about · email me · subscribe
Spurious correlation #4,740 · 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 Boston and the second variable is Kerosene used in United States.  The chart goes from 1980 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in Boston made people realize they didn't need to burn as much kerosene to light their homes, so there was a nationwide decrease in kerosene usage.

Model: dalle-3
Prompt: Generate an image that captures the essence of a vibrant Boston cityscape at night, enveloped in a Vaporwave aesthetic. The image should emanate a sense of futuristic serenity as the bright city lights illuminate the streets of Boston amid a crisp, clear night sky. The reduced smog and enhanced visibility contribute to the ambiance, showcasing a cleaner and more environmentally conscious urban environment. The city should appear positively transformed, with fewer kerosene lamps illuminating homes and a noticeable decrease in street noise. The overall scene should exude a feeling of progress and tranquility in a retro-futuristic style. 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 Boston and Kerosene used in United States. 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: An image that looks like it is a scene from a Pixar movie Vaporwave Glitch art Voxel art Cubism
ChatGPT: Vaporwave

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 Boston and Kerosene used in United States, in the following situation: The cleaner air in Boston made people realize they didn't need to burn as much kerosene to light their homes, so there was a nationwide decrease in kerosene usage.. Keep the description simple.
ChatGPT: Bright city lights illuminate the streets of Boston under a clear night sky. The air is noticeably cleaner, with fewer smog clouds and clearer visibility. People in the city have fewer kerosene lamps lit in their homes, and the streets are quieter as a nationwide decrease in kerosene usage takes effect.

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: [ Vaporwave ] and depicting this scene: Bright city lights illuminate the streets of Boston under a clear night sky. The air is noticeably cleaner, with fewer smog clouds and clearer visibility. People in the city have fewer kerosene lamps lit in their homes, and the streets are quieter as a nationwide decrease in kerosene usage takes effect. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that captures the essence of a vibrant Boston cityscape at night, enveloped in a Vaporwave aesthetic. The image should emanate a sense of futuristic serenity as the bright city lights illuminate the streets of Boston amid a crisp, clear night sky. The reduced smog and enhanced visibility contribute to the ambiance, showcasing a cleaner and more environmentally conscious urban environment. The city should appear positively transformed, with fewer kerosene lamps illuminating homes and a noticeable decrease in street noise. The overall scene should exude a feeling of progress and tranquility in a retro-futuristic style.

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

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in Air pollution in Boston caused Kerosene used in United States to decrease.

AI academic paper

(Because p < 0.01)
Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States

The Journal of Environmental Quirks and Quandaries

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from Environmental Protection Agency and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.8650919 and p < 0.01 for 1980 to 2022.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Air pollution is a pervasive issue with far-reaching implications for public health and environmental quality. The increase in urbanization and industrialization in recent decades has led to heightened concerns about the impact of pollutants on air quality. Amidst this atmospheric milieu, kerosene has often been relegated to the background, with its role in air pollution receiving less attention than other more prominent sources. However, our study aims to illuminate the potential connection between kerosene consumption in the United States and air pollution levels in the city of Boston, shedding light on this unexplored relationship.

While kerosene has historically been a popular choice for lighting and heating homes, particularly in rural and low-income areas, its influence on broader environmental factors has been relatively understudied. Indeed, one might say kerosene has been left in the dark when it comes to discussions of air pollution, overshadowed by more prominent sources such as vehicular emissions and industrial processes. Nevertheless, as we delve into the data, we aim to uncover whether kerosene might have a more significant role to play in perpetuating the hazy conditions enveloping our urban centers.

The city of Boston, with its rich historical significance and vibrant urban landscape, provides an intriguing backdrop for our investigation. Known for its diverse population and atmospheric conditions that are sometimes as unpredictable as a New England winter, Boston offers an ideal setting for examining the intricate interplay between human activities and atmospheric phenomena. Through our rigorous analysis of air pollution data in Boston and kerosene consumption patterns across the United States, we aim to bring this relationship to the forefront - effectively dragging kerosene out of the shadows and into the spotlight, if you will.

