Spurious correlation #1,673 · 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 Maryland. 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 Maryland. 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 switched to almond milk, they became more 'nutty' about home security, creating a 'fortress' mentality that deterred burglars.

^{Show image generation prompt} Model: dalle-3
Prompt: [A photo-realistic image] Generate an illustration depicting a serene, suburban neighborhood in Maryland. In the foreground, a diverse group of neighbors is shown sipping on glasses of milk while casually conversing. The houses exude a warm, welcoming glow, creating a sense of safety and community. The neighbors appear watchful and vigilant, intermittently glancing around to maintain a lookout for potential burglars. The subdued moonlight casts gentle shadows, adding a touch of serene suspense to 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 Maryland. 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: Glitch art A photo-realistic image Cyberpunk A scene from Skyrim a Polaroid photo
ChatGPT: A photo-realistic image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Milk consumption and Burglaries in Maryland together. Keep the description simple.
ChatGPT: A group of neighbors in Maryland sipping on glasses of milk while keeping an eye out for burglars in their quiet suburban neighborhood.

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 photo-realistic image ] and depicting this scene: A group of neighbors in Maryland sipping on glasses of milk while keeping an eye out for burglars in their quiet suburban neighborhood. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [A photo-realistic image] Generate an illustration depicting a serene, suburban neighborhood in Maryland. In the foreground, a diverse group of neighbors is shown sipping on glasses of milk while casually conversing. The houses exude a warm, welcoming glow, creating a sense of safety and community. The neighbors appear watchful and vigilant, intermittently glancing around to maintain a lookout for potential burglars. The subdued moonlight casts gentle shadows, adding a touch of serene suspense to 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 Maryland to decrease.

AI academic paper

(Because p < 0.01)

Milk and Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

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 Maryland. 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]]
Milk and Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

[[ABSTRACT]]
This study investigates the curious connection between milk consumption and burglaries in the charming state of Maryland. Utilizing data from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services, our research team embarked on a quest to disentangle this peculiar correlation. Our findings reveal a surprising correlation coefficient of 0.9788994 and a p-value less than 0.01 for the years 1990 to 2021, shedding light on the milk-mischief mystery.

We delved into the data with fervor, aiming to bottle up any misconceptions about this seemingly implausible association. Our rigorous analysis not only validated the link between milk intake and burglary rates but also unveiled a thought-provoking conundrum surrounding the purported innocuous nature of consuming this dairy delight. We couldn't help but recall the jest, "I told my wife she should embrace her mistakes. She gave me a hug," as our findings reflected the unexpected embrace between milk and burglary.

Furthermore, our study accentuates the need for further research into the deeper reasons behind this unlikely relationship. Could it be that the mere act of sipping milk enhances mischievous tendencies, or is there a deeper, lactose-larceny linkage at play? Our results leave us moo-ved to question conventional wisdom and delve deeper into understanding the enigmatic dynamics at the intersection of dairy consumption and criminal activity.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between milk consumption and criminal behavior has often been overlooked in the annals of scientific inquiry. It is a topic as rich and creamy as a glass of whole milk, yet as mysterious as the origins of lactose intolerance. Our study seeks to unravel this enigmatic connection, shedding light on the curious correlation between milk intake and burglary rates in the delightful state of Maryland. As the saying goes, "I asked the dairy farmer if he could breed a cow to give buttermilk. He said it was butter impossible," and indeed, the conundrum at hand seems equally improbable.
In recent years, the notion that milk and criminal activity could be linked has been dismissed as an utter folly. However, our findings, akin to a cow's penchant for grazing, graze upon the fertile pasture of statistical significance, revealing a robust correlation coefficient of 0.9788994 and a p-value less than 0.01. This raises the question: Is there truly a moo-tive behind this unexpected association?

As we embarked on our research, we pondered the words of wisdom, "I accidentally drank skim milk, and then I laughed so hard, the milk came out my nose," and reflected on the potentially far-reaching consequences of our findings. Could it be that milk consumption, much like a poorly timed joke, triggers a chain of events that leads to unlawful activities? Or is this correlation merely an udder coincidence, akin to finding a needle in a haystack?
Our study invites the scientific community to join us in milking this peculiar correlation for all its worth, delving into the underlying mechanisms and behavioral pathways that may explain the link between milk and mischief. We are eager to embark on this journey, much like a calf eagerly approaching its mother's udder, in search of the nourishment of knowledge.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Numerous studies have sought to unravel the perplexing connection between milk consumption and criminal behavior. In "Smith et al.," the authors find a positive correlation between milk intake and various antisocial behaviors, sparking intrigue and curiosity within the scientific community. This serious endeavor, however, soon takes an unexpected turn, much like a cow attempting a pirouette in a pasture.

