about · email me · subscribe
Spurious correlation #3,950 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Milk consumption and the second variable is Robberies in Idaho.  The chart goes from 1990 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

Fewer dairy-related daredevils were attempting to execute the infamous "milk run" heists, resulting in a udderly dramatic drop in dairy crime. As moo-ving as it may seem, the correlation between milk consumption and robberies in Idaho was nothing but a dairy coincidence!

Model: dalle-3
Prompt: "Generate a colorful pop art style image of a peaceful Idaho town scene. In the foreground, depict a group of smiling people, each with a glass of milk in hand, sitting on their front porches. The evening setting should be serene, with quiet streets and no signs of trouble or illicit activities. The residents are content and at peace, with no need for late-night snack runs or robberies. Emphasize vibrant colors and bold, graphic elements to capture the essence of pop art." 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: Milk consumption and Robberies in Idaho. 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: Brutalism Pop art Psychedelic Symbolism Surrealism
ChatGPT: Pop art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Milk consumption and Robberies in Idaho, in the following situation: Because fewer people had lactose intolerance, leading to less stomach discomfort and crankiness, resulting in decreased motivation for late-night snack runs and robberies in Idaho.. Keep the description simple.
ChatGPT: In a peaceful Idaho town, a group of smiling people are seen enjoying glasses of milk on their front porches in the evening. The streets are quiet, with no sign of any trouble or illicit activities taking place, as the contented residents have no need for late-night snack runs or robberies.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Pop art ] and depicting this scene: In a peaceful Idaho town, a group of smiling people are seen enjoying glasses of milk on their front porches in the evening. The streets are quiet, with no sign of any trouble or illicit activities taking place, as the contented residents have no need for late-night snack runs or robberies. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: "Generate a colorful pop art style image of a peaceful Idaho town scene. In the foreground, depict a group of smiling people, each with a glass of milk in hand, sitting on their front porches. The evening setting should be serene, with quiet streets and no signs of trouble or illicit activities. The residents are content and at peace, with no need for late-night snack runs or robberies. Emphasize vibrant colors and bold, graphic elements to capture the essence of pop art."

*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 Milk consumption caused Robberies in Idaho to decrease.

AI academic paper

(Because p < 0.01)
Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho

The Journal of Dairy Delinquency

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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Your research team used data from USDA and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.8588979 and p < 0.01 for 1990 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]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

The relationship between dietary habits and societal behavior has long been a subject of intrigue and curiosity. While the impact of nutrition on physical health has been well-documented, the potential influence of food consumption on criminal activity has received limited attention in the hallowed halls of academia. However, as the wheels of research grind on, the field of "culinary criminology" has begun to churn out studies investigating the curious connections between what we consume and how we behave, often yielding results that are both surprising and udderly intriguing.

In this vein, our research delves into the enigmatic intersection of dairy consumption and criminal mischief in the unassuming state of Idaho. The choice of Idaho as the focal point for our inquiry is not arbitrary; indeed, as the land of potatoes and pristine landscapes, one might rarely envision it as a hotbed of criminal activity. Nevertheless, as the saying goes, there is always more than meets the "eye-daho."

Galloping swiftly over the hills of statistical analysis, we have sought to milk the data available from the USDA and the FBI Criminal Justice Information Services to tease out any potential correlation between milk consumption and robberies. By meticulously examining trends from 1990 to 2021, we have strived to unravel the dairy enigma, hoping to shed some light on whether there is, in fact, a creamy connection between these seemingly disparate variables.

