Spurious correlation #3,307 · 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 Tennessee. 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 Tennessee. The chart goes from 1990 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

Fewer late-night cereal cravings led to less clattering of spoons in the dark, inadvertently creating a neighborhood watch system as sleep-deprived individuals patrolled their kitchens. Turns out, it’s udderly hard to milk a situation for all it’s worth when the moo-tivation is lacking.

^{Show image generation prompt} Model: dalle-3
Prompt: Generate a pop art-style depiction of a deserted street in Tennessee, with empty milk cartons strewn about. In the scene, a group of defeated burglars are scattered around the milk cartons, frozen in disbelief. A getaway car is parked nearby. Onlookers gossip about the dwindling milk supply while holding their stomachs in discomfort, hinting that lactose intolerance is on the rise in the area. Use bold and contrasting colors to create a visually striking and vibrant pop art representation of the scene. 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 Tennessee. 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: Macabre Steampunk Pop art 3D Pixar Style Art nouveau
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 Burglaries in Tennessee, in the following situation: As the milk supply dried up, so did the burglars' ability to make a clean getaway. With lactose intolerance on the rise, no one could stomach the thought of milking the situation for all it's worth. The lack of moo juice left the criminals feeling utterly defeated, and they simply couldn't dairy to commit any more crimes.. Keep the description simple.
ChatGPT: In Tennessee, empty milk cartons are strewn across a deserted street, and a group of defeated burglars are scattered around them. The culprits stand frozen in disbelief, their getaway car parked nearby. Onlookers gossip about the dwindling milk supply while holding their stomachs in discomfort, hinting that lactose intolerance is on the rise in the area.

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 Tennessee, empty milk cartons are strewn across a deserted street, and a group of defeated burglars are scattered around them. The culprits stand frozen in disbelief, their getaway car parked nearby. Onlookers gossip about the dwindling milk supply while holding their stomachs in discomfort, hinting that lactose intolerance is on the rise in the area. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a pop art-style depiction of a deserted street in Tennessee, with empty milk cartons strewn about. In the scene, a group of defeated burglars are scattered around the milk cartons, frozen in disbelief. A getaway car is parked nearby. Onlookers gossip about the dwindling milk supply while holding their stomachs in discomfort, hinting that lactose intolerance is on the rise in the area. Use bold and contrasting colors to create a visually striking and vibrant pop art representation of the scene.

*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 Tennessee to decrease.

AI academic paper

(Because p < 0.01)

Milk and Crime: A Tennessee Time

Journal of Dairy Delinquency

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 Tennessee. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
Milk and Crime: A Tennessee Time

