about · email me · subscribe
Spurious correlation #3,903 · 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 Arizona.  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

The decrease in milk consumption led to a decrease in lactose intolerance, resulting in less stomach discomfort and irritability, thus reducing the inclination to commit robberies in Arizona. Because when it comes to crime, it's all about keeping your calcium cool!

Model: dalle-3
Prompt: Generate an image of a warm and welcoming kitchen scene set in Arizona, where families are peacefully enjoying breakfast. Show a cozy interior with a clutter-free countertop holding a few cereal bowls and a half-full milk carton. The ambiance should evoke a sense of tranquility, with no signs of chaos or spills. Meanwhile, outside the kitchen window, depict quiet streets and a subtle decrease in criminal activity, symbolized by a lack of slippery surfaces hindering potential robbers. Capture the serene and idyllic atmosphere of a morning in Arizona, where safety and comfort prevail. 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 Arizona. 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: Cutsy art illustration Cute cartoon Hyper-realistic Macabre A scene from Skyrim
ChatGPT: A scene from Skyrim

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 Arizona, in the following situation: Because fewer people were eating cereal at night, they were less likely to spill milk, reducing slippery surfaces and making it harder for robbers to make a quick getaway.. Keep the description simple.
ChatGPT: In a cozy kitchen in Arizona, a few cereal bowls sit on the counter, with families enjoying their breakfast in the morning. The milk carton is half-full, and there are no spills in sight. Outside, the streets are quiet, and the police report fewer robberies thanks to the lack of slippery surfaces making it harder for robbers to escape.

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 scene from Skyrim ] and depicting this scene: In a cozy kitchen in Arizona, a few cereal bowls sit on the counter, with families enjoying their breakfast in the morning. The milk carton is half-full, and there are no spills in sight. Outside, the streets are quiet, and the police report fewer robberies thanks to the lack of slippery surfaces making it harder for robbers to escape. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a warm and welcoming kitchen scene set in Arizona, where families are peacefully enjoying breakfast. Show a cozy interior with a clutter-free countertop holding a few cereal bowls and a half-full milk carton. The ambiance should evoke a sense of tranquility, with no signs of chaos or spills. Meanwhile, outside the kitchen window, depict quiet streets and a subtle decrease in criminal activity, symbolized by a lack of slippery surfaces hindering potential robbers. Capture the serene and idyllic atmosphere of a morning in Arizona, where safety and comfort prevail.

*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 Arizona to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

The Journal of Bovine Behavior and Social Sciences

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 silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

Make the title seem 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 0.9305673 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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

When one thinks of the great state of Arizona, images of cacti, arid landscapes, and maybe even an occasional tumbleweed rolling by come to mind. However, what might be less expected is the possibility of a creamy, calcium-rich connection between milk consumption and robbery rates. Yes, you heard it right! The idea that something as innocent as sipping on a glass of moo juice could have any conceivable link to criminal activity may sound utterly preposterous, but our research has uncovered an utterly intriguing correlation that will definitely pique your curiosity.

Why, you may ask, would we embark on such a curious investigation? Well, to put it bluntly, we simply wanted to milk the opportunity to explore an unconventional and udderly amusing topic that challenges conventional thinking. Unveiling the relationship between milk and crime not only tickled our funny bones but also left us scratching our heads with bewilderment. It's not every day you get to ponder the possibility of dairy-induced delinquency, after all!

As we hoisted our statistical lassos and corralled the data from the USDA and FBI Criminal Justice Information Services, we were utterly astounded by what we found. Our analysis revealed a striking correlation coefficient of 0.9305673 and a p-value lower than a cow's belly for the years 1990 to 2021. To the skeptics out there, we assure you that these findings weren't pulled out of a cow pie. They're as real as a pasture full of grazing cattle.

So, what does this all mean? How do we make sense of these milk-gnificant findings, and where do we go from here? Before we delve into the udderly intriguing details, let's take a moment to appreciate the beauty of such dairy peculiarities and how they challenge our perceptions of cause and effect. What we've stumbled upon begs the question: Could there be something inherent in the creamy concoction of milk that churns up criminal behavior, or is this simply a case of statistical "udder" coincidence? Our study aims to delve into this murky pool of milk-sterious correlations and offer a fresh, unpasteurized perspective on the matter.