Our pursuit of this connection is not purely for academic intrigue; rather, it stems from the inherent necessity to understand and mitigate the factors contributing to air pollution. By unraveling the potential association between kerosene usage and air quality, we endeavor to pave the way for more informed policy decisions and targeted interventions to address this looming environmental concern. Let's hope that our findings shed some light on this issue, much like a well-lit kerosene lamp on a dark, stormy night - minus the fumes, of course!

As we embark on this endeavor, we invite the reader to join us on this scientific journey, where we transition from merely flickering a match in the darkness to illuminating the underexplored corridors of environmental research. So, let's roll up our sleeves and dive into the data, armed with a spirit of inquiry and perhaps a dash of humor, as we uncover the possible relationship between air pollution in Boston and the unassuming yet potentially influential kerosene consumption across the United States.

Stay tuned for our findings, as we aim to reveal the hidden connections and dispel the haze surrounding this intriguing association.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Air pollution is a pervasive issue with far-reaching implications for public health and environmental quality. The increase in urbanization and industrialization in recent decades has led to heightened concerns about the impact of pollutants on air quality. Amidst this atmospheric milieu, kerosene has often been relegated to the background, with its role in air pollution receiving less attention than other more prominent sources. However, our study aims to illuminate the potential connection between kerosene consumption in the United States and air pollution levels in the city of Boston, shedding light on this unexplored relationship.
While kerosene has historically been a popular choice for lighting and heating homes, particularly in rural and low-income areas, its influence on broader environmental factors has been relatively understudied. Indeed, one might say kerosene has been left in the dark when it comes to discussions of air pollution, overshadowed by more prominent sources such as vehicular emissions and industrial processes. Nevertheless, as we delve into the data, we aim to uncover whether kerosene might have a more significant role to play in perpetuating the hazy conditions enveloping our urban centers.
The city of Boston, with its rich historical significance and vibrant urban landscape, provides an intriguing backdrop for our investigation. Known for its diverse population and atmospheric conditions that are sometimes as unpredictable as a New England winter, Boston offers an ideal setting for examining the intricate interplay between human activities and atmospheric phenomena. Through our rigorous analysis of air pollution data in Boston and kerosene consumption patterns across the United States, we aim to bring this relationship to the forefront - effectively dragging kerosene out of the shadows and into the spotlight, if you will.
Our pursuit of this connection is not purely for academic intrigue; rather, it stems from the inherent necessity to understand and mitigate the factors contributing to air pollution. By unraveling the potential association between kerosene usage and air quality, we endeavor to pave the way for more informed policy decisions and targeted interventions to address this looming environmental concern. Let's hope that our findings shed some light on this issue, much like a well-lit kerosene lamp on a dark, stormy night - minus the fumes, of course!
As we embark on this endeavor, we invite the reader to join us on this scientific journey, where we transition from merely flickering a match in the darkness to illuminating the underexplored corridors of environmental research. So, let's roll up our sleeves and dive into the data, armed with a spirit of inquiry and perhaps a dash of humor, as we uncover the possible relationship between air pollution in Boston and the unassuming yet potentially influential kerosene consumption across the United States.
Stay tuned for our findings, as we aim to reveal the hidden connections and dispel the haze surrounding this intriguing association.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The potential link between air pollution in urban areas and various sources of fuel consumption has been a subject of growing interest in environmental research. Smith et al. (2015) conducted a comprehensive analysis of air quality data in major U.S. cities, including Boston, and identified key contributors to particulate matter and volatile organic compound emissions. Meanwhile, Doe and Jones (2018) delved into the patterns of kerosene usage in residential settings across the United States, highlighting its prevalence in regions with limited access to electricity and natural gas. These studies have laid the groundwork for understanding the intricate dynamics at play in the atmospheric composition of urban environments, paving the way for our investigation into the potential association between air pollution in Boston and kerosene consumption in the United States.

Turning to non-fiction literature, "The Air We Breathe" by Francesca Barber highlights the profound impacts of air pollution on public health and environmental well-being. The book offers a sobering account of the challenges posed by pollutants in urban settings, reminding us that the air we breathe is an inextricable part of our daily existence - much like an unwanted roommate with questionable hygiene habits.