The implications of such an investigation are not to be trivialized, as they could churn the wheels of crime prevention strategies and prompt a re-evaluation of public health campaigns. As we embark on this udderly unconventional scientific journey, we invite the reader to join us in unraveling the creamy mysteries and discovering whether the age-old question "Got milk?" might actually be a criminal inquiry in disguise.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The relationship between dietary habits and societal behavior has long been a subject of intrigue and curiosity. While the impact of nutrition on physical health has been well-documented, the potential influence of food consumption on criminal activity has received limited attention in the hallowed halls of academia. However, as the wheels of research grind on, the field of "culinary criminology" has begun to churn out studies investigating the curious connections between what we consume and how we behave, often yielding results that are both surprising and udderly intriguing.
In this vein, our research delves into the enigmatic intersection of dairy consumption and criminal mischief in the unassuming state of Idaho. The choice of Idaho as the focal point for our inquiry is not arbitrary; indeed, as the land of potatoes and pristine landscapes, one might rarely envision it as a hotbed of criminal activity. Nevertheless, as the saying goes, there is always more than meets the "eye-daho."
Galloping swiftly over the hills of statistical analysis, we have sought to milk the data available from the USDA and the FBI Criminal Justice Information Services to tease out any potential correlation between milk consumption and robberies. By meticulously examining trends from 1990 to 2021, we have strived to unravel the dairy enigma, hoping to shed some light on whether there is, in fact, a creamy connection between these seemingly disparate variables.
The implications of such an investigation are not to be trivialized, as they could churn the wheels of crime prevention strategies and prompt a re-evaluation of public health campaigns. As we embark on this udderly unconventional scientific journey, we invite the reader to join us in unraveling the creamy mysteries and discovering whether the age-old question "Got milk?" might actually be a criminal inquiry in disguise.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The existing body of literature on the association between dietary consumption and criminal behavior has provided valuable insights into the potential links between these seemingly unrelated domains. Several seminal studies have delved into the impact of various food items on societal conduct. Smith et al. (2015) explored the effects of sugar consumption on impulse control, while Doe and Johnson (2018) investigated the relationship between caffeine intake and aggression. Furthermore, Jones (2020) conducted a comprehensive meta-analysis of the influence of spicy food on risk-taking behaviors. These studies have shed light on the intricate interplay between dietary choices and human actions, setting the stage for our peculiar inquiry into the relationship between milk consumption and robberies in Idaho.

Turning to more specific literature relevant to dairy consumption, "Milk: The White Elixir" by Dairy Association outlines the nutritional benefits of milk, emphasizing its role in bone health and overall well-being. Additionally, "The Big Book of Cheese" by Curd Enthusiasts United provides a comprehensive overview of various dairy products and their cultural significance. These works offer valuable context for understanding the centrality of milk in the culinary landscape.

In the fictional realm, the detective novel "The Case of the Missing Milk Carton" by Agatha Creamy and the crime thriller "The Dairy Heist" by M. Oolaha further illustrate the intersection of dairy products and criminal activities, albeit in a lighthearted and imaginative manner.

In the sphere of social media, a tweet by @CowConspiracy claims, "More milk, more mischief! #GotAlibis." Although lacking empirical evidence, such anecdotal observations from online platforms add an element of popular discourse to our investigation, stirring curiosity about the potential implications of milk consumption on criminal behavior.

The conjunction of these sources, both scholarly and anecdotal, sets the stage for our inquiry into the creamy connection between milk consumption and robberies in Idaho, unveiling a journey that promises to be both enlightening and utterly amusing.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from USDA and FBI Criminal Justice Information Services . You used data from 1990 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]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

[[INTRODUCTION]]
INTRODUCTION
The relationship between dietary habits and societal behavior has long been a subject of intrigue and curiosity. While the impact of nutrition on physical health has been well-documented, the potential influence of food consumption on criminal activity has received limited attention in the hallowed halls of academia. However, as the wheels of research grind on, the field of "culinary criminology" has begun to churn out studies investigating the curious connections between what we consume and how we behave, often yielding results that are both surprising and udderly intriguing.
In this vein, our research delves into the enigmatic intersection of dairy consumption and criminal mischief in the unassuming state of Idaho. The choice of Idaho as the focal point for our inquiry is not arbitrary; indeed, as the land of potatoes and pristine landscapes, one might rarely envision it as a hotbed of criminal activity. Nevertheless, as the saying goes, there is always more than meets the "eye-daho."
Galloping swiftly over the hills of statistical analysis, we have sought to milk the data available from the USDA and the FBI Criminal Justice Information Services to tease out any potential correlation between milk consumption and robberies. By meticulously examining trends from 1990 to 2021, we have strived to unravel the dairy enigma, hoping to shed some light on whether there is, in fact, a creamy connection between these seemingly disparate variables.
The implications of such an investigation are not to be trivialized, as they could churn the wheels of crime prevention strategies and prompt a re-evaluation of public health campaigns. As we embark on this udderly unconventional scientific journey, we invite the reader to join us in unraveling the creamy mysteries and discovering whether the age-old question "Got milk?" might actually be a criminal inquiry in disguise.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data used in this study was obtained from the USDA for milk consumption and the FBI Criminal Justice Information Services for robbery incidents in Idaho. The extensive data collection process involved utilizing various sources from the internet to gather information spanning from 1990 to 2021. The selection of this time frame allowed for a comprehensive analysis of long-term trends and fluctuations in milk consumption and robbery rates, ensuring that no potential anomalies were left unexamined.

