about · email me · subscribe
Spurious correlation #4,020 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of locker room attendants in Michigan and the second variable is Carjackings in the US.  The chart goes from 2003 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the number of locker room attendants in Michigan dwindled, so did the availability of fresh towels. This unexpected towel shortage led to a decrease in carjackings across the US, as would-be thieves found it much harder to get a clean getaway. It seems that without those fluffy incentives, the criminals just couldn't make the "heist and dry"!

Model: dalle-3
Prompt: Generate an image of a futuristic gym parking lot in Michigan, bustling with activity as several high-tech locker room attendants diligently monitor rows of sleek, metallic lockers. In the background, shadowy figures lurk behind a row of lockers, waiting to surprise unsuspecting gym-goers and steal their keys. The scene captures the high-tech contrast between the vigilant attendants and the covert carjackers, highlighting the technological advances amidst the threat of theft. 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: The number of locker room attendants in Michigan and Carjackings in the US. 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: a funny image you would see on reddit Cyber folk High-tech Futuristic Cutsy graphics
ChatGPT: High-tech

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 The number of locker room attendants in Michigan and Carjackings in the US, in the following situation: Carjackings in the US increased because with fewer locker room attendants in Michigan, there were more unattended lockers for thieves to hide in and surprise unsuspecting gym goers. This led to an increase in stolen keys and car thefts from gym parking lots across the country.. Keep the description simple.
ChatGPT: In a bustling gym parking lot, several locker room attendants in Michigan diligently monitor the rows of lockers, while in the background, carjackers take advantage of the increased number of unattended lockers. Hidden behind a row of lockers, they wait to surprise unsuspecting gym goers and steal their keys, leading to a surge in car thefts across the country.

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: [ High-tech ] and depicting this scene: In a bustling gym parking lot, several locker room attendants in Michigan diligently monitor the rows of lockers, while in the background, carjackers take advantage of the increased number of unattended lockers. Hidden behind a row of lockers, they wait to surprise unsuspecting gym goers and steal their keys, leading to a surge in car thefts across the country. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic gym parking lot in Michigan, bustling with activity as several high-tech locker room attendants diligently monitor rows of sleek, metallic lockers. In the background, shadowy figures lurk behind a row of lockers, waiting to surprise unsuspecting gym-goers and steal their keys. The scene captures the high-tech contrast between the vigilant attendants and the covert carjackers, highlighting the technological advances amidst the threat of theft.

*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 The number of locker room attendants in Michigan caused Carjackings in the US to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

Journal of Crime and Laughter

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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Bureau of Larbor Statistics and Bureau of Justice Statistics to assess this nagging question. You found a correlation coefficient of 0.8187273 and p < 0.01 for 2003 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]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the realm of statistics, one often encounters unexpected and confounding connections. Our study delves into the peculiar and perhaps improbable relationship between the number of locker room attendants in Michigan and carjackings in the United States. While these two subjects may seem as unrelated as a pair of mismatched socks, our research has uncovered a statistical linkage that is as surprising as finding a pineapple on a pizza – it defies conventional wisdom and piques the curiosity of even the most seasoned statistical sleuths.

As the proverbial plot thickens, one may wonder, how could the presence of locker room attendants in a Midwestern state possibly be associated with the occurrence of vehicular theft on a national scale? It is indeed a head-scratcher of a question, but we are not here to simply scratch our heads. We are here to rigorously analyze data, crunch numbers, and serve up a statistical feast that will satisfy even the most discerning appetites for empirical inquiry.

Our study aims to provide an engrossing exploration of this perplexing correlation, invoking a journey into the curious corridors of statistical significance. By mining data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, we have embarked on a voyage that promises to deliver not only a deeper understanding of this unlikely association but also a few unexpected chuckles along the way. The central thesis of our inquiry may seem as improbable as finding a unicorn in a field of cabbages, but we assure our esteemed readers that our findings are as robust as a sturdy oak tree in a tempest.

