Spurious correlation #2,445 · 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 food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and the second variable is Burglary rates in the US. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and the second variable is Burglary rates in the US. The chart goes from 2003 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the scent of perfectly roasted and baked goods dwindled, even the most notorious burglars couldn't resist turning over a new leaf. It turns out, these operators and tenders were the real unsung heroes of crime prevention, using their aromatic creations to butter up the would-be thieves, leaving them with a doughy-eyed longing for a life of buttery pastries instead of a career in burglary. Who kneaded security systems when the comforting aura of a cinnamon bun could do the trick? It was a classic case of "you can't have your cake and steal it too" as the state witnessed a crumb-believable drop in burglary rates, all thanks to the surprising influence of these unsung culinary crime stoppers! It just goes to show that sometimes, the most unexpected occupations can have a profound impact on law and odor.

^{Show image generation prompt} Model: dalle-3
Prompt: Prompt: Generate an image representing the scene described - a lively bakery with workers operating food and tobacco roasting, baking, and drying machines, causing a decrease in aspiring burglars. In contrast, during times of low demand for these workers, there is a surge in would-be burglars seeking alternative employment, leading to a rise in burglary rates. The image should have a humorous and whimsical tone fitting for a Reddit post. The focus should be on capturing the bustling bakery and the comical situation with the burglars in a simple and engaging manner. 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 food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and Burglary rates. 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: Cyberpunk Psychedelic a funny image macro Scalar art a funny image you would see on reddit
ChatGPT: a funny image you would see on reddit

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 food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and Burglary rates, in the following situation: As the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas fluctuates, it directly impacts the employment opportunities for aspiring burglars. When the demand for machine operators and tenders is high, fewer individuals turn to a life of crime, leading to a decrease in burglary rates. Conversely, during times of low demand for these specialized workers, there is a sudden surge in would-be burglars seeking alternative employment...in the burglary industry. It's a real "bake or break" situation for the crime rate in Arkansas.. Keep the description simple.
ChatGPT: In Arkansas, as the number of food and tobacco roasting, baking, and drying machine operators and tenders increases, the employment opportunities for aspiring burglars decrease. Picture a bakery bustling with workers operating the machines, and as a result, there are fewer individuals turning to a life of crime. However, during times of low demand for these specialized workers, we see a surge in would-be burglars seeking alternative employment, leading to a rise in burglary rates.

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 funny image you would see on reddit ] and depicting this scene: In Arkansas, as the number of food and tobacco roasting, baking, and drying machine operators and tenders increases, the employment opportunities for aspiring burglars decrease. Picture a bakery bustling with workers operating the machines, and as a result, there are fewer individuals turning to a life of crime. However, during times of low demand for these specialized workers, we see a surge in would-be burglars seeking alternative employment, leading to a rise in burglary rates. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image representing the scene described - a lively bakery with workers operating food and tobacco roasting, baking, and drying machines, causing a decrease in aspiring burglars. In contrast, during times of low demand for these workers, there is a surge in would-be burglars seeking alternative employment, leading to a rise in burglary rates. The image should have a humorous and whimsical tone fitting for a Reddit post. The focus should be on capturing the bustling bakery and the comical situation with the burglars in a simple and engaging manner.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas caused Burglary rates to decrease.

AI academic paper

(Because p < 0.01)

The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates

The Journal of Culinary Criminology

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and Burglary rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates

[[ABSTRACT]]
This study explores the seemingly unrelated realms of food and tobacco roasting, baking, and drying machine operation and burglary rates in Arkansas. Leveraging data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services, our research team embarked on a most unconventional journey. To our surprise, we discovered a striking correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders and burglary rates, with a correlation coefficient of 0.8616508 and p < 0.01 from 2003 to 2021. This correlation, though initially fishy, remained robust under rigorous scrutiny. Our findings challenge traditional assumptions and will hopefully spark further clandestine investigations into the curious connections between employment in food and tobacco processing and crime rates. So, are these operators and tenders unwitting accomplices or mere coincidental bystanders in the realm of burglary? The answers may roast your assumptions and leave you feeling a little smoked as we delve into this sizzling analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between employment in food and tobacco roasting, baking, and drying machine operation and crime rates has long been shrouded in mystery, much like the aroma of freshly roasted coffee beans. While the two may appear as unrelated as a peanut butter and anchovy sandwich, our research seeks to shed light on this peculiar association, serving as the Sherlock Holmes to this enigmatic puzzle.
Our investigation may seem as unconventional as a pineapple pizza, but with a dash of statistical seasoning, we aim to uncover whether there is indeed a smoldering connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. Much like a chemist meticulously mixing reagents in a laboratory, we have meticulously manipulated and analyzed the data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services to bring forth the findings about this curious relationship.
As we embark on this aromatic journey, we invite our readers to keep an open mind and prepare for the unexpected. Our findings may challenge conventional wisdom, leaving you pondering whether there's more to these seemingly unrelated variables than meets the eye. So, grab your lab coat and magnifying glass as we dive into this crispy analysis that promises to bring the heat and perhaps even some smoked salmon.
In the words of Erwin Schrödinger, "If you want to find new results, you have to do new things." We intend to do just that and invite our readers to join us in this scientific sleuthing expedition.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," a comprehensive analysis of employment trends in the agricultural and food processing sectors is presented. Although the focus is not specifically on Arkansas, the study provides valuable insights into the broader landscape of food and tobacco processing industries, which serves as a flavorful backdrop for our investigation. The authors identify a range of occupations within these sectors, including roasting, baking, and drying machine operators and tenders, thereby laying the groundwork for our more targeted examination of the potential link to burglary rates.

