Spurious correlation #2,427 · 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 Burglaries in Vermont. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

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 Burglaries in Vermont. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As people stopped crying over spilled milk, there was a decrease in the emotional distress that often triggers irrational behavior, like breaking into a house. With fewer lactose-related larcenies, it seems the dairy doers had finally churned over a new leaf. It looks like the only thing being stolen now is a bit of gouda humor.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a peaceful and picturesque Vermont town at sunset, with rolling green hills in the background. In one frame, depict a cozy kitchen filled with laughing residents raising glasses of fresh milk. In another frame, show would-be burglars doubled over in stomach discomfort, unable to carry out their plans. Capture the town's low burglary rate due to the reduction in milk consumption, creating a funny and whimsical image. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Milk consumption and Burglaries in Vermont. 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: Psychedelic Whimsical illustration a funny image you would see on reddit a funny image you would see on reddit Futuristic
ChatGPT: a funny image you would see on reddit

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 Burglaries in Vermont, in the following situation: As the old saying goes, "got milk, got crime"... or in this case, less milk, less crime! It's utterly ridiculous, but here's the cheesy connection: turns out, when folks in Vermont cut back on their milk intake, they were simply too lactose intolerant to partake in nefarious activities. It seems that without the moo-tivation from calcium-rich dairy, the would-be burglars just didn't have the whey-thin to carry out their mischievous plans. Perhaps it's a case of "moo-dunnits" turning into "moo-don'ts"! So, in the end, it's safe to say that when milk consumption curdled, the burglary rates whey-ned down to a dairy low. Looks like the real missing "knead" was a good old-fashioned glass of milk to keep those burglars at bay! Who knew that a udderly bizarre correlation could milk so many laughs?. Keep the description simple.
ChatGPT: Picture a peaceful and picturesque Vermont town, where the sun sets behind rolling green hills. In one frame, a group of residents gathers in a cozy kitchen, sipping on glasses of fresh milk. Laughter fills the air as they enjoy the dairy goodness. Meanwhile, in another frame, would-be burglars, with mischievous glints in their eyes, are stymied in their attempts as they struggle with stomach discomfort, doubled over and unable to carry out their plans. The town's low burglary rate is evident, all thanks to the reduction in milk consumption.

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 funny image you would see on reddit ] and depicting this scene: Picture a peaceful and picturesque Vermont town, where the sun sets behind rolling green hills. In one frame, a group of residents gathers in a cozy kitchen, sipping on glasses of fresh milk. Laughter fills the air as they enjoy the dairy goodness. Meanwhile, in another frame, would-be burglars, with mischievous glints in their eyes, are stymied in their attempts as they struggle with stomach discomfort, doubled over and unable to carry out their plans. The town's low burglary rate is evident, all thanks to the reduction in milk consumption. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a peaceful and picturesque Vermont town at sunset, with rolling green hills in the background. In one frame, depict a cozy kitchen filled with laughing residents raising glasses of fresh milk. In another frame, show would-be burglars doubled over in stomach discomfort, unable to carry out their plans. Capture the town's low burglary rate due to the reduction in milk consumption, creating a funny and whimsical image.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} 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 Burglaries in Vermont to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

The Journal of Dairy Criminology

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 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 Burglaries in Vermont. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

[[ABSTRACT]]
This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.

While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!

Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.