So, grab a cold glass of milk, take a seat, and prepare to be "udderly" entertained and enlightened as we unravel the bovine-induced riddles that lie within the dairy aisle of academia. This study doesn't just skim the surface of a seemingly absurd connection; it drinks deep from the milk jug of empirical udderstanding, all the while keeping a healthy dose of lactose-based humor in the mix. Welcome to the mooo-ving world of offbeat academic research!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. 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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
When one thinks of the great state of Arizona, images of cacti, arid landscapes, and maybe even an occasional tumbleweed rolling by come to mind. However, what might be less expected is the possibility of a creamy, calcium-rich connection between milk consumption and robbery rates. Yes, you heard it right! The idea that something as innocent as sipping on a glass of moo juice could have any conceivable link to criminal activity may sound utterly preposterous, but our research has uncovered an utterly intriguing correlation that will definitely pique your curiosity.
Why, you may ask, would we embark on such a curious investigation? Well, to put it bluntly, we simply wanted to milk the opportunity to explore an unconventional and udderly amusing topic that challenges conventional thinking. Unveiling the relationship between milk and crime not only tickled our funny bones but also left us scratching our heads with bewilderment. It's not every day you get to ponder the possibility of dairy-induced delinquency, after all!
As we hoisted our statistical lassos and corralled the data from the USDA and FBI Criminal Justice Information Services, we were utterly astounded by what we found. Our analysis revealed a striking correlation coefficient of 0.9305673 and a p-value lower than a cow's belly for the years 1990 to 2021. To the skeptics out there, we assure you that these findings weren't pulled out of a cow pie. They're as real as a pasture full of grazing cattle.
So, what does this all mean? How do we make sense of these milk-gnificant findings, and where do we go from here? Before we delve into the udderly intriguing details, let's take a moment to appreciate the beauty of such dairy peculiarities and how they challenge our perceptions of cause and effect. What we've stumbled upon begs the question: Could there be something inherent in the creamy concoction of milk that churns up criminal behavior, or is this simply a case of statistical "udder" coincidence? Our study aims to delve into this murky pool of milk-sterious correlations and offer a fresh, unpasteurized perspective on the matter.
So, grab a cold glass of milk, take a seat, and prepare to be "udderly" entertained and enlightened as we unravel the bovine-induced riddles that lie within the dairy aisle of academia. This study doesn't just skim the surface of a seemingly absurd connection; it drinks deep from the milk jug of empirical udderstanding, all the while keeping a healthy dose of lactose-based humor in the mix. Welcome to the mooo-ving world of offbeat academic research!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Numerous studies have delved into the intriguing realms of both dietary habits and criminal behavior. Smith and Doe (2015) investigated the impact of calcium-rich foods on the brain, while Jones et al. (2018) explored correlations between nutritional preferences and criminal decision-making. These studies laid the groundwork for our investigation into the curious connection between milk consumption and robbery rates in Arizona.

Turning to the world of non-fiction, "Milk: The Surprising Story of Milk Through the Ages" by Mark Kurlansky and "Gang Leader for a Day" by Sudhir Venkatesh are among the many sources that guided our exploration. Kurlansky's comprehensive history of milk provides a rich understanding of this dairy delight, while Venkatesh's immersive account of gang life in Chicago sheds light on the complex dynamics of criminal behavior.

In the realm of fiction, authors like Agatha Christie have woven tales of suspense and crime in settings where milk features prominently in the narrative. With stories such as "The Mirror Crack'd" and "The Moving Finger", Christie's mysteries offer a delightfully devious backdrop against which to ponder the unlikely pairing of dairy consumption and roguery.

Moreover, the internet meme culture has not been immune to mirthful musings on milk-related shenanigans. The "Got Milk?" advertising campaign, perhaps one of the most iconic and ubiquitous in recent memory, has elicited both chuckles and contemplations on the influence of the ubiquitous beverage. Likewise, the "Milkshake Duck" meme, with its veritable rollercoaster of emotions, serves as a quirky reminder of the unpredictable twists and turns in life – and in research.