[[ABSTRACT]]
The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between dietary habits and criminal behavior has long been a topic of interest in the fields of criminology and public health. While the old saying "you are what you eat" might be a bit of a stretch when it comes to crime, it is worth exploring whether there is any merit to the idea that one's choice of beverage could be linked to unlawful activities. In this study, we delve into the "udder"ly fascinating correlation between milk consumption and burglaries in Tennessee, aiming to shed light on this unusual association.
As researchers, we often find ourselves in the unique position of un"herd"ing unexpected relationships in data. It is not uncommon for statistical analysis to produce findings that seem quite "moo"ving, even if they defy conventional wisdom or the laws of causality. Our investigation into the consumption of milk and its potential impact on crime rates in Tennessee is no exception. While it may sound like a "moo-t" point to some, our findings paint a picture that is both thought-provoking and, dare we say, "legendairy."
Taking a closer look at the data, we encountered a correlation that was "milk-iously" strong, with a coefficient of 0.9613492 and a p-value less than 0.01. This robust relationship was quite "udderly" unexpected, prompting us to consider whether there might be a "creamy" connection between the two variables. While we hesitate to jump to "conclu-sips," our findings certainly warrant further exploration and may lead to a "bovine" revelation in the field of criminology.
It is important to acknowledge that correlation does not imply causation, and we must tread carefully when interpreting these results. The notion that milk consumption could be associated with an increased likelihood of burglaries may seem "lactose-intolerable" to some. However, as researchers, it is our duty to approach the data with an open mind and a willingness to entertain even the most "moo-t" hypotheses. After all, in the world of statistics, sometimes the un"herd" of cannot be dismissed outright.
In light of these findings, we invite our readers to consider the potential implications of a link between milk consumption and criminal behavior. While the idea of a "moo-tive" for burglary may seem far-fetched, our research suggests that there may be more to the old adage "got milk" than meets the eye. As we endeavor to understand the mechanisms at play, we are left pondering the age-old question: Is there something inherently "dairy-ious" about the allure of a glass of milk that leads individuals down a nefarious path? We cannot help but wonder if, in the world of crime, the "milk of human kindness" might be more closely intertwined with the "cereal" mischief than we previously imagined.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their study, Smith and Doe (2010) investigate the potential link between dietary habits and criminal behavior, focusing specifically on the consumption of dairy products and property crimes. Their analysis reveals a moderate positive correlation between milk intake and burglaries in a sample of U.S. states, prompting further exploration of this unexpected association. Similarly, Jones et al. (2015) examine the relationship between calcium-rich beverages and antisocial activities, finding intriguing patterns that raise questions about the role of milk consumption in deviant behavior. These initial findings lay the groundwork for our investigation into the connection between milk consumption and burglaries in Tennessee.

Turning to non-fiction publications, "The Big Moo: Stop Trying to Be Perfect and Start Being Remarkable" by Seth Godin presents insights into the nature of human behavior and societal norms, offering a fresh perspective on the "moo-ving" forces that drive individuals to engage in criminal activities. Furthermore, "Got Milked? The Great Dairy Deception and Why You'll Thrive Without Milk" by Alissa Hamilton explores the cultural significance of milk consumption and its potential ramifications, shedding light on the complex dynamics at play within the dairy industry.

On a more whimsical note, the fiction novel "The Cows" by Dawn O'Porter takes a satirical view of societal expectations and unconventional choices, drawing parallels to the "udderly" peculiar correlation between milk consumption and burglaries in our study. Likewise, "Moo-Moo and the Three Witches" by Myller and Bednar depicts magical shenanigans with a bovine twist, offering a lighthearted parallel to the enigmatic relationship between milk and mischief.

Drawing inspiration from the world of board games, the classic title "Clue" provides an allegorical representation of the investigative process, reminding researchers that uncovering unexpected correlations requires both keen observation and a willingness to entertain seemingly outlandish possibilities. Similarly, "Catan: Dairy Edition" playfully integrates the concept of resource management with the nuances of agricultural production, serving as a metaphor for the intricate dynamics underlying our exploration of dairy consumption and criminal behavior.

As we traverse the diverse landscape of literature and entertainment, we are reminded that the inexplicable link between milk consumption and burglaries in Tennessee continues to captivate the imagination, prompting us to ponder the intricate interplay between dietary choices and unlawful activities. In pondering these peculiar parallels, we contemplate the timeless question: If a cow commits a crime, would it be considered a "moo-dunnit"?

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 Tennessee. 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]]
Milk and Crime: A Tennessee Time

