about · email me · subscribe
Spurious correlation #1,786 · View random

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

AI explanation

As people switched to dairy alternatives, they became ‘udderly’ mellow and lactose-tolerant, moo-ving away from a life of crime. Without the urge to ‘case-einate’ or ‘cream’ the scene, there was a significant ‘dairy’th of robberies as everyone was too busy ‘moo-ving’ on with their peaceful, almond-crusted lives. The police even considered changing their sirens to cow ‘moo’sic as a tribute to this ‘legendairy’ shift in behavior. It seems that in this case, the real criminals were the ones milking it for all it was worth, but now the only thing getting stolen is a few hearts over a soy latte. It’s a case of ‘got milk’ turning into ‘got no milk, got no problem’ in the annals of bizarrely wholesome crime statistics!

Model: dalle-3
Prompt: Create an image of a cozy Rhode Island kitchen with a person standing by the counter, pouring a glass of milk. They are glancing out the window, where a thief is seen fleeing with a bag of stolen goods. The warm lighting from the kitchen accents the domestic setting, while the dramatic action outside adds a thrilling element 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 Robberies in Rhode Island. 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: Cubism Oragami Celtic art A Discovery magazine cover image Cubism
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Milk consumption and Robberies in Rhode Island together. Keep the description simple.
ChatGPT: In a cozy Rhode Island kitchen, a person pours a glass of milk while glancing out the window at a thief fleeing with a bag of stolen goods.

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 Discovery magazine cover image ] and depicting this scene: In a cozy Rhode Island kitchen, a person pours a glass of milk while glancing out the window at a thief fleeing with a bag of stolen goods. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a cozy Rhode Island kitchen with a person standing by the counter, pouring a glass of milk. They are glancing out the window, where a thief is seen fleeing with a bag of stolen goods. The warm lighting from the kitchen accents the domestic setting, while the dramatic action outside adds a thrilling element 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.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Milk consumption caused Robberies in Rhode Island to decrease.

AI academic paper

(Because p < 0.01)
The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island

The International Journal of Milkology and Crime Studies

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns.

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

Your research team used data from USDA and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.9269046 and p < 0.01 for 1990 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
Introduction

Milk, the creamy elixir that finds its way into our cereal bowls, coffee cups, and increasingly, into the annals of criminal research. The age-old question of whether "Got Milk?" leads to "Got Crime?" has sparked both curiosity and skepticism among scholars and aficionados of dairy. In this paper, we take a lactose-fueled leap into the synergistic world of milk consumption and robberies in the enchanting locale of Rhode Island.

Past studies have left us with a cheese-like hole in our understanding of the potential linkage between calcium-rich beverages and unlawful activities. Some have postulated that the calcium content in milk may exercise a calming effect on individuals, akin to the soothing strokes of a calcium-rich kitten. Conversely, others have suggested that lactose intolerance might lead to irritable dispositions, compelling individuals to take on acts of desperation, including perhaps snatching the last carton of lactose-free milk from the local supermarket.

As researchers, we were udderly intrigued by these ideas but remained skeptical, determined to separate the whey from the curds of speculation. Against this backdrop, we embarked on a quest to uncover whether the nuances of milk consumption could indeed influence the frequency of robberies in the smallest state in the union. We thirsted for knowledge, not only to quench our scientific curiosity but also to provide real-world implications for policymakers, law enforcement, and dairy enthusiasts alike.

Our mission led us to delve into a heaping bowl of data, drawing from the USDA's voluminous archives of milk consumption statistics and the FBI's Criminal Justice Information Services' treasure trove of crime data. From 1990 to 2021, we applied rigorous statistical analyses, embracing regression models, correlation coefficients, and other mathematical incantations in our pursuit of truth. Lo and behold, our findings yielded a correlation coefficient of 0.9269046, and a p-value of less than 0.01, indicating a robust association between milk consumption and robberies in Rhode Island.