As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the dairy industry's slogan "got milk?" has echoed through the decades, our research team couldn't help but wonder, "got crime?" Quite unexpectedly, our investigation into the relationship between milk consumption and burglaries in Vermont yielded some fascinating findings. It appears that dairy intake and criminal activities may be more intertwined than one might have previously suspected – a concept as ripe for puns as a wheel of cheddar!
We were utterly amused by the statistical correlation we unearthed, prompting one of our team members to quip, "I guess it's true what they say, 'you can't cry over spilt milk, but you can weep over stolen dairy!'" While the connection between calcium-rich beverages and illicit activities may seem far-fetched, the numbers tell a different tale, one that certainly demands further scrutiny.
Through rigorous analysis of data from the USDA and FBI Criminal Justice Information Services, spanning over three decades, we calculated a correlation coefficient of 0.9173518 and a p-value less than 0.01, indicating a strikingly significant relationship between milk consumption and burglaries. Our statistical model left us as surprised as a calf seeing a cow jump over the moon, yet the evidence was as solid as a fresh block of Vermont cheddar.
The initial reaction to our findings was akin to a farmer discovering a missing cow – bewildered, but ultimately compelled to make sense of the situation. If milk consumption is indeed associated with an increase in burglaries, it would be quite the bovine caper, reminiscent of a crime novel featuring a gang of dairy-loving bandits. Nonetheless, our research compels us to take this matter seriously, albeit with a healthy dash of humor.
In the pursuit of scientific discovery, it's crucial to milk every possible avenue for knowledge, even if some may appear unconventional. With that in mind, we invite our readers to delve into this udderly surprising connection between milk consumption and burglaries, and perhaps appreciate the levity of the situation with a dairy-themed dad joke or two along the whey.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Several studies have sought to unravel the enigmatic relationship between dietary habits and criminal behavior. In "Milk and Crime," Smith examines the potential link between milk consumption and various types of unlawful activities. Similarly, Doe explores the impact of dairy intake on deviant behavior in "Dairy and Misdemeanors." These works lay the groundwork for our investigation into the unusual connection between milk consumption and burglaries in Vermont.

One cannot discuss dairy-related phenomena without delving into the literary world. Books such as "The Big Moo: Lessons on Societal Misbehaviors" by Jones and "The Milk Manifesto: A Dairy's Daydream" by White provide valuable insights into the societal implications of milk consumption and its potential repercussions.

On a lighter note, fictional works such as "The Case of the Missing Milk Carton" by Agatha Christie and "Gouda is for Gangsters" by Sir Arthur Conan Doyle offer tantalizing narratives that, albeit not grounded in empirical evidence, tantalizingly moooove the imagination when considering dairy and crime.

In the realm of cinema, movies such as "Got Milk, Got Crime" and "The Fast and the Furriest: A Dairy Heist" have touched upon the intersection of dairy products and criminal activities, albeit in a more sensationalized manner. While these cinematic representations are far from scientific, they showcase the enduring intrigue of this peculiar connection to a wider audience.

Taking a more serious turn, we must acknowledge that the relationship between milk consumption and burglaries may seem utterly absurd at first glance. However, our research has shown that the statistical association is not to be milked lightly. After all, as the joke goes, "Why did the cow go to outer space? To visit the Milky Way." It appears that our findings have indeed led us to the bovine equivalent of the Milky Way, a mysterious yet alluring pathway to understanding the unexpected ties between dairy consumption and criminal mischief.

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 Burglaries in Vermont. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

[[ABSTRACT]]
This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.

While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!

Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.

As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

[[INTRODUCTION]]
As the dairy industry's slogan "got milk?" has echoed through the decades, our research team couldn't help but wonder, "got crime?" Quite unexpectedly, our investigation into the relationship between milk consumption and burglaries in Vermont yielded some fascinating findings. It appears that dairy intake and criminal activities may be more intertwined than one might have previously suspected – a concept as ripe for puns as a wheel of cheddar!
We were utterly amused by the statistical correlation we unearthed, prompting one of our team members to quip, "I guess it's true what they say, 'you can't cry over spilt milk, but you can weep over stolen dairy!'" While the connection between calcium-rich beverages and illicit activities may seem far-fetched, the numbers tell a different tale, one that certainly demands further scrutiny.
Through rigorous analysis of data from the USDA and FBI Criminal Justice Information Services, spanning over three decades, we calculated a correlation coefficient of 0.9173518 and a p-value less than 0.01, indicating a strikingly significant relationship between milk consumption and burglaries. Our statistical model left us as surprised as a calf seeing a cow jump over the moon, yet the evidence was as solid as a fresh block of Vermont cheddar.
The initial reaction to our findings was akin to a farmer discovering a missing cow – bewildered, but ultimately compelled to make sense of the situation. If milk consumption is indeed associated with an increase in burglaries, it would be quite the bovine caper, reminiscent of a crime novel featuring a gang of dairy-loving bandits. Nonetheless, our research compels us to take this matter seriously, albeit with a healthy dash of humor.
In the pursuit of scientific discovery, it's crucial to milk every possible avenue for knowledge, even if some may appear unconventional. With that in mind, we invite our readers to delve into this udderly surprising connection between milk consumption and burglaries, and perhaps appreciate the levity of the situation with a dairy-themed dad joke or two along the whey.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]
The methodology employed in this investigation was as robust and exacting as the process of milking a cow – thorough, systematic, and occasionally accompanied by the sound of gentle musing. Data on milk consumption in Vermont was extracted from the USDA's National Agricultural Statistics Service, documenting the volume of milk produced and distributed within the state from 1990 to 2021. Meanwhile, information on burglaries was sourced from the FBI's Uniform Crime Reporting (UCR) Program, encompassing reported incidents of unlawful entry or burglary over the same timeframe.

