particularly the incidence of higher-order multiple births. Surprisingly, this lacuna in the literature has left a considerable gap in our understanding of the potential atmospheric influence on fertility.

In "Airborne Antics: The Witty World of Particulate Matter," the authors emphasize the pervasive presence of airborne pollutants and their insidious infiltration of human habitats, setting the stage for a tale that is anything but airy. Similarly, "Fumes and Fetuses: Exploring the Uncharted Terrain of Air Quality and Fertility" offers compelling insights into the potential ramifications of polluted air on fertility, beckoning researchers to delve deeper into this unexplored domain.

As we traverse beyond the boundaries of traditional scholarly research, let us not overlook the fictional works that, while not grounded in empirical evidence, hold a whimsical mirror to our research endeavors. Lending an imaginative touch to our academic pursuit, "Cloudy with a Chance of Multiples" and "The Smoggy Stork: When Pollution Takes Flight" present fanciful accounts of environmental influences on birth outcomes. These literary creations, while far removed from the rigor of empirical inquiry, serve as a reminder of the captivating allure of our research topic.

Adding a cinematic twist to our journey, the films "The Air We Breathe" and "Triple Threat: A Tale of Three Times the Trouble" offer cinematic narratives that, albeit tangentially related, touch upon the intertwining dynamics of air quality and human fertility. While these filmic portrayals may lack the precision of scholarly investigation, they infuse an element of whimsy into our scholarly pursuits, reminding us of the multifaceted ways in which our research topic can captivate the imagination.


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 Air pollution in Pittsburgh and US birth rates of triplets or more. Make lots of 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 Environmental Protection Agency and CDC . You used data from 2002 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

[[INTRODUCTION]]
INTRODUCTION
The atmosphere, like a nosy neighbor, has been eavesdropping on Pittsburgh's air quality, and the findings will take your breath away! While the Steel City is renowned for its industrial prowess, its notoriety for air pollution has sparked curiosity about its potential impact on human fertility. Our study delved into this intriguing intersection of air quality and reproductive outcomes, specifically focusing on the incidence of triplet or higher-order births in the United States.
As we embarked on this research journey, the initial reaction from our colleagues was one of bemusement. After all, pondering the potential link between Pittsburgh's smoky skies and the birth of three (or more!) infants simultaneously seemed like traversing uncharted territory. However, armed with a passion for unraveling scientific mysteries and a penchant for wordplay, we set out to explore this unusual yet captivating relationship.
Armed with data from the Environmental Protection Agency and the Centers for Disease Control and Prevention, we sought to unmask the hidden connection between air pollution levels in Pittsburgh and the birth rates of triplets or more across the United States. Our statistical analysis unfurled an eyebrow-raising correlation coefficient of 0.8250760, complete with a p-value less than 0.01! A statistically significant finding, indeed - and one that prompted us to take a deep breath and dissect the implications with scholarly rigor.
Through this investigation, we aim not only to shed light on the atmospheric impact on triplet totals but also to inject a breath of fresh air into the discourse surrounding air quality and its unforeseen repercussions on human fertility. So, dear reader, fasten your seatbelts, as we embark on a scholarly journey that will challenge your preconceptions and, dare we say, leave you breathless with fascination!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data collection process commenced with a methodical scouring of various online databases, predominantly focusing on information from the Environmental Protection Agency (EPA) and the Centers for Disease Control and Prevention (CDC). Our research team utilized air quality measurements from monitoring stations in Pittsburgh, spanning the years 2002 to 2021. Simultaneously, birth data for triplets or higher-order multiples in the United States was procured from vital statistics reports and birth registries maintained by the CDC.

To maintain data integrity, we painstakingly cross-referenced and harmonized the disparate datasets, ensuring that the meteorological and demographic variables were amalgamated with precision. The amalgamation process, much like a scientific jigsaw puzzle, involved meticulous attention to detail and copious amounts of caffeine.

Variable Selection:
The selection of variables underwent rigorous scrutiny to encapsulate the multifaceted dimensions of air pollution and its putative influence on triplet births. Key variables included ambient air quality parameters such as particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), sulfur dioxide (SO2), carbon monoxide (CO), and ozone (O3). Meteorological variables encompassed temperature, humidity, wind speed, and precipitation, capturing the climatic milieu that might interact with air pollutants to orchestrate reproductive outcomes.

To complement these atmospheric variables, socioeconomic and demographic covariates were also incorporated to delineate potential confounding factors. Factors such as maternal age, race/ethnicity, education, access to healthcare, and urbanization served as covariates in the statistical modeling, aiming to illuminate the nuanced interplay between environmental exposures and maternal characteristics.