With this diverse array of sources in mind, it's clear that our investigation into the linkage between milk consumption and robberies in Arizona is steeped in a rich tapestry of literature – both serious and light-hearted. This synthesis of perspectives sets the stage for our own buttery exploration of this utterly bewildering correlation. Hold onto your cowbells, because things are about to get milk-ceptionally wild!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

[[INTRODUCTION]]
When one thinks of the great state of Arizona, images of cacti, arid landscapes, and maybe even an occasional tumbleweed rolling by come to mind. However, what might be less expected is the possibility of a creamy, calcium-rich connection between milk consumption and robbery rates. Yes, you heard it right! The idea that something as innocent as sipping on a glass of moo juice could have any conceivable link to criminal activity may sound utterly preposterous, but our research has uncovered an utterly intriguing correlation that will definitely pique your curiosity.
Why, you may ask, would we embark on such a curious investigation? Well, to put it bluntly, we simply wanted to milk the opportunity to explore an unconventional and udderly amusing topic that challenges conventional thinking. Unveiling the relationship between milk and crime not only tickled our funny bones but also left us scratching our heads with bewilderment. It's not every day you get to ponder the possibility of dairy-induced delinquency, after all!
As we hoisted our statistical lassos and corralled the data from the USDA and FBI Criminal Justice Information Services, we were utterly astounded by what we found. Our analysis revealed a striking correlation coefficient of 0.9305673 and a p-value lower than a cow's belly for the years 1990 to 2021. To the skeptics out there, we assure you that these findings weren't pulled out of a cow pie. They're as real as a pasture full of grazing cattle.
So, what does this all mean? How do we make sense of these milk-gnificant findings, and where do we go from here? Before we delve into the udderly intriguing details, let's take a moment to appreciate the beauty of such dairy peculiarities and how they challenge our perceptions of cause and effect. What we've stumbled upon begs the question: Could there be something inherent in the creamy concoction of milk that churns up criminal behavior, or is this simply a case of statistical "udder" coincidence? Our study aims to delve into this murky pool of milk-sterious correlations and offer a fresh, unpasteurized perspective on the matter.
So, grab a cold glass of milk, take a seat, and prepare to be "udderly" entertained and enlightened as we unravel the bovine-induced riddles that lie within the dairy aisle of academia. This study doesn't just skim the surface of a seemingly absurd connection; it drinks deep from the milk jug of empirical udderstanding, all the while keeping a healthy dose of lactose-based humor in the mix. Welcome to the mooo-ving world of offbeat academic research!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the mooo-sterious connection between milk consumption and robberies in Arizona, we employed a methodological approach that was as rigorous as it was utterly pun-derful. Our research team, affectionately dubbed the "Milk Mates," embarked on a dairy-aired journey, navigating through statistical fields and pastures of data to churn out some calf-tivating insights.

Data Collection:
We rustled up data from the USDA and FBI Criminal Justice Information Services, meticulously sifting through datasets like a dairy farmer separating cream from milk. From 1990 to 2021, we milked these sources for all they were worth, gathering information on milk consumption patterns, robbery rates, and other relevant socio-economic variables.

Statistical Analysis:
The statistical tools we employed were as sharp as the tip of a cow's horn. We conducted a series of correlations and regressions, using techniques that were both udderly sophisticated and delightfully cheesy. Our analysis explored the relationship between monthly milk consumption per capita and monthly robbery rates, allowing us to milk out the underlying patterns and associations.

Control Variables:
To ensure our findings weren't just a case of "udder" coincidence, we roped in some control variables to corral the potential confounders. Factors such as unemployment rates, income levels, and demographic composition were included to keep our statistical pasture as fresh as possible and prevent any souring of the results.

Cow-rrections for Data Accuracy:
We didn't just take the data at face value; we milked every last bit of accuracy from it. Quality checks and verifications were conducted to ensure that our findings were as creamy and reliable as a tall glass of whole milk. After all, when it comes to statistical analysis, there's no room for half-and-half measures.

Robbery Classification:
We also mooo-ved towards a deeper understanding of robbery types, categorizing them into various "udderly" intriguing subgroups. This allowed us to explore whether certain types of robberies showed a stronger association with milk consumption, shedding light on the potential nuances in this peculiar relationship.

Ethical Considerations:
No cows were harmed in the making of this research, and all ethical guidelines for dairy-related studies were strictly adhered to. The utmost respect was paid to the privacy and confidentiality of the data sources, ensuring that the udderly fascinating findings we collected were obtained with the highest standards of integrity and respect.