Statistical Analysis:
To analyze the relationship between milk consumption and robberies in Idaho, a series of statistical methods were employed. Firstly, descriptive statistics were used to characterize the central tendency, dispersion, and shape of the distributions of both milk consumption and robbery incidents. This allowed for a thorough exploration of the raw data, as well as providing valuable insights into the variability and distribution of the variables, without crying over spilled milk!

Following this, a correlation analysis was conducted to assess the degree of association between milk consumption and robbery rates. We calculated the correlation coefficient to quantify the strength and direction of the linear relationship between the two variables. This rigorous analysis sought to milk every bit of insight from the data, ensuring that no potential link between dairy intake and criminal activity was skimmed over.

Furthermore, a time series analysis was performed to track the temporal patterns in milk consumption and robbery incidents over the study period. By delving into the seasonal fluctuations and long-term trends, this analysis aimed to uncover any cyclical patterns or trends that might have otherwise been overlooked. The utilization of such methods offered a butter understanding of the dynamic interplay between milk consumption and robberies, providing a more holistic perspective and preventing any statistical curdling of the findings.

Finally, a regression analysis was carried out to ascertain the predictive power of milk consumption on robbery rates, controlling for potential confounding factors. This modeling approach permitted a deeper exploration of the underlying relationships and potential causal mechanisms, unpicking the intricacies of the creamy connection between dairy intake and criminal behavior.

Ethical Considerations:
In conducting this research, ethical guidelines for the use of public data and statistical analysis were strictly adhered to. The anonymity and confidentiality of the individuals represented in the robbery data were carefully maintained, ensuring that no individual or community could be identified or targeted based on the findings. The researchers exercised utmost caution to prevent any ethical "faux pas" in the pursuit of knowledge and understanding, as the last thing anyone wants is a souring of the research process due to ethical breaches.

In conclusion, the comprehensive methodology employed in this study sought to meticulously analyze the relationship between milk consumption and robberies in Idaho, aiming to unveil any potential creamy correlations that may have eluded previous investigations. The rigor and thoroughness of the approach aimed to capture the nuances of these variables, providing a robust foundation for interpreting the findings and challenging conventional wisdom about the purported innocence of dairy products.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1990 to 2021, you found a correlation 0.8588979, r-squared of 0.7377057, 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]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The relationship between dietary habits and societal behavior has long been a subject of intrigue and curiosity. While the impact of nutrition on physical health has been well-documented, the potential influence of food consumption on criminal activity has received limited attention in the hallowed halls of academia. However, as the wheels of research grind on, the field of "culinary criminology" has begun to churn out studies investigating the curious connections between what we consume and how we behave, often yielding results that are both surprising and udderly intriguing.
In this vein, our research delves into the enigmatic intersection of dairy consumption and criminal mischief in the unassuming state of Idaho. The choice of Idaho as the focal point for our inquiry is not arbitrary; indeed, as the land of potatoes and pristine landscapes, one might rarely envision it as a hotbed of criminal activity. Nevertheless, as the saying goes, there is always more than meets the "eye-daho."
Galloping swiftly over the hills of statistical analysis, we have sought to milk the data available from the USDA and the FBI Criminal Justice Information Services to tease out any potential correlation between milk consumption and robberies. By meticulously examining trends from 1990 to 2021, we have strived to unravel the dairy enigma, hoping to shed some light on whether there is, in fact, a creamy connection between these seemingly disparate variables.
The implications of such an investigation are not to be trivialized, as they could churn the wheels of crime prevention strategies and prompt a re-evaluation of public health campaigns. As we embark on this udderly unconventional scientific journey, we invite the reader to join us in unraveling the creamy mysteries and discovering whether the age-old question "Got milk?" might actually be a criminal inquiry in disguise.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis revealed a correlation coefficient (r) of 0.8588979 between milk consumption and robberies in Idaho for the period of 1990 to 2021. This robust correlation suggests a noteworthy relationship between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7377057, indicating that approximately 73.77% of the variability in robberies can be explained by fluctuations in milk consumption. This finding underscores the substantive impact of dairy intake on criminal behavior in the Gem State.

Moreover, the p-value obtained from the analysis was less than 0.01, further substantiating the strength of the observed association. This indicates that the likelihood of obtaining such a strong correlation purely by chance is exceedingly low, lending additional support to the hypothesis that there exists a tangible link between milk consumption and robberies in Idaho.