Statistical Analysis:
The integration of these diverse variables culminated in a comprehensive statistical analysis, unfolding like a data-driven symphony of variables and coefficients. Utilizing advanced time-series and panel data methodologies, we orchestrated a ballet of regression models to discern the association between air pollution in Pittsburgh and the national birth rates of triplets or more.

Hypothesis testing, much like unraveling a scientific enigma, was conducted to assess the strength and significance of the relationship between air pollution levels in Pittsburgh and the incidence of triplet births. The analytical framework spanned from traditional linear regressions to sophisticated hierarchical models, offering a panoramic view of the atmospheric impact on triplet totals.

Ethical Considerations:
In adherence to ethical standards, our research adhered to the principles of data privacy and confidentiality. The utilization of aggregate, de-identified data from the EPA and CDC ensured the anonymity of individuals, safeguarding their personal information from prying eyes. Moreover, the dissemination of findings prioritized the protection of privacy and the responsible communication of scientific results, echoing the reverberating importance of ethical conduct in scientific inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft 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 Air pollution in Pittsburgh and US birth rates of triplets or more. Make lots of 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 Environmental Protection Agency and CDC .

For the time period 2002 to 2021, you found a correlation 0.8250760, r-squared of 0.6807504, 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The atmosphere, like a nosy neighbor, has been eavesdropping on Pittsburgh's air quality, and the findings will take your breath away! While the Steel City is renowned for its industrial prowess, its notoriety for air pollution has sparked curiosity about its potential impact on human fertility. Our study delved into this intriguing intersection of air quality and reproductive outcomes, specifically focusing on the incidence of triplet or higher-order births in the United States.
As we embarked on this research journey, the initial reaction from our colleagues was one of bemusement. After all, pondering the potential link between Pittsburgh's smoky skies and the birth of three (or more!) infants simultaneously seemed like traversing uncharted territory. However, armed with a passion for unraveling scientific mysteries and a penchant for wordplay, we set out to explore this unusual yet captivating relationship.
Armed with data from the Environmental Protection Agency and the Centers for Disease Control and Prevention, we sought to unmask the hidden connection between air pollution levels in Pittsburgh and the birth rates of triplets or more across the United States. Our statistical analysis unfurled an eyebrow-raising correlation coefficient of 0.8250760, complete with a p-value less than 0.01! A statistically significant finding, indeed - and one that prompted us to take a deep breath and dissect the implications with scholarly rigor.
Through this investigation, we aim not only to shed light on the atmospheric impact on triplet totals but also to inject a breath of fresh air into the discourse surrounding air quality and its unforeseen repercussions on human fertility. So, dear reader, fasten your seatbelts, as we embark on a scholarly journey that will challenge your preconceptions and, dare we say, leave you breathless with fascination!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation yielded an astounding correlation coefficient of 0.8250760 between air pollution levels in Pittsburgh and the birth rates of triplets or more in the United States over the period from 2002 to 2021. This robust correlation suggests a strong association between the atmospheric composition of Pittsburgh and the occurrence of higher-order multiple births across the nation. With an r-squared value of 0.6807504, our model accounts for an impressive 68.07% of the variability in triplet birth rates, indicating that the relationship between air pollution and triplet totals is not merely a fleeting breeze, but a veritable whirlwind of statistical significance.

Furthermore, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no relationship between air pollution in Pittsburgh and the incidence of triplets or higher-order births in the United States. This result is as clear as the skies on a breezy day, reaffirming the notion that the atmospheric conditions in Pittsburgh may indeed play a noteworthy role in shaping the fertility landscape across the nation.

To visually encapsulate the strength of this relationship, we present Figure 1, a scatterplot illustrating the striking correlation between air pollution levels in Pittsburgh and the birth rates of triplets or more. This graphical depiction serves as a testament to the palpable connection we uncovered, providing a breath of fresh air in the visualization of this peculiar phenomenon.

In summary, our findings paint a compelling picture of the intertwining forces at play, where the atmospheric whispers of Pittsburgh seem to echo across the nation in the form of remarkable triplet birth rates. As we interpret these results, it is clear that this atmospheric entanglement with human fertility is no mere flight of fancy, but a phenomenon ripe for further exploration and, dare we say, air-raising discourse.


Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft the discussion section of 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 Air pollution in Pittsburgh and US birth rates of triplets or more. Make lots of 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

[[LITERATURE REVIEW]]
Numerous studies have documented the adverse effects of air pollution on human health, with a special focus on respiratory ailments and cardiovascular complications (Smith, 2015; Doe, 2018; Jones, 2020). However, the research has largely circumvented the enchanting realm of reproductive outcomes, particularly the incidence of higher-order multiple births. Surprisingly, this lacuna in the literature has left a considerable gap in our understanding of the potential atmospheric influence on fertility.
In "Airborne Antics: The Witty World of Particulate Matter," the authors emphasize the pervasive presence of airborne pollutants and their insidious infiltration of human habitats, setting the stage for a tale that is anything but airy. Similarly, "Fumes and Fetuses: Exploring the Uncharted Terrain of Air Quality and Fertility" offers compelling insights into the potential ramifications of polluted air on fertility, beckoning researchers to delve deeper into this unexplored domain.
As we traverse beyond the boundaries of traditional scholarly research, let us not overlook the fictional works that, while not grounded in empirical evidence, hold a whimsical mirror to our research endeavors. Lending an imaginative touch to our academic pursuit, "Cloudy with a Chance of Multiples" and "The Smoggy Stork: When Pollution Takes Flight" present fanciful accounts of environmental influences on birth outcomes. These literary creations, while far removed from the rigor of empirical inquiry, serve as a reminder of the captivating allure of our research topic.
Adding a cinematic twist to our journey, the films "The Air We Breathe" and "Triple Threat: A Tale of Three Times the Trouble" offer cinematic narratives that, albeit tangentially related, touch upon the intertwining dynamics of air quality and human fertility. While these filmic portrayals may lack the precision of scholarly investigation, they infuse an element of whimsy into our scholarly pursuits, reminding us of the multifaceted ways in which our research topic can captivate the imagination.

[[RESULTS]]
The results of our investigation yielded an astounding correlation coefficient of 0.8250760 between air pollution levels in Pittsburgh and the birth rates of triplets or more in the United States over the period from 2002 to 2021. This robust correlation suggests a strong association between the atmospheric composition of Pittsburgh and the occurrence of higher-order multiple births across the nation. With an r-squared value of 0.6807504, our model accounts for an impressive 68.07% of the variability in triplet birth rates, indicating that the relationship between air pollution and triplet totals is not merely a fleeting breeze, but a veritable whirlwind of statistical significance.
Furthermore, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no relationship between air pollution in Pittsburgh and the incidence of triplets or higher-order births in the United States. This result is as clear as the skies on a breezy day, reaffirming the notion that the atmospheric conditions in Pittsburgh may indeed play a noteworthy role in shaping the fertility landscape across the nation.
To visually encapsulate the strength of this relationship, we present Figure 1, a scatterplot illustrating the striking correlation between air pollution levels in Pittsburgh and the birth rates of triplets or more. This graphical depiction serves as a testament to the palpable connection we uncovered, providing a breath of fresh air in the visualization of this peculiar phenomenon.
In summary, our findings paint a compelling picture of the intertwining forces at play, where the atmospheric whispers of Pittsburgh seem to echo across the nation in the form of remarkable triplet birth rates. As we interpret these results, it is clear that this atmospheric entanglement with human fertility is no mere flight of fancy, but a phenomenon ripe for further exploration and, dare we say, air-raising discourse.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The resounding resonance of our findings with prior research reaffirms the weighty significance of atmospheric conditions in shaping the fertility landscape. The robust correlation coefficient of 0.8250760 fortifies the notion that the atmospheric composition of Pittsburgh is not to be taken lightly when considering its impact on the incidence of higher-order multiple births across the nation. Much like the airborne pollutants that pervade human habitats, the influence of Pittsburgh's atmospheric emissions appears to reach far and wide, leaving an indelible mark on the triplet totals in the United States.

As we reflect on the literature review, it is clear that the enchanting realm of atmospheric influence on fertility has long been a subject of intrigue. Our findings, aligning with previous studies that accentuated the insidious infiltration of pollutants, provide empirical evidence to bolster this captivating narrative. The fictional works "Cloudy with a Chance of Multiples" and "The Smoggy Stork: When Pollution Takes Flight," while not grounded in empirical evidence, serve as whimsical reminders of the imaginative allure that underpins our research endeavors, now validated by our statistically significant findings.

The enticing cinematic narratives of "The Air We Breathe" and "Triple Threat: A Tale of Three Times the Trouble," while tangential to our scholarly pursuits, underscore the multifaceted ways in which our research topic can captivate the imagination. Through our rigorous investigation, we have breathed life into these fanciful accounts, shining a statistical spotlight on the intertwining dynamics of air quality and human fertility.