In conclusion, our methodology was as thorough as it was delightfully whimsical, tapping into the full absurdity of investigating the connection between milk and crime. These methods allowed us to churn out findings that are not only statistically robust but also a delightful treat for the academic palate. Our study doesn't just skim the surface; it dives deep into the creamy depths of empirical inquiry, leaving no lactose stone unturned. And now, let's mooo-ve on to the results, where the real cream of the crop awaits!


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

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 0.9305673, r-squared of 0.8659556, 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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
When one thinks of the great state of Arizona, images of cacti, arid landscapes, and maybe even an occasional tumbleweed rolling by come to mind. However, what might be less expected is the possibility of a creamy, calcium-rich connection between milk consumption and robbery rates. Yes, you heard it right! The idea that something as innocent as sipping on a glass of moo juice could have any conceivable link to criminal activity may sound utterly preposterous, but our research has uncovered an utterly intriguing correlation that will definitely pique your curiosity.
Why, you may ask, would we embark on such a curious investigation? Well, to put it bluntly, we simply wanted to milk the opportunity to explore an unconventional and udderly amusing topic that challenges conventional thinking. Unveiling the relationship between milk and crime not only tickled our funny bones but also left us scratching our heads with bewilderment. It's not every day you get to ponder the possibility of dairy-induced delinquency, after all!
As we hoisted our statistical lassos and corralled the data from the USDA and FBI Criminal Justice Information Services, we were utterly astounded by what we found. Our analysis revealed a striking correlation coefficient of 0.9305673 and a p-value lower than a cow's belly for the years 1990 to 2021. To the skeptics out there, we assure you that these findings weren't pulled out of a cow pie. They're as real as a pasture full of grazing cattle.
So, what does this all mean? How do we make sense of these milk-gnificant findings, and where do we go from here? Before we delve into the udderly intriguing details, let's take a moment to appreciate the beauty of such dairy peculiarities and how they challenge our perceptions of cause and effect. What we've stumbled upon begs the question: Could there be something inherent in the creamy concoction of milk that churns up criminal behavior, or is this simply a case of statistical "udder" coincidence? Our study aims to delve into this murky pool of milk-sterious correlations and offer a fresh, unpasteurized perspective on the matter.
So, grab a cold glass of milk, take a seat, and prepare to be "udderly" entertained and enlightened as we unravel the bovine-induced riddles that lie within the dairy aisle of academia. This study doesn't just skim the surface of a seemingly absurd connection; it drinks deep from the milk jug of empirical udderstanding, all the while keeping a healthy dose of lactose-based humor in the mix. Welcome to the mooo-ving world of offbeat academic research!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis cow-nclude a striking correlation between milk consumption and robbery rates in Arizona. We found a correlation coefficient of 0.9305673 and an r-squared of 0.8659556 for the time period spanning from 1990 to 2021. This correlation is stronger than the grip of a calf on a milk bottle and has left us udderly speechless.

Fig. 1 displays a scatterplot that visually encapsulates this bovine-esque connection. One glance at this graph confirms that the relationship between milk consumption and robberies is not just a mere cowincidence, but rather an udderly compelling pattern that demands further scrutiny.

We must acknowledge that skepticism may arise among those who question the validity of our findings. We assure you that these results were not cooked up in some dairy-based daydream; rather, they are as robust as a mighty bull's horns. With a p-value of less than 0.01, the likelihood of this correlation being a statistical fluke is lower than a cow's belly dragging in the mud.

In light of these milk-sterious findings, we must embrace the thought that the dairy aisle may hold more than just gallons of creamy goodness. Could there be something inherently milky that churns up crime in the Grand Canyon State, or is this simply a case of statistical "udder" coincidence? We dare not milk the issue any further without thorough investigation.

These results elevate our understanding to a higher pasture, challenging conventional thinking and leading us to ponder the milk-nificent mysteries that lie within. As we tiptoe through the tulips of empirical udderstanding, we are reminded that the world of academia, much like a sprawling farmland, holds unexpected surprises and lessons waiting to be gleaned.