To establish the staggering connection between dairy intake and criminal activities, a series of complex statistical analyses reminiscent of a labyrinthine bovine maze were conducted. Firstly, the p-values were calculated using a multivariate regression analysis, allowing us to ascertain the significance of the relationship between milk consumption and burglaries while controlling for other pertinent variables. This analytical approach helped us untangle the convoluted interplay of factors, much like separating curds from whey.

Following this, a Pearson correlation coefficient was computed to measure the strength and direction of the linear relationship between milk consumption and burglaries. This quantitative exercise illuminated a correlation of 0.9173518, indicating an exceptionally strong association that is as conspicuous as a Holstein cow in a snow-covered field. The statistical significance of this finding, with a p-value less than 0.01, further reinforced the gravity of our dairy-themed revelation, prompting our team to exclaim, "It looks like the verdict is in – the proof is in the pudding, or perhaps, in the cheese!"

Concurrently, to guard against potential confounding variables and spurious correlations, a series of sensitivity analyses and robustness checks were performed. Sensitivity analyses evaluated the impact of variations in the measurement of milk consumption and burglaries, ensuring that our results were as robust as a sturdy milk churn. These methodological precautions were as essential as checking for rogue dairy products before embarking on a lactose-intolerant individual's grocery run.

Furthermore, a series of geographic and temporal sub-analyses were executed to discern whether the milk-burglary nexus exhibited consistent patterns across different regions and epochs within Vermont. The depth and breadth of our spatial-temporal scrutiny were as vast as the verdant pastures of the Green Mountain State, ensuring that no stone was left unturned in our quest for empirical elucidation.

In summation, the methodology harnessed in this investigation mirrored the intricate processes of cheese-making – a meticulous blend of precision, patience, and a dash of scientific flair. Through the amalgamation of data collection, multivariate regression analyses, correlation computations, sensitivity checks, and temporal sub-analyses, we endeavored to illuminate the surprising relationship between milk consumption and burglaries in Vermont, all while ensuring the punnet of knowledge remained free from metaphorical pungent odors.

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 Burglaries in Vermont. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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 0.9173518, r-squared of 0.8415344, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

[[ABSTRACT]]
This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.

While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!

Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.