[[ABSTRACT]]
The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

[[INTRODUCTION]]
The relationship between dietary habits and criminal behavior has long been a topic of interest in the fields of criminology and public health. While the old saying "you are what you eat" might be a bit of a stretch when it comes to crime, it is worth exploring whether there is any merit to the idea that one's choice of beverage could be linked to unlawful activities. In this study, we delve into the "udder"ly fascinating correlation between milk consumption and burglaries in Tennessee, aiming to shed light on this unusual association.
As researchers, we often find ourselves in the unique position of un"herd"ing unexpected relationships in data. It is not uncommon for statistical analysis to produce findings that seem quite "moo"ving, even if they defy conventional wisdom or the laws of causality. Our investigation into the consumption of milk and its potential impact on crime rates in Tennessee is no exception. While it may sound like a "moo-t" point to some, our findings paint a picture that is both thought-provoking and, dare we say, "legendairy."
Taking a closer look at the data, we encountered a correlation that was "milk-iously" strong, with a coefficient of 0.9613492 and a p-value less than 0.01. This robust relationship was quite "udderly" unexpected, prompting us to consider whether there might be a "creamy" connection between the two variables. While we hesitate to jump to "conclu-sips," our findings certainly warrant further exploration and may lead to a "bovine" revelation in the field of criminology.
It is important to acknowledge that correlation does not imply causation, and we must tread carefully when interpreting these results. The notion that milk consumption could be associated with an increased likelihood of burglaries may seem "lactose-intolerable" to some. However, as researchers, it is our duty to approach the data with an open mind and a willingness to entertain even the most "moo-t" hypotheses. After all, in the world of statistics, sometimes the un"herd" of cannot be dismissed outright.
In light of these findings, we invite our readers to consider the potential implications of a link between milk consumption and criminal behavior. While the idea of a "moo-tive" for burglary may seem far-fetched, our research suggests that there may be more to the old adage "got milk" than meets the eye. As we endeavor to understand the mechanisms at play, we are left pondering the age-old question: Is there something inherently "dairy-ious" about the allure of a glass of milk that leads individuals down a nefarious path? We cannot help but wonder if, in the world of crime, the "milk of human kindness" might be more closely intertwined with the "cereal" mischief than we previously imagined.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To examine the relationship between milk consumption and burglaries in Tennessee, our research employed a multi-faceted approach, utilizing data spanning from 1990 to 2021. The data utilized in this study was primarily sourced from the USDA, with additional information obtained from the FBI Criminal Justice Information Services.

The first step in our methodology involved analyzing the per capita milk consumption in Tennessee over the specified time period. This data provided us with a comprehensive overview of milk intake, allowing us to assess any potential fluctuations and trends in consumption. In essence, we endeavored to milk the data for all it was worth.

Next, we turned our attention to the incidence of burglaries in Tennessee during the same timeframe. This involved poring over crime statistics, identifying patterns, and looking for any correlations with the patterns observed in milk consumption. This phase of the research was undoubtedly a "grate" undertaking, as we sought to slice through the data to extract meaningful insights.

Having gathered the relevant data, we proceeded to conduct a series of regression analyses to ascertain the statistical relationship between milk consumption and burglaries. We employed various models to tease out any potential associations, making sure to "curdle" any assumptions that could compromise the rigor of our analysis.

Furthermore, in an effort to account for potential confounding variables, we conducted a thorough review of socioeconomic indicators, population demographics, and other contextual factors that could influence both milk consumption and burglary rates. This exploration helped to ensure that our findings were not merely a case of spurious correlation, but a robust reflection of the interplay between milk and mischief in Tennessee.

In order to ensure the validity and reliability of our findings, we also undertook sensitivity analyses and cross-validated our models using different time periods and subsets of the data. This process ensured that our results were not merely a "flash in the pan," but rather a consistent pattern deserving of exploration.

Finally, we applied various statistical tests to quantify the strength of the relationship between milk consumption and burglaries, producing a correlation coefficient that was "moo-rely" astonishing and a p-value that was quite "udderly" convincing.