So, to anyone who still thinks that studying the relationship between milk consumption and robberies is utterly nonsensical, we say, "Don't have a cow!" These findings are as legitimate as a prized Holstein winning a blue ribbon at the county fair.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

[[LITERATURE REVIEW]]
Numerous studies have delved into the intriguing realms of both dietary habits and criminal behavior. Smith and Doe (2015) investigated the impact of calcium-rich foods on the brain, while Jones et al. (2018) explored correlations between nutritional preferences and criminal decision-making. These studies laid the groundwork for our investigation into the curious connection between milk consumption and robbery rates in Arizona.
Turning to the world of non-fiction, "Milk: The Surprising Story of Milk Through the Ages" by Mark Kurlansky and "Gang Leader for a Day" by Sudhir Venkatesh are among the many sources that guided our exploration. Kurlansky's comprehensive history of milk provides a rich understanding of this dairy delight, while Venkatesh's immersive account of gang life in Chicago sheds light on the complex dynamics of criminal behavior.
In the realm of fiction, authors like Agatha Christie have woven tales of suspense and crime in settings where milk features prominently in the narrative. With stories such as "The Mirror Crack'd" and "The Moving Finger", Christie's mysteries offer a delightfully devious backdrop against which to ponder the unlikely pairing of dairy consumption and roguery.
Moreover, the internet meme culture has not been immune to mirthful musings on milk-related shenanigans. The "Got Milk?" advertising campaign, perhaps one of the most iconic and ubiquitous in recent memory, has elicited both chuckles and contemplations on the influence of the ubiquitous beverage. Likewise, the "Milkshake Duck" meme, with its veritable rollercoaster of emotions, serves as a quirky reminder of the unpredictable twists and turns in life – and in research.
With this diverse array of sources in mind, it's clear that our investigation into the linkage between milk consumption and robberies in Arizona is steeped in a rich tapestry of literature – both serious and light-hearted. This synthesis of perspectives sets the stage for our own buttery exploration of this utterly bewildering correlation. Hold onto your cowbells, because things are about to get milk-ceptionally wild!

[[RESULTS]]
The results of our analysis cow-nclude a striking correlation between milk consumption and robbery rates in Arizona. We found a correlation coefficient of 0.9305673 and an r-squared of 0.8659556 for the time period spanning from 1990 to 2021. This correlation is stronger than the grip of a calf on a milk bottle and has left us udderly speechless.
Fig. 1 displays a scatterplot that visually encapsulates this bovine-esque connection. One glance at this graph confirms that the relationship between milk consumption and robberies is not just a mere cowincidence, but rather an udderly compelling pattern that demands further scrutiny.
We must acknowledge that skepticism may arise among those who question the validity of our findings. We assure you that these results were not cooked up in some dairy-based daydream; rather, they are as robust as a mighty bull's horns. With a p-value of less than 0.01, the likelihood of this correlation being a statistical fluke is lower than a cow's belly dragging in the mud.
In light of these milk-sterious findings, we must embrace the thought that the dairy aisle may hold more than just gallons of creamy goodness. Could there be something inherently milky that churns up crime in the Grand Canyon State, or is this simply a case of statistical "udder" coincidence? We dare not milk the issue any further without thorough investigation.
These results elevate our understanding to a higher pasture, challenging conventional thinking and leading us to ponder the milk-nificent mysteries that lie within. As we tiptoe through the tulips of empirical udderstanding, we are reminded that the world of academia, much like a sprawling farmland, holds unexpected surprises and lessons waiting to be gleaned.
So, to anyone who still thinks that studying the relationship between milk consumption and robberies is utterly nonsensical, we say, "Don't have a cow!" These findings are as legitimate as a prized Holstein winning a blue ribbon at the county fair.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The correlation between milk consumption and robbery rates in Arizona, highlighted by our study, offers a veritable dairy tale of intrigue. Our findings not only milk-shake the existing literature but also churn up some wholly unexpected implications. With the r-squared of 0.8659556 and a correlation coefficient of 0.9305673, we've udderly confirmed a statistical connection that's stronger than a weightlifting cow.

Drawing from the bountiful udder-sourced wit in the literature review, let's not cry over spilled milk but instead pour over these milky connections. Smith and Doe's inquiry into calcium-rich foods and brain function sets the stage for our findings. It's no gouda to merely skim over the robustness of our correlation, which supports the notion that dairy intake may indeed impact cognitive and behavioral patterns – or perhaps there's a creamy caper at play in Arizona.

Let's not forget the influence of fiction on our investigation, as evident in Agatha Christie's work. Her devious narratives showcase the potential for seemingly innocent elements like milk to play a pivotal role in the commission of crimes. Similarly, the "Got Milk?" advertising campaign's far-reaching impact can't be dismissed as mere lactose-laden mirth. Its ubiquity suggests that milk may wield sway in unsuspected ways, a notion underpinned by our results.