Our compelling results, with an r-squared value of 0.6807504, signal that the relationship between air pollution and triplet totals is not a mere fleeting breeze, but a veritable whirlwind of statistical significance. This statistical whirlwind has a much higher chance of knocking someone off their feet than a mild zephyr. The p-value of less than 0.01, akin to clear skies on a breezy day, confirms the eminent relationship between air pollution in Pittsburgh and the occurrence of triplets or higher-order births in the United States.

In the realm of statistics, where the winds of uncertainty often blow, our findings stand as a beacon of clarity amidst the atmospheric turbulence. The visualization of our results in the form of a scatterplot, akin to a breath of fresh air in the visualization of this peculiar phenomenon, presents a compelling visual testament to the palpable connection we have uncovered. This visualization is not to be taken lightly, much like the swirling winds of a statistical storm.

In conclusion, our research has unearthed a phenomenon brimming with potential for further exploration and, dare we say, air-raising discourse. As the atmospheric whispers of Pittsburgh continue to echo across the nation in the form of remarkable triplet birth rates, the winds of statistical significance propel us forward toward broader discussions and research ventures in this enthralling domain.


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 Air pollution in Pittsburgh and US birth rates of triplets or more. Make lots of 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]]
Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh

[[ABSTRACT]]
This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

[[INTRDUCTION]]
INTRODUCTION
The atmosphere, like a nosy neighbor, has been eavesdropping on Pittsburgh's air quality, and the findings will take your breath away! While the Steel City is renowned for its industrial prowess, its notoriety for air pollution has sparked curiosity about its potential impact on human fertility. Our study delved into this intriguing intersection of air quality and reproductive outcomes, specifically focusing on the incidence of triplet or higher-order births in the United States.
As we embarked on this research journey, the initial reaction from our colleagues was one of bemusement. After all, pondering the potential link between Pittsburgh's smoky skies and the birth of three (or more!) infants simultaneously seemed like traversing uncharted territory. However, armed with a passion for unraveling scientific mysteries and a penchant for wordplay, we set out to explore this unusual yet captivating relationship.
Armed with data from the Environmental Protection Agency and the Centers for Disease Control and Prevention, we sought to unmask the hidden connection between air pollution levels in Pittsburgh and the birth rates of triplets or more across the United States. Our statistical analysis unfurled an eyebrow-raising correlation coefficient of 0.8250760, complete with a p-value less than 0.01! A statistically significant finding, indeed - and one that prompted us to take a deep breath and dissect the implications with scholarly rigor.
Through this investigation, we aim not only to shed light on the atmospheric impact on triplet totals but also to inject a breath of fresh air into the discourse surrounding air quality and its unforeseen repercussions on human fertility. So, dear reader, fasten your seatbelts, as we embark on a scholarly journey that will challenge your preconceptions and, dare we say, leave you breathless with fascination!

[[RESULTS]]
The results of our investigation yielded an astounding correlation coefficient of 0.8250760 between air pollution levels in Pittsburgh and the birth rates of triplets or more in the United States over the period from 2002 to 2021. This robust correlation suggests a strong association between the atmospheric composition of Pittsburgh and the occurrence of higher-order multiple births across the nation. With an r-squared value of 0.6807504, our model accounts for an impressive 68.07% of the variability in triplet birth rates, indicating that the relationship between air pollution and triplet totals is not merely a fleeting breeze, but a veritable whirlwind of statistical significance.
Furthermore, the p-value of less than 0.01 provides compelling evidence to reject the null hypothesis that there is no relationship between air pollution in Pittsburgh and the incidence of triplets or higher-order births in the United States. This result is as clear as the skies on a breezy day, reaffirming the notion that the atmospheric conditions in Pittsburgh may indeed play a noteworthy role in shaping the fertility landscape across the nation.
To visually encapsulate the strength of this relationship, we present Figure 1, a scatterplot illustrating the striking correlation between air pollution levels in Pittsburgh and the birth rates of triplets or more. This graphical depiction serves as a testament to the palpable connection we uncovered, providing a breath of fresh air in the visualization of this peculiar phenomenon.
In summary, our findings paint a compelling picture of the intertwining forces at play, where the atmospheric whispers of Pittsburgh seem to echo across the nation in the form of remarkable triplet birth rates. As we interpret these results, it is clear that this atmospheric entanglement with human fertility is no mere flight of fancy, but a phenomenon ripe for further exploration and, dare we say, air-raising discourse.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has not only unearthed a robust correlation between air pollution levels in Pittsburgh and the birth rates of triplets or more in the United States but has also blown the lid off a previously undetected connection that is as intriguing as it is unexpected. The atmospheric impact on triplet totals appears to be more than just a gust of wind in the world of reproductive outcomes. Our findings suggest that the winds of change in Pittsburgh may be gusts of fertility across the nation!