The scatterplot (Fig. 1) visually depicts the pronounced correlation between milk consumption and incidents of robberies, offering a compelling illustration of the relationship uncovered in this study. The scatterplot's juxtaposition of milk consumption and robberies forms an intriguing visual narrative, encapsulating the creamy connection between these seemingly unrelated variables.

In summary, the results of the present investigation unveiled a compelling correlation between milk consumption and robberies in Idaho, shedding light on the potential influence of dairy intake on criminal activity in this picturesque state. The implications of these findings transcend the boundaries of traditional criminology, inviting a reevaluation of conventional wisdom and prompting further scrutiny into the enigmatic interplay of dietary habits and societal behavior.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

[[LITERATURE REVIEW]]
The existing body of literature on the association between dietary consumption and criminal behavior has provided valuable insights into the potential links between these seemingly unrelated domains. Several seminal studies have delved into the impact of various food items on societal conduct. Smith et al. (2015) explored the effects of sugar consumption on impulse control, while Doe and Johnson (2018) investigated the relationship between caffeine intake and aggression. Furthermore, Jones (2020) conducted a comprehensive meta-analysis of the influence of spicy food on risk-taking behaviors. These studies have shed light on the intricate interplay between dietary choices and human actions, setting the stage for our peculiar inquiry into the relationship between milk consumption and robberies in Idaho.
Turning to more specific literature relevant to dairy consumption, "Milk: The White Elixir" by Dairy Association outlines the nutritional benefits of milk, emphasizing its role in bone health and overall well-being. Additionally, "The Big Book of Cheese" by Curd Enthusiasts United provides a comprehensive overview of various dairy products and their cultural significance. These works offer valuable context for understanding the centrality of milk in the culinary landscape.
In the fictional realm, the detective novel "The Case of the Missing Milk Carton" by Agatha Creamy and the crime thriller "The Dairy Heist" by M. Oolaha further illustrate the intersection of dairy products and criminal activities, albeit in a lighthearted and imaginative manner.
In the sphere of social media, a tweet by @CowConspiracy claims, "More milk, more mischief! #GotAlibis." Although lacking empirical evidence, such anecdotal observations from online platforms add an element of popular discourse to our investigation, stirring curiosity about the potential implications of milk consumption on criminal behavior.
The conjunction of these sources, both scholarly and anecdotal, sets the stage for our inquiry into the creamy connection between milk consumption and robberies in Idaho, unveiling a journey that promises to be both enlightening and utterly amusing.

[[RESULTS]]
The statistical analysis revealed a correlation coefficient (r) of 0.8588979 between milk consumption and robberies in Idaho for the period of 1990 to 2021. This robust correlation suggests a noteworthy relationship between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7377057, indicating that approximately 73.77% of the variability in robberies can be explained by fluctuations in milk consumption. This finding underscores the substantive impact of dairy intake on criminal behavior in the Gem State.
Moreover, the p-value obtained from the analysis was less than 0.01, further substantiating the strength of the observed association. This indicates that the likelihood of obtaining such a strong correlation purely by chance is exceedingly low, lending additional support to the hypothesis that there exists a tangible link between milk consumption and robberies in Idaho.
The scatterplot (Fig. 1) visually depicts the pronounced correlation between milk consumption and incidents of robberies, offering a compelling illustration of the relationship uncovered in this study. The scatterplot's juxtaposition of milk consumption and robberies forms an intriguing visual narrative, encapsulating the creamy connection between these seemingly unrelated variables.
In summary, the results of the present investigation unveiled a compelling correlation between milk consumption and robberies in Idaho, shedding light on the potential influence of dairy intake on criminal activity in this picturesque state. The implications of these findings transcend the boundaries of traditional criminology, inviting a reevaluation of conventional wisdom and prompting further scrutiny into the enigmatic interplay of dietary habits and societal behavior.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The discussion section of this study proffers a thoughtful rumination on the interplay between milk consumption and robberies in Idaho, probing the web of factors that may underlie the ostensibly perplexing correlation uncovered in the analysis. The robust correlation coefficient and the minuscule p-value warrant a comprehensive exploration of the potential mechanisms driving this creamy connection.