On a lighter note, the fictional works of J.R.R. Tolkien in "The Lord of the Rings" trilogy feature an array of atmospheric phenomena, albeit in a fantastical context. While kerosene is notably absent in Middle-earth, the portrayal of smoky mountains and fiery landscapes sparks curious parallels to our exploration of air pollution and fuel consumption. Perhaps we should take a page from the hobbits' book and embark on our own unexpected journey through the realm of environmental research.

Furthermore, social media posts such as "Just saw a kerosene lamp for the first time since my grandmother's stories about her childhood. Did you know they contribute to air pollution?" provide anecdotal insights into public perceptions of kerosene usage and its potential environmental implications. Although these posts may not reflect scientific rigor, they serve as a reminder of the everyday relevance of our research questions and the need to bridge the gap between academic inquiry and public awareness.

As we synthesize these diverse sources of information, we acknowledge the breadth and depth of existing literature on air pollution and fuel consumption. Our study seeks to build upon this foundation, adding a touch of whimsy to the serious business of environmental research. Here's to shedding light on unexpected connections and uncovering the hidden gems of knowledge amidst the haze of scientific inquiry. Cheers to illuminating the path ahead, much like a well-lit kerosene lamp - minus the fumes, of course!


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration . You used data from 1980 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]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

[[INTRODUCTION]]
Air pollution is a pervasive issue with far-reaching implications for public health and environmental quality. The increase in urbanization and industrialization in recent decades has led to heightened concerns about the impact of pollutants on air quality. Amidst this atmospheric milieu, kerosene has often been relegated to the background, with its role in air pollution receiving less attention than other more prominent sources. However, our study aims to illuminate the potential connection between kerosene consumption in the United States and air pollution levels in the city of Boston, shedding light on this unexplored relationship.
While kerosene has historically been a popular choice for lighting and heating homes, particularly in rural and low-income areas, its influence on broader environmental factors has been relatively understudied. Indeed, one might say kerosene has been left in the dark when it comes to discussions of air pollution, overshadowed by more prominent sources such as vehicular emissions and industrial processes. Nevertheless, as we delve into the data, we aim to uncover whether kerosene might have a more significant role to play in perpetuating the hazy conditions enveloping our urban centers.
The city of Boston, with its rich historical significance and vibrant urban landscape, provides an intriguing backdrop for our investigation. Known for its diverse population and atmospheric conditions that are sometimes as unpredictable as a New England winter, Boston offers an ideal setting for examining the intricate interplay between human activities and atmospheric phenomena. Through our rigorous analysis of air pollution data in Boston and kerosene consumption patterns across the United States, we aim to bring this relationship to the forefront - effectively dragging kerosene out of the shadows and into the spotlight, if you will.
Our pursuit of this connection is not purely for academic intrigue; rather, it stems from the inherent necessity to understand and mitigate the factors contributing to air pollution. By unraveling the potential association between kerosene usage and air quality, we endeavor to pave the way for more informed policy decisions and targeted interventions to address this looming environmental concern. Let's hope that our findings shed some light on this issue, much like a well-lit kerosene lamp on a dark, stormy night - minus the fumes, of course!
As we embark on this endeavor, we invite the reader to join us on this scientific journey, where we transition from merely flickering a match in the darkness to illuminating the underexplored corridors of environmental research. So, let's roll up our sleeves and dive into the data, armed with a spirit of inquiry and perhaps a dash of humor, as we uncover the possible relationship between air pollution in Boston and the unassuming yet potentially influential kerosene consumption across the United States.
Stay tuned for our findings, as we aim to reveal the hidden connections and dispel the haze surrounding this intriguing association.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Our research team embarked on this investigative odyssey with the goal of unraveling the enigmatic connection between air pollution in Boston and the widespread consumption of kerosene across the United States. Utilizing a blend of data wrangling wizardry and statistical sorcery, we delved into the treasure trove of information amassed by the Environmental Protection Agency (EPA) and the Energy Information Administration (EIA). Our data collection process resembled a digital scavenger hunt, with forays into the depths of internet repositories and databases, armed with nothing but our wits and a reliable internet connection – not unlike seeking hidden treasures in the vast expanse of cyberspace.