Expanding the scope further, "Doe and Jones" examine the socioeconomic factors influencing crime rates in rural communities. While their study does not directly delve into the occupational dynamics of food and tobacco processing, it offers a tantalizing glimpse into the complex interplay of employment, community dynamics, and criminal behavior. This provides us with an appetizing appetizer before we sink our teeth into the main course of our analysis.

Turning now to non-fiction sources of interest, "The Omnivore's Dilemma" by Michael Pollan offers a savory exploration of the food industry, delving into the intricate relationships between food production, distribution, and consumption. While Pollan's work does not specifically address tobacco processing, it nourishes our understanding of the broader context in which our investigation unfolds.

In a similar vein, "Fast Food Nation" by Eric Schlosser provides a deep-fried examination of the fast-food industry and its impact on society. While not directly related to tobacco processing or burglary rates, the book offers a thought-provoking look at the interconnectedness of food, employment, and societal outcomes. Plus, it's definitely a must-read for anyone who has ever contemplated the depths of a french fry.

Venturing into the realm of fiction, Dashiell Hammett's "The Maltese Falcon" showcases the art of deduction and sleuthing, setting the stage for our own investigative exploits. While the novel focuses on solving a mystery of a different kind, it primes our detective instincts for uncovering the secrets of the food and tobacco roasting, baking, and drying machine operators and their potential involvement in burglary rates.

As we reach the fringes of traditional literature review, it's worth noting that the back of a shampoo bottle in a secluded shower stall can yield unexpected insights. The seclusion and solitude provide a perfect environment for reconnecting with one's inner researcher, and the sudsy contemplation of shampoo ingredients can indeed lead to unforeseen epiphanies. After all, who's to say that the correlation coefficient of lather viscosity to crime rates is not a subject worthy of investigation? But I digress, for such musings may lead us down the drain of academic irrelevance.

With the foundation laid by these diverse sources, both serious and whimsical, we are poised to step into the smoky expanse of data analysis and unearth the surprising connections between food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. And who knows, perhaps we'll also uncover the elusive key to the perfect cup of coffee along the way.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and Burglary rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates

[[ABSTRACT]]
This study explores the seemingly unrelated realms of food and tobacco roasting, baking, and drying machine operation and burglary rates in Arkansas. Leveraging data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services, our research team embarked on a most unconventional journey. To our surprise, we discovered a striking correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders and burglary rates, with a correlation coefficient of 0.8616508 and p < 0.01 from 2003 to 2021. This correlation, though initially fishy, remained robust under rigorous scrutiny. Our findings challenge traditional assumptions and will hopefully spark further clandestine investigations into the curious connections between employment in food and tobacco processing and crime rates. So, are these operators and tenders unwitting accomplices or mere coincidental bystanders in the realm of burglary? The answers may roast your assumptions and leave you feeling a little smoked as we delve into this sizzling analysis.

[[LITERATURE REVIEW]]
In "Smith et al.," a comprehensive analysis of employment trends in the agricultural and food processing sectors is presented. Although the focus is not specifically on Arkansas, the study provides valuable insights into the broader landscape of food and tobacco processing industries, which serves as a flavorful backdrop for our investigation. The authors identify a range of occupations within these sectors, including roasting, baking, and drying machine operators and tenders, thereby laying the groundwork for our more targeted examination of the potential link to burglary rates.
Expanding the scope further, "Doe and Jones" examine the socioeconomic factors influencing crime rates in rural communities. While their study does not directly delve into the occupational dynamics of food and tobacco processing, it offers a tantalizing glimpse into the complex interplay of employment, community dynamics, and criminal behavior. This provides us with an appetizing appetizer before we sink our teeth into the main course of our analysis.
Turning now to non-fiction sources of interest, "The Omnivore's Dilemma" by Michael Pollan offers a savory exploration of the food industry, delving into the intricate relationships between food production, distribution, and consumption. While Pollan's work does not specifically address tobacco processing, it nourishes our understanding of the broader context in which our investigation unfolds.
In a similar vein, "Fast Food Nation" by Eric Schlosser provides a deep-fried examination of the fast-food industry and its impact on society. While not directly related to tobacco processing or burglary rates, the book offers a thought-provoking look at the interconnectedness of food, employment, and societal outcomes. Plus, it's definitely a must-read for anyone who has ever contemplated the depths of a french fry.
Venturing into the realm of fiction, Dashiell Hammett's "The Maltese Falcon" showcases the art of deduction and sleuthing, setting the stage for our own investigative exploits. While the novel focuses on solving a mystery of a different kind, it primes our detective instincts for uncovering the secrets of the food and tobacco roasting, baking, and drying machine operators and their potential involvement in burglary rates.
As we reach the fringes of traditional literature review, it's worth noting that the back of a shampoo bottle in a secluded shower stall can yield unexpected insights. The seclusion and solitude provide a perfect environment for reconnecting with one's inner researcher, and the sudsy contemplation of shampoo ingredients can indeed lead to unforeseen epiphanies. After all, who's to say that the correlation coefficient of lather viscosity to crime rates is not a subject worthy of investigation? But I digress, for such musings may lead us down the drain of academic irrelevance.
With the foundation laid by these diverse sources, both serious and whimsical, we are poised to step into the smoky expanse of data analysis and unearth the surprising connections between food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. And who knows, perhaps we'll also uncover the elusive key to the perfect cup of coffee along the way.

[[RESULTS]]
The findings of our investigation revealed a tantalizing relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. The correlation coefficient of 0.8616508 between these seemingly unrelated variables was reminiscent of a surprising chemical reaction, challenging preconceived notions and leaving us with a sense of disbelief akin to a magician’s disappearing act.
Notably, the r-squared value of 0.7424422 indicated that a considerable portion of the variation in burglary rates in Arkansas could be explained by the employment of food and tobacco roasting, baking, and drying machine operators and tenders. It's as if these occupations were performing a symphony with the burglary rates, conducting a harmonious yet perplexing tune that defies conventional wisdom.
The p-value of less than 0.01 further confirmed the strength of this correlation, leaving us with the undeniable impression that there is more than meets the eye - much like a hard-to-decipher optical illusion.
Fig. 1 depicts a scatterplot that visually encapsulates the robust nature of this correlation. One cannot help but marvel at the way these data points align themselves, almost as if they were part of an intricate puzzle falling into place. The scatterplot serves as a compelling visual representation of our findings, beckoning the audience to contemplate the interplay between food and tobacco roasting, baking, and drying machine operation and burglary rates, much like a captivating piece of abstract art.
In conclusion, our research has unearthed a connection that raises eyebrows, challenges assumptions, and sparks curiosity. The surprising correlation between these distinct variables calls for further investigations, as we endeavor to unravel the mysteries lurking beneath the surface of statistical analyses, just like uncovering unexpected toppings on a pizza.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study indeed confirm and amplify the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. Our findings align with previous literature, including the "Smith et al." study, which provided a solid foundation for understanding the occupational dynamics within the food and tobacco processing industries. Similarly, the work of "Doe and Jones" shed light on the socioeconomic factors influencing crime rates, bolstering our appreciation for the complex interplay of employment and criminal behavior. Despite starting as seemingly unrelated variables, our research has roasted and baked these connections, leaving us with a tantalizing aroma of statistical significance.

The robust correlation coefficient of 0.8616508 not only reaffirms the strength of the relationship between these variables but also prompts a deeper reflection on the underlying mechanisms at play. Much like the captivating puzzle mentioned in the literature review, the alignment of these data points in our scatterplot suggests a deeper, intricate connection waiting to be unraveled. It's as if the employment of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas conducts an unseen symphony, with burglary rates dancing to its enigmatic tune. This, paired with the r-squared value of 0.7424422, underscores the substantial explanatory power of these employment patterns in understanding variations in burglary rates, almost like a magician revealing only a portion of the illusion.

Furthermore, the p-value of less than 0.01 acts as a stamp of statistical approval, signaling the unwavering strength of this relationship. One cannot help but feel a sense of bewilderment akin to deciphering a complex optical illusion when faced with such compelling statistical evidence.

In essence, our results add a flavorful twist to the conventional understanding of occupational trends and their potential impact on crime rates. The sizzling analysis of this unlikely relationship challenges traditional assumptions and piques the interest of researchers and policymakers alike. As we peel back the layers of this enigma, it's clear that the connections between employment in food and tobacco processing and crime rates continuously surprise and intrigue, much like an unexpected topping on an already enticing pizza.

In our subsequent steps, we aim to delve deeper into the underlying mechanisms driving this connection, unravelling the flavors of this statistical sizzle while keeping our detective hats firmly on. The apparent correlation between these variables calls for further scrutiny, potentially unlocking the keys to understanding the complex interplay of employment dynamics and societal outcomes – a mystery that promises to be as captivating as a well-crafted novel or a perfectly brewed cup of coffee.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and Burglary rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates

[[ABSTRACT]]
This study explores the seemingly unrelated realms of food and tobacco roasting, baking, and drying machine operation and burglary rates in Arkansas. Leveraging data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services, our research team embarked on a most unconventional journey. To our surprise, we discovered a striking correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders and burglary rates, with a correlation coefficient of 0.8616508 and p < 0.01 from 2003 to 2021. This correlation, though initially fishy, remained robust under rigorous scrutiny. Our findings challenge traditional assumptions and will hopefully spark further clandestine investigations into the curious connections between employment in food and tobacco processing and crime rates. So, are these operators and tenders unwitting accomplices or mere coincidental bystanders in the realm of burglary? The answers may roast your assumptions and leave you feeling a little smoked as we delve into this sizzling analysis.

[[INTRDUCTION]]
The relationship between employment in food and tobacco roasting, baking, and drying machine operation and crime rates has long been shrouded in mystery, much like the aroma of freshly roasted coffee beans. While the two may appear as unrelated as a peanut butter and anchovy sandwich, our research seeks to shed light on this peculiar association, serving as the Sherlock Holmes to this enigmatic puzzle.
Our investigation may seem as unconventional as a pineapple pizza, but with a dash of statistical seasoning, we aim to uncover whether there is indeed a smoldering connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. Much like a chemist meticulously mixing reagents in a laboratory, we have meticulously manipulated and analyzed the data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services to bring forth the findings about this curious relationship.
As we embark on this aromatic journey, we invite our readers to keep an open mind and prepare for the unexpected. Our findings may challenge conventional wisdom, leaving you pondering whether there's more to these seemingly unrelated variables than meets the eye. So, grab your lab coat and magnifying glass as we dive into this crispy analysis that promises to bring the heat and perhaps even some smoked salmon.
In the words of Erwin Schrödinger, "If you want to find new results, you have to do new things." We intend to do just that and invite our readers to join us in this scientific sleuthing expedition.

[[RESULTS]]
The findings of our investigation revealed a tantalizing relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates. The correlation coefficient of 0.8616508 between these seemingly unrelated variables was reminiscent of a surprising chemical reaction, challenging preconceived notions and leaving us with a sense of disbelief akin to a magician’s disappearing act.
Notably, the r-squared value of 0.7424422 indicated that a considerable portion of the variation in burglary rates in Arkansas could be explained by the employment of food and tobacco roasting, baking, and drying machine operators and tenders. It's as if these occupations were performing a symphony with the burglary rates, conducting a harmonious yet perplexing tune that defies conventional wisdom.
The p-value of less than 0.01 further confirmed the strength of this correlation, leaving us with the undeniable impression that there is more than meets the eye - much like a hard-to-decipher optical illusion.
Fig. 1 depicts a scatterplot that visually encapsulates the robust nature of this correlation. One cannot help but marvel at the way these data points align themselves, almost as if they were part of an intricate puzzle falling into place. The scatterplot serves as a compelling visual representation of our findings, beckoning the audience to contemplate the interplay between food and tobacco roasting, baking, and drying machine operation and burglary rates, much like a captivating piece of abstract art.
In conclusion, our research has unearthed a connection that raises eyebrows, challenges assumptions, and sparks curiosity. The surprising correlation between these distinct variables calls for further investigations, as we endeavor to unravel the mysteries lurking beneath the surface of statistical analyses, just like uncovering unexpected toppings on a pizza.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has peeled back the layers of ambiguity surrounding the connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas and burglary rates, much like unraveling a particularly complex onion. The correlation coefficient of 0.8616508 not only raised eyebrows but also served as a smokescreen for traditional assumptions about the seemingly unrelated realms of food and tobacco processing and criminal activity. It's as if these employment figures were baking a cake of statistical significance, leaving us with a flavor of intrigue and a dash of bewilderment.

The robustness of the correlation, with an r-squared value of 0.7424422, left us feeling like we had stumbled upon a real statistical gem - a rare find in the world of data analysis that's harder to come by than a perfectly ripe avocado. The p-value of less than 0.01 further solidified the credibility of this connection, casting a shadow of doubt on any skeptics who might have tried to sweep these fascinating results under the rug.

Fig. 1, our scatterplot, was as visually stunning as a meticulously crafted dessert, offering a feast for the eyes and an invitation to contemplate the savory relationship between employment in food and tobacco roasting, baking, and drying machine operation and burglary rates. The scatterplot, much like a piece of abstract art, beckons us to ponder the deeper meaning behind the alignment of these data points, just like deciphering a cryptic crossword puzzle in the Sunday newspaper.

Our findings not only challenge traditional assumptions but also shine a spotlight on the need for further clandestine investigations into these curious connections. It's like embarking on a scientific expedition into uncharted territory, armed with nothing but a magnifying glass and an insatiable curiosity, in search of the elusive answers that may linger just beneath the surface.

In light of these revelations, we assert that no further research is needed in this area. The evidence we've presented is as clear as the nose on your face, and delving any deeper into this matter would be like using a sledgehammer to crack a walnut. Our findings stand as a testament to the unexpected twists and turns that scientific inquiry can take, reminding us that the most intriguing connections may lurk in the most unexpected of places.

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of academic journals. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding research, scientific, or academic journal that would publish a paper entited The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Culinary Criminology

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Culinary Criminology Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates with an abstract of This study explores the seemingly unrelated realms of food and tobacco roasting, baking, and drying machine operation and burglary rates in Arkansas. Leveraging data from the Bureau of Labor Statistics and the FBI Criminal Justice Information Services, our research team embarked on a most unconventional journey. To our surprise, we discovered a striking correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders and burglary rates, with a correlation coefficient of 0.8616508 and p < 0.01 from 2003 to 2021. This correlation, though initially fishy, remained robust under rigorous scrutiny. Our findings challenge traditional assumptions and will hopefully spark further clandestine investigations into the curious connections between employment in food and tobacco processing and crime rates. So, are these operators and tenders unwitting accomplices or mere coincidental bystanders in the realm of burglary? The answers may roast your assumptions and leave you feeling a little smoked as we delve into this sizzling analysis.

ChatGPT:

food and tobacco roasting machine operators, baking and drying machine tenders, burglary rates Arkansas, Bureau of Labor Statistics, FBI Criminal Justice Information Services, correlation between employment and crime rates, food and tobacco processing and crime, correlation coefficient, unconventional study, clandestine investigation

*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 food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas
Detailed data title: BLS estimate of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas
Source: Bureau of Larbor Statistics
See what else correlates with The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas

Burglary rates in the US
Detailed data title: The burglary rate per 100,000 residents in United States
Source: FBI Criminal Justice Information Services
See what else correlates with Burglary rates in the US

Correlation r = 0.8616508 (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 = 0.7424422 (Coefficient of determination)
This means 74.2% of the change in the one variable (i.e., Burglary rates in the US) is predictable based on the change in the other (i.e., The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.1E-6.^Show 0.0000021370107271214200000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.86 in 0.00021% of random cases. Said differently, if you correlated 467,943 random variables^Note You don't actually need 467 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, ^Note 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.

[ 0.67, 0.95 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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

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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.

	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas (Laborers)	420	450	320	250	340	340	430	370	370	350	300	270	230	150	100	110	70	40	230
Burglary rates in the US (Burglary rate)	741	730.3	726.9	733.1	726.1	733	717.7	701	701.3	672.2	610.5	537.2	494.7	468.9	429.7	378	340.5	314.2	270.9

Why this works

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

For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

(This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.

Try it yourself

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

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

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

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

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

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

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

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

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

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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([420,450,320,250,340,340,430,370,370,350,300,270,230,150,100,110,70,40,230,])
array_2 = np.array([741,730.3,726.9,733.1,726.1,733,717.7,701,701.3,672.2,610.5,537.2,494.7,468.9,429.7,378,340.5,314.2,270.9,])
array_1_name = "The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas"
array_2_name = "Burglary rates 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. ^Note Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

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

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

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

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

Download images for these variables:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only The number of food and tobacco roasting, baking, and drying machine operators and tenders in Arkansas
Line chart for only Burglary rates in the US
AI-generated correlation image
The spurious research paper: The Smoking Gun: A Crispy Analysis of the Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Arkansas and Burglary Rates

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 2445 · Black Variable ID: 5295 · Red Variable ID: 20084


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