In "Doe and Jones," the authors delve into the socioeconomic factors associated with milk consumption and its potential implications for criminal activity. Their meticulous analysis and insightful findings urge contemplation on the broader societal implications of this unlikely relationship. Speaking of unlikely relationships, did you hear about the dairy farmer who fell in love with a movie star? He was utterly smitten.

Turning to non-fiction literature, "The Big Moo" by Seth Godin offers a creative exploration of unconventional ideas, reminiscent of the unconventional relationship between milk and burglary rates. In a similar vein, "Got Milked: The Great Dairy Deception and Why You'll Thrive Without Milk" by Alissa Hamilton presents a thought-provoking critique of milk consumption, perhaps shedding light on the unexpected mischief associated with milk.

In the realm of fiction, the works of Agatha Christie, renowned for their intricate mysteries, bear a subtle resemblance to the enigmatic link between milk and burglaries. "The Milkman" by Anna Burns also offers a tantalizing narrative that may metaphorically mirror the surprising findings of our study. Speaking of milk, I tried to make some cheese jokes, but they were all too cheesy.

Furthermore, several cinematic endeavors present tangential connections to our research topic. "Got Milk?" – a series of famous advertisements – serves as a light-hearted reminder of the ubiquitous presence of milk in our daily lives. Meanwhile, "Home Alone" captures the essence of mischief and mayhem, drawing parallels to the unexpected correlation between milk consumption and burglaries. It seems the misadventures of the "Wet Bandits" are not too far from the unassuming nature of milk-induced mischief.

In light of the literature's multifaceted inquiries into the realm of milk and its unforeseen connections, our research endeavors to unravel this captivating conundrum, much like a cow untangling a knotty problem. We are propelled by an irresistible urge to explore the uncharted territories of dairy dynamics and criminal causality, all while serving a side of dad jokes with our scholarly pursuits.

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 Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

[[ABSTRACT]]
This study investigates the curious connection between milk consumption and burglaries in the charming state of Maryland. Utilizing data from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services, our research team embarked on a quest to disentangle this peculiar correlation. Our findings reveal a surprising correlation coefficient of 0.9788994 and a p-value less than 0.01 for the years 1990 to 2021, shedding light on the milk-mischief mystery.

We delved into the data with fervor, aiming to bottle up any misconceptions about this seemingly implausible association. Our rigorous analysis not only validated the link between milk intake and burglary rates but also unveiled a thought-provoking conundrum surrounding the purported innocuous nature of consuming this dairy delight. We couldn't help but recall the jest, "I told my wife she should embrace her mistakes. She gave me a hug," as our findings reflected the unexpected embrace between milk and burglary.

Furthermore, our study accentuates the need for further research into the deeper reasons behind this unlikely relationship. Could it be that the mere act of sipping milk enhances mischievous tendencies, or is there a deeper, lactose-larceny linkage at play? Our results leave us moo-ved to question conventional wisdom and delve deeper into understanding the enigmatic dynamics at the intersection of dairy consumption and criminal activity.

[[INTRODUCTION]]
The relationship between milk consumption and criminal behavior has often been overlooked in the annals of scientific inquiry. It is a topic as rich and creamy as a glass of whole milk, yet as mysterious as the origins of lactose intolerance. Our study seeks to unravel this enigmatic connection, shedding light on the curious correlation between milk intake and burglary rates in the delightful state of Maryland. As the saying goes, "I asked the dairy farmer if he could breed a cow to give buttermilk. He said it was butter impossible," and indeed, the conundrum at hand seems equally improbable.
In recent years, the notion that milk and criminal activity could be linked has been dismissed as an utter folly. However, our findings, akin to a cow's penchant for grazing, graze upon the fertile pasture of statistical significance, revealing a robust correlation coefficient of 0.9788994 and a p-value less than 0.01. This raises the question: Is there truly a moo-tive behind this unexpected association?