The primary sources of data included air quality measurements in Boston and kerosene consumption statistics across the United States from 1980 to 2022. Our selection of this time frame was akin to peering through the historical telescope, allowing us to capture the temporal evolution of these variables and discern any underlying patterns or trends. It was as if we were archeologists digging into layers of temporal sediment, unearthing the relics of data from bygone eras to piece together the puzzle of this intriguing association.

To unveil the potential nexus between air pollution and kerosene usage, we employed a medley of analytical techniques, including correlation analysis, time-series modeling, and spatial mapping. Our statistical toolkit was akin to an assortment of Swiss army knives, each adorned with a precision-engineered blade or tweezer tailored to extract the choicest insights from our data. We meticulously sifted through the data grains, teasing out the subtle nuances of the relationship between air pollution levels in Boston and the consumption of kerosene across the United States.

The heart of our empirical endeavor lay in the calculation and interpretation of correlation coefficients, which served as the Rosetta Stone for deciphering the cryptic language of association between these variables. With bated breath, we scrutinized the numerical output of statistical tests, eagerly anticipating the unveiling of any meaningful relationships lurking within the data labyrinth. Our quest was reminiscent of fumbling through a treasure map, meticulously following each lead in the hope of stumbling upon the elusive X that marked the spot of statistical significance.

Furthermore, our foray into time-series modeling involved the deployment of sophisticated models to capture the temporal dynamics of air pollution levels and kerosene consumption, akin to crafting a time-bending contraption to peer into the past and foresee the future. The data metamorphosed into an intricate tapestry of temporal patterns, revealing the ebb and flow of these variables across the years in a symphony of statistical harmonics.

Finally, we undertook the ambitious task of spatial mapping, harnessing the power of geographic information systems to visualize the spatial distribution of air pollution and kerosene consumption across the United States. Our cartographic escapade resembled wielding a paintbrush to craft a masterpiece, as we transmuted the raw data into visually striking maps that vividly portrayed the geographical footprints of air pollution and kerosene utilization. These maps not only served as visual artifacts of our analysis but also provided a cartographic compass to navigate the spatial nuances of the studied variables.

In summation, our research methodology encompassed a blend of meticulous data collection, rigorous statistical analysis, and spatial visualization, akin to crafting an intricate tapestry that weaves together the threads of air pollution and kerosene consumption into a compelling narrative. With these methodological tools at our disposal, we ventured forth to untangle the enigma of their interconnectedness, armed with curiosity, statistical prowess, and perhaps a hint of academic whimsy.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Energy Information Administration .

For the time period 1980 to 2022, you found a correlation 0.8650919, r-squared of 0.7483841, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Air pollution is a pervasive issue with far-reaching implications for public health and environmental quality. The increase in urbanization and industrialization in recent decades has led to heightened concerns about the impact of pollutants on air quality. Amidst this atmospheric milieu, kerosene has often been relegated to the background, with its role in air pollution receiving less attention than other more prominent sources. However, our study aims to illuminate the potential connection between kerosene consumption in the United States and air pollution levels in the city of Boston, shedding light on this unexplored relationship.
While kerosene has historically been a popular choice for lighting and heating homes, particularly in rural and low-income areas, its influence on broader environmental factors has been relatively understudied. Indeed, one might say kerosene has been left in the dark when it comes to discussions of air pollution, overshadowed by more prominent sources such as vehicular emissions and industrial processes. Nevertheless, as we delve into the data, we aim to uncover whether kerosene might have a more significant role to play in perpetuating the hazy conditions enveloping our urban centers.
The city of Boston, with its rich historical significance and vibrant urban landscape, provides an intriguing backdrop for our investigation. Known for its diverse population and atmospheric conditions that are sometimes as unpredictable as a New England winter, Boston offers an ideal setting for examining the intricate interplay between human activities and atmospheric phenomena. Through our rigorous analysis of air pollution data in Boston and kerosene consumption patterns across the United States, we aim to bring this relationship to the forefront - effectively dragging kerosene out of the shadows and into the spotlight, if you will.
Our pursuit of this connection is not purely for academic intrigue; rather, it stems from the inherent necessity to understand and mitigate the factors contributing to air pollution. By unraveling the potential association between kerosene usage and air quality, we endeavor to pave the way for more informed policy decisions and targeted interventions to address this looming environmental concern. Let's hope that our findings shed some light on this issue, much like a well-lit kerosene lamp on a dark, stormy night - minus the fumes, of course!
As we embark on this endeavor, we invite the reader to join us on this scientific journey, where we transition from merely flickering a match in the darkness to illuminating the underexplored corridors of environmental research. So, let's roll up our sleeves and dive into the data, armed with a spirit of inquiry and perhaps a dash of humor, as we uncover the possible relationship between air pollution in Boston and the unassuming yet potentially influential kerosene consumption across the United States.
Stay tuned for our findings, as we aim to reveal the hidden connections and dispel the haze surrounding this intriguing association.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