Our findings certainly butter our understanding of criminal behavior, begging the question: Could milk consumption be a stealthy catalyst for misdeeds in Arizona? This study, much like a cow's curiosity, has led us to graze in uncharted pastures of empirical investigation. We've milked these findings for all they're worth, yet the reality remains as murky as skim milk on a cloudy day.

It's crucial to acknowledge potential limitations in our study, particularly the correlation-causation conundrum. While our results point to a compelling relationship, we'd caution against leaping to conclusions that milk consumption directly spurs criminal activity. As tempting as it may be to milk puns and indulge in a pasture of lactose-laden levity, the implications of our findings warrant a solemn consideration of their real-world impact.

In conclusion, our study has certainly churned up a plethora of thought-provoking musings. Whether we'll eventually have to cry over the spilt milk of erroneous assumptions or toast to the discovery of a truly milk-nificent mystery remains to be seen. This field of research, much like a spirited game of cow tipping, continues to offer us unexpected twists and challenges, underscoring the need for ongoing inquiry into the unpastureable connection between milk consumption and criminal behavior in Arizona.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 Arizona. Make lots of jokes, goofy observations, and puns.

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]]
Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona

[[ABSTRACT]]
This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

[[INTRDUCTION]]
When one thinks of the great state of Arizona, images of cacti, arid landscapes, and maybe even an occasional tumbleweed rolling by come to mind. However, what might be less expected is the possibility of a creamy, calcium-rich connection between milk consumption and robbery rates. Yes, you heard it right! The idea that something as innocent as sipping on a glass of moo juice could have any conceivable link to criminal activity may sound utterly preposterous, but our research has uncovered an utterly intriguing correlation that will definitely pique your curiosity.
Why, you may ask, would we embark on such a curious investigation? Well, to put it bluntly, we simply wanted to milk the opportunity to explore an unconventional and udderly amusing topic that challenges conventional thinking. Unveiling the relationship between milk and crime not only tickled our funny bones but also left us scratching our heads with bewilderment. It's not every day you get to ponder the possibility of dairy-induced delinquency, after all!
As we hoisted our statistical lassos and corralled the data from the USDA and FBI Criminal Justice Information Services, we were utterly astounded by what we found. Our analysis revealed a striking correlation coefficient of 0.9305673 and a p-value lower than a cow's belly for the years 1990 to 2021. To the skeptics out there, we assure you that these findings weren't pulled out of a cow pie. They're as real as a pasture full of grazing cattle.
So, what does this all mean? How do we make sense of these milk-gnificant findings, and where do we go from here? Before we delve into the udderly intriguing details, let's take a moment to appreciate the beauty of such dairy peculiarities and how they challenge our perceptions of cause and effect. What we've stumbled upon begs the question: Could there be something inherent in the creamy concoction of milk that churns up criminal behavior, or is this simply a case of statistical "udder" coincidence? Our study aims to delve into this murky pool of milk-sterious correlations and offer a fresh, unpasteurized perspective on the matter.
So, grab a cold glass of milk, take a seat, and prepare to be "udderly" entertained and enlightened as we unravel the bovine-induced riddles that lie within the dairy aisle of academia. This study doesn't just skim the surface of a seemingly absurd connection; it drinks deep from the milk jug of empirical udderstanding, all the while keeping a healthy dose of lactose-based humor in the mix. Welcome to the mooo-ving world of offbeat academic research!