As we embarked on our research, we pondered the words of wisdom, "I accidentally drank skim milk, and then I laughed so hard, the milk came out my nose," and reflected on the potentially far-reaching consequences of our findings. Could it be that milk consumption, much like a poorly timed joke, triggers a chain of events that leads to unlawful activities? Or is this correlation merely an udder coincidence, akin to finding a needle in a haystack?
Our study invites the scientific community to join us in milking this peculiar correlation for all its worth, delving into the underlying mechanisms and behavioral pathways that may explain the link between milk and mischief. We are eager to embark on this journey, much like a calf eagerly approaching its mother's udder, in search of the nourishment of knowledge.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data for milk consumption was obtained from the United States Department of Agriculture (USDA), which provides comprehensive statistics on dairy product consumption in various states from 1990 to 2021. Data on burglary rates was sourced from the FBI Criminal Justice Information Services, offering detailed records of reported burglaries in Maryland during the same time frame. The use of these sources ensured a reliable and comprehensive dataset for our analysis. As the data poured in, we couldn't help but think, "Why don't scientists trust atoms? Because they make up everything."

Outlier Detection:
To ensure the integrity of our analysis, we implemented a whimsical yet rigorous outlier detection method, inspired by the principles of dairy farming. Analogous to separating the cream from milk, we identified outliers in the dataset using a novel algorithm based on the notion of "separating the uncommon from the common." This process allowed us to ensure that our findings were not skewed by errant data points. Just like detangling a mischievous calf from a fence, removing outliers from the dataset required patience and precision.

Correlation Analysis:
The heart of our analysis lay in the exploration of the correlation between milk consumption and burglary rates. Utilizing advanced statistical techniques, including Pearson's correlation coefficient and linear regression models, we delved into the depths of this seemingly implausible connection. The correlation coefficient, akin to a dairy farmer's keen eye for the quality of milk, allowed us to quantify the strength and direction of the relationship between these variables. As we navigated through the statistical analyses, we pondered the age-old question, "What do you call a cow that has just given birth? Decalfinated."

Time-Series Modeling:
Recognizing the temporal nature of the data, we employed time-series modeling to capture the dynamic interplay between milk consumption and burglaries over the years. Drawing inspiration from the steady rhythm of a cow's grazing, we applied autoregressive integrated moving average (ARIMA) models to unearth any underlying patterns or cyclical trends in the data. This approach enabled us to milk the temporal dimension of the dataset, revealing the ebbs and flows of the milk-burglary nexus across different years.

Drawing from the wealth of data and analytical techniques, our methodology laid the foundation for a comprehensive exploration of the connection between milk consumption and burglaries in Maryland. Much like a curdled joke, our methods aimed to unravel the seemingly incongruous relationship between these variables, leaving no stone unturned in our pursuit of scientific understanding.

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 Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

[[ABSTRACT]]
This study investigates the curious connection between milk consumption and burglaries in the charming state of Maryland. Utilizing data from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services, our research team embarked on a quest to disentangle this peculiar correlation. Our findings reveal a surprising correlation coefficient of 0.9788994 and a p-value less than 0.01 for the years 1990 to 2021, shedding light on the milk-mischief mystery.

We delved into the data with fervor, aiming to bottle up any misconceptions about this seemingly implausible association. Our rigorous analysis not only validated the link between milk intake and burglary rates but also unveiled a thought-provoking conundrum surrounding the purported innocuous nature of consuming this dairy delight. We couldn't help but recall the jest, "I told my wife she should embrace her mistakes. She gave me a hug," as our findings reflected the unexpected embrace between milk and burglary.

Furthermore, our study accentuates the need for further research into the deeper reasons behind this unlikely relationship. Could it be that the mere act of sipping milk enhances mischievous tendencies, or is there a deeper, lactose-larceny linkage at play? Our results leave us moo-ved to question conventional wisdom and delve deeper into understanding the enigmatic dynamics at the intersection of dairy consumption and criminal activity.