In this paper, we present our findings with a dairy-infused flair, leaving no stone-cold unchurned in our exploration of the dairy-crime nexus. From bovine serenity to lactase-induced larceny, this research aims to unravel the conundrum of how a seemingly innocuous beverage could potentially be intertwined with criminal activities.

So, grab a glass of milk, sit back, and prepare to be whipped into a frenzy of dairy-inspired revelations. Let the udderly captivating journey into the intriguing realm of milk and misdemeanors commence!


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
Milk, the creamy elixir that finds its way into our cereal bowls, coffee cups, and increasingly, into the annals of criminal research. The age-old question of whether "Got Milk?" leads to "Got Crime?" has sparked both curiosity and skepticism among scholars and aficionados of dairy. In this paper, we take a lactose-fueled leap into the synergistic world of milk consumption and robberies in the enchanting locale of Rhode Island.
Past studies have left us with a cheese-like hole in our understanding of the potential linkage between calcium-rich beverages and unlawful activities. Some have postulated that the calcium content in milk may exercise a calming effect on individuals, akin to the soothing strokes of a calcium-rich kitten. Conversely, others have suggested that lactose intolerance might lead to irritable dispositions, compelling individuals to take on acts of desperation, including perhaps snatching the last carton of lactose-free milk from the local supermarket.
As researchers, we were udderly intrigued by these ideas but remained skeptical, determined to separate the whey from the curds of speculation. Against this backdrop, we embarked on a quest to uncover whether the nuances of milk consumption could indeed influence the frequency of robberies in the smallest state in the union. We thirsted for knowledge, not only to quench our scientific curiosity but also to provide real-world implications for policymakers, law enforcement, and dairy enthusiasts alike.
Our mission led us to delve into a heaping bowl of data, drawing from the USDA's voluminous archives of milk consumption statistics and the FBI's Criminal Justice Information Services' treasure trove of crime data. From 1990 to 2021, we applied rigorous statistical analyses, embracing regression models, correlation coefficients, and other mathematical incantations in our pursuit of truth. Lo and behold, our findings yielded a correlation coefficient of 0.9269046, and a p-value of less than 0.01, indicating a robust association between milk consumption and robberies in Rhode Island.
In this paper, we present our findings with a dairy-infused flair, leaving no stone-cold unchurned in our exploration of the dairy-crime nexus. From bovine serenity to lactase-induced larceny, this research aims to unravel the conundrum of how a seemingly innocuous beverage could potentially be intertwined with criminal activities.
So, grab a glass of milk, sit back, and prepare to be whipped into a frenzy of dairy-inspired revelations. Let the udderly captivating journey into the intriguing realm of milk and misdemeanors commence!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
**LITERATURE REVIEW**

Numerous scholarly works have attempted to discern the enigmatic relationship between milk consumption and criminal behavior. Smith et al., in their seminal study "Dairy Dynamics: Exploring the Correlation Between Milk Intake and Lawlessness," unearthed intriguing preliminary evidence suggesting a potential link between calcium-laden libations and unlawful activities. Doe and Jones expanded on this line of inquiry in "Milk and Misdemeanors: A Holistic Examination of Dairy Deviance," delving into lactose intolerance as a possible catalyst for nefarious deeds. Building on this foundation, our study endeavors to froth up the debate further, focusing specifically on the empirical nuances of milk consumption and its association with robberies in the state of Rhode Island.

Turning to the world of non-fiction literature, titles such as "Milk: A Complete Guide to Its Role in Human Health" and "The Big Moo: Stop Trying to Be Perfect and Start Being Remarkable" add richness to our understanding of milk's multifaceted influences. On the fictional front, works like "The Curious Incident of the Milk in the Night-Time" and "A Clockwork Orange Creamsicle" provide whimsical yet thought-provoking narratives that resonate with our research theme.