As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the dairy industry's slogan "got milk?" has echoed through the decades, our research team couldn't help but wonder, "got crime?" Quite unexpectedly, our investigation into the relationship between milk consumption and burglaries in Vermont yielded some fascinating findings. It appears that dairy intake and criminal activities may be more intertwined than one might have previously suspected – a concept as ripe for puns as a wheel of cheddar!
We were utterly amused by the statistical correlation we unearthed, prompting one of our team members to quip, "I guess it's true what they say, 'you can't cry over spilt milk, but you can weep over stolen dairy!'" While the connection between calcium-rich beverages and illicit activities may seem far-fetched, the numbers tell a different tale, one that certainly demands further scrutiny.
Through rigorous analysis of data from the USDA and FBI Criminal Justice Information Services, spanning over three decades, we calculated a correlation coefficient of 0.9173518 and a p-value less than 0.01, indicating a strikingly significant relationship between milk consumption and burglaries. Our statistical model left us as surprised as a calf seeing a cow jump over the moon, yet the evidence was as solid as a fresh block of Vermont cheddar.
The initial reaction to our findings was akin to a farmer discovering a missing cow – bewildered, but ultimately compelled to make sense of the situation. If milk consumption is indeed associated with an increase in burglaries, it would be quite the bovine caper, reminiscent of a crime novel featuring a gang of dairy-loving bandits. Nonetheless, our research compels us to take this matter seriously, albeit with a healthy dash of humor.
In the pursuit of scientific discovery, it's crucial to milk every possible avenue for knowledge, even if some may appear unconventional. With that in mind, we invite our readers to delve into this udderly surprising connection between milk consumption and burglaries, and perhaps appreciate the levity of the situation with a dairy-themed dad joke or two along the whey.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The correlation analysis between milk consumption and burglaries in Vermont revealed a remarkably strong positive correlation of 0.9173518 over the period of 1990 to 2021. This result suggests a striking relationship between these seemingly unrelated variables, leaving our research team utterly bewildered yet utterly amused. It seems that when it comes to milk and mischief, there's more than meets the "I"!

The r-squared value of 0.8415344 further supports the robustness of the association between milk consumption and burglaries, indicating that approximately 84.15% of the variance in burglary rates can be explained by variations in milk consumption. This high explanatory power underscores the significance of our findings, much like a cowbell ringing through a quiet pasture.

The p-value of less than 0.01 indicates that the observed correlation is highly statistically significant, reinforcing the credibility of the relationship we uncovered. This result is as conclusive as the final dregs of milk in a churn – there's no denying the connection between dairy indulgence and illicit activities in the Green Mountain State.

In Figure 1, the scatterplot visually portrays the robust correlation between milk consumption and burglaries, painting a clear picture of the positive linear relationship, much like a dairy-themed portrait.

Amidst these compelling statistical revelations, a relevant dad joke springs to mind: "Why did the milk go to school? Because it wanted to be pasteurized!" In a similarly unexpected manner, our research has revealed an education in the unlikely relationship between dairy products and criminal behavior.

In light of these findings, it is evident that the seemingly whimsical link between milk consumption and burglaries warrants further exploration and deliberation. The statistical evidence, much like a glass of milk, is difficult to refute, and it is imperative to approach this surprising correlation with both scientific rigor and a sense of levity.

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 Burglaries in Vermont. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

[[ABSTRACT]]
This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.

While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!

Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.

As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

[[LITERATURE REVIEW]]
Several studies have sought to unravel the enigmatic relationship between dietary habits and criminal behavior. In "Milk and Crime," Smith examines the potential link between milk consumption and various types of unlawful activities. Similarly, Doe explores the impact of dairy intake on deviant behavior in "Dairy and Misdemeanors." These works lay the groundwork for our investigation into the unusual connection between milk consumption and burglaries in Vermont.
One cannot discuss dairy-related phenomena without delving into the literary world. Books such as "The Big Moo: Lessons on Societal Misbehaviors" by Jones and "The Milk Manifesto: A Dairy's Daydream" by White provide valuable insights into the societal implications of milk consumption and its potential repercussions.
On a lighter note, fictional works such as "The Case of the Missing Milk Carton" by Agatha Christie and "Gouda is for Gangsters" by Sir Arthur Conan Doyle offer tantalizing narratives that, albeit not grounded in empirical evidence, tantalizingly moooove the imagination when considering dairy and crime.
In the realm of cinema, movies such as "Got Milk, Got Crime" and "The Fast and the Furriest: A Dairy Heist" have touched upon the intersection of dairy products and criminal activities, albeit in a more sensationalized manner. While these cinematic representations are far from scientific, they showcase the enduring intrigue of this peculiar connection to a wider audience.
Taking a more serious turn, we must acknowledge that the relationship between milk consumption and burglaries may seem utterly absurd at first glance. However, our research has shown that the statistical association is not to be milked lightly. After all, as the joke goes, "Why did the cow go to outer space? To visit the Milky Way." It appears that our findings have indeed led us to the bovine equivalent of the Milky Way, a mysterious yet alluring pathway to understanding the unexpected ties between dairy consumption and criminal mischief.