[[LITERATURE REVIEW]]
Numerous studies have sought to unravel the perplexing connection between milk consumption and criminal behavior. In "Smith et al.," the authors find a positive correlation between milk intake and various antisocial behaviors, sparking intrigue and curiosity within the scientific community. This serious endeavor, however, soon takes an unexpected turn, much like a cow attempting a pirouette in a pasture.
In "Doe and Jones," the authors delve into the socioeconomic factors associated with milk consumption and its potential implications for criminal activity. Their meticulous analysis and insightful findings urge contemplation on the broader societal implications of this unlikely relationship. Speaking of unlikely relationships, did you hear about the dairy farmer who fell in love with a movie star? He was utterly smitten.
Turning to non-fiction literature, "The Big Moo" by Seth Godin offers a creative exploration of unconventional ideas, reminiscent of the unconventional relationship between milk and burglary rates. In a similar vein, "Got Milked: The Great Dairy Deception and Why You'll Thrive Without Milk" by Alissa Hamilton presents a thought-provoking critique of milk consumption, perhaps shedding light on the unexpected mischief associated with milk.
In the realm of fiction, the works of Agatha Christie, renowned for their intricate mysteries, bear a subtle resemblance to the enigmatic link between milk and burglaries. "The Milkman" by Anna Burns also offers a tantalizing narrative that may metaphorically mirror the surprising findings of our study. Speaking of milk, I tried to make some cheese jokes, but they were all too cheesy.
Furthermore, several cinematic endeavors present tangential connections to our research topic. "Got Milk?" – a series of famous advertisements – serves as a light-hearted reminder of the ubiquitous presence of milk in our daily lives. Meanwhile, "Home Alone" captures the essence of mischief and mayhem, drawing parallels to the unexpected correlation between milk consumption and burglaries. It seems the misadventures of the "Wet Bandits" are not too far from the unassuming nature of milk-induced mischief.
In light of the literature's multifaceted inquiries into the realm of milk and its unforeseen connections, our research endeavors to unravel this captivating conundrum, much like a cow untangling a knotty problem. We are propelled by an irresistible urge to explore the uncharted territories of dairy dynamics and criminal causality, all while serving a side of dad jokes with our scholarly pursuits.

[[RESULTS]]
The analysis of the data revealed a striking correlation between milk consumption and burglary rates in Maryland, with a correlation coefficient of 0.9788994, indicating a remarkably strong relationship between the two variables. This finding suggests that there may indeed be a substantial association between the act of sipping milk and the propensity for unlawful activities, reminding us of the quip, "I'm reading a book on anti-gravity. It's impossible to put down."
The r-squared value of 0.9582440 further corroborated the robustness of the relationship, indicating that approximately 95.82% of the variability in burglary rates can be explained by variations in milk consumption. This result left us utterly astounded, much like the feeling of discovering an unexpected ingredient in a well-baked cake.
Additionally, the p-value of less than 0.01 underscored the statistical significance of the correlation, rejecting the null hypothesis and affirming the unlikely yet compelling connection between milk and mischief. This discovery brought to mind the amusing adage, "I told my wife she should embrace her mistakes. She gave me a hug," as our research unraveled the unsuspected "hug" between milk consumption and criminal behavior.
To visually represent this extraordinary correlation, we present Figure 1, a scatterplot depicting the substantial association between milk consumption and burglary rates in Maryland. The scatterplot showcases the data points clustering tightly around a positively sloped regression line, emphasizing the compelling nature of the observed relationship. This visual evidence serves as a testament to the unexpected entanglement of milk and mischief, evoking a sense of curiosity reminiscent of unraveling a captivating mystery.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study provide compelling evidence supporting the intricate relationship between milk consumption and burglaries in Maryland. The remarkably strong correlation coefficient and the statistically significant p-value lend credence to the notion that there exists a substantive association between these seemingly disparate variables. Our results underscore the need for further exploration into the underlying mechanisms that may explain this unexpected nexus, evoking thoughts of an unforeseen door of inquiry opening within the dairy aisle.

The present study aligns with previous research by Smith et al. and Doe and Jones, which hinted at a positive correlation between milk consumption and antisocial behaviors, substantiating the notion that milk intake may indeed be linked to criminal activities. Furthermore, the robustness of the relationship, as indicated by the high r-squared value, reiterates the pertinence of this association, leaving little room for skepticism. One could say that our findings "moo-ve" in the same direction as prior research, building upon the existing body of knowledge with udderly intriguing revelations.

The scatterplot, as showcased in Figure 1, serves as a visual testament to the compelling nature of the identified relationship. The tight clustering of data points around the positively sloped regression line vividly portrays the unmistakable bond between milk consumption and burglary rates, akin to uncovering the unexpected link between two supposedly unrelated phenomena. In a sense, it is akin to finding a misplaced cookie in the milk carton – surprising, but undeniably present.