In the words of the great Louis Pasteur, "In the field of observation, chance favors only the prepared mind." We trust that our rigorous methodology and thorough analysis have positioned us to present these findings with resounding confidence, laying the groundwork for future research and contemplation into the curious connection between milk and 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 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 Tennessee. 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 0.9613492, r-squared of 0.9241923, 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 Crime: A Tennessee Time

[[ABSTRACT]]
The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between dietary habits and criminal behavior has long been a topic of interest in the fields of criminology and public health. While the old saying "you are what you eat" might be a bit of a stretch when it comes to crime, it is worth exploring whether there is any merit to the idea that one's choice of beverage could be linked to unlawful activities. In this study, we delve into the "udder"ly fascinating correlation between milk consumption and burglaries in Tennessee, aiming to shed light on this unusual association.
As researchers, we often find ourselves in the unique position of un"herd"ing unexpected relationships in data. It is not uncommon for statistical analysis to produce findings that seem quite "moo"ving, even if they defy conventional wisdom or the laws of causality. Our investigation into the consumption of milk and its potential impact on crime rates in Tennessee is no exception. While it may sound like a "moo-t" point to some, our findings paint a picture that is both thought-provoking and, dare we say, "legendairy."
Taking a closer look at the data, we encountered a correlation that was "milk-iously" strong, with a coefficient of 0.9613492 and a p-value less than 0.01. This robust relationship was quite "udderly" unexpected, prompting us to consider whether there might be a "creamy" connection between the two variables. While we hesitate to jump to "conclu-sips," our findings certainly warrant further exploration and may lead to a "bovine" revelation in the field of criminology.
It is important to acknowledge that correlation does not imply causation, and we must tread carefully when interpreting these results. The notion that milk consumption could be associated with an increased likelihood of burglaries may seem "lactose-intolerable" to some. However, as researchers, it is our duty to approach the data with an open mind and a willingness to entertain even the most "moo-t" hypotheses. After all, in the world of statistics, sometimes the un"herd" of cannot be dismissed outright.
In light of these findings, we invite our readers to consider the potential implications of a link between milk consumption and criminal behavior. While the idea of a "moo-tive" for burglary may seem far-fetched, our research suggests that there may be more to the old adage "got milk" than meets the eye. As we endeavor to understand the mechanisms at play, we are left pondering the age-old question: Is there something inherently "dairy-ious" about the allure of a glass of milk that leads individuals down a nefarious path? We cannot help but wonder if, in the world of crime, the "milk of human kindness" might be more closely intertwined with the "cereal" mischief than we previously imagined.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The time period from 1990 to 2021 revealed a striking correlation coefficient of 0.9613492 between milk consumption and burglaries in Tennessee, indicating a remarkably strong positive relationship. This result is "moo-ving" in its magnitude, suggesting that as milk consumption increased, so did the occurrence of burglaries in the state. The r-squared value of 0.9241923 further underscores the robustness of this association, offering substantial support for the notion that there is more than meets the eye behind the innocuous act of drinking milk. The p-value of less than 0.01 solidifies the statistical significance of this correlation, rendering it a finding that cannot be dismissed as mere "cow-incidence."

The figure (Fig. 1) accompanying this analysis visually depicts the clear positive relationship between milk consumption and burglaries in Tennessee. Much like a glass of milk, the correlation is crystal clear, leaving little room for doubt. However, one cannot resist the urge to ask: "Is this what they meant by 'don't cry over spilled milk'?"

While the nature of causation remains a conundrum, the data indisputably point to a noteworthy connection between these seemingly unrelated variables. It seems that in the realm of statistical relationships, sometimes the answers are hidden in the unlikeliest of places – much like finding a needle in a haystack. This leads us to contemplate whether, in the grand scheme of things, the phrase "milk it for all it's worth" takes on a whole new significance in the context of criminal behavior.

As researchers, we are reminded that correlation does not imply causation, and to jump to conclusions would be as reckless as milking a wild cow. Nevertheless, the implications of our findings are nothing to be scoffed at. The unexpected interplay of milk consumption and burglaries in Tennessee raises a myriad of questions, not the least of which is whether we have overlooked a dairy serious factor in understanding criminal behavior. After all, when it comes to research, sometimes the only way out is through – or in this case, "moo."

In conclusion, our findings shed light on a perplexing association that challenges conventional wisdom and beckons further exploration. As we embark on the next phase of inquiry, we are reminded that in the world of research, the unexpected can be both perplexing and "udderly" intriguing. For now, the question lingers: do we dare to milk this connection for all it's worth, or should we simply raise a toast to the curious mysteries of statistical relationships?

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.You draft 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 Tennessee. 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]]
Milk and Crime: A Tennessee Time

[[ABSTRACT]]
The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

[[LITERATURE REVIEW]]
In their study, Smith and Doe (2010) investigate the potential link between dietary habits and criminal behavior, focusing specifically on the consumption of dairy products and property crimes. Their analysis reveals a moderate positive correlation between milk intake and burglaries in a sample of U.S. states, prompting further exploration of this unexpected association. Similarly, Jones et al. (2015) examine the relationship between calcium-rich beverages and antisocial activities, finding intriguing patterns that raise questions about the role of milk consumption in deviant behavior. These initial findings lay the groundwork for our investigation into the connection between milk consumption and burglaries in Tennessee.
Turning to non-fiction publications, "The Big Moo: Stop Trying to Be Perfect and Start Being Remarkable" by Seth Godin presents insights into the nature of human behavior and societal norms, offering a fresh perspective on the "moo-ving" forces that drive individuals to engage in criminal activities. Furthermore, "Got Milked? The Great Dairy Deception and Why You'll Thrive Without Milk" by Alissa Hamilton explores the cultural significance of milk consumption and its potential ramifications, shedding light on the complex dynamics at play within the dairy industry.
On a more whimsical note, the fiction novel "The Cows" by Dawn O'Porter takes a satirical view of societal expectations and unconventional choices, drawing parallels to the "udderly" peculiar correlation between milk consumption and burglaries in our study. Likewise, "Moo-Moo and the Three Witches" by Myller and Bednar depicts magical shenanigans with a bovine twist, offering a lighthearted parallel to the enigmatic relationship between milk and mischief.
Drawing inspiration from the world of board games, the classic title "Clue" provides an allegorical representation of the investigative process, reminding researchers that uncovering unexpected correlations requires both keen observation and a willingness to entertain seemingly outlandish possibilities. Similarly, "Catan: Dairy Edition" playfully integrates the concept of resource management with the nuances of agricultural production, serving as a metaphor for the intricate dynamics underlying our exploration of dairy consumption and criminal behavior.
As we traverse the diverse landscape of literature and entertainment, we are reminded that the inexplicable link between milk consumption and burglaries in Tennessee continues to captivate the imagination, prompting us to ponder the intricate interplay between dietary choices and unlawful activities. In pondering these peculiar parallels, we contemplate the timeless question: If a cow commits a crime, would it be considered a "moo-dunnit"?

[[RESULTS]]
The time period from 1990 to 2021 revealed a striking correlation coefficient of 0.9613492 between milk consumption and burglaries in Tennessee, indicating a remarkably strong positive relationship. This result is "moo-ving" in its magnitude, suggesting that as milk consumption increased, so did the occurrence of burglaries in the state. The r-squared value of 0.9241923 further underscores the robustness of this association, offering substantial support for the notion that there is more than meets the eye behind the innocuous act of drinking milk. The p-value of less than 0.01 solidifies the statistical significance of this correlation, rendering it a finding that cannot be dismissed as mere "cow-incidence."
The figure (Fig. 1) accompanying this analysis visually depicts the clear positive relationship between milk consumption and burglaries in Tennessee. Much like a glass of milk, the correlation is crystal clear, leaving little room for doubt. However, one cannot resist the urge to ask: "Is this what they meant by 'don't cry over spilled milk'?"
While the nature of causation remains a conundrum, the data indisputably point to a noteworthy connection between these seemingly unrelated variables. It seems that in the realm of statistical relationships, sometimes the answers are hidden in the unlikeliest of places – much like finding a needle in a haystack. This leads us to contemplate whether, in the grand scheme of things, the phrase "milk it for all it's worth" takes on a whole new significance in the context of criminal behavior.
As researchers, we are reminded that correlation does not imply causation, and to jump to conclusions would be as reckless as milking a wild cow. Nevertheless, the implications of our findings are nothing to be scoffed at. The unexpected interplay of milk consumption and burglaries in Tennessee raises a myriad of questions, not the least of which is whether we have overlooked a dairy serious factor in understanding criminal behavior. After all, when it comes to research, sometimes the only way out is through – or in this case, "moo."
In conclusion, our findings shed light on a perplexing association that challenges conventional wisdom and beckons further exploration. As we embark on the next phase of inquiry, we are reminded that in the world of research, the unexpected can be both perplexing and "udderly" intriguing. For now, the question lingers: do we dare to milk this connection for all it's worth, or should we simply raise a toast to the curious mysteries of statistical relationships?

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of our study provide compelling support for the previously hypothesized connection between milk consumption and burglaries in Tennessee. Our robust correlation coefficient of 0.9613492 aligns with the moderate positive correlation observed in prior research by Smith and Doe (2010) and Jones et al. (2015). These results suggest that the "got milk" phenomenon may indeed imply "got mischief." It appears that the "dairy" implications of dietary choices on criminal behavior cannot be brushed aside as mere coincidence. One cannot help but ponder: if a burglar gets caught, do they cry over spilled milk?

The literature review, while featuring some less conventional sources such as "The Cows" by Dawn O'Porter and "Moo-Moo and the Three Witches" by Myller and Bednar, playfully drew parallels to our earnest investigation, reinforcing the unexpected nature of this correlation. The whimsical likening of our study to the board game "Clue" and the concept of "Catan: Dairy Edition" reflects the necessity for researchers to entertain seemingly outlandish possibilities. After all, who would have thought that the dairy aisle and crime would have anything in common?

The r-squared value of 0.9241923 further emphasizes the strong relationship between milk consumption and burglaries in Tennessee. This statistical robustness, combined with a p-value of less than 0.01, points to a notable association that cannot be overlooked. It seems that in statistical relationships, sometimes the answers truly are hidden in the unlikeliest of places – not unlike finding a needle in a haystack. It brings to mind the question: Is this what they meant by "don't cry over spilled milk"?

It is important to remember that correlation does not imply causation, and that researchers must not jump to conclusions as recklessly as milking a wild cow. Nevertheless, the implications of our findings raise a dairy serious challenge to conventional understanding of criminal behavior. Perhaps there is more to the phrase "milk it for all it's worth" than previously thought. As we ponder the enigmatic relationship between milk consumption and burglaries, we are reminded that sometimes, the only way out is through – or, in this case, "moo."

While we have "moo-ved" closer to understanding the association between milk consumption and burglaries in Tennessee, our study naturally gives rise to further questions and avenues for exploration. Nonetheless, for now, we must raise a toast to the curious mysteries of statistical relationships and dare to milk this connection for all it's worth. After all, in the world of research, the unexpected can be both perplexing and "udderly" intriguing.

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 Tennessee. 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]]
Milk and Crime: A Tennessee Time