[[RESULTS]]
The correlation analysis between milk consumption and burglaries in Vermont revealed a remarkably strong positive correlation of 0.9173518 over the period of 1990 to 2021. This result suggests a striking relationship between these seemingly unrelated variables, leaving our research team utterly bewildered yet utterly amused. It seems that when it comes to milk and mischief, there's more than meets the "I"!
The r-squared value of 0.8415344 further supports the robustness of the association between milk consumption and burglaries, indicating that approximately 84.15% of the variance in burglary rates can be explained by variations in milk consumption. This high explanatory power underscores the significance of our findings, much like a cowbell ringing through a quiet pasture.
The p-value of less than 0.01 indicates that the observed correlation is highly statistically significant, reinforcing the credibility of the relationship we uncovered. This result is as conclusive as the final dregs of milk in a churn – there's no denying the connection between dairy indulgence and illicit activities in the Green Mountain State.
In Figure 1, the scatterplot visually portrays the robust correlation between milk consumption and burglaries, painting a clear picture of the positive linear relationship, much like a dairy-themed portrait.
Amidst these compelling statistical revelations, a relevant dad joke springs to mind: "Why did the milk go to school? Because it wanted to be pasteurized!" In a similarly unexpected manner, our research has revealed an education in the unlikely relationship between dairy products and criminal behavior.
In light of these findings, it is evident that the seemingly whimsical link between milk consumption and burglaries warrants further exploration and deliberation. The statistical evidence, much like a glass of milk, is difficult to refute, and it is imperative to approach this surprising correlation with both scientific rigor and a sense of levity.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unveiled an intriguing and robust association between milk consumption and burglaries in Vermont, substantiating the whimsical leanings of prior research in this domain. The substantial positive correlation coefficient of 0.9173518, accompanied by a strikingly low p-value, has left our research team utterly convinced of the statistical significance of this udderly unexpected relationship. It seems that much like a stealthy cat burglar, the connection between milk and mischief has been sneaking past us all along!

Our findings align with the earlier works of Smith in "Milk and Crime" and Doe in "Dairy and Misdemeanors," both of which hinted at the potential link between dairy intake and unlawful activities. It appears that the inquiry into this curious connection is not to be taken lightly, much like the weight of a Holstein's hooves on a dairy farm. Our results have indeed lent credence to the notion that milk consumption may have ramifications beyond lactose tolerance, eliciting a chuckle as unexpected as finding a cow in the produce section.

The high explanatory power of the correlation, with an r-squared value of 0.8415344, reinforces the robustness of the association, much like the sturdiness of a dairy barn in a summer storm. Furthermore, the visual representation of the positive linear relationship in the scatterplot, akin to a picturesque bovine landscape, provides a compelling visual narrative of the milk-burglary linkage.

In line with our earlier tongue-in-cheek references to bovine humor, it seems that this investigation has indeed taken us on a scientific journey through the Milky Way of statistical revelations. As we consider the implications of our findings, one cannot help but be reminded of the age-old question: "What do you call a cow who has just given birth? Decalfinated!" In a similar vein, our research has decaffeinated any doubts about the unusual link between dairy consumption and criminal activities, offering food for thought and fodder for future investigations.

In response to the unexpected nature of our results, we remind our esteemed colleagues that the world of statistical inquiry is just as unpredictable as a herd of cows on a moonlit night. Nevertheless, with the evidence at hand, it is clear that the interplay between milk consumption and burglaries in Vermont merits continued scholarly attention. As with any research endeavor, our findings should be taken with a grain of salt – or perhaps a pinch of cheesy humor – as we mull over the intriguing implications of this dairy-fueled mystery.

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 Burglaries in Vermont. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. 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]]
The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

[[ABSTRACT]]
This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.

While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!

Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.

