Spurious correlation #1,816 · 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 Indiana and the second variable is Jet fuel used in Kiribati. 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 Indiana and the second variable is Jet fuel used in Kiribati. 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 number of these operators and tenders in Indiana increased, so did the level of *hot air* produced. This led to a chain reaction of *smokin'* interference with the air currents, ultimately causing a disproportionate amount of jet fuel to be diverted towards Kiribati. It seems the Hoosier state's sizzling workforce inadvertently put the *heat* on Kiribati's aviation fuel supply!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a Discovery magazine cover featuring a scene in Indiana, with food and tobacco roasting, baking, and drying machine operators and tenders working inside a factory. In the background, depict a sleek jet soaring through the skies above Kiribati, leaving behind a trail of jet fuel exhaust. Capture the industrious atmosphere of the factory and the dynamic motion of the jet, creating a visually compelling juxtaposition of industry and technology. 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 Indiana and Jet fuel used in Kiribati. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: A Discovery magazine cover image A photo-realistic image Minimalism Cutsy art illustration Hyper-realistic
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Jet fuel used in Kiribati together. Keep the description simple.
ChatGPT: In Indiana, a row of food and tobacco roasting, baking, and drying machine operators and tenders work diligently inside a factory. Nearby, a sleek jet soars through the skies above Kiribati, leaving behind a trail of jet fuel exhaust.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In Indiana, a row of food and tobacco roasting, baking, and drying machine operators and tenders work diligently inside a factory. Nearby, a sleek jet soars through the skies above Kiribati, leaving behind a trail of jet fuel exhaust. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a Discovery magazine cover featuring a scene in Indiana, with food and tobacco roasting, baking, and drying machine operators and tenders working inside a factory. In the background, depict a sleek jet soaring through the skies above Kiribati, leaving behind a trail of jet fuel exhaust. Capture the industrious atmosphere of the factory and the dynamic motion of the jet, creating a visually compelling juxtaposition of industry and technology.

*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 increases in The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana negatively influenced Jet fuel used in Kiribati. Include one good pun.

AI academic paper

(Because p < 0.01)

Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

Journal of Culinary Science and Environmental Economics

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Jet fuel used in Kiribati. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

[[ABSTRACT]]
This study delves into the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the jet fuel used in Kiribati. Using data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2021, we discovered a striking correlation coefficient of -0.7414567 and p < 0.01. Despite the seemingly unrelated nature of these variables, our findings reveal a significant negative relationship, hinting at a potential causal link between the two. This illuminating discovery not only sheds light on the enigmatic interplay between seemingly disparate industries but also serves as a reminder that in the labyrinth of statistical analysis, surprises often abound. We invite fellow researchers to join us in unraveling the tangled web of connections in the world of labor and energy consumption.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The examination of inter-industry relationships within the realms of labor and energy consumption has long been a source of fascination for researchers. Uncovering unexpected connections can yield valuable insights and provide a deeper understanding of the intricate web of economic activities. In this study, we embark on a journey to explore the seemingly incongruous association between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati.
The cryptic allure of this correlation beckons us to delve into the intricate tapestry of industrial dynamics, where seemingly disparate entities may, upon closer examination, reveal unsuspected ties. As we navigate the labyrinth of statistical analysis, it is crucial to remain vigilant, for in the midst of seemingly unrelated variables, hidden patterns and relationships can emerge, much like a well-baked surprise in the oven of empirical investigation.
Our investigation stems from a recognition of the paradoxical nature of the global economic landscape, where the mundane and the extraordinary often converge in the dance of data points and coefficients. Like a skilled baker crafting a delicate soufflé, we seek to carefully sift through the data, aiming to extract meaning from the seemingly incongruous association between the labor force in Indiana's roasting, baking, and drying sector and the consumption of jet fuel in the remote archipelago of Kiribati.
As we embark on this academic endeavor, we are confronted with the enigma of the negative correlation coefficient (-0.7414567) that permeates our findings, leaving us pondering the intricacies of causality and influence. This unexpected revelation serves as a poignant reminder that in the domain of statistical analysis, serendipitous discoveries are not unlike the sudden aroma of freshly roasted coffee beans – an unexpected delight that enlivens the senses and prompts further inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati has been a topic of limited inquiry within the scholarly literature. Smith (2010) examined the occupational dynamics of food and tobacco roasting, baking, and drying machine operators and tenders, focusing on their role in the food processing industry. The study, however, did not extend its analysis to explore potential interconnections between the labor force in Indiana and energy usage in distant locales.

In a similar vein, Doe (2015) conducted a comprehensive analysis of energy consumption patterns in Oceania, with a particular emphasis on Kiribati. The study offered valuable insights into the sources and trends of energy consumption in the region but did not specifically consider the influence of labor dynamics in distant geographic areas.

Jones (2018) investigated the intersection of labor markets and energy usage, scrutinizing the dynamics of occupational sectors in various U.S. states. While shedding light on the distribution of labor across industries, the study did not delve into the curious juxtaposition between the labor force in Indiana's food and tobacco sector and the utilization of jet fuel in Kiribati.

Turning to non-fiction works that could potentially shed light on this enigmatic correlation, "Energy and Employment: A Just Transition" by Garcia et al. (2017) offers a comprehensive exploration of the intricate relationship between labor markets and energy consumption. However, the text does not specifically address the peculiar juxtaposition of the labor force in Indiana and energy usage in Kiribati.

Similarly, "Global Food, Global Justice: Essays on Eating Under Globalization" edited by Sollund (2015) provides a thought-provoking analysis of the global food industry and its social, economic, and environmental dimensions. While the volume offers valuable perspectives on the food sector, it does not explicitly explore the interplay between food industry labor in Indiana and jet fuel usage in Kiribati.

In the realm of fiction works that tangentially touch upon the themes of labor and energy, George Orwell's "Down and Out in Paris and London" could provide an insightful allegorical perspective on the toils of labor and the underlying dynamics of economic systems. However, the novel does not directly address the specific correlation under investigation in this study.

Similarly, Aldous Huxley's "Brave New World" presents a dystopian vision of a future society, raising pertinent questions about labor, consumption, and societal structures. Yet, the novel does not offer direct insights into the interrelation between food and tobacco roasting, baking, and drying machine operators in Indiana and jet fuel consumption in Kiribati.

While not directly related to the academic inquiry at hand, the researchers found it pertinent to note that the film "Planes, Trains and Automobiles" serves as a lighthearted depiction of travel and transportation, albeit not specifically focused on jet fuel usage. Additionally, the film "The Devil Wears Prada" offers a satirical portrayal of the fashion industry, which, though unrelated to the study's focus, underscores the varied domains encompassed within the realm of labor and industry.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Jet fuel used in Kiribati. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration . You used data from 2003 to 2021

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

[[ABSTRACT]]
This study delves into the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the jet fuel used in Kiribati. Using data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2021, we discovered a striking correlation coefficient of -0.7414567 and p < 0.01. Despite the seemingly unrelated nature of these variables, our findings reveal a significant negative relationship, hinting at a potential causal link between the two. This illuminating discovery not only sheds light on the enigmatic interplay between seemingly disparate industries but also serves as a reminder that in the labyrinth of statistical analysis, surprises often abound. We invite fellow researchers to join us in unraveling the tangled web of connections in the world of labor and energy consumption.

[[INTRODUCTION]]
The examination of inter-industry relationships within the realms of labor and energy consumption has long been a source of fascination for researchers. Uncovering unexpected connections can yield valuable insights and provide a deeper understanding of the intricate web of economic activities. In this study, we embark on a journey to explore the seemingly incongruous association between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati.
The cryptic allure of this correlation beckons us to delve into the intricate tapestry of industrial dynamics, where seemingly disparate entities may, upon closer examination, reveal unsuspected ties. As we navigate the labyrinth of statistical analysis, it is crucial to remain vigilant, for in the midst of seemingly unrelated variables, hidden patterns and relationships can emerge, much like a well-baked surprise in the oven of empirical investigation.
Our investigation stems from a recognition of the paradoxical nature of the global economic landscape, where the mundane and the extraordinary often converge in the dance of data points and coefficients. Like a skilled baker crafting a delicate soufflé, we seek to carefully sift through the data, aiming to extract meaning from the seemingly incongruous association between the labor force in Indiana's roasting, baking, and drying sector and the consumption of jet fuel in the remote archipelago of Kiribati.
As we embark on this academic endeavor, we are confronted with the enigma of the negative correlation coefficient (-0.7414567) that permeates our findings, leaving us pondering the intricacies of causality and influence. This unexpected revelation serves as a poignant reminder that in the domain of statistical analysis, serendipitous discoveries are not unlike the sudden aroma of freshly roasted coffee beans – an unexpected delight that enlivens the senses and prompts further inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

Data Collection:
The data utilized in this study were primarily sourced from the Bureau of Labor Statistics and the Energy Information Administration. Our research team meticulously combed through the labyrinthine expanse of online databases, seeking out information spanning from 2003 to 2021. The data on the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana was collected with the diligence of a pastry chef meticulously measuring ingredients for a delicate confection, whereas jet fuel consumption in Kiribati was scrutinized with the meticulous attention to detail reminiscent of a discerning sommelier examining a fine vintage.

Data Analysis:
Employing a blend of statistical methods akin to an intricate recipe, we performed a series of analyses to unravel the enigmatic relationship between the variables under scrutiny. The correlation coefficient, akin to a well-baked soufflé, was carefully monitored and scrutinized for its magnitude and significance. The resulting coefficient of -0.7414567 prompted a moment of astonishment among our team, akin to the surprise of finding an unexpected ingredient in a familiar dish. The utilization of p < 0.01 as the threshold for statistical significance allowed for the identification of a robust relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati.

Control Variables:
To ensure the robustness and reliability of our findings, an array of control variables was included in our analyses. These included economic indicators, demographic factors, and geographical peculiarities, akin to the meticulous consideration of complementary flavors and textures in the preparation of a gastronomic masterpiece. The inclusion of these control variables sought to temper the statistical concoction, much like a discerning chef fine-tuning a complex dish to achieve the perfect harmony of flavors.

Limitations:
Despite the comprehensive nature of our data collection and analysis, this study is not without its limitations. The use of secondary data, while providing a rich and diverse pool of information, may impart a degree of nuance reminiscent of a subtle seasoning – it lends flavor to the analysis but may introduce an element of uncertainty. Additionally, the complexities inherent in conducting cross-industry comparisons across distinct geographical locations pose inherent challenges, presenting a journey akin to traversing diverse culinary traditions in search of a unifying theme.

Conclusion:
As we conclude this section of methodological explication, it is abundantly clear that the study of the unexpected relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati is not dissimilar to the art of culinary exploration. It demands an eye for detail, a willingness to embrace surprises, and an unwavering commitment to unraveling the complex flavors of economic and industrial interactions.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Jet fuel used in Kiribati. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

[[ABSTRACT]]
This study delves into the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the jet fuel used in Kiribati. Using data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2021, we discovered a striking correlation coefficient of -0.7414567 and p < 0.01. Despite the seemingly unrelated nature of these variables, our findings reveal a significant negative relationship, hinting at a potential causal link between the two. This illuminating discovery not only sheds light on the enigmatic interplay between seemingly disparate industries but also serves as a reminder that in the labyrinth of statistical analysis, surprises often abound. We invite fellow researchers to join us in unraveling the tangled web of connections in the world of labor and energy consumption.

[[LITERATURE REVIEW]]
The connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati has been a topic of limited inquiry within the scholarly literature. Smith (2010) examined the occupational dynamics of food and tobacco roasting, baking, and drying machine operators and tenders, focusing on their role in the food processing industry. The study, however, did not extend its analysis to explore potential interconnections between the labor force in Indiana and energy usage in distant locales.
In a similar vein, Doe (2015) conducted a comprehensive analysis of energy consumption patterns in Oceania, with a particular emphasis on Kiribati. The study offered valuable insights into the sources and trends of energy consumption in the region but did not specifically consider the influence of labor dynamics in distant geographic areas.
Jones (2018) investigated the intersection of labor markets and energy usage, scrutinizing the dynamics of occupational sectors in various U.S. states. While shedding light on the distribution of labor across industries, the study did not delve into the curious juxtaposition between the labor force in Indiana's food and tobacco sector and the utilization of jet fuel in Kiribati.
Turning to non-fiction works that could potentially shed light on this enigmatic correlation, "Energy and Employment: A Just Transition" by Garcia et al. (2017) offers a comprehensive exploration of the intricate relationship between labor markets and energy consumption. However, the text does not specifically address the peculiar juxtaposition of the labor force in Indiana and energy usage in Kiribati.
Similarly, "Global Food, Global Justice: Essays on Eating Under Globalization" edited by Sollund (2015) provides a thought-provoking analysis of the global food industry and its social, economic, and environmental dimensions. While the volume offers valuable perspectives on the food sector, it does not explicitly explore the interplay between food industry labor in Indiana and jet fuel usage in Kiribati.
In the realm of fiction works that tangentially touch upon the themes of labor and energy, George Orwell's "Down and Out in Paris and London" could provide an insightful allegorical perspective on the toils of labor and the underlying dynamics of economic systems. However, the novel does not directly address the specific correlation under investigation in this study.
Similarly, Aldous Huxley's "Brave New World" presents a dystopian vision of a future society, raising pertinent questions about labor, consumption, and societal structures. Yet, the novel does not offer direct insights into the interrelation between food and tobacco roasting, baking, and drying machine operators in Indiana and jet fuel consumption in Kiribati.
While not directly related to the academic inquiry at hand, the researchers found it pertinent to note that the film "Planes, Trains and Automobiles" serves as a lighthearted depiction of travel and transportation, albeit not specifically focused on jet fuel usage. Additionally, the film "The Devil Wears Prada" offers a satirical portrayal of the fashion industry, which, though unrelated to the study's focus, underscores the varied domains encompassed within the realm of labor and industry.

[[RESULTS]]
The results of our analysis revealed a striking correlation coefficient of -0.7414567 between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati for the period of 2003 to 2021. The coefficient of determination (r-squared) was calculated to be 0.5497581, indicating that a substantial portion of the variability in jet fuel consumption in Kiribati can be explained by the changes in the number of machine operators and tenders in Indiana. Furthermore, the p-value of less than 0.01 suggests that the correlation is statistically significant, providing robust evidence for the relationship between these seemingly incongruous variables.
Fig. 1 depicts a scatterplot illustrating the strong negative correlation between the two variables, emphasizing the unexpected nature of this association. The downward trend displayed in the scatterplot underscores the inverse relationship between the number of machine operators and tenders in Indiana and jet fuel consumption in Kiribati. This visually compelling representation serves as a poignant reminder of the serendipitous connections that can emerge from the labyrinth of statistical analysis, akin to stumbling upon an unexpected recipe for success in the culinary world.
The negative correlation coefficient observed in our study prompts contemplation of the underlying mechanisms driving this relationship. While the specific causal pathways remain elusive within the confines of this analysis, the robust statistical evidence invites further exploration into the potential drivers of this intriguing association. This unexpected revelation emphasizes the intricacies of economic interplay and underscores the need for researchers to remain open to unanticipated findings, much like the sudden burst of flavor in an otherwise ordinary dish.
In summary, our investigation into the correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati has unearthed a thought-provoking relationship. This revelatory discovery not only offers a glimpse into the enigmatic interconnections within the realms of labor and energy consumption but also serves as a testament to the potential for unexpected discoveries in the course of empirical inquiry.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

The pronounced negative correlation coefficient uncovered in this study prompts contemplation of the underlying causative mechanisms driving this peculiar relationship. The robust statistical evidence supports the prior research findings of Smith (2010) and Doe (2015), albeit in a rather unforeseen manner. While these previous works did not explicitly address the connection between the labor force in Indiana and energy utilization in Kiribati, our results tangentially corroborate the general inquiry into the interplay between labor dynamics and energy consumption patterns.

The negative relationship between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati is a surprising twist, reminiscent of an unexpected flavor combination in a culinary creation. Despite the disparate nature of these variables, our findings suggest a significant and robust linkage, akin to stumbling upon an unexpected recipe for success in the culinary world.

The downward trend illustrated in the scatterplot serves as a compelling visual representation of the counterintuitive association between the two variables. This unexpected revelation underscores the intricate web of connections within the realms of labor and energy consumption, much like the sudden burst of flavor in an otherwise ordinary dish. It is a reminder that in the labyrinth of statistical analysis, surprises often abound.

While the specific causal pathways driving this relationship remain elusive within the confines of this analysis, it is imperative to recognize that statistical correlations do not necessarily imply causation. Therefore, further exploration into the potential drivers of this intriguing association is warranted. The unexpected nature of this discovery emphasizes the need for researchers to remain open to unanticipated findings, much like the unpredictable twists in a compelling narrative.

In conclusion, our study has brought to light an intriguing correlation between the seemingly dissimilar worlds of labor in Indiana and jet fuel consumption in Kiribati. Furthermore, it underscores the potential for unanticipated discoveries in the course of empirical inquiry, much like stumbling upon an unexpected ingredient that elevates a dish from ordinary to extraordinary. This study paves the way for future investigations into the complex and often surprising interconnections within the realms of labor and energy consumption.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and Jet fuel used in Kiribati. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

[[ABSTRACT]]
This study delves into the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the jet fuel used in Kiribati. Using data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2021, we discovered a striking correlation coefficient of -0.7414567 and p < 0.01. Despite the seemingly unrelated nature of these variables, our findings reveal a significant negative relationship, hinting at a potential causal link between the two. This illuminating discovery not only sheds light on the enigmatic interplay between seemingly disparate industries but also serves as a reminder that in the labyrinth of statistical analysis, surprises often abound. We invite fellow researchers to join us in unraveling the tangled web of connections in the world of labor and energy consumption.

[[INTRDUCTION]]
The examination of inter-industry relationships within the realms of labor and energy consumption has long been a source of fascination for researchers. Uncovering unexpected connections can yield valuable insights and provide a deeper understanding of the intricate web of economic activities. In this study, we embark on a journey to explore the seemingly incongruous association between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati.
The cryptic allure of this correlation beckons us to delve into the intricate tapestry of industrial dynamics, where seemingly disparate entities may, upon closer examination, reveal unsuspected ties. As we navigate the labyrinth of statistical analysis, it is crucial to remain vigilant, for in the midst of seemingly unrelated variables, hidden patterns and relationships can emerge, much like a well-baked surprise in the oven of empirical investigation.
Our investigation stems from a recognition of the paradoxical nature of the global economic landscape, where the mundane and the extraordinary often converge in the dance of data points and coefficients. Like a skilled baker crafting a delicate soufflé, we seek to carefully sift through the data, aiming to extract meaning from the seemingly incongruous association between the labor force in Indiana's roasting, baking, and drying sector and the consumption of jet fuel in the remote archipelago of Kiribati.
As we embark on this academic endeavor, we are confronted with the enigma of the negative correlation coefficient (-0.7414567) that permeates our findings, leaving us pondering the intricacies of causality and influence. This unexpected revelation serves as a poignant reminder that in the domain of statistical analysis, serendipitous discoveries are not unlike the sudden aroma of freshly roasted coffee beans – an unexpected delight that enlivens the senses and prompts further inquiry.

[[RESULTS]]
The results of our analysis revealed a striking correlation coefficient of -0.7414567 between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati for the period of 2003 to 2021. The coefficient of determination (r-squared) was calculated to be 0.5497581, indicating that a substantial portion of the variability in jet fuel consumption in Kiribati can be explained by the changes in the number of machine operators and tenders in Indiana. Furthermore, the p-value of less than 0.01 suggests that the correlation is statistically significant, providing robust evidence for the relationship between these seemingly incongruous variables.
Fig. 1 depicts a scatterplot illustrating the strong negative correlation between the two variables, emphasizing the unexpected nature of this association. The downward trend displayed in the scatterplot underscores the inverse relationship between the number of machine operators and tenders in Indiana and jet fuel consumption in Kiribati. This visually compelling representation serves as a poignant reminder of the serendipitous connections that can emerge from the labyrinth of statistical analysis, akin to stumbling upon an unexpected recipe for success in the culinary world.
The negative correlation coefficient observed in our study prompts contemplation of the underlying mechanisms driving this relationship. While the specific causal pathways remain elusive within the confines of this analysis, the robust statistical evidence invites further exploration into the potential drivers of this intriguing association. This unexpected revelation emphasizes the intricacies of economic interplay and underscores the need for researchers to remain open to unanticipated findings, much like the sudden burst of flavor in an otherwise ordinary dish.
In summary, our investigation into the correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and jet fuel consumption in Kiribati has unearthed a thought-provoking relationship. This revelatory discovery not only offers a glimpse into the enigmatic interconnections within the realms of labor and energy consumption but also serves as a testament to the potential for unexpected discoveries in the course of empirical inquiry.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our exploration of the connection between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the consumption of jet fuel in Kiribati has revealed a compelling, if not confounding, correlation. The striking negative correlation coefficient (-0.7414567) and the statistically significant p-value provide robust evidence for this unexpected relationship, leaving us to ponder the mechanisms at play. While we refrain from hastily attributing causality, the substantial portion of variability in jet fuel consumption in Kiribati explained by changes in the number of machine operators and tenders in Indiana raises intriguing questions.

The scatterplot visually encapsulates the inverse nature of this association, much like the eccentric pairing of a smoky barbecue with an unexpected dash of citrus. As we navigate the convoluted terrain of economic interactions, this revelation serves as a savory tidbit, reminding us that beneath the surface of mundane data lie tantalizing connections waiting to be uncovered.

However, our study has its limitations, akin to a soufflé that doesn't quite rise to perfection. The specifics of the causal pathways elude us, beckoning further investigation. While we have peeled back a layer of the enigmatic interplay between labor and energy consumption, there remains an entire cake to be fully baked in unraveling the intricacies of this correlation.

In light of our findings, we assert that no further research is needed in this area. The unexpected nature of this correlation stands as a testament to the whimsical dance of statistical analysis, reminding us that within the intricate tapestry of data lie hidden delights waiting to be savored.

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 Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Culinary Science and Environmental Economics

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 Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Culinary Connections and Global Energy Patterns

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 Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati with an abstract of This study delves into the unexpected correlation between the number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana and the jet fuel used in Kiribati. Using data from the Bureau of Labor Statistics and the Energy Information Administration spanning from 2003 to 2021, we discovered a striking correlation coefficient of -0.7414567 and p < 0.01. Despite the seemingly unrelated nature of these variables, our findings reveal a significant negative relationship, hinting at a potential causal link between the two. This illuminating discovery not only sheds light on the enigmatic interplay between seemingly disparate industries but also serves as a reminder that in the labyrinth of statistical analysis, surprises often abound. We invite fellow researchers to join us in unraveling the tangled web of connections in the world of labor and energy consumption.

ChatGPT:

food and tobacco roasting, baking and drying machine operators, tenders, Indiana, jet fuel consumption, Kiribati, correlation, Bureau of Labor Statistics, Energy Information Administration, statistical analysis, labor and energy consumption, causal link

*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 Indiana
Detailed data title: BLS estimate of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana
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 Indiana

Jet fuel used in Kiribati
Detailed data title: Volume of jet fuel used consumed in Kiribati in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Jet fuel used in Kiribati

Correlation r = -0.7414567 (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 = 0.5497581 (Coefficient of determination)
This means 55% of the change in the one variable (i.e., Jet fuel used in Kiribati) 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 Indiana) over the 19 years from 2003 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.00028.^Show 0.0002801254097200124700000000
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 -0.74 in 0.028% of random cases. Said differently, if you correlated 3,570 random variables^Note Which I absolutely did.
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.

[ -0.89, -0.43 ] 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 Indiana (Laborers)	370	340	310	220	160	130	120	360	450	430	190	310	380	370	350	320	370	190	330
Jet fuel used in Kiribati (Million Barrels/Day)	0.021726	0.0216667	0.021726	0.032589	0.0630055	0.0606667	0.0499699	0.032589	0.021726	0.02275	0.0247677	0.0219433	0.021943	0.0226	0.0299819	0.0304164	0.030851	0.0292846	0.03024

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.
Inverted Y-axis: I inverted the Y-axis on the chart above so that the lines would move together. This is visually pleasing, but not at all intuitive. Below is a line graph that does not invert the Y-axis and starts at zero.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{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([370,340,310,220,160,130,120,360,450,430,190,310,380,370,350,320,370,190,330,])
array_2 = np.array([0.021726,0.0216667,0.021726,0.032589,0.0630055,0.0606667,0.0499699,0.032589,0.021726,0.02275,0.0247677,0.0219433,0.021943,0.0226,0.0299819,0.0304164,0.030851,0.0292846,0.03024,])
array_1_name = "The number of food and tobacco roasting, baking, and drying machine operators and tenders in Indiana"
array_2_name = "Jet fuel used in Kiribati"

# 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 Indiana
Line chart for only Jet fuel used in Kiribati
AI-generated correlation image
The spurious research paper: Burning the Midnight Oil: An Unlikely Relationship Between Food and Tobacco Roasting, Baking, and Drying Machine Operators and Tenders in Indiana and Jet Fuel Consumption in Kiribati

View another random correlation

How fun was this correlation?

You're the correlation whisperer we needed!

Correlation ID: 1816 · Black Variable ID: 7818 · Red Variable ID: 24596


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