In the realm of popular culture, the ubiquitous "Got Milk?" campaign has seeped into the collective consciousness, with its iconic mustached celebrities leaving an indelible mark on milk's public image. Additionally, internet memes such as the "Milk Jug Bandit" have playfully toyed with the notion of milk-related crime, blurring the lines between internet humor and our serious academic inquiry.

As we embark on our investigation, we are attentive to the quixotic nature of our endeavor. However, armed with statistical rigor and a healthy dose of lactose-induced curiosity, we set forth to illuminate the creamy conundrum of dairy's potential impact on illicit activities. Through our exploration, we aim to bring a smile to the faces of readers and perhaps, it is our hope, to also bring a chuckle - a little dairy humor to whet the intellectual appetite.

So, without further ado, let us dive headfirst into the bewildering realm of milk, mischief, and the captivating nuances of our criminal yet calcium-rich world.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from USDA and FBI Criminal Justice Information Services . You used data from 1990 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

[[INTRODUCTION]]
Introduction
Milk, the creamy elixir that finds its way into our cereal bowls, coffee cups, and increasingly, into the annals of criminal research. The age-old question of whether "Got Milk?" leads to "Got Crime?" has sparked both curiosity and skepticism among scholars and aficionados of dairy. In this paper, we take a lactose-fueled leap into the synergistic world of milk consumption and robberies in the enchanting locale of Rhode Island.
Past studies have left us with a cheese-like hole in our understanding of the potential linkage between calcium-rich beverages and unlawful activities. Some have postulated that the calcium content in milk may exercise a calming effect on individuals, akin to the soothing strokes of a calcium-rich kitten. Conversely, others have suggested that lactose intolerance might lead to irritable dispositions, compelling individuals to take on acts of desperation, including perhaps snatching the last carton of lactose-free milk from the local supermarket.
As researchers, we were udderly intrigued by these ideas but remained skeptical, determined to separate the whey from the curds of speculation. Against this backdrop, we embarked on a quest to uncover whether the nuances of milk consumption could indeed influence the frequency of robberies in the smallest state in the union. We thirsted for knowledge, not only to quench our scientific curiosity but also to provide real-world implications for policymakers, law enforcement, and dairy enthusiasts alike.
Our mission led us to delve into a heaping bowl of data, drawing from the USDA's voluminous archives of milk consumption statistics and the FBI's Criminal Justice Information Services' treasure trove of crime data. From 1990 to 2021, we applied rigorous statistical analyses, embracing regression models, correlation coefficients, and other mathematical incantations in our pursuit of truth. Lo and behold, our findings yielded a correlation coefficient of 0.9269046, and a p-value of less than 0.01, indicating a robust association between milk consumption and robberies in Rhode Island.
In this paper, we present our findings with a dairy-infused flair, leaving no stone-cold unchurned in our exploration of the dairy-crime nexus. From bovine serenity to lactase-induced larceny, this research aims to unravel the conundrum of how a seemingly innocuous beverage could potentially be intertwined with criminal activities.
So, grab a glass of milk, sit back, and prepare to be whipped into a frenzy of dairy-inspired revelations. Let the udderly captivating journey into the intriguing realm of milk and misdemeanors commence!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the mysteries of the dairy-crime nexus, we employed a methodological approach that was as meticulously crafted as a barista's latte art. Our data collection journey began with an exhaustive exploration of the USDA's hoard of milk consumption statistics, which we lovingly referred to as "the Milky Way." We deftly extracted and scrutinized data spanning the years 1990 to 2021, seeking to extract the cream of the crop for our analyses.

Our next foray led us to the hallowed grounds of the FBI's Criminal Justice Information Services, a veritable treasure trove of criminal data that would make even the most elusive cat burglar green with envy. Here, we unearthed detailed records of robberies in the picturesque state of Rhode Island, setting the stage for a convergence of dairy and dastardly deeds.