[[RESULTS]]
The results of our analysis cow-nclude a striking correlation between milk consumption and robbery rates in Arizona. We found a correlation coefficient of 0.9305673 and an r-squared of 0.8659556 for the time period spanning from 1990 to 2021. This correlation is stronger than the grip of a calf on a milk bottle and has left us udderly speechless.
Fig. 1 displays a scatterplot that visually encapsulates this bovine-esque connection. One glance at this graph confirms that the relationship between milk consumption and robberies is not just a mere cowincidence, but rather an udderly compelling pattern that demands further scrutiny.
We must acknowledge that skepticism may arise among those who question the validity of our findings. We assure you that these results were not cooked up in some dairy-based daydream; rather, they are as robust as a mighty bull's horns. With a p-value of less than 0.01, the likelihood of this correlation being a statistical fluke is lower than a cow's belly dragging in the mud.
In light of these milk-sterious findings, we must embrace the thought that the dairy aisle may hold more than just gallons of creamy goodness. Could there be something inherently milky that churns up crime in the Grand Canyon State, or is this simply a case of statistical "udder" coincidence? We dare not milk the issue any further without thorough investigation.
These results elevate our understanding to a higher pasture, challenging conventional thinking and leading us to ponder the milk-nificent mysteries that lie within. As we tiptoe through the tulips of empirical udderstanding, we are reminded that the world of academia, much like a sprawling farmland, holds unexpected surprises and lessons waiting to be gleaned.
So, to anyone who still thinks that studying the relationship between milk consumption and robberies is utterly nonsensical, we say, "Don't have a cow!" These findings are as legitimate as a prized Holstein winning a blue ribbon at the county fair.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our findings have churned up quite the commotion in the world of empirical udderstanding. The correlation between milk consumption and robberies in Arizona has left us utterly mooo-dified. It's a case where it's not just the robbers who are doing the milking! The results of this study not only raise eyebrows but also raise udders in surprise.

The milk-terious connection we uncovered is as intriguing as trying to find a needle in a haystack - or in this case, a haystack of milk cartons. We udderstand if some are skeptical, but the statistical evidence is as strong as a bull's determination in a china shop. Furthermore, the significance of the correlation is about as rare as finding a cow jumping over the moon.

It's safe to say that we've milked this topic for all it's worth, and we can confidently assert that no more research is needed in this area. As the saying goes, "Let's not cry over spilled milk." The findings stand as sturdy as a barn in a storm, and any further investigation would be as unnecessary as bringing ice cream to the Arctic. So, let's put a lid on this study and moove on to greener pastures of research.

With this lactose-laden laughter, we bid adieu to the cow-mical world of milk-related crime correlations. Until next time, may the dairy be ever in your favor!


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 Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Bovine Behavior and Social Sciences


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 Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Dairy Research and Crime 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 Got Milk? An Udderly Surprising Connection: Assessing the Correlation Between Milk Consumption and Robberies in Arizona with an abstract of This study examines an exceptionally curious topic that's got everyone asking, "What in the hay?" We investigated the relationship between milk consumption and rates of robbery in Arizona with a statistical approach that's a-moo-sing to many. By analyzing data from the USDA and FBI Criminal Justice Information Services, we discovered a correlation coefficient of 0.9305673 and a p-value less than 0.01 for the years 1990 to 2021. Our findings are truly milk-teresting and raise some questions that are truly unpastureable, offering food for thought that's utterly thought-provoking. We suggest that researchers should not only think outside the milk carton but also keep an open mind to uncovering the dairy peculiarities behind this connection. This study aims to contribute to the field of empirical udderstanding and provide a dose of lactose-based humor to the world of academia.

ChatGPT:

milk consumption, robbery rates, correlation, Arizona, USDA data, FBI crime statistics, statistical analysis, empirical study

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

Correlation r = 0.9305673 (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 = 0.8659556 (Coefficient of determination)
This means 86.6% of the change in the one variable (i.e., Robberies in Arizona) is predictable based on the change in the other (i.e., Milk consumption) over the 32 years from 1990 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.3E-14. 0.0000000000000125218128037535
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 1.3E-12% of random cases. Said differently, if you correlated 79,860,641,240,400 random variables You don't actually need 79 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.

[ 0.86, 0.97 ] 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 Arizona (Robbery rate)160.9165.7153.1162.9162173.8167.8165.7165.2152.5146.3167.1147136.6134.5144.1153.9154150.9124.3108.4110.5112.7100.392.593.3102105.590.986.583.772.5




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




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([160.9,165.7,153.1,162.9,162,173.8,167.8,165.7,165.2,152.5,146.3,167.1,147,136.6,134.5,144.1,153.9,154,150.9,124.3,108.4,110.5,112.7,100.3,92.5,93.3,102,105.5,90.9,86.5,83.7,72.5,])
array_1_name = "Milk consumption"
array_2_name = "Robberies in Arizona"

# 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?

Your rating skills are top-notch!


Correlation ID: 3903 · Black Variable ID: 554 · Red Variable ID: 20193
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0