We discovered a significant correlation between air pollution levels in Boston and kerosene consumption in the United States over the 42-year period from 1980 to 2022. Our analysis of the data obtained from the Environmental Protection Agency and the Energy Information Administration revealed a correlation coefficient of 0.8650919, indicating a strong positive association between these two seemingly disparate variables. With an r-squared value of 0.7483841, we found that approximately 74.8% of the variability in air pollution levels in Boston can be explained by the variability in kerosene consumption across the United States. The p-value of less than 0.01 further emphasizes the statistical significance of this relationship, affirming that this connection is no mere statistical fluke.

Notably, Fig. 1 visually encapsulates the compelling correlation we observed, illustrating how kerosene consumption across the United States aligns with air pollution levels in Boston. The scatterplot showcases the tight clustering of data points, indicating a strong linear relationship between the two variables. It seems that kerosene might not only be lighting up homes but also lighting up the pollution levels in Boston – talk about a multi-talented fuel!

Our findings lend credence to the notion that seemingly unrelated environmental factors can intermingle in ways that might surprise even the keenest observers. This study underscores the importance of delving into unconventional relationships, reminding us that there's more to the environmental puzzle than meets the eye. Our hope is that this revelation will ignite further interest in untangling the complex web of connections shaping our environmental landscape - though preferably without adding any more pollutants to the mix!


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

[[LITERATURE REVIEW]]
The potential link between air pollution in urban areas and various sources of fuel consumption has been a subject of growing interest in environmental research. Smith et al. (2015) conducted a comprehensive analysis of air quality data in major U.S. cities, including Boston, and identified key contributors to particulate matter and volatile organic compound emissions. Meanwhile, Doe and Jones (2018) delved into the patterns of kerosene usage in residential settings across the United States, highlighting its prevalence in regions with limited access to electricity and natural gas. These studies have laid the groundwork for understanding the intricate dynamics at play in the atmospheric composition of urban environments, paving the way for our investigation into the potential association between air pollution in Boston and kerosene consumption in the United States.
Turning to non-fiction literature, "The Air We Breathe" by Francesca Barber highlights the profound impacts of air pollution on public health and environmental well-being. The book offers a sobering account of the challenges posed by pollutants in urban settings, reminding us that the air we breathe is an inextricable part of our daily existence - much like an unwanted roommate with questionable hygiene habits.
On a lighter note, the fictional works of J.R.R. Tolkien in "The Lord of the Rings" trilogy feature an array of atmospheric phenomena, albeit in a fantastical context. While kerosene is notably absent in Middle-earth, the portrayal of smoky mountains and fiery landscapes sparks curious parallels to our exploration of air pollution and fuel consumption. Perhaps we should take a page from the hobbits' book and embark on our own unexpected journey through the realm of environmental research.
Furthermore, social media posts such as "Just saw a kerosene lamp for the first time since my grandmother's stories about her childhood. Did you know they contribute to air pollution?" provide anecdotal insights into public perceptions of kerosene usage and its potential environmental implications. Although these posts may not reflect scientific rigor, they serve as a reminder of the everyday relevance of our research questions and the need to bridge the gap between academic inquiry and public awareness.
As we synthesize these diverse sources of information, we acknowledge the breadth and depth of existing literature on air pollution and fuel consumption. Our study seeks to build upon this foundation, adding a touch of whimsy to the serious business of environmental research. Here's to shedding light on unexpected connections and uncovering the hidden gems of knowledge amidst the haze of scientific inquiry. Cheers to illuminating the path ahead, much like a well-lit kerosene lamp - minus the fumes, of course!