With our data sets in hand, we embarked on a statistical odyssey worthy of Odysseus himself. First, we employed a time series analysis to track the undulating waves of milk consumption and robbery frequency over the decades, navigating through statistical shoals and p-values as capricious as the winds of Aeolus.

To quantify the potential association between milk consumption and robberies, we turned to the venerable correlation coefficient, a stalwart companion in the tumultuous seas of data analysis. Through rigorous calculations and iterations that might have rivaled the legendary labors of Hercules, we uncovered a correlation coefficient of 0.9269046, donning our statistical laurels with pride. Additionally, our p-value, akin to the elusive pearl in an oyster, shimmered brightly at less than 0.01, signaling a statistical relationship more compelling than a dairy aficionado's love for cheese fondue.

In our pursuit of scholarly rigor, we fortified our analyses with a multiple regression model, embellishing our statistical canvas with predictor variables and coefficients as vibrant as a Jackson Pollock masterpiece. Through this model, we sought to disentangle the complex interplay between milk consumption and other potential factors influencing the incidence of robberies in Rhode Island, from the waxing and waning phases of the moon to the rise and fall of lactose-free alternatives on supermarket shelves.

Anchored in the principles of empirical inquiry and with a sprinkle of whimsical allure, our methodological expedition stands as a testament to the pursuit of knowledge, swathed in the velvety mantle of scientific inquiry and perhaps a hint of milk foam.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1990 to 2021, you found a correlation 0.9269046, r-squared of 0.8591521, and p < 0.01.

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

Here is the title and abstract of the paper:
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
Milk, the creamy elixir that finds its way into our cereal bowls, coffee cups, and increasingly, into the annals of criminal research. The age-old question of whether "Got Milk?" leads to "Got Crime?" has sparked both curiosity and skepticism among scholars and aficionados of dairy. In this paper, we take a lactose-fueled leap into the synergistic world of milk consumption and robberies in the enchanting locale of Rhode Island.
Past studies have left us with a cheese-like hole in our understanding of the potential linkage between calcium-rich beverages and unlawful activities. Some have postulated that the calcium content in milk may exercise a calming effect on individuals, akin to the soothing strokes of a calcium-rich kitten. Conversely, others have suggested that lactose intolerance might lead to irritable dispositions, compelling individuals to take on acts of desperation, including perhaps snatching the last carton of lactose-free milk from the local supermarket.
As researchers, we were udderly intrigued by these ideas but remained skeptical, determined to separate the whey from the curds of speculation. Against this backdrop, we embarked on a quest to uncover whether the nuances of milk consumption could indeed influence the frequency of robberies in the smallest state in the union. We thirsted for knowledge, not only to quench our scientific curiosity but also to provide real-world implications for policymakers, law enforcement, and dairy enthusiasts alike.
Our mission led us to delve into a heaping bowl of data, drawing from the USDA's voluminous archives of milk consumption statistics and the FBI's Criminal Justice Information Services' treasure trove of crime data. From 1990 to 2021, we applied rigorous statistical analyses, embracing regression models, correlation coefficients, and other mathematical incantations in our pursuit of truth. Lo and behold, our findings yielded a correlation coefficient of 0.9269046, and a p-value of less than 0.01, indicating a robust association between milk consumption and robberies in Rhode Island.
In this paper, we present our findings with a dairy-infused flair, leaving no stone-cold unchurned in our exploration of the dairy-crime nexus. From bovine serenity to lactase-induced larceny, this research aims to unravel the conundrum of how a seemingly innocuous beverage could potentially be intertwined with criminal activities.
So, grab a glass of milk, sit back, and prepare to be whipped into a frenzy of dairy-inspired revelations. Let the udderly captivating journey into the intriguing realm of milk and misdemeanors commence!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation into the relationship between milk consumption and robberies in Rhode Island unveiled a remarkably strong correlation, prompting both excitement and a sprinkling of dairy-related puns among the research team. From 1990 to 2021, the data led us on a wild "moo-sic"-filled journey, culminating in a correlation coefficient of 0.9269046 and an r-squared of 0.8591521. This bovine-inspired statistical revelation certainly churned up more than just data; it churned up a whole batch of dairy jokes to accompany our findings.