As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

[[INTRDUCTION]]
As the dairy industry's slogan "got milk?" has echoed through the decades, our research team couldn't help but wonder, "got crime?" Quite unexpectedly, our investigation into the relationship between milk consumption and burglaries in Vermont yielded some fascinating findings. It appears that dairy intake and criminal activities may be more intertwined than one might have previously suspected – a concept as ripe for puns as a wheel of cheddar!
We were utterly amused by the statistical correlation we unearthed, prompting one of our team members to quip, "I guess it's true what they say, 'you can't cry over spilt milk, but you can weep over stolen dairy!'" While the connection between calcium-rich beverages and illicit activities may seem far-fetched, the numbers tell a different tale, one that certainly demands further scrutiny.
Through rigorous analysis of data from the USDA and FBI Criminal Justice Information Services, spanning over three decades, we calculated a correlation coefficient of 0.9173518 and a p-value less than 0.01, indicating a strikingly significant relationship between milk consumption and burglaries. Our statistical model left us as surprised as a calf seeing a cow jump over the moon, yet the evidence was as solid as a fresh block of Vermont cheddar.
The initial reaction to our findings was akin to a farmer discovering a missing cow – bewildered, but ultimately compelled to make sense of the situation. If milk consumption is indeed associated with an increase in burglaries, it would be quite the bovine caper, reminiscent of a crime novel featuring a gang of dairy-loving bandits. Nonetheless, our research compels us to take this matter seriously, albeit with a healthy dash of humor.
In the pursuit of scientific discovery, it's crucial to milk every possible avenue for knowledge, even if some may appear unconventional. With that in mind, we invite our readers to delve into this udderly surprising connection between milk consumption and burglaries, and perhaps appreciate the levity of the situation with a dairy-themed dad joke or two along the whey.

[[RESULTS]]
The correlation analysis between milk consumption and burglaries in Vermont revealed a remarkably strong positive correlation of 0.9173518 over the period of 1990 to 2021. This result suggests a striking relationship between these seemingly unrelated variables, leaving our research team utterly bewildered yet utterly amused. It seems that when it comes to milk and mischief, there's more than meets the "I"!
The r-squared value of 0.8415344 further supports the robustness of the association between milk consumption and burglaries, indicating that approximately 84.15% of the variance in burglary rates can be explained by variations in milk consumption. This high explanatory power underscores the significance of our findings, much like a cowbell ringing through a quiet pasture.
The p-value of less than 0.01 indicates that the observed correlation is highly statistically significant, reinforcing the credibility of the relationship we uncovered. This result is as conclusive as the final dregs of milk in a churn – there's no denying the connection between dairy indulgence and illicit activities in the Green Mountain State.
In Figure 1, the scatterplot visually portrays the robust correlation between milk consumption and burglaries, painting a clear picture of the positive linear relationship, much like a dairy-themed portrait.
Amidst these compelling statistical revelations, a relevant dad joke springs to mind: "Why did the milk go to school? Because it wanted to be pasteurized!" In a similarly unexpected manner, our research has revealed an education in the unlikely relationship between dairy products and criminal behavior.
In light of these findings, it is evident that the seemingly whimsical link between milk consumption and burglaries warrants further exploration and deliberation. The statistical evidence, much like a glass of milk, is difficult to refute, and it is imperative to approach this surprising correlation with both scientific rigor and a sense of levity.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our investigation has yielded a remarkably strong positive correlation of 0.9173518 between milk consumption and burglaries in Vermont over the span of three decades. The relationship is as clear as a glass of fresh milk, and the statistical evidence is stronger than a lactose-intolerant person's aversion to dairy. It seems that when it comes to crime and calcium, there's an unexpected bond that simply can't be curdled!

The high explanatory power of approximately 84.15% reinforces the robustness of this association, indicating that the variations in burglary rates can be largely explained by fluctuations in milk consumption. It's as if the crime rates are saying, "You want the truth? You can't handle the proof!"

Moreover, the p-value of less than 0.01 solidifies the statistical significance, leaving little room for udder interpretation. The evidence stands as firm as a well-constructed fence around a pasture – there's no escaping the correlation between dairy delight and unlawful deeds.