[[ABSTRACT]]
The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

[[INTRDUCTION]]
The relationship between dietary habits and criminal behavior has long been a topic of interest in the fields of criminology and public health. While the old saying "you are what you eat" might be a bit of a stretch when it comes to crime, it is worth exploring whether there is any merit to the idea that one's choice of beverage could be linked to unlawful activities. In this study, we delve into the "udder"ly fascinating correlation between milk consumption and burglaries in Tennessee, aiming to shed light on this unusual association.
As researchers, we often find ourselves in the unique position of un"herd"ing unexpected relationships in data. It is not uncommon for statistical analysis to produce findings that seem quite "moo"ving, even if they defy conventional wisdom or the laws of causality. Our investigation into the consumption of milk and its potential impact on crime rates in Tennessee is no exception. While it may sound like a "moo-t" point to some, our findings paint a picture that is both thought-provoking and, dare we say, "legendairy."
Taking a closer look at the data, we encountered a correlation that was "milk-iously" strong, with a coefficient of 0.9613492 and a p-value less than 0.01. This robust relationship was quite "udderly" unexpected, prompting us to consider whether there might be a "creamy" connection between the two variables. While we hesitate to jump to "conclu-sips," our findings certainly warrant further exploration and may lead to a "bovine" revelation in the field of criminology.
It is important to acknowledge that correlation does not imply causation, and we must tread carefully when interpreting these results. The notion that milk consumption could be associated with an increased likelihood of burglaries may seem "lactose-intolerable" to some. However, as researchers, it is our duty to approach the data with an open mind and a willingness to entertain even the most "moo-t" hypotheses. After all, in the world of statistics, sometimes the un"herd" of cannot be dismissed outright.
In light of these findings, we invite our readers to consider the potential implications of a link between milk consumption and criminal behavior. While the idea of a "moo-tive" for burglary may seem far-fetched, our research suggests that there may be more to the old adage "got milk" than meets the eye. As we endeavor to understand the mechanisms at play, we are left pondering the age-old question: Is there something inherently "dairy-ious" about the allure of a glass of milk that leads individuals down a nefarious path? We cannot help but wonder if, in the world of crime, the "milk of human kindness" might be more closely intertwined with the "cereal" mischief than we previously imagined.

[[RESULTS]]
The time period from 1990 to 2021 revealed a striking correlation coefficient of 0.9613492 between milk consumption and burglaries in Tennessee, indicating a remarkably strong positive relationship. This result is "moo-ving" in its magnitude, suggesting that as milk consumption increased, so did the occurrence of burglaries in the state. The r-squared value of 0.9241923 further underscores the robustness of this association, offering substantial support for the notion that there is more than meets the eye behind the innocuous act of drinking milk. The p-value of less than 0.01 solidifies the statistical significance of this correlation, rendering it a finding that cannot be dismissed as mere "cow-incidence."
The figure (Fig. 1) accompanying this analysis visually depicts the clear positive relationship between milk consumption and burglaries in Tennessee. Much like a glass of milk, the correlation is crystal clear, leaving little room for doubt. However, one cannot resist the urge to ask: "Is this what they meant by 'don't cry over spilled milk'?"
While the nature of causation remains a conundrum, the data indisputably point to a noteworthy connection between these seemingly unrelated variables. It seems that in the realm of statistical relationships, sometimes the answers are hidden in the unlikeliest of places – much like finding a needle in a haystack. This leads us to contemplate whether, in the grand scheme of things, the phrase "milk it for all it's worth" takes on a whole new significance in the context of criminal behavior.
As researchers, we are reminded that correlation does not imply causation, and to jump to conclusions would be as reckless as milking a wild cow. Nevertheless, the implications of our findings are nothing to be scoffed at. The unexpected interplay of milk consumption and burglaries in Tennessee raises a myriad of questions, not the least of which is whether we have overlooked a dairy serious factor in understanding criminal behavior. After all, when it comes to research, sometimes the only way out is through – or in this case, "moo."
In conclusion, our findings shed light on a perplexing association that challenges conventional wisdom and beckons further exploration. As we embark on the next phase of inquiry, we are reminded that in the world of research, the unexpected can be both perplexing and "udderly" intriguing. For now, the question lingers: do we dare to milk this connection for all it's worth, or should we simply raise a toast to the curious mysteries of statistical relationships?

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

The findings of this study provide compelling evidence of a substantial correlation between milk consumption and burglaries in Tennessee. The "moo-ving" correlation coefficient of 0.9613492 and a p-value less than 0.01 undoubtedly point to a remarkable association between these seemingly unrelated variables. It appears that as the dairy intake increased, so did the incidence of burglaries in the state. But before we start crying over spilled milk, it's crucial to acknowledge that correlation does not imply causation.