It is abundantly clear that this study has opened a window into the intricate relationship between air quality and human fertility, revealing a breeze of statistical significance that cannot simply be swept under the rug. This correlation is not to be taken lightly; it demands to be aired out, discussed, and further investigated with the vigor and thoroughness that it deserves.

Moreover, as we reflect on the implications of our research, it becomes apparent that the connection between Pittsburgh's atmospheric composition and the occurrence of higher-order multiple births across the nation is not just a statistical blip on the radar. It is a full-blown tornado of scientific curiosity, swirling with potential implications and avenues for future exploration.

With these compelling findings in mind, it is our scholarly duty to ensure that this groundbreaking revelation receives the attention it deserves. The link between air pollution and triplet birth rates is ripe for further investigation, discussion, and the occasional pun-filled academic paper.

In light of our in-depth analysis, it is our firm assertion that no further research is needed in this area. The evidence is as clear as the skies on a breezy day - or should we say, as clear as the statistical significance in our findings! Let these results serve as a breath of fresh air, ushering in a new era of scientific inquiry and curiosity. With that, we bid adieu to this peculiar phenomenon, leaving it to waft through the annals of scientific intrigue, where it shall undoubtedly linger like an atmospheric enigma.


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 Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Atmospheric Studies


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 Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh. Respond only with the name of a fictional organization.

ChatGPT:

The Association for Urban Air 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 Taking a Breather: The Atmospheric Impact on Triplet Totals in Pittsburgh with an abstract of This study aimed to explore the elusive connection between air pollution in Pittsburgh and the incidence of triplet or higher-order births in the United States. Utilizing data from the Environmental Protection Agency and the Centers for Disease Control and Prevention spanning the years 2002 to 2021, our research team identified a significant correlation coefficient of 0.8250760, with a p-value less than 0.01. The analysis revealed a striking relationship between air pollution levels in Pittsburgh and the national birth rates of triplets or more, shedding light on a previously unexplored facet of human reproduction. Through this investigation, we hope to inspire further research and ventilation of this peculiar phenomenon.

ChatGPT:

air pollution, Pittsburgh, birth rates, triplets, higher-order births, atmospheric impact, Environmental Protection Agency data, Centers for Disease Control and Prevention data, 2002-2021, correlation coefficient, human reproduction

*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

Air pollution in Pittsburgh
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Pittsburgh, PA
Source: Environmental Protection Agency
See what else correlates with Air pollution in Pittsburgh

US birth rates of triplets or more
Source: CDC
See what else correlates with US birth rates of triplets or more

Correlation r = 0.8250760 (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 = 0.6807504 (Coefficient of determination)
This means 68.1% of the change in the one variable (i.e., US birth rates of triplets or more) is predictable based on the change in the other (i.e., Air pollution in Pittsburgh) over the 20 years from 2002 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.6E-6. 0.0000075728283044560010000000
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 0.83 in 0.00076% of random cases. Said differently, if you correlated 132,051 random variables You don't actually need 132 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 19 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.6, 0.93 ] 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.
20022003200420052006200720082009201020112012201320142015201620172018201920202021
Air pollution in Pittsburgh (Bad air quality days)10.68495.479454.644817.397264.109596.575343.005461.369864.109591.095891.366120.2739730.2739730.2739730.2732240.2739730.2739731.0958900.273973
US birth rates of triplets or more (Birth rate per 100,000)183186180170156151148152138137124.4119.5113.5103.6101.4101.69387.779.680




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([10.6849,5.47945,4.64481,7.39726,4.10959,6.57534,3.00546,1.36986,4.10959,1.09589,1.36612,0.273973,0.273973,0.273973,0.273224,0.273973,0.273973,1.09589,0,0.273973,])
array_2 = np.array([183,186,180,170,156,151,148,152,138,137,124.4,119.5,113.5,103.6,101.4,101.6,93,87.7,79.6,80,])
array_1_name = "Air pollution in Pittsburgh"
array_2_name = "US birth rates of triplets or more"

# 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?

Your rating is pure awesomeness!


Correlation ID: 3690 · Black Variable ID: 21064 · Red Variable ID: 55
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0