The findings of this study echo and expand upon the extant literature that has delved into the influence of dietary choices on human conduct. While previous research has primarily focused on the impact of individual components such as sugar, caffeine, and spices, the present investigation broadens the scope to encompass the dairy domain and its unexpected entanglement with criminal behavior. The conspicuous correlation coefficient aligns with the prior insight offered by the fictional works "The Case of the Missing Milk Carton" and "The Dairy Heist," offering a nuanced portrayal of dairy's dim association with illicit activities.

Mechanistically, the link between milk consumption and robberies may stem from a myriad of subtle and intricate pathways that intertwine dietary preferences with neurobiological and sociological factors. It is plausible that the physiological effects of milk constituents, such as the casomorphins with their opioid-like properties, may modulate mood and behavior, potentially influencing the propensity for criminal acts. Additionally, the psychological and cultural connotations of milk as a symbol of comfort and nostalgia could intertwine with societal attitudes and norms, imparting a surreptitious influence on criminal inclinations.

The implications of this study extend beyond the idyllic landscapes of Idaho, beckoning a reevaluation of dietary interventions in crime prevention strategies. The age-old adage "Got milk?" may indeed assume a new poignancy in the context of criminal alibis, urging a systematic consideration of dairy's role in societal conduct. As we ruminate on the implications of this creamy correlation, the research community is prompted to milk the depths of interdisciplinary inquiry, synergizing the realms of nutrition, criminology, and behavioral sciences to churn out a comprehensive understanding of this intriguing nexus.

In conclusion, the unresolved mystery of the milk-robbery nexus invites a whimsical yet earnest pursuit of knowledge, emblematic of the idiosyncrasies that pervade the scientific enterprise. The present study advances this quest, offering a creamy conundrum that tantalizingly teases the intellect, all while prodding the reader to ponder, if not laugh, at the unexpected twists that science unwaveringly unfurls.


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 Milk consumption and Robberies in Idaho. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho"

[[ABSTRACT]]
The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

[[INTRDUCTION]]
INTRODUCTION
The relationship between dietary habits and societal behavior has long been a subject of intrigue and curiosity. While the impact of nutrition on physical health has been well-documented, the potential influence of food consumption on criminal activity has received limited attention in the hallowed halls of academia. However, as the wheels of research grind on, the field of "culinary criminology" has begun to churn out studies investigating the curious connections between what we consume and how we behave, often yielding results that are both surprising and udderly intriguing.
In this vein, our research delves into the enigmatic intersection of dairy consumption and criminal mischief in the unassuming state of Idaho. The choice of Idaho as the focal point for our inquiry is not arbitrary; indeed, as the land of potatoes and pristine landscapes, one might rarely envision it as a hotbed of criminal activity. Nevertheless, as the saying goes, there is always more than meets the "eye-daho."
Galloping swiftly over the hills of statistical analysis, we have sought to milk the data available from the USDA and the FBI Criminal Justice Information Services to tease out any potential correlation between milk consumption and robberies. By meticulously examining trends from 1990 to 2021, we have strived to unravel the dairy enigma, hoping to shed some light on whether there is, in fact, a creamy connection between these seemingly disparate variables.
The implications of such an investigation are not to be trivialized, as they could churn the wheels of crime prevention strategies and prompt a re-evaluation of public health campaigns. As we embark on this udderly unconventional scientific journey, we invite the reader to join us in unraveling the creamy mysteries and discovering whether the age-old question "Got milk?" might actually be a criminal inquiry in disguise.

[[RESULTS]]
The statistical analysis revealed a correlation coefficient (r) of 0.8588979 between milk consumption and robberies in Idaho for the period of 1990 to 2021. This robust correlation suggests a noteworthy relationship between the two variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.7377057, indicating that approximately 73.77% of the variability in robberies can be explained by fluctuations in milk consumption. This finding underscores the substantive impact of dairy intake on criminal behavior in the Gem State.
Moreover, the p-value obtained from the analysis was less than 0.01, further substantiating the strength of the observed association. This indicates that the likelihood of obtaining such a strong correlation purely by chance is exceedingly low, lending additional support to the hypothesis that there exists a tangible link between milk consumption and robberies in Idaho.
The scatterplot (Fig. 1) visually depicts the pronounced correlation between milk consumption and incidents of robberies, offering a compelling illustration of the relationship uncovered in this study. The scatterplot's juxtaposition of milk consumption and robberies forms an intriguing visual narrative, encapsulating the creamy connection between these seemingly unrelated variables.
In summary, the results of the present investigation unveiled a compelling correlation between milk consumption and robberies in Idaho, shedding light on the potential influence of dairy intake on criminal activity in this picturesque state. The implications of these findings transcend the boundaries of traditional criminology, inviting a reevaluation of conventional wisdom and prompting further scrutiny into the enigmatic interplay of dietary habits and societal behavior.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

The findings of this study offer an udderly intriguing perspective on the potential connection between milk consumption and criminal activity in the serene state of Idaho. The striking correlation coefficient of 0.8588979, which could be dubbed as "milk-mane's coefficient," and the p-value of less than 0.01 amusingly underscore the robust relationship between these seemingly unrelated variables. This robust association begs the question: is it possible that while milk does a body good, it might also do a criminal mind bad?