This study sheds light on the need for a deeper understanding of the dynamics at play, raising thought-provoking questions about the potential mechanisms underlying the correlation between milk consumption and criminal behavior. Is there something inherently criminogenic about the act of consuming milk, or are there external factors at play that influence this association? The juxtaposition of milk and mischief presents an unforeseen conundrum, much like a cat-and-mouse game in a dairy farm.

In conclusion, our study contributes meaningfully to the burgeoning body of literature exploring the relationship between dietary habits and criminal activities. The unexpected alliance between milk consumption and burglaries in Maryland challenges conventional wisdom and beckons future investigations into this unlikely yet captivating nexus. As we endeavor to milk every opportunity for academic inquiry, it is evident that the dairy aisle holds more than just the promise of a wholesome breakfast – it holds complex sociological and criminological mysteries waiting to be unraveled.

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 Maryland. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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 Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

[[ABSTRACT]]
This study investigates the curious connection between milk consumption and burglaries in the charming state of Maryland. Utilizing data from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services, our research team embarked on a quest to disentangle this peculiar correlation. Our findings reveal a surprising correlation coefficient of 0.9788994 and a p-value less than 0.01 for the years 1990 to 2021, shedding light on the milk-mischief mystery.

We delved into the data with fervor, aiming to bottle up any misconceptions about this seemingly implausible association. Our rigorous analysis not only validated the link between milk intake and burglary rates but also unveiled a thought-provoking conundrum surrounding the purported innocuous nature of consuming this dairy delight. We couldn't help but recall the jest, "I told my wife she should embrace her mistakes. She gave me a hug," as our findings reflected the unexpected embrace between milk and burglary.

Furthermore, our study accentuates the need for further research into the deeper reasons behind this unlikely relationship. Could it be that the mere act of sipping milk enhances mischievous tendencies, or is there a deeper, lactose-larceny linkage at play? Our results leave us moo-ved to question conventional wisdom and delve deeper into understanding the enigmatic dynamics at the intersection of dairy consumption and criminal activity.

[[INTRDUCTION]]
The relationship between milk consumption and criminal behavior has often been overlooked in the annals of scientific inquiry. It is a topic as rich and creamy as a glass of whole milk, yet as mysterious as the origins of lactose intolerance. Our study seeks to unravel this enigmatic connection, shedding light on the curious correlation between milk intake and burglary rates in the delightful state of Maryland. As the saying goes, "I asked the dairy farmer if he could breed a cow to give buttermilk. He said it was butter impossible," and indeed, the conundrum at hand seems equally improbable.
In recent years, the notion that milk and criminal activity could be linked has been dismissed as an utter folly. However, our findings, akin to a cow's penchant for grazing, graze upon the fertile pasture of statistical significance, revealing a robust correlation coefficient of 0.9788994 and a p-value less than 0.01. This raises the question: Is there truly a moo-tive behind this unexpected association?

As we embarked on our research, we pondered the words of wisdom, "I accidentally drank skim milk, and then I laughed so hard, the milk came out my nose," and reflected on the potentially far-reaching consequences of our findings. Could it be that milk consumption, much like a poorly timed joke, triggers a chain of events that leads to unlawful activities? Or is this correlation merely an udder coincidence, akin to finding a needle in a haystack?
Our study invites the scientific community to join us in milking this peculiar correlation for all its worth, delving into the underlying mechanisms and behavioral pathways that may explain the link between milk and mischief. We are eager to embark on this journey, much like a calf eagerly approaching its mother's udder, in search of the nourishment of knowledge.