The p-value of less than 0.01 provided a level of significance that would make any statistical analysis tip its hat and say, "Well, butter my biscuit, that's some top-grade correlation!" Indeed, we were utterly thrilled by the robustness of the association between milk consumption and robberies, but perhaps not as much as we were thrilled about the opportunity to infuse the world of academia with dairy-based puns.

In Figure 1 (not provided here but incredibly moo-ving), we present a scatterplot that visually captures the strong correlation between milk consumption and robberies in Rhode Island. Picture a field of creamy data points marching in lockstep with crime rates, reminding us that not all correlations are as easy to swallow as a glass of milk.

Underlying this seemingly udderly bizarre relationship is a wealth of unanswered questions and a lactose-laden concoction of curiosity. Our results beg the question: Is it the calcium content in milk that lulls potential perpetrators into a state of calm, or is there a surreptitious lactose intolerance conspiracy at play, compelling individuals to engage in nefarious activities to secure the last lactose-free carton at the grocery store?

This correlation, akin to a creamy latte on a chilly morning, warms our academic hearts and tickles our scientific fancy. While the connection between milk consumption and crime in Rhode Island may seem like a whimsical yarn spun from a cheesy daydream, our findings stand as a beacon, urging further investigation into the enchanting nexus of dairy and deviance.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

[[LITERATURE REVIEW]]
Numerous scholarly works have attempted to discern the enigmatic relationship between milk consumption and criminal behavior. Smith et al., in their seminal study "Dairy Dynamics: Exploring the Correlation Between Milk Intake and Lawlessness," unearthed intriguing preliminary evidence suggesting a potential link between calcium-laden libations and unlawful activities. Doe and Jones expanded on this line of inquiry in "Milk and Misdemeanors: A Holistic Examination of Dairy Deviance," delving into lactose intolerance as a possible catalyst for nefarious deeds. Building on this foundation, our study endeavors to froth up the debate further, focusing specifically on the empirical nuances of milk consumption and its association with robberies in the state of Rhode Island.
Turning to the world of non-fiction literature, titles such as "Milk: A Complete Guide to Its Role in Human Health" and "The Big Moo: Stop Trying to Be Perfect and Start Being Remarkable" add richness to our understanding of milk's multifaceted influences. On the fictional front, works like "The Curious Incident of the Milk in the Night-Time" and "A Clockwork Orange Creamsicle" provide whimsical yet thought-provoking narratives that resonate with our research theme.
In the realm of popular culture, the ubiquitous "Got Milk?" campaign has seeped into the collective consciousness, with its iconic mustached celebrities leaving an indelible mark on milk's public image. Additionally, internet memes such as the "Milk Jug Bandit" have playfully toyed with the notion of milk-related crime, blurring the lines between internet humor and our serious academic inquiry.
As we embark on our investigation, we are attentive to the quixotic nature of our endeavor. However, armed with statistical rigor and a healthy dose of lactose-induced curiosity, we set forth to illuminate the creamy conundrum of dairy's potential impact on illicit activities. Through our exploration, we aim to bring a smile to the faces of readers and perhaps, it is our hope, to also bring a chuckle - a little dairy humor to whet the intellectual appetite.
So, without further ado, let us dive headfirst into the bewildering realm of milk, mischief, and the captivating nuances of our criminal yet calcium-rich world.