The robustness of this relationship raises intriguing questions about the potential mechanisms at play. Could it be that individuals are "udderly" emboldened by a glass of milk, leading them to make snap (c)pereal decisions when it comes to property crimes? This unexpected connection certainly offers much food for thought, reminiscent of the old adage, "got milk, got mischief."

Despite the statistical significance of our findings, it is essential to approach them with cautious skepticism. After all, jumping to conclusions in research is as hazardous as telling a bad dairy joke – it's just not "brie-lliant." While it's tempting to milk this association for all it's worth, it is clear that more empirical evidence and theoretical exploration are needed to unravel the causative underpinnings of this intriguing correlation.

In light of these findings, we confidently assert that further research in this area is not needed. The substantial correlation coefficient and statistical significance of this association speak for themselves, and we are left with the dairy-licious conclusion that milk consumption and burglaries in Tennessee are indeed surprisingly connected. So, let's raise a glass of milk to the curious mysteries of statistical relationships and leave the rest to be churned over by future researchers.

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 Crime: A Tennessee Time. Respond only with the name of a fictional academic journal.

ChatGPT:

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 Crime: A Tennessee Time. Respond only with the name of a fictional organization.

ChatGPT:

Society for the Advancement of Dairy Economics and Criminology

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 Crime: A Tennessee Time with an abstract of The relationship between milk consumption and burglaries in Tennessee has been a topic of utter curiosity and bewilderment. Despite the udder absurdity of such an investigation, our research team conducted a thorough analysis of data from the USDA and FBI Criminal Justice Information Services to moo-ve beyond the anecdotal evidence. We assessed the time period from 1990 to 2021 to determine whether any meaningful connection between milk consumption and burglaries existed. Surprise! We found a noteworthy correlation coefficient of 0.9613492 and p < 0.01, which raises the question: does "got milk" imply "got mischief"? Our findings suggest a possible association between increased milk consumption and a rise in burglaries, but the causation remains as elusive as the source of the Milky Way. As we churn through these findings, we are reminded of the age-old question: If you steal someone's milk, is it considered a dairy heist?

ChatGPT:

milk consumption, burglaries, Tennessee, correlation coefficient, USDA data, FBI criminal justice information, milk consumption and crime, dairy consumption, crime statistics, Tennessee crime trend, dairy product consumption, burglary rates, milk consumption and burglary correlation

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

Correlation r = 0.9613492 (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 = 0.9241923 (Coefficient of determination)
This means 92.4% of the change in the one variable (i.e., Burglaries in Tennessee) 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 2.4E-18.^Show 0.0000000000000000023522091911
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 0.96 in 2.4E-16% of random cases. Said differently, if you correlated 425,132,256,001,582,272 random variables^Note You don't actually need 425 quadrillion 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.

[ 0.92, 0.98 ] 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 Tennessee (Burglary rate)	1264	1365	1267.2	1182.6	1141.6	1143.2	1163.5	1171.7	1075.9	936.7	990.4	1038.5	1057.9	1083.3	1024.7	1032.8	1043.7	1004.1	1047.4	1013.8	1011.3	981.8	871.1	790.1	714.7	663.4	610.7	578.6	495.3	438.8	384.5	339

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([1264,1365,1267.2,1182.6,1141.6,1143.2,1163.5,1171.7,1075.9,936.7,990.4,1038.5,1057.9,1083.3,1024.7,1032.8,1043.7,1004.1,1047.4,1013.8,1011.3,981.8,871.1,790.1,714.7,663.4,610.7,578.6,495.3,438.8,384.5,339,])
array_1_name = "Milk consumption"
array_2_name = "Burglaries in Tennessee"

# 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 Tennessee
AI-generated correlation image
The spurious research paper: Milk and Crime: A Tennessee Time

View another random correlation

How fun was this correlation?

Cheers to you for rating this correlation!

Correlation ID: 3307 · Black Variable ID: 554 · Red Variable ID: 20121


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