The scatterplot (Fig. 1) provides a visual feast for the eyes, depicting the creamy correlation between milk consumption and robberies. It is a testament to the notion that sometimes, the most unexpected relationships can be unveiled through the lens of statistical analysis.

As we churn through the implications of these findings, it becomes clear that the phrase "Got milk?" may now be tinged with a hint of suspicion, prompting one to ponder, "Got alibis?" While the origins of this correlation remain enshrouded in mystery, the implications for crime prevention strategies and public health initiatives may be as vast as the Idahoan plains themselves.

However, in the grand tradition of academic research, it is necessary to recognize that correlation does not imply causation. The relationship between milk consumption and robberies, while statistically noteworthy, should be interpreted with caution, lest we cry over spilled milk. Additional factors, such as socioeconomic conditions and cultural aspects, may contribute to the observed correlation.

In light of these findings, it seems that further research in this area would be, to put it bluntly, a mere "sour milk endeavor." Hence, it is with great confidence that we assert that no more research is needed in this particular field of study.


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 Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Delinquency


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 Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho. Respond only with the name of a fictional organization.

ChatGPT:

The Bovine Behavioral Research Institute


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 Milk and Moolah: Exploring the Creamy Connection Between Milk Consumption and Robberies in Idaho with an abstract of The intriguing relationship between dairy consumption and criminal activity has been a topic of debate for many moons. In this study, we examine the association between milk intake and robberies in the picturesque state of Idaho. Utilizing comprehensive data from the USDA and the FBI Criminal Justice Information Services, we rigorously scrutinized the fluctuations in milk consumption and the incidents of robberies from 1990 to 2021. Our analysis reveals a striking correlation coefficient of 0.8588979, with a p-value of less than 0.01, illustrating a robust connection between the two variables. The implications of these findings might challenge the age-old adage "Got milk?" to "Got alibis?" as we consider the potential ramifications of this creamy correlation on crime prevention strategies and public health initiatives.

ChatGPT:

milk consumption, crime rates, milk intake, dairy consumption, robbery incidents, Idaho, USDA data, FBI crime statistics, correlation coefficient, crime prevention strategies, public health initiatives

*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

Milk consumption
Detailed data title: Per capita consumption of Fluid beverage milk in the US
Source: USDA
See what else correlates with Milk consumption

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

Correlation r = 0.8588979 (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 = 0.7377057 (Coefficient of determination)
This means 73.8% of the change in the one variable (i.e., Robberies in Idaho) is predictable based on the change in the other (i.e., Milk consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.2E-10. 0.0000000003183807609703005000
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 0.86 in 3.2E-8% of random cases. Said differently, if you correlated 3,140,893,303 random variables You don't actually need 3 billion 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 31 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 31 because we have two variables measured over a period of 32 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.73, 0.93 ] 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.
19901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Milk consumption (Pounds per person)220218215210208205205201198197196192191188185185185183181181177173169164158155153149145141141134
Robberies in Idaho (Robbery rate)1520.721.516.918.42420.319.621.517.817.218.617.917.917.318.62016.215.716.413.611.915.213.612.411.612.712.911.199.58.3




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. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




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([220,218,215,210,208,205,205,201,198,197,196,192,191,188,185,185,185,183,181,181,177,173,169,164,158,155,153,149,145,141,141,134,])
array_2 = np.array([15,20.7,21.5,16.9,18.4,24,20.3,19.6,21.5,17.8,17.2,18.6,17.9,17.9,17.3,18.6,20,16.2,15.7,16.4,13.6,11.9,15.2,13.6,12.4,11.6,12.7,12.9,11.1,9,9.5,8.3,])
array_1_name = "Milk consumption"
array_2_name = "Robberies in Idaho"

# 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?

Big thanks for reviewing!


Correlation ID: 3950 · Black Variable ID: 554 · Red Variable ID: 20185
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0