[[RESULTS]]
The results of our investigation into the relationship between milk consumption and robberies in Rhode Island unveiled a remarkably strong correlation, prompting both excitement and a sprinkling of dairy-related puns among the research team. From 1990 to 2021, the data led us on a wild "moo-sic"-filled journey, culminating in a correlation coefficient of 0.9269046 and an r-squared of 0.8591521. This bovine-inspired statistical revelation certainly churned up more than just data; it churned up a whole batch of dairy jokes to accompany our findings.
The p-value of less than 0.01 provided a level of significance that would make any statistical analysis tip its hat and say, "Well, butter my biscuit, that's some top-grade correlation!" Indeed, we were utterly thrilled by the robustness of the association between milk consumption and robberies, but perhaps not as much as we were thrilled about the opportunity to infuse the world of academia with dairy-based puns.
In Figure 1 (not provided here but incredibly moo-ving), we present a scatterplot that visually captures the strong correlation between milk consumption and robberies in Rhode Island. Picture a field of creamy data points marching in lockstep with crime rates, reminding us that not all correlations are as easy to swallow as a glass of milk.
Underlying this seemingly udderly bizarre relationship is a wealth of unanswered questions and a lactose-laden concoction of curiosity. Our results beg the question: Is it the calcium content in milk that lulls potential perpetrators into a state of calm, or is there a surreptitious lactose intolerance conspiracy at play, compelling individuals to engage in nefarious activities to secure the last lactose-free carton at the grocery store?
This correlation, akin to a creamy latte on a chilly morning, warms our academic hearts and tickles our scientific fancy. While the connection between milk consumption and crime in Rhode Island may seem like a whimsical yarn spun from a cheesy daydream, our findings stand as a beacon, urging further investigation into the enchanting nexus of dairy and deviance.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The robust correlation between milk consumption and robberies in Rhode Island has churned up quite the dairy delight, prompting us to lactose intolerantly thirst for more understanding of this utterly bewildering relationship. Our findings align with prior research, illuminating the exquisite dance of calcium-laden libations and illicit activities. The association between the two variables is as captivating as a thrilling true crime novel, leaving us with the lingering suspicion that there may be more than meets the eye – or should we say, the dairy – when it comes to criminal behavior.

Our study's results are like a finely aged cheese, only increasing in richness and complexity as we contemplate the potential mechanisms driving this correlation. Could it be that the calcium content in milk acts as a soothing balm on the wild hearts of would-be miscreants, or might lactose intolerance instigate a last-resort scramble for the last lactose-free carton, culminating in furtive capers and nefarious exploits? The creamy intrigue continues, leaving us with a delightful blend of scientific curiosity and mild confusion.

Drawing upon the delightful quixotry of prior literature, our study has essentially poured further cream into the milk-filled narrative of dairy's potential impact on criminal activities. In some ways, our findings have given the milk of human kindness new meaning, as we unravel the curdled mystery of how a seemingly innocuous beverage might intersect with the darker underbelly of human behavior.

Figure 1, awash with visually delightful creamy data points, serves as a visual testament to the strong correlation between milk consumption and robberies in Rhode Island. Imagine each data point as the frothy top of a latte, marching in harmonious lockstep with crime rates, reminding us that not all correlations are as easy to swallow as a glass of milk. The visual representation of our findings is as compelling as a Renaissance still life – an artistic portrayal of correlation that is both captivating and utterly milk-themed.

In conclusion, as we delve further into the creamy conundrum of dairy's potential impact on criminal activities, we are left with a lingering sense of awe and amusement. But, perhaps, there is also a faint whisper of skepticism, reminding us that correlation does not equate to causation – a reminder to approach our findings with a healthy dose of scientific scrutiny and a sprinkling of powdered sugar. So, join us as we raise a metaphorical glass of milk to future investigations, where we hope to sip on more answers and perhaps a few riddles offered by our dairy-infused world.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Milk consumption and Robberies in Rhode Island. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island"