Through the application of cutting-edge statistical techniques, we have calculated a correlation coefficient that is as striking as a bolt of lightning on a clear summer day. Our results, replete with their statistical significance and unpredicted coherence, will cast a spotlight on the intersection of seemingly disparate variables and prompt contemplation of the intricate tapestry of causation and correlation.

So gather around, dear readers, as we unravel the enigma of locker room attendants and carjackings. This scholarly odyssey promises to be as enlightening as it is entertaining, demonstrating the whimsical and thought-provoking outcomes that can stem from the meticulous scrutiny of data. Let us embark on this intellectual adventure, armed with statistical rigor and a sense of humor, as we unveil the mysteries of "Lock and Steal."


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of locker room attendants in Michigan and Carjackings in the US. 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. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of statistics, one often encounters unexpected and confounding connections. Our study delves into the peculiar and perhaps improbable relationship between the number of locker room attendants in Michigan and carjackings in the United States. While these two subjects may seem as unrelated as a pair of mismatched socks, our research has uncovered a statistical linkage that is as surprising as finding a pineapple on a pizza – it defies conventional wisdom and piques the curiosity of even the most seasoned statistical sleuths.
As the proverbial plot thickens, one may wonder, how could the presence of locker room attendants in a Midwestern state possibly be associated with the occurrence of vehicular theft on a national scale? It is indeed a head-scratcher of a question, but we are not here to simply scratch our heads. We are here to rigorously analyze data, crunch numbers, and serve up a statistical feast that will satisfy even the most discerning appetites for empirical inquiry.
Our study aims to provide an engrossing exploration of this perplexing correlation, invoking a journey into the curious corridors of statistical significance. By mining data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, we have embarked on a voyage that promises to deliver not only a deeper understanding of this unlikely association but also a few unexpected chuckles along the way. The central thesis of our inquiry may seem as improbable as finding a unicorn in a field of cabbages, but we assure our esteemed readers that our findings are as robust as a sturdy oak tree in a tempest.
Through the application of cutting-edge statistical techniques, we have calculated a correlation coefficient that is as striking as a bolt of lightning on a clear summer day. Our results, replete with their statistical significance and unpredicted coherence, will cast a spotlight on the intersection of seemingly disparate variables and prompt contemplation of the intricate tapestry of causation and correlation.
So gather around, dear readers, as we unravel the enigma of locker room attendants and carjackings. This scholarly odyssey promises to be as enlightening as it is entertaining, demonstrating the whimsical and thought-provoking outcomes that can stem from the meticulous scrutiny of data. Let us embark on this intellectual adventure, armed with statistical rigor and a sense of humor, as we unveil the mysteries of "Lock and Steal."

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In the realm of statistical inquiry, few subjects have sparked as much curiosity and bewilderment as the connection between the number of locker room attendants in Michigan and the prevalence of carjackings in the United States. While one may initially raise an eyebrow at the seemingly absurd juxtaposition of these two phenomena, the literature contains a surprising array of insights that speak to the intersection of these seemingly unrelated variables.

Smith, Doe, and Jones (2015) conducted a groundbreaking study that delved into the social and economic implications of service industry employment in the Midwest. While their focus was not explicitly on car theft, their findings shed light on the complex dynamics of labor markets in states such as Michigan, which serve as a potential breeding ground for offbeat statistical associations.

Expanding our horizons beyond the strictly empirical, "The Art of Carjacking: A Comprehensive Guide" by Auto Theft Enthusiasts Publishing (2010) offers a thought-provoking exploration of the cultural, psychological, and logistical dimensions of vehicular theft. While this volume may not directly address the role of locker room attendants, its insights into the world of car theft prompt us to consider the myriad factors that might contribute to this phenomenon.

In a more lighthearted yet surprisingly relevant addition to the literature, the classic board game "Clue" by Parker Brothers (1949) invites players to investigate a murder in a mansion, incorporating various elements of deception and sleuthing. While the game revolves around solving a high-stakes crime rather than analyzing statistical patterns, its emphasis on uncovering unexpected connections and piecing together disparate clues serves as a whimsical parallel to our own research endeavors.

On a more fictional note, the novel "Locke & Key" by Joe Hill (2008) weaves a tale of supernatural intrigue and hidden secrets, all centered around a mysterious set of magical keys. While the book may not contribute directly to the empirical understanding of car theft or labor markets, its thematic exploration of concealed correlations and enigmatic connections serves as a literary nod to the enigmatic interplay between locker room attendants and carjackings.

As we navigate through this eclectic array of literature, we are reminded that the pursuit of knowledge often leads us down unexpected avenues. While our investigation may appear to be a statistical rollercoaster with a penchant for the bizarre, we remain steadfast in our commitment to unraveling the peculiar entanglement of locker room attendants and carjackings. As we proceed with our analysis, we invite readers to embrace both the serious and the absurd aspects of our scholarly pursuit, knowing that behind every statistical correlation lies the potential for a dash of unexpected humor.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Bureau of Justice Statistics . You used data from 2003 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]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

[[INTRODUCTION]]
In the realm of statistics, one often encounters unexpected and confounding connections. Our study delves into the peculiar and perhaps improbable relationship between the number of locker room attendants in Michigan and carjackings in the United States. While these two subjects may seem as unrelated as a pair of mismatched socks, our research has uncovered a statistical linkage that is as surprising as finding a pineapple on a pizza – it defies conventional wisdom and piques the curiosity of even the most seasoned statistical sleuths.
As the proverbial plot thickens, one may wonder, how could the presence of locker room attendants in a Midwestern state possibly be associated with the occurrence of vehicular theft on a national scale? It is indeed a head-scratcher of a question, but we are not here to simply scratch our heads. We are here to rigorously analyze data, crunch numbers, and serve up a statistical feast that will satisfy even the most discerning appetites for empirical inquiry.
Our study aims to provide an engrossing exploration of this perplexing correlation, invoking a journey into the curious corridors of statistical significance. By mining data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, we have embarked on a voyage that promises to deliver not only a deeper understanding of this unlikely association but also a few unexpected chuckles along the way. The central thesis of our inquiry may seem as improbable as finding a unicorn in a field of cabbages, but we assure our esteemed readers that our findings are as robust as a sturdy oak tree in a tempest.
Through the application of cutting-edge statistical techniques, we have calculated a correlation coefficient that is as striking as a bolt of lightning on a clear summer day. Our results, replete with their statistical significance and unpredicted coherence, will cast a spotlight on the intersection of seemingly disparate variables and prompt contemplation of the intricate tapestry of causation and correlation.
So gather around, dear readers, as we unravel the enigma of locker room attendants and carjackings. This scholarly odyssey promises to be as enlightening as it is entertaining, demonstrating the whimsical and thought-provoking outcomes that can stem from the meticulous scrutiny of data. Let us embark on this intellectual adventure, armed with statistical rigor and a sense of humor, as we unveil the mysteries of "Lock and Steal."

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To explore the potential link between the number of locker room attendants in Michigan and carjackings in the United States, our research team embarked on a quest that resembled a statistical scavenger hunt. We scoured the digital landscapes of the Bureau of Labor Statistics and the Bureau of Justice Statistics, akin to intrepid explorers navigating the vast and treacherous terrain of the internet. Our data collection efforts took us through the proverbial labyrinth of spreadsheets, charts, and tables, with occasional detours into the confusing realm of government websites. After painstakingly collecting and organizing the relevant data from 2003 to 2021, we emerged triumphantly with a plethora of numbers that were as abundant as a cornucopia of statistical delights.

The statistical analysis employed in this study involved techniques as diverse as a smorgasbord of statistical methods. We conducted a series of regression analyses, harnessing the power of multiple linear regression to unveil the potential relationship between the number of locker room attendants in Michigan and the incidence of carjackings in the United States. By manipulating matrices and pondering over residuals, we distilled the essence of our data into a cohesive framework that was as sturdy as the foundation of a mighty empire.

Moreover, we also ventured into the realm of time series analysis, viewing our data through the lens of temporal dynamics that was as mesmerizing as watching a time-lapse video of a blooming flower. Investigating the temporal patterns of locker room attendants and carjackings allowed us to capture the ebb and flow of this quirky connection, akin to witnessing the tides of a statistical ocean. Our statistical journey through time was rife with surprises and revelations, enriching our understanding of the nuanced interplay between these seemingly disparate variables.

Additionally, we conducted sensitivity analyses and robustness checks to ensure the reliability and validity of our findings, safeguarding our conclusions against unforeseen statistical pitfalls. Our methodology was as thorough as a meticulous librarian organizing a labyrinthine collection of books, ensuring that our results stood as resolutely as a granite statue in the face of statistical scrutiny.

In essence, our methodology embodied the essence of tenacious statistical inquiry, flavored with a hint of quirkiness and a dollop of academic rigor. With data collection techniques as diverse as a box of assorted chocolates and statistical analyses as robust as a sturdy oak tree in a tempest, our methodological approach laid the groundwork for uncovering the unexpected and enigmatic intersection of lockers and stolen cars.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Bureau of Justice Statistics .

For the time period 2003 to 2021, you found a correlation 0.8187273, r-squared of 0.6703144, 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]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of statistics, one often encounters unexpected and confounding connections. Our study delves into the peculiar and perhaps improbable relationship between the number of locker room attendants in Michigan and carjackings in the United States. While these two subjects may seem as unrelated as a pair of mismatched socks, our research has uncovered a statistical linkage that is as surprising as finding a pineapple on a pizza – it defies conventional wisdom and piques the curiosity of even the most seasoned statistical sleuths.
As the proverbial plot thickens, one may wonder, how could the presence of locker room attendants in a Midwestern state possibly be associated with the occurrence of vehicular theft on a national scale? It is indeed a head-scratcher of a question, but we are not here to simply scratch our heads. We are here to rigorously analyze data, crunch numbers, and serve up a statistical feast that will satisfy even the most discerning appetites for empirical inquiry.
Our study aims to provide an engrossing exploration of this perplexing correlation, invoking a journey into the curious corridors of statistical significance. By mining data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, we have embarked on a voyage that promises to deliver not only a deeper understanding of this unlikely association but also a few unexpected chuckles along the way. The central thesis of our inquiry may seem as improbable as finding a unicorn in a field of cabbages, but we assure our esteemed readers that our findings are as robust as a sturdy oak tree in a tempest.
Through the application of cutting-edge statistical techniques, we have calculated a correlation coefficient that is as striking as a bolt of lightning on a clear summer day. Our results, replete with their statistical significance and unpredicted coherence, will cast a spotlight on the intersection of seemingly disparate variables and prompt contemplation of the intricate tapestry of causation and correlation.
So gather around, dear readers, as we unravel the enigma of locker room attendants and carjackings. This scholarly odyssey promises to be as enlightening as it is entertaining, demonstrating the whimsical and thought-provoking outcomes that can stem from the meticulous scrutiny of data. Let us embark on this intellectual adventure, armed with statistical rigor and a sense of humor, as we unveil the mysteries of "Lock and Steal."

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

In the pursuit of unraveling the statistical relationship between the number of locker room attendants in Michigan and carjackings in the United States, our research team has navigated a path riddled with both disbelief and amusement. Despite initial skepticism surrounding the plausibility of such an association, our findings revealed a significant correlation coefficient of 0.8187273, with an r-squared of 0.6703144, and a p-value of less than 0.01 for the period spanning from 2003 to 2021.

The correlation coefficient of 0.8187273 suggests a strong positive relationship between the two variables, akin to an unexpected friendship between a polar bear and a penguin. This indicates that as the number of locker room attendants in Michigan increased, there was a notable tendency for carjackings in the US to also rise. The r-squared of 0.6703144 further emphasizes the substantial degree to which the variance in carjackings can be explained by the variance in the number of locker room attendants.

To visually capture the robustness of this relationship, we present Figure 1, a scatterplot that proudly displays the tightly woven connection between these seemingly unrelated phenomena. This scatterplot serves as a poignant reminder of statistical surprises, much like stumbling upon a four-leaf clover in a sea of three-leafed specimens.

Our results have uncovered a correlation so unexpected and remarkable that it simulates the feeling of stumbling upon a unicorn in a world-renowned art museum – an utter shock, yet undeniably present. The statistical significance of our findings reaffirms that the universe of correlations is richer and more whimsical than initially presumed, not unlike finding a hidden treasure trove in a place long overlooked.

While unlocking the mysteries behind the connection of locker room attendants and carjackings, our findings cannot help but evoke a sense of irony and amusement. We invite readers to join us on this statistical rollercoaster, where improbable correlations and unexpected insights blend to form a tableau as amusing as it is enlightening. Our study stands as a testament to the serendipitous discoveries that await those who dare to explore the uncharted territories of statistical inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

[[LITERATURE REVIEW]]
In the realm of statistical inquiry, few subjects have sparked as much curiosity and bewilderment as the connection between the number of locker room attendants in Michigan and the prevalence of carjackings in the United States. While one may initially raise an eyebrow at the seemingly absurd juxtaposition of these two phenomena, the literature contains a surprising array of insights that speak to the intersection of these seemingly unrelated variables.
Smith, Doe, and Jones (2015) conducted a groundbreaking study that delved into the social and economic implications of service industry employment in the Midwest. While their focus was not explicitly on car theft, their findings shed light on the complex dynamics of labor markets in states such as Michigan, which serve as a potential breeding ground for offbeat statistical associations.
Expanding our horizons beyond the strictly empirical, "The Art of Carjacking: A Comprehensive Guide" by Auto Theft Enthusiasts Publishing (2010) offers a thought-provoking exploration of the cultural, psychological, and logistical dimensions of vehicular theft. While this volume may not directly address the role of locker room attendants, its insights into the world of car theft prompt us to consider the myriad factors that might contribute to this phenomenon.
In a more lighthearted yet surprisingly relevant addition to the literature, the classic board game "Clue" by Parker Brothers (1949) invites players to investigate a murder in a mansion, incorporating various elements of deception and sleuthing. While the game revolves around solving a high-stakes crime rather than analyzing statistical patterns, its emphasis on uncovering unexpected connections and piecing together disparate clues serves as a whimsical parallel to our own research endeavors.
On a more fictional note, the novel "Locke & Key" by Joe Hill (2008) weaves a tale of supernatural intrigue and hidden secrets, all centered around a mysterious set of magical keys. While the book may not contribute directly to the empirical understanding of car theft or labor markets, its thematic exploration of concealed correlations and enigmatic connections serves as a literary nod to the enigmatic interplay between locker room attendants and carjackings.
As we navigate through this eclectic array of literature, we are reminded that the pursuit of knowledge often leads us down unexpected avenues. While our investigation may appear to be a statistical rollercoaster with a penchant for the bizarre, we remain steadfast in our commitment to unraveling the peculiar entanglement of locker room attendants and carjackings. As we proceed with our analysis, we invite readers to embrace both the serious and the absurd aspects of our scholarly pursuit, knowing that behind every statistical correlation lies the potential for a dash of unexpected humor.

[[RESULTS]]
In the pursuit of unraveling the statistical relationship between the number of locker room attendants in Michigan and carjackings in the United States, our research team has navigated a path riddled with both disbelief and amusement. Despite initial skepticism surrounding the plausibility of such an association, our findings revealed a significant correlation coefficient of 0.8187273, with an r-squared of 0.6703144, and a p-value of less than 0.01 for the period spanning from 2003 to 2021.
The correlation coefficient of 0.8187273 suggests a strong positive relationship between the two variables, akin to an unexpected friendship between a polar bear and a penguin. This indicates that as the number of locker room attendants in Michigan increased, there was a notable tendency for carjackings in the US to also rise. The r-squared of 0.6703144 further emphasizes the substantial degree to which the variance in carjackings can be explained by the variance in the number of locker room attendants.
To visually capture the robustness of this relationship, we present Figure 1, a scatterplot that proudly displays the tightly woven connection between these seemingly unrelated phenomena. This scatterplot serves as a poignant reminder of statistical surprises, much like stumbling upon a four-leaf clover in a sea of three-leafed specimens.
Our results have uncovered a correlation so unexpected and remarkable that it simulates the feeling of stumbling upon a unicorn in a world-renowned art museum – an utter shock, yet undeniably present. The statistical significance of our findings reaffirms that the universe of correlations is richer and more whimsical than initially presumed, not unlike finding a hidden treasure trove in a place long overlooked.
While unlocking the mysteries behind the connection of locker room attendants and carjackings, our findings cannot help but evoke a sense of irony and amusement. We invite readers to join us on this statistical rollercoaster, where improbable correlations and unexpected insights blend to form a tableau as amusing as it is enlightening. Our study stands as a testament to the serendipitous discoveries that await those who dare to explore the uncharted territories of statistical inquiry.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The robust correlation identified between the number of locker room attendants in Michigan and carjackings in the United States opens the door to a realm of statistical oddities and unexpected connections. Our findings, akin to stumbling upon a hidden treasure map in a library book, add a touch of whimsy to the often-serious landscape of empirical inquiry.

Expanding on the quirky elements highlighted in the literature review, our research lends empirical support to the peculiar but plausible relationship between the presence of locker room attendants and the prevalence of carjackings. Smith, Doe, and Jones (2015) illuminated the socioeconomic complexities of service industry employment, unwittingly laying the groundwork for our investigation. Similarly, the dramatic irony of discovering a connection as unforeseen as a penguin navigating polar tundra adds a layer of amusement to the traditionally solemn practice of hypothesis testing.

Undoubtedly, our results align with the unexpected humor found in the exploration of concealed correlations and enigmatic connections, akin to the mystical keys within the pages of "Locke & Key" by Joe Hill (2008). Although not directly related to the empirical understanding of car theft or labor markets, the thematic undercurrents of concealed correlations in literature stand as a lighthearted nod to the enigmatic interplay between seemingly unrelated variables.

Despite the apparent absurdity of our investigation at its inception, the statistically significant correlation coefficient of 0.8187273 and the r-squared of 0.6703144 underscore the concrete nature of this unexpected linkage, serving as a whimsical reminder that truth, as they say, is often stranger than fiction. This unexpected statistical friendship between locker room attendants and carjackings offers a playful contrast to the serious pursuit of empirical knowledge, akin to discovering a witty joke in a textbook on calculus.

In essence, our research has unveiled a statistical rollercoaster ride infused with drollness and unpredictability, echoing the sentiment of unlocking the mysteries behind the connection of locker room attendants and carjackings. Our findings serve as both an amusement park for statistical enthusiasts and a significant contribution to the understanding of improbable correlations, underscoring the rich tapestry of relationships that can be uncovered through dedicated empirical inquiry.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of locker room attendants in Michigan and Carjackings in the US. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US

[[ABSTRACT]]
This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

[[INTRDUCTION]]
In the realm of statistics, one often encounters unexpected and confounding connections. Our study delves into the peculiar and perhaps improbable relationship between the number of locker room attendants in Michigan and carjackings in the United States. While these two subjects may seem as unrelated as a pair of mismatched socks, our research has uncovered a statistical linkage that is as surprising as finding a pineapple on a pizza – it defies conventional wisdom and piques the curiosity of even the most seasoned statistical sleuths.
As the proverbial plot thickens, one may wonder, how could the presence of locker room attendants in a Midwestern state possibly be associated with the occurrence of vehicular theft on a national scale? It is indeed a head-scratcher of a question, but we are not here to simply scratch our heads. We are here to rigorously analyze data, crunch numbers, and serve up a statistical feast that will satisfy even the most discerning appetites for empirical inquiry.
Our study aims to provide an engrossing exploration of this perplexing correlation, invoking a journey into the curious corridors of statistical significance. By mining data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, we have embarked on a voyage that promises to deliver not only a deeper understanding of this unlikely association but also a few unexpected chuckles along the way. The central thesis of our inquiry may seem as improbable as finding a unicorn in a field of cabbages, but we assure our esteemed readers that our findings are as robust as a sturdy oak tree in a tempest.
Through the application of cutting-edge statistical techniques, we have calculated a correlation coefficient that is as striking as a bolt of lightning on a clear summer day. Our results, replete with their statistical significance and unpredicted coherence, will cast a spotlight on the intersection of seemingly disparate variables and prompt contemplation of the intricate tapestry of causation and correlation.
So gather around, dear readers, as we unravel the enigma of locker room attendants and carjackings. This scholarly odyssey promises to be as enlightening as it is entertaining, demonstrating the whimsical and thought-provoking outcomes that can stem from the meticulous scrutiny of data. Let us embark on this intellectual adventure, armed with statistical rigor and a sense of humor, as we unveil the mysteries of "Lock and Steal."

[[RESULTS]]
In the pursuit of unraveling the statistical relationship between the number of locker room attendants in Michigan and carjackings in the United States, our research team has navigated a path riddled with both disbelief and amusement. Despite initial skepticism surrounding the plausibility of such an association, our findings revealed a significant correlation coefficient of 0.8187273, with an r-squared of 0.6703144, and a p-value of less than 0.01 for the period spanning from 2003 to 2021.
The correlation coefficient of 0.8187273 suggests a strong positive relationship between the two variables, akin to an unexpected friendship between a polar bear and a penguin. This indicates that as the number of locker room attendants in Michigan increased, there was a notable tendency for carjackings in the US to also rise. The r-squared of 0.6703144 further emphasizes the substantial degree to which the variance in carjackings can be explained by the variance in the number of locker room attendants.
To visually capture the robustness of this relationship, we present Figure 1, a scatterplot that proudly displays the tightly woven connection between these seemingly unrelated phenomena. This scatterplot serves as a poignant reminder of statistical surprises, much like stumbling upon a four-leaf clover in a sea of three-leafed specimens.
Our results have uncovered a correlation so unexpected and remarkable that it simulates the feeling of stumbling upon a unicorn in a world-renowned art museum – an utter shock, yet undeniably present. The statistical significance of our findings reaffirms that the universe of correlations is richer and more whimsical than initially presumed, not unlike finding a hidden treasure trove in a place long overlooked.
While unlocking the mysteries behind the connection of locker room attendants and carjackings, our findings cannot help but evoke a sense of irony and amusement. We invite readers to join us on this statistical rollercoaster, where improbable correlations and unexpected insights blend to form a tableau as amusing as it is enlightening. Our study stands as a testament to the serendipitous discoveries that await those who dare to explore the uncharted territories of statistical inquiry.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has untangled the web of correlation between the number of locker room attendants in Michigan and carjackings in the United States, revealing a connection as surprising as discovering a penguin in the Sahara – unexpected yet undeniably present. The robust correlation coefficient of 0.8187273 serves as an eccentric dance partner in the statistical waltz, demonstrating a strong positive relationship that would make even the most seasoned statistician do a double-take.

The r-squared value of 0.6703144 further enhances the vividness of this statistical tapestry, illustrating that the variance in carjackings can be ascribed to the variance in the number of locker room attendants with a degree of certainty akin to finding a parking spot in a crowded mall on a busy Saturday afternoon.

As we bid adieu to this unusual and enthralling journey, we must acknowledge the plethora of whimsical surprises that statistical inquiry has to offer. The visual depiction of our findings in Figure 1 is as eye-catching as a neon sign in the desert, boldly proclaiming the existence of this improbable yet tangible relationship.

Despite the undeniable amusement that this correlation brings, we must solemnly declare that no further research is needed in this area. We present this study as a lighthearted monument to the delightful eccentricities that statistical analysis can uncover, much like stumbling upon a treasure map that leads to a pot of gold at the end of a rainbow – improbable, delightful, and thoroughly enjoyable.

As we turn the final page of this statistical rollercoaster, we hope our findings will inspire future researchers to venture into the uncharted territories of statistical inquiry, reminding them that the realm of correlations is as unpredictable and amusing as a surprise birthday party at a statistics conference.


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 Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Crime and Laughter


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 Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US. Respond only with the name of a fictional organization.

ChatGPT:

The Consortium for Unconventional Social Research (CUSP)


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 Lock and Steal: Exploring the Potential Link between Locker Room Attendants in Michigan and Carjackings in the US with an abstract of This paper investigates the intriguing and somewhat comical relationship between the number of locker room attendants in Michigan and carjackings in the United States. Drawing on data from the Bureau of Labor Statistics and the Bureau of Justice Statistics, our research team has endeavored to shed light on this unusual yet captivating connection. By employing statistical analysis, we have established a significant correlation coefficient of 0.8187273 with a p-value of less than 0.01 for the period spanning from 2003 to 2021. The results are remarkable, and we invite readers to embark on this statistical rollercoaster ride with us as we navigate the surprising intersection of locker room attendants and carjackings. Our findings may elicit both laughter and reflection, serving as a delightful reminder of the quirky correlations that can be uncovered through rigorous statistical inquiry.

ChatGPT:

locker room attendants, carjackings, Michigan, United States, Bureau of Labor Statistics, Bureau of Justice Statistics, statistical analysis, correlation coefficient, p-value, quirky correlations

*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

The number of locker room attendants in Michigan
Detailed data title: BLS estimate of locker room, coatroom, and dressing room attendants in Michigan
Source: Bureau of Larbor Statistics
See what else correlates with The number of locker room attendants in Michigan

Carjackings in the US
Detailed data title: Rate of nonfatal carjacking victimization per 1,000 persons age 16 or older (3-year moving averages)
Source: Bureau of Justice Statistics
See what else correlates with Carjackings in the US

Correlation r = 0.8187273 (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 = 0.6703144 (Coefficient of determination)
This means 67% of the change in the one variable (i.e., Carjackings in the US) is predictable based on the change in the other (i.e., The number of locker room attendants in Michigan) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.8E-5. 0.0000182131962418103250000000
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 0.82 in 0.0018% of random cases. Said differently, if you correlated 54,905 random variables You don't actually need 54 thousand 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 18 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.58, 0.93 ] 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.
2003200420052006200720082009201020112012201320142015201620172018201920202021
The number of locker room attendants in Michigan (Laborers)11201070930690790690690420410440500530600570580410350150830
Carjackings in the US (Carjackings)0.230.190.220.1850.1850.1850.150.130.090.090.120.150.140.110.090.10.10.10.12




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([1120,1070,930,690,790,690,690,420,410,440,500,530,600,570,580,410,350,150,830,])
array_2 = np.array([0.23,0.19,0.22,0.185,0.185,0.185,0.15,0.13,0.09,0.09,0.12,0.15,0.14,0.11,0.09,0.1,0.1,0.1,0.12,])
array_1_name = "The number of locker room attendants in Michigan"
array_2_name = "Carjackings in the US"

# 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 correlation inspection deserves a standing ovation!


Correlation ID: 4020 · Black Variable ID: 9737 · Red Variable ID: 1200
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0