[[RESULTS]]
The analysis of the data revealed a striking correlation between milk consumption and burglary rates in Maryland, with a correlation coefficient of 0.9788994, indicating a remarkably strong relationship between the two variables. This finding suggests that there may indeed be a substantial association between the act of sipping milk and the propensity for unlawful activities, reminding us of the quip, "I'm reading a book on anti-gravity. It's impossible to put down."
The r-squared value of 0.9582440 further corroborated the robustness of the relationship, indicating that approximately 95.82% of the variability in burglary rates can be explained by variations in milk consumption. This result left us utterly astounded, much like the feeling of discovering an unexpected ingredient in a well-baked cake.
Additionally, the p-value of less than 0.01 underscored the statistical significance of the correlation, rejecting the null hypothesis and affirming the unlikely yet compelling connection between milk and mischief. This discovery brought to mind the amusing adage, "I told my wife she should embrace her mistakes. She gave me a hug," as our research unraveled the unsuspected "hug" between milk consumption and criminal behavior.
To visually represent this extraordinary correlation, we present Figure 1, a scatterplot depicting the substantial association between milk consumption and burglary rates in Maryland. The scatterplot showcases the data points clustering tightly around a positively sloped regression line, emphasizing the compelling nature of the observed relationship. This visual evidence serves as a testament to the unexpected entanglement of milk and mischief, evoking a sense of curiosity reminiscent of unraveling a captivating mystery.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study illuminates the strong and improbable correlation between milk consumption and burglary rates in the delightful state of Maryland. Our findings highlight a remarkable correlation coefficient of 0.9788994 and a p-value less than 0.01, leaving us with a milk-mischief mystery akin to a dairy-laden riddle. It seems that there is more to this lactose-larceny linkage than meets the eye, reminding us of the jest, "I'm reading a book on anti-gravity. It's impossible to put down."

Our research leaves us pondering the udderly intriguing question of what prompts this unanticipated association. Is it the creamy goodness of milk that incites mischievous tendencies, or is there an unforeseen lactose-larceny linkage at play, akin to finding a needle in a haystack of hypotheses?

Further research in this area is not needed.

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 Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland. 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 Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Dairy Delinquency 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 Milk and Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland with an abstract of This study investigates the curious connection between milk consumption and burglaries in the charming state of Maryland. Utilizing data from the United States Department of Agriculture (USDA) and the FBI Criminal Justice Information Services, our research team embarked on a quest to disentangle this peculiar correlation. Our findings reveal a surprising correlation coefficient of 0.9788994 and a p-value less than 0.01 for the years 1990 to 2021, shedding light on the milk-mischief mystery.
We delved into the data with fervor, aiming to bottle up any misconceptions about this seemingly implausible association. Our rigorous analysis not only validated the link between milk intake and burglary rates but also unveiled a thought-provoking conundrum surrounding the purported innocuous nature of consuming this dairy delight. We couldn't help but recall the jest, "I told my wife she should embrace her mistakes. She gave me a hug," as our findings reflected the unexpected embrace between milk and burglary.
Furthermore, our study accentuates the need for further research into the deeper reasons behind this unlikely relationship. Could it be that the mere act of sipping milk enhances mischievous tendencies, or is there a deeper, lactose-larceny linkage at play? Our results leave us moo-ved to question conventional wisdom and delve deeper into understanding the enigmatic dynamics at the intersection of dairy consumption and criminal activity.

ChatGPT:

milk consumption, burglaries, Maryland, correlation coefficient, p-value, USDA data, FBI criminal justice information services, dairy consumption, burglary rates, lactose-larceny linkage, dairy and criminal activity, milk and mischief relationship

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

Correlation r = 0.9788994 (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 = 0.9582440 (Coefficient of determination)
This means 95.8% of the change in the one variable (i.e., Burglaries in Maryland) is predictable based on the change in the other (i.e., Milk consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.01E-22.^Show 0.0000000000000000000003014528
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 0.98 in 3.01E-20% of random cases. Said differently, if you correlated 3,317,268,905,778,947,817,472 random variables^Note You don't actually need 3 sextillion 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.

[ 0.96, 0.99 ] 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 Maryland (Burglary rate)	1119.9	1157.6	1131.2	1132.8	1043.4	1057.5	992.3	940.7	922.9	835.9	744.4	771.5	729.6	701	660	642.7	667	660.2	689.6	647.5	634.4	613.5	574.4	538	470.8	440.9	412.2	390.5	313.3	278.6	252	210.9

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([1119.9,1157.6,1131.2,1132.8,1043.4,1057.5,992.3,940.7,922.9,835.9,744.4,771.5,729.6,701,660,642.7,667,660.2,689.6,647.5,634.4,613.5,574.4,538,470.8,440.9,412.2,390.5,313.3,278.6,252,210.9,])
array_1_name = "Milk consumption"
array_2_name = "Burglaries in Maryland"

# 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 Maryland
AI-generated correlation image
The spurious research paper: Milk and Cookies: Unscrambling the Relationship Between Milk Consumption and Burglaries in Maryland

View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!

Correlation ID: 1673 · Black Variable ID: 554 · Red Variable ID: 20097


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