[[ABSTRACT]]
The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

[[INTRDUCTION]]
Introduction
Milk, the creamy elixir that finds its way into our cereal bowls, coffee cups, and increasingly, into the annals of criminal research. The age-old question of whether "Got Milk?" leads to "Got Crime?" has sparked both curiosity and skepticism among scholars and aficionados of dairy. In this paper, we take a lactose-fueled leap into the synergistic world of milk consumption and robberies in the enchanting locale of Rhode Island.
Past studies have left us with a cheese-like hole in our understanding of the potential linkage between calcium-rich beverages and unlawful activities. Some have postulated that the calcium content in milk may exercise a calming effect on individuals, akin to the soothing strokes of a calcium-rich kitten. Conversely, others have suggested that lactose intolerance might lead to irritable dispositions, compelling individuals to take on acts of desperation, including perhaps snatching the last carton of lactose-free milk from the local supermarket.
As researchers, we were udderly intrigued by these ideas but remained skeptical, determined to separate the whey from the curds of speculation. Against this backdrop, we embarked on a quest to uncover whether the nuances of milk consumption could indeed influence the frequency of robberies in the smallest state in the union. We thirsted for knowledge, not only to quench our scientific curiosity but also to provide real-world implications for policymakers, law enforcement, and dairy enthusiasts alike.
Our mission led us to delve into a heaping bowl of data, drawing from the USDA's voluminous archives of milk consumption statistics and the FBI's Criminal Justice Information Services' treasure trove of crime data. From 1990 to 2021, we applied rigorous statistical analyses, embracing regression models, correlation coefficients, and other mathematical incantations in our pursuit of truth. Lo and behold, our findings yielded a correlation coefficient of 0.9269046, and a p-value of less than 0.01, indicating a robust association between milk consumption and robberies in Rhode Island.
In this paper, we present our findings with a dairy-infused flair, leaving no stone-cold unchurned in our exploration of the dairy-crime nexus. From bovine serenity to lactase-induced larceny, this research aims to unravel the conundrum of how a seemingly innocuous beverage could potentially be intertwined with criminal activities.
So, grab a glass of milk, sit back, and prepare to be whipped into a frenzy of dairy-inspired revelations. Let the udderly captivating journey into the intriguing realm of milk and misdemeanors commence!

[[RESULTS]]
The results of our investigation into the relationship between milk consumption and robberies in Rhode Island unveiled a remarkably strong correlation, prompting both excitement and a sprinkling of dairy-related puns among the research team. From 1990 to 2021, the data led us on a wild "moo-sic"-filled journey, culminating in a correlation coefficient of 0.9269046 and an r-squared of 0.8591521. This bovine-inspired statistical revelation certainly churned up more than just data; it churned up a whole batch of dairy jokes to accompany our findings.
The p-value of less than 0.01 provided a level of significance that would make any statistical analysis tip its hat and say, "Well, butter my biscuit, that's some top-grade correlation!" Indeed, we were utterly thrilled by the robustness of the association between milk consumption and robberies, but perhaps not as much as we were thrilled about the opportunity to infuse the world of academia with dairy-based puns.
In Figure 1 (not provided here but incredibly moo-ving), we present a scatterplot that visually captures the strong correlation between milk consumption and robberies in Rhode Island. Picture a field of creamy data points marching in lockstep with crime rates, reminding us that not all correlations are as easy to swallow as a glass of milk.
Underlying this seemingly udderly bizarre relationship is a wealth of unanswered questions and a lactose-laden concoction of curiosity. Our results beg the question: Is it the calcium content in milk that lulls potential perpetrators into a state of calm, or is there a surreptitious lactose intolerance conspiracy at play, compelling individuals to engage in nefarious activities to secure the last lactose-free carton at the grocery store?
This correlation, akin to a creamy latte on a chilly morning, warms our academic hearts and tickles our scientific fancy. While the connection between milk consumption and crime in Rhode Island may seem like a whimsical yarn spun from a cheesy daydream, our findings stand as a beacon, urging further investigation into the enchanting nexus of dairy and deviance.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

Concluding this dairy-fueled odyssey, our findings have churned up a robust correlation between milk consumption and robberies in Rhode Island. With a correlation coefficient of 0.9269046 and a p-value less than 0.01, it's clear that there's more to this creamy concoction than meets the eye. Our results suggest that this relationship is as tangible as a lactose-intolerant person's fear of an ice cream social. We've certainly milked this study for all it's worth, uncovering a dairy-infused connection that's no mere udder fantasy.

The implications of our findings are as rich and complex as a triple-layered cheesecake. Policymakers and law enforcement alike may need to rethink their crime-fighting strategies, considering the potential influence of calcium-rich beverages on criminal behavior. While our study brings a frothy concoction of questions to the forefront, such as whether milk mustaches are potential criminal trademarks, it also serves as a creamy reminder of the mysterious ways in which human behavior is influenced.

In the end, we must acknowledge the need for caution in interpretation, as correlation does not necessarily imply causation, but in this case, it does imply an opportunity for utterly hilarious research. As we raise a glass of milk to toast to our findings, we assert with udder certainty that no further research is needed in this dairy-drenched realm. The dairy-crime nexus has been churned, mixed, and frothed, leaving us all with a rich, creamy taste of scientific discovery that can only be described as utterly satisfying. And remember, folks, when it comes to getting to the bottom of unusual correlations, there's no use crying over unanalyzed milk!


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Milkology and Crime Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Holistic Dairy Research and Analysis


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Dairy Connection: Got Milk, Got Crime? A Study of Milk Consumption and Robberies in Rhode Island with an abstract of The relationship between milk consumption and criminal activity has long been a topic of debate, with speculation ranging from the potential effects of calcium on brain function to the role of lactose intolerance in promoting discontent. In this study, we delved into the creamy landscape of data on milk consumption and crime, focusing on the specific context of Rhode Island. Using comprehensive data from the USDA and the FBI Criminal Justice Information Services, we conducted a thorough analysis covering the period from 1990 to 2021. Our investigation revealed a surprisingly robust correlation coefficient of 0.9269046 and a p-value less than 0.01, suggesting a strong association between milk consumption and robberies in the Ocean State. The findings of this study not only shed light on the potential dynamics at play but also raise a frothy array of questions that warrant further exploration. Whether it’s the insidious influence of lactic acid or the elusive connection between milk mustaches and criminal masterminds, this research uncovers the curdled mystery of dairy's impact on illicit activities.

ChatGPT:

milk consumption, crime rate, Rhode Island, USDA data, FBI crime statistics, milk consumption and robberies, calcium and brain function, lactose intolerance and discontent, correlation coefficient, p-value, dairy impact on illicit activities

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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

Correlation r = 0.9269046 (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 = 0.8591521 (Coefficient of determination)
This means 85.9% of the change in the one variable (i.e., Robberies in Rhode Island) 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 2.6E-14. 0.0000000000000264107761747206
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.93 in 2.6E-12% of random cases. Said differently, if you correlated 37,863,332,504,297 random variables You don't actually need 37 trillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 31 degrees of freedom, 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.

[ 0.85, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
19901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021
Milk consumption (Pounds per person)220218215210208205205201198197196192191188185185185183181181177173169164158155153149145141141134
Robberies in Rhode Island (Robbery rate)122122.994.5101.187.392.383.271.666.779.5889385.777.167.772.369.371.883.774.574.370.868.164.850.251.851.244.942.839.831.825.3




Why this works

  1. Data dredging: I have 25,213 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 635,695,369 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([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([122,122.9,94.5,101.1,87.3,92.3,83.2,71.6,66.7,79.5,88,93,85.7,77.1,67.7,72.3,69.3,71.8,83.7,74.5,74.3,70.8,68.1,64.8,50.2,51.8,51.2,44.9,42.8,39.8,31.8,25.3,])
array_1_name = "Milk consumption"
array_2_name = "Robberies in Rhode Island"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!


Correlation ID: 1786 · Black Variable ID: 554 · Red Variable ID: 20214
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0