As we ponder the implications of our findings, a dairy-themed dad joke comes to mind: "What do you call a cow who plays the guitar? A moo-sician!" Similarly, our research has struck a surprising chord, revealing the unexplored symphony of milk consumption and criminal activity in the Green Mountain State.

Therefore, it is with great confidence that we assert no further research is needed in this area. Our findings speak louder than a herd of cows at feeding time, and it's time to milk this topic for all it's worth. After all, when it comes to unexpected connections, this research is truly udderly unparalleled!

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Dairy Criminology

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Bovine Behavior 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 The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont with an abstract of This research paper delves into the intriguing and, dare we say, utterly unexpected relationship between milk consumption and burglaries in the picturesque state of Vermont. Leveraging data from the USDA and FBI Criminal Justice Information Services spanning from 1990 to 2021, a correlation coefficient of 0.9173518 and p < 0.01 was calculated, shedding light on this seemingly whimsical yet statistically significant connection.
While pondering the peculiar association between dairy intake and criminal activities, our research team was equally bemused and enthused by the bond we uncovered – a relationship that, much like a cow's sense of humor, is not to be milked lightly!
Amidst the empirical revelations, a notable dad joke surfaced: "Why don't cows ever have any money? Because the farmers milk them dry!" It seems that the bovine world has been sending us subtle messages all along.
As we dissect the statistical milky way that unraveled before us, we encourage our esteemed readers to feast upon this research with an open mind, perhaps over a glass of milk – but be sure to keep a vigilant eye on the homestead. After all, as our findings suggest, the abundant consumption of dairy products may just be udderly related to a surge in burglaries in the Green Mountain State.

ChatGPT:

"milk consumption criminal activities correlation", "dairy intake burglary relationship", "Vermont burglaries milk consumption connection", "USDA FBI data correlation milk consumption crimes", "dairy consumption crime statistics Vermont", "milk consumption burglary rates Vermont", "dairy products crime correlation study", "relationship between milk consumption and theft in Vermont", "correlation between dairy intake and criminal activities", "milk consumption statistical significance burglaries"

*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

Burglaries in Vermont
Detailed data title: The burglary rate per 100,000 residents in Vermont
Source: FBI Criminal Justice Information Services
See what else correlates with Burglaries in Vermont

Correlation r = 0.9173518 (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 = 0.8415344 (Coefficient of determination)
This means 84.2% of the change in the one variable (i.e., Burglaries in Vermont) 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 1.6E-13.^Show 0.0000000000001562173691664529
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.92 in 1.6E-11% of random cases. Said differently, if you correlated 6,401,336,838,124 random variables^Note You don't actually need 6 trillion 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, ^Note 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.

[ 0.84, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Milk consumption (Pounds per person)	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
Burglaries in Vermont (Burglary rate)	1087.3	1020.1	825.6	874.3	736.9	760.9	673	613.1	671.1	595.7	575	513.9	566	487.1	552.9	511.7	551.8	515.1	565.8	558.3	534.9	612.5	667.6	534.7	333.8	324.9	302.2	311.4	239.6	206.1	154.2	181.8

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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.
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. ^Note 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. ^{Show the steps to do this.} 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([1087.3,1020.1,825.6,874.3,736.9,760.9,673,613.1,671.1,595.7,575,513.9,566,487.1,552.9,511.7,551.8,515.1,565.8,558.3,534.9,612.5,667.6,534.7,333.8,324.9,302.2,311.4,239.6,206.1,154.2,181.8,])
array_1_name = "Milk consumption"
array_2_name = "Burglaries in Vermont"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Milk consumption
Line chart for only Burglaries in Vermont
AI-generated correlation image
The spurious research paper: The Milky Way: An Udderly Surprising Connection Between Milk Consumption and Burglaries in Vermont

View another random correlation

How fun was this correlation?

Your correlation inspection deserves a standing ovation!

Correlation ID: 2427 · Black Variable ID: 554 · Red Variable ID: 20124


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: