Spurious correlation #3,514 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air pollution in Duluth and the second variable is The number of cooks, short order in Minnesota. The chart goes from 2003 to 2022, 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 Air pollution in Duluth and the second variable is The number of cooks, short order in Minnesota. The chart goes from 2003 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The cleaner air in Duluth blew away all the short order cook's hat which demotivated all the cooks in Minnesota. They just couldn't seem to ketchup with the new cooking trends. They decided to skillet and look for greener pastures.

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image using [ Charcoal ] that depicts a scene of Duluth under a clear sky marred by a thick smog, symbolizing high air pollution levels. In a bustling diner in Minnesota, illustrate the once lively kitchen with fewer short order cooks as comfort food demand diminishes. 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: Air pollution in Duluth and The number of cooks, short order in Minnesota. 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: Charcoal Oragami 3D Pixar Style Minimalism Psychedelic
ChatGPT: Charcoal

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 Air pollution in Duluth and The number of cooks, short order in Minnesota, in the following situation: Because with cleaner air, people were less hungry for comfort food, leading to a decrease in demand for short order cooks in Minnesota.. Keep the description simple.
ChatGPT: In Duluth, the clear sky was marred by a thick haze of smog, indicating high air pollution levels. Meanwhile, in a bustling diner in Minnesota, the once crowded kitchen now had fewer short order cooks working as the demand for comfort food decreased.

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: [ Charcoal ] and depicting this scene: In Duluth, the clear sky was marred by a thick haze of smog, indicating high air pollution levels. Meanwhile, in a bustling diner in Minnesota, the once crowded kitchen now had fewer short order cooks working as the demand for comfort food decreased. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image using [ Charcoal ] that depicts a scene of Duluth under a clear sky marred by a thick smog, symbolizing high air pollution levels. In a bustling diner in Minnesota, illustrate the once lively kitchen with fewer short order cooks as comfort food demand diminishes.

*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 Air pollution in Duluth caused The number of cooks, short order in Minnesota to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

The Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

The Journal of Atmospheric Culinary Studies

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 Air pollution in Duluth and The number of cooks, short order in Minnesota. 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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
The Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

[[ABSTRACT]]
This study delves into the unconventional relationship between air pollution in the charming city of Duluth and the bustling world of short order cooks in the state of Minnesota. With an air of curiosity and a dash of statistical rigor, our research team harnessed the data from the Environmental Protection Agency and the Bureau of Labor Statistics to embark on a whimsical quest. Through our meticulous analysis, we stumbled upon a correlation coefficient of 0.8820454 and a p-value less than 0.01 for the years spanning from 2003 to 2022.

While the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota may initially seem as incongruous as a vegetarian at a barbecue, our findings beg to differ. The results of our study not only beg the question but tickle the imagination: could there be an invisible, aromatic link between the sooty skies of Duluth and the sizzling griddles in Minnesota's diners and eateries? Our research beckons further investigation into the whimsical nuances of our culinary and atmospheric landscapes, shedding light on the potential impacts of air quality on the savory art of short order cooking.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The interplay between atmospheric conditions and culinary prowess has long captivated the curious minds of researchers and food enthusiasts alike. In this paper, we set forth to explore a lesser-known association – the correlation between air pollution in the delightful city of Duluth and the population of short order cooks in the state of Minnesota. As we embark on this unconventional venture, we approach our subject matter with a blend of scientific rigor and unapologetic whimsy, aiming to uncover any hidden flavors in the data.
Venturing into the realms of air quality and the bustling world of short order cooking may seem like an odd amalgamation, akin to mixing peas with mashed potatoes, but our inquisitive minds were not deterred. Leveraging data from the Environmental Protection Agency to quantify the atmospheric nuances and tapping into the Bureau of Labor Statistics for the savory statistics on short order cooks, our research team sought to untangle the aromatic mystery.
The substantial correlation coefficient of 0.8820454 that emerged from our analysis waved at us like a steamy spatula, daring us to ignore its sizzle. A p-value less than 0.01 further tantalized our senses, beckoning us to delve deeper into the enigmatic connection that seemed to permeate the very essence of the air in Duluth and the bustling kitchens of Minnesota.
While some may be quick to dismiss this correlation as a mere statistical quirk, we are compelled to peel back the layers, much like one would unravel a blossoming onion. Could it be that the ethereal dance of air particles in Duluth is intricately intertwined with the rhythmic clatter of skillets and the aromatic symphony of sizzling meats and spices in Minnesota's culinary landscape? As we ponder this thought, we invite our fellow researchers to join us on this whimsical inquiry, embracing the curious dance between air pollution and the nuanced art of short order cooking.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The investigation of the correlation between air pollution in specific locales and the employment of short order cooks has elicited both serious inquiry and whimsical speculation in the existing literature. Smith et al. (2010) laid the groundwork for this peculiar line of investigation by examining the impact of regional air quality on various occupational categories. Their findings hinted at potential links between atmospheric pollutants and the culinary workforce, setting the stage for further exploration.

Doe and Jones (2015) expanded upon this intriguing thread of research, delving into the nuanced dynamics of air quality in the Great Lakes region and its potential influence on the labor market in neighboring states. Their comprehensive analysis hinted at a compelling relationship, prompting the inklings of a culinary conundrum that we aim to untangle in the present study.

Turning to non-fiction works, "The Omnivore's Dilemma" by Michael Pollan offers a tantalizing perspective on the interplay between environmental factors and the culinary landscape, albeit within the context of consumer choices rather than employment trends. Similarly, "The Big Necessity" by Rose George delves into the intricate world of waste management and its implications for public health, inspiring contemplation of the broader environmental influences that may extend to the domain of culinary arts and labor dynamics.

As we meander into the realm of fiction, the works of Laura Esquivel, particularly "Like Water for Chocolate," beckon with their enchanting blend of culinary symbolism and whimsical narratives. While the focus of these literary works may not be on air pollution or labor statistics, the alluring fusion of savory delights and atmospheric allure serves as a captivating parallel to our own explorations.

In a departure from conventional scholarship, we cannot overlook the unconventional sources that have informed our inquiry. Indeed, the seemingly mundane and oft-overlooked artifacts of contemporary life – such as grocery receipts, kitchen napkins, and serendipitous encounters with culinary enthusiasts – have dotted our intellectual landscape, adding a sprinkle of unorthodox inspiration to our research endeavors.

As we traverse the diverse terrain of literature, our pursuit of understanding the interplay between air pollution in Duluth and the number of short order cooks in Minnesota has been underscored by a blend of academic diligence and irrepressible whimsy. In the words of Julia Child, "The only real stumbling block is fear of failure. In cooking, you've got to have a what-the-hell attitude." With this irreverent spirit in tow, we march onward to shed light on the curious dance between atmospheric intricacies and culinary artistry.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Duluth and The number of cooks, short order in Minnesota. 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.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Bureau of Larbor Statistics . You used data from 2003 to 2022

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

[[ABSTRACT]]
This study delves into the unconventional relationship between air pollution in the charming city of Duluth and the bustling world of short order cooks in the state of Minnesota. With an air of curiosity and a dash of statistical rigor, our research team harnessed the data from the Environmental Protection Agency and the Bureau of Labor Statistics to embark on a whimsical quest. Through our meticulous analysis, we stumbled upon a correlation coefficient of 0.8820454 and a p-value less than 0.01 for the years spanning from 2003 to 2022.

While the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota may initially seem as incongruous as a vegetarian at a barbecue, our findings beg to differ. The results of our study not only beg the question but tickle the imagination: could there be an invisible, aromatic link between the sooty skies of Duluth and the sizzling griddles in Minnesota's diners and eateries? Our research beckons further investigation into the whimsical nuances of our culinary and atmospheric landscapes, shedding light on the potential impacts of air quality on the savory art of short order cooking.

[[INTRODUCTION]]
The interplay between atmospheric conditions and culinary prowess has long captivated the curious minds of researchers and food enthusiasts alike. In this paper, we set forth to explore a lesser-known association – the correlation between air pollution in the delightful city of Duluth and the population of short order cooks in the state of Minnesota. As we embark on this unconventional venture, we approach our subject matter with a blend of scientific rigor and unapologetic whimsy, aiming to uncover any hidden flavors in the data.
Venturing into the realms of air quality and the bustling world of short order cooking may seem like an odd amalgamation, akin to mixing peas with mashed potatoes, but our inquisitive minds were not deterred. Leveraging data from the Environmental Protection Agency to quantify the atmospheric nuances and tapping into the Bureau of Labor Statistics for the savory statistics on short order cooks, our research team sought to untangle the aromatic mystery.
The substantial correlation coefficient of 0.8820454 that emerged from our analysis waved at us like a steamy spatula, daring us to ignore its sizzle. A p-value less than 0.01 further tantalized our senses, beckoning us to delve deeper into the enigmatic connection that seemed to permeate the very essence of the air in Duluth and the bustling kitchens of Minnesota.
While some may be quick to dismiss this correlation as a mere statistical quirk, we are compelled to peel back the layers, much like one would unravel a blossoming onion. Could it be that the ethereal dance of air particles in Duluth is intricately intertwined with the rhythmic clatter of skillets and the aromatic symphony of sizzling meats and spices in Minnesota's culinary landscape? As we ponder this thought, we invite our fellow researchers to join us on this whimsical inquiry, embracing the curious dance between air pollution and the nuanced art of short order cooking.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

In order to unravel the peculiar correlation between air pollution in Duluth and the number of short order cooks in Minnesota, our research utilized a concoction of data mining methods that could rival even the most elaborate culinary recipes. Our data collection endeavors were akin to a culinary scavenger hunt, with the Environmental Protection Agency and the Bureau of Labor Statistics serving as our virtual spice markets.

First, we engaged in a thorough foraging expedition through the labyrinthine archives of the Environmental Protection Agency (EPA) to procure a delectable assortment of air quality data specific to the picturesque city of Duluth. The EPA's databases were scoured meticulously, much like a chef carefully selecting the freshest ingredients for a gourmet dish, to obtain hourly, daily, and yearly air pollution indices, including but not limited to levels of particulate matter, nitrogen dioxide, sulfur dioxide, and ozone, spanning the time period from 2003 to 2022.

Next, we ventured into the culinary cosmos of the Bureau of Labor Statistics (BLS) to unearth the statistical bounty relating to the number of short order cooks in the state of Minnesota. We utilized their Occupational Employment Statistics and Employment Projections programs to extract comprehensive data on the employment trends and workforce composition within the realm of short order cooking, spanning the same period as our air quality data.

With our troves of data in hand, we endeavored to concoct a statistical feast of analyses to discern the potential connection between these seemingly disparate variables. Our methods were as robust and intricate as a meticulously crafted molecular gastronomy dish, incorporating correlation analysis, regression models, and time series techniques to distill the essence of our findings.

The statistical software packages R and Python served as the trusty sous chefs in our research kitchen, aiding us in executing the complex statistical recipes required to tease out any inherent associations between air pollution in Duluth and the population of short order cooks in Minnesota. We meticulously seasoned our analyses with considerations for potential confounding variables, ensuring that our findings were as pristine and unadulterated as a fresh bouquet garni.

The delicate dance between the atmospheric measurements and the savory statistics culminated in the emergence of an eyebrow-raising correlation coefficient of 0.8820454 and a p-value less than 0.01, serving as the pièce de résistance in our gastronomical odyssey. These results not only piqued our scientific palate but also infused a sense of wonder and mirth into our understanding of the interconnectedness of air pollution and the art of short order cooking in Minnesota.

The capricious nature of our investigation prompts us to pursue further avenues of research, blending the flavors of atmospheric science with the aromatic essence of culinary arts. As we venture onward, our fervent hope is to inspire fellow researchers to join us in this whimsical inquiry, kindling a spirit of scientific and culinary camaraderie in unraveling the enigmatic bond between air quality in Duluth and the bustling world of short order cooks in Minnesota.

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 Air pollution in Duluth and The number of cooks, short order in Minnesota. 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 Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

[[ABSTRACT]]
This study delves into the unconventional relationship between air pollution in the charming city of Duluth and the bustling world of short order cooks in the state of Minnesota. With an air of curiosity and a dash of statistical rigor, our research team harnessed the data from the Environmental Protection Agency and the Bureau of Labor Statistics to embark on a whimsical quest. Through our meticulous analysis, we stumbled upon a correlation coefficient of 0.8820454 and a p-value less than 0.01 for the years spanning from 2003 to 2022.

While the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota may initially seem as incongruous as a vegetarian at a barbecue, our findings beg to differ. The results of our study not only beg the question but tickle the imagination: could there be an invisible, aromatic link between the sooty skies of Duluth and the sizzling griddles in Minnesota's diners and eateries? Our research beckons further investigation into the whimsical nuances of our culinary and atmospheric landscapes, shedding light on the potential impacts of air quality on the savory art of short order cooking.

[[LITERATURE REVIEW]]
The investigation of the correlation between air pollution in specific locales and the employment of short order cooks has elicited both serious inquiry and whimsical speculation in the existing literature. Smith et al. (2010) laid the groundwork for this peculiar line of investigation by examining the impact of regional air quality on various occupational categories. Their findings hinted at potential links between atmospheric pollutants and the culinary workforce, setting the stage for further exploration.
Doe and Jones (2015) expanded upon this intriguing thread of research, delving into the nuanced dynamics of air quality in the Great Lakes region and its potential influence on the labor market in neighboring states. Their comprehensive analysis hinted at a compelling relationship, prompting the inklings of a culinary conundrum that we aim to untangle in the present study.
Turning to non-fiction works, "The Omnivore's Dilemma" by Michael Pollan offers a tantalizing perspective on the interplay between environmental factors and the culinary landscape, albeit within the context of consumer choices rather than employment trends. Similarly, "The Big Necessity" by Rose George delves into the intricate world of waste management and its implications for public health, inspiring contemplation of the broader environmental influences that may extend to the domain of culinary arts and labor dynamics.
As we meander into the realm of fiction, the works of Laura Esquivel, particularly "Like Water for Chocolate," beckon with their enchanting blend of culinary symbolism and whimsical narratives. While the focus of these literary works may not be on air pollution or labor statistics, the alluring fusion of savory delights and atmospheric allure serves as a captivating parallel to our own explorations.
In a departure from conventional scholarship, we cannot overlook the unconventional sources that have informed our inquiry. Indeed, the seemingly mundane and oft-overlooked artifacts of contemporary life – such as grocery receipts, kitchen napkins, and serendipitous encounters with culinary enthusiasts – have dotted our intellectual landscape, adding a sprinkle of unorthodox inspiration to our research endeavors.
As we traverse the diverse terrain of literature, our pursuit of understanding the interplay between air pollution in Duluth and the number of short order cooks in Minnesota has been underscored by a blend of academic diligence and irrepressible whimsy. In the words of Julia Child, "The only real stumbling block is fear of failure. In cooking, you've got to have a what-the-hell attitude." With this irreverent spirit in tow, we march onward to shed light on the curious dance between atmospheric intricacies and culinary artistry.

[[RESULTS]]
The correlation analysis between air pollution levels in Duluth and the number of short order cooks in Minnesota yielded some tantalizing findings. We found a robust correlation coefficient of 0.8820454, indicating a strong positive relationship between these seemingly disparate variables. This correlation coefficient flirted with our curiosity like a well-seasoned skillet, leaving us to ponder the aromatic implications.
Additionally, the coefficient of determination (r-squared) of 0.7780040 suggested that approximately 77.8% of the variability in the number of short order cooks in Minnesota could be explained by variations in air pollution levels in Duluth. This finding sent our statistical taste buds into a frenzy, as we marveled at the explanatory power of these seemingly incongruous factors.
Furthermore, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis of no relationship between the two variables. Like a scientifically approved spice blend, this p-value added an extra kick of significance to our findings, affirming the robustness of the observed correlation.
Figure 1 presents a visual representation of this striking correlation, depicted in a scatterplot that could rival the eclectic ingredients of a chef's signature dish. The scatterplot showcases the clustering of data points, accentuating the strong positive trend between air pollution levels in Duluth and the number of short order cooks in Minnesota. It's a graph that could make any data visualization enthusiast's heart flutter - or at least produce a knowing nod and an appreciative eyebrow raise.
In essence, our findings beckon further exploration into the whimsical interplay between air quality and the savory world of short order cooking. While this correlation may initially seem as improbable as a statistically significant unicorn, the data speaks for itself, urging us to embrace the eccentric nuances of culinary statistics with the same fervor as an adventurous eater at a food truck rally.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study provide compelling evidence in support of the prior research on the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota. Expanding upon the foundational work of Smith et al. (2010) and the subsequent investigations by Doe and Jones (2015), our findings bolster the growing body of literature that explores the intersection of atmospheric quality and labor dynamics in the culinary domain.

While the whimsical nature of our research endeavor may bring to mind the flavor-bursting concoctions of a daring chef, the statistical rigor underpinning our analysis cannot be overlooked. The robust correlation coefficient of 0.8820454 and the p-value of less than 0.01 echo the indicative nature of previous studies, anchoring the seemingly fantastical correlation between air pollution in Duluth and the employment of short order cooks in the empirical realm of statistical significance. It's as if the scientific method donned a chef's hat and whipped up a delectable dish of correlative insights, garnished with a sprinkling of p-values and confidence intervals.

The coefficient of determination (r-squared) of 0.7780040 underscores the substantial explanatory power of air pollution levels in Duluth in elucidating the variations in the number of short order cooks in Minnesota. This echoes the tantalizing inklings put forth by earlier researchers, infusing our findings with a depth that is as captivating as a complex umami flavor profile.

The whimsy of our investigation, inspired by literary narratives and unconventional sources, has been complemented by the unyielding precision of statistical analysis. In a serendipitous intertwining of the whimsical and the methodical, our research conjures a culinary metaphor that captures the essence of our scholarly pursuit: just as a pinch of salt accentuates the flavors of a dish in unexpected ways, the peculiar relationship between air pollution in Duluth and the number of short order cooks in Minnesota introduces an unexpected resonance in the palate of statistical inquiry.

The scatterplot, akin to a masterfully crafted composition of culinary artistry, visually encapsulates the robust correlation between our variables, inviting contemplation on the aromatic implications of atmospheric nuances. This graphical representation serves as a visual feast for the eyes, mirroring the amalgamation of flavors in an expertly crafted dish, albeit in the form of data points and trend lines.

In light of our findings, we invite further investigation into the whimsical interplay between atmospheric intricacies and the savory world of short order cooking, urging future researchers to embrace the eccentric nuances of culinary statistics with the same fervor as a food connoisseur at a gastronomic symposium. As we savor the tantalizing implications of our results, we look forward to the future elucidation of this culinary conundrum and the unfolding narratives it holds for the scientific community.

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 Air pollution in Duluth and The number of cooks, short order in Minnesota. 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 Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

[[ABSTRACT]]
This study delves into the unconventional relationship between air pollution in the charming city of Duluth and the bustling world of short order cooks in the state of Minnesota. With an air of curiosity and a dash of statistical rigor, our research team harnessed the data from the Environmental Protection Agency and the Bureau of Labor Statistics to embark on a whimsical quest. Through our meticulous analysis, we stumbled upon a correlation coefficient of 0.8820454 and a p-value less than 0.01 for the years spanning from 2003 to 2022.

While the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota may initially seem as incongruous as a vegetarian at a barbecue, our findings beg to differ. The results of our study not only beg the question but tickle the imagination: could there be an invisible, aromatic link between the sooty skies of Duluth and the sizzling griddles in Minnesota's diners and eateries? Our research beckons further investigation into the whimsical nuances of our culinary and atmospheric landscapes, shedding light on the potential impacts of air quality on the savory art of short order cooking.

[[INTRDUCTION]]
The interplay between atmospheric conditions and culinary prowess has long captivated the curious minds of researchers and food enthusiasts alike. In this paper, we set forth to explore a lesser-known association – the correlation between air pollution in the delightful city of Duluth and the population of short order cooks in the state of Minnesota. As we embark on this unconventional venture, we approach our subject matter with a blend of scientific rigor and unapologetic whimsy, aiming to uncover any hidden flavors in the data.
Venturing into the realms of air quality and the bustling world of short order cooking may seem like an odd amalgamation, akin to mixing peas with mashed potatoes, but our inquisitive minds were not deterred. Leveraging data from the Environmental Protection Agency to quantify the atmospheric nuances and tapping into the Bureau of Labor Statistics for the savory statistics on short order cooks, our research team sought to untangle the aromatic mystery.
The substantial correlation coefficient of 0.8820454 that emerged from our analysis waved at us like a steamy spatula, daring us to ignore its sizzle. A p-value less than 0.01 further tantalized our senses, beckoning us to delve deeper into the enigmatic connection that seemed to permeate the very essence of the air in Duluth and the bustling kitchens of Minnesota.
While some may be quick to dismiss this correlation as a mere statistical quirk, we are compelled to peel back the layers, much like one would unravel a blossoming onion. Could it be that the ethereal dance of air particles in Duluth is intricately intertwined with the rhythmic clatter of skillets and the aromatic symphony of sizzling meats and spices in Minnesota's culinary landscape? As we ponder this thought, we invite our fellow researchers to join us on this whimsical inquiry, embracing the curious dance between air pollution and the nuanced art of short order cooking.

[[RESULTS]]
The correlation analysis between air pollution levels in Duluth and the number of short order cooks in Minnesota yielded some tantalizing findings. We found a robust correlation coefficient of 0.8820454, indicating a strong positive relationship between these seemingly disparate variables. This correlation coefficient flirted with our curiosity like a well-seasoned skillet, leaving us to ponder the aromatic implications.
Additionally, the coefficient of determination (r-squared) of 0.7780040 suggested that approximately 77.8% of the variability in the number of short order cooks in Minnesota could be explained by variations in air pollution levels in Duluth. This finding sent our statistical taste buds into a frenzy, as we marveled at the explanatory power of these seemingly incongruous factors.
Furthermore, the p-value of less than 0.01 provided compelling evidence to reject the null hypothesis of no relationship between the two variables. Like a scientifically approved spice blend, this p-value added an extra kick of significance to our findings, affirming the robustness of the observed correlation.
Figure 1 presents a visual representation of this striking correlation, depicted in a scatterplot that could rival the eclectic ingredients of a chef's signature dish. The scatterplot showcases the clustering of data points, accentuating the strong positive trend between air pollution levels in Duluth and the number of short order cooks in Minnesota. It's a graph that could make any data visualization enthusiast's heart flutter - or at least produce a knowing nod and an appreciative eyebrow raise.
In essence, our findings beckon further exploration into the whimsical interplay between air quality and the savory world of short order cooking. While this correlation may initially seem as improbable as a statistically significant unicorn, the data speaks for itself, urging us to embrace the eccentric nuances of culinary statistics with the same fervor as an adventurous eater at a food truck rally.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has unearthed a robust correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota that is as surprising as finding a secret ingredient in a recipe. With a correlation coefficient winking at us more flirtatiously than a crispy bacon strip, and a p-value sauntering in with more significance than a Michelin-starred chef, the evidence is as clear as a perfectly filtered consommé – there's something sizzling between the soot and the skillet.

While these findings may prompt a few raised eyebrows, like realizing that a well-seasoned cast iron skillet is indeed non-stick, further studies in this area might be as unnecessary as a culinary school for cats. It appears that this peculiar correlation is as strong as garlic in a marinara sauce, leaving little room for doubt.

Therefore, we assert with the confidence of a seasoned sous chef measuring ingredients by eye that no more research is needed in this area. It's time for us to hang up our aprons and savor the nicely seasoned results of our quirky culinary and atmospheric investigation.

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 Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric Culinary Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Atmospheric Inquiry and Culinary 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 Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota with an abstract of This study delves into the unconventional relationship between air pollution in the charming city of Duluth and the bustling world of short order cooks in the state of Minnesota. With an air of curiosity and a dash of statistical rigor, our research team harnessed the data from the Environmental Protection Agency and the Bureau of Labor Statistics to embark on a whimsical quest. Through our meticulous analysis, we stumbled upon a correlation coefficient of 0.8820454 and a p-value less than 0.01 for the years spanning from 2003 to 2022.
While the correlation between air pollution levels in Duluth and the number of short order cooks in Minnesota may initially seem as incongruous as a vegetarian at a barbecue, our findings beg to differ. The results of our study not only beg the question but tickle the imagination: could there be an invisible, aromatic link between the sooty skies of Duluth and the sizzling griddles in Minnesota's diners and eateries? Our research beckons further investigation into the whimsical nuances of our culinary and atmospheric landscapes, shedding light on the potential impacts of air quality on the savory art of short order cooking.

ChatGPT:

air pollution, Duluth, short order cooks, Minnesota, correlation analysis, environmental protection agency, Bureau of Labor Statistics, correlation coefficient, p-value, culinary landscape, atmospheric impacts, air quality, statistical analysis

*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

Air pollution in Duluth
Detailed data title: Percentage of days with moderate or worse air quality in Duluth, MN-WI
Source: Environmental Protection Agency
See what else correlates with Air pollution in Duluth

The number of cooks, short order in Minnesota
Detailed data title: BLS estimate of cooks, short order in Minnesota
Source: Bureau of Larbor Statistics
See what else correlates with The number of cooks, short order in Minnesota

Correlation r = 0.8820454 (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 = 0.7780040 (Coefficient of determination)
This means 77.8% of the change in the one variable (i.e., The number of cooks, short order in Minnesota) is predictable based on the change in the other (i.e., Air pollution in Duluth) over the 20 years from 2003 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.7E-7.^Show 0.0000002715687927978759000000
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 0.88 in 2.7E-5% of random cases. Said differently, if you correlated 3,682,308 random variables^Note You don't actually need 3 million 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.72, 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	2022
Air pollution in Duluth (Bad air quality days)	30.137	22.4044	28.7671	32.6027	33.6986	25.6831	24.3836	19.1781	17.5342	15.5738	19.4521	19.1781	10.9589	7.10383	9.86301	16.4384	10.9589	8.74317	17.2603	5.75342
The number of cooks, short order in Minnesota (Cooks, Short Order)	3870	3810	4530	4330	3930	3530	2470	2730	2230	2100	1270	1470	1320	1300	940	720	960	770	1940	1130

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.

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([30.137,22.4044,28.7671,32.6027,33.6986,25.6831,24.3836,19.1781,17.5342,15.5738,19.4521,19.1781,10.9589,7.10383,9.86301,16.4384,10.9589,8.74317,17.2603,5.75342,])
array_2 = np.array([3870,3810,4530,4330,3930,3530,2470,2730,2230,2100,1270,1470,1320,1300,940,720,960,770,1940,1130,])
array_1_name = "Air pollution in Duluth"
array_2_name = "The number of cooks, short order in Minnesota"

# 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 Air pollution in Duluth
Line chart for only The number of cooks, short order in Minnesota
AI-generated correlation image
The spurious research paper: The Airest of Them All: A Correlative Analysis of Air Pollution in Duluth and the Number of Short Order Cooks in Minnesota

View another random correlation

How fun was this correlation?

I'm grateful for your review!

Correlation ID: 3514 · Black Variable ID: 20565 · Red Variable ID: 9995


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