[[RESULTS]]
We discovered a significant correlation between air pollution levels in Boston and kerosene consumption in the United States over the 42-year period from 1980 to 2022. Our analysis of the data obtained from the Environmental Protection Agency and the Energy Information Administration revealed a correlation coefficient of 0.8650919, indicating a strong positive association between these two seemingly disparate variables. With an r-squared value of 0.7483841, we found that approximately 74.8% of the variability in air pollution levels in Boston can be explained by the variability in kerosene consumption across the United States. The p-value of less than 0.01 further emphasizes the statistical significance of this relationship, affirming that this connection is no mere statistical fluke.
Notably, Fig. 1 visually encapsulates the compelling correlation we observed, illustrating how kerosene consumption across the United States aligns with air pollution levels in Boston. The scatterplot showcases the tight clustering of data points, indicating a strong linear relationship between the two variables. It seems that kerosene might not only be lighting up homes but also lighting up the pollution levels in Boston – talk about a multi-talented fuel!
Our findings lend credence to the notion that seemingly unrelated environmental factors can intermingle in ways that might surprise even the keenest observers. This study underscores the importance of delving into unconventional relationships, reminding us that there's more to the environmental puzzle than meets the eye. Our hope is that this revelation will ignite further interest in untangling the complex web of connections shaping our environmental landscape - though preferably without adding any more pollutants to the mix!

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Turning our attention to the implications of our findings, it is evident that the relationship between air pollution in Boston and kerosene consumption in the United States is no mere whimsy but a robust statistical reality. Our results align with prior research, demonstrating a strong correlation between these two seemingly distant variables. Much like the unexpected connection between a suddenly relevant meme and an econometric phenomenon, the link between air pollution and kerosene consumption has surpassed mere coincidence. The tight clustering of data points in our scatterplot, akin to a bustling city street during rush hour, underscores the undeniable association between these factors.

Smith et al.'s (2015) work on air quality in major U.S. cities, including Boston, provided a solid foundation for our investigation. Their identification of key contributors to particulate matter aligns with our own findings, bolstering the notion that kerosene consumption indeed plays a pivotal role in shaping air quality. Additionally, Doe and Jones' (2018) exploration of kerosene usage in residential settings across the United States not only sheds light on the prevalence of this fuel but also serves as a beacon, guiding our research towards this unexpected yet tangible association. Moreover, the keen observations from social media posts, seemingly trivial at first glance, bear relevance to our findings and underscore the everyday impact of our research.

Our study adds a touch of levity to the serious discourse on environmental factors, much like a well-timed joke lightening the mood at a high-stakes conference. However, amidst the humor, our findings carry weight, emphasizing the need to further investigate the interconnected web of relationships between seemingly disparate variables. As we continue shedding light on this association (sans kerosene flames, of course), we pave the way for future research to unveil the intricacies of our atmospheric composition, much like an uncovering of unexpected comedic timing in academic prose.

In conclusion (which will be written separately), our investigation into the link between air pollution in Boston and kerosene consumption in the United States not only raises eyebrows but also elevates the discourse on environmental dynamics to new heights. Let's continue to illuminate the path ahead, much like a well-lit kerosene lamp, without the fumes, of course!


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Boston and Kerosene used in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States"

[[ABSTRACT]]
In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

[[INTRDUCTION]]
Air pollution is a pervasive issue with far-reaching implications for public health and environmental quality. The increase in urbanization and industrialization in recent decades has led to heightened concerns about the impact of pollutants on air quality. Amidst this atmospheric milieu, kerosene has often been relegated to the background, with its role in air pollution receiving less attention than other more prominent sources. However, our study aims to illuminate the potential connection between kerosene consumption in the United States and air pollution levels in the city of Boston, shedding light on this unexplored relationship.
While kerosene has historically been a popular choice for lighting and heating homes, particularly in rural and low-income areas, its influence on broader environmental factors has been relatively understudied. Indeed, one might say kerosene has been left in the dark when it comes to discussions of air pollution, overshadowed by more prominent sources such as vehicular emissions and industrial processes. Nevertheless, as we delve into the data, we aim to uncover whether kerosene might have a more significant role to play in perpetuating the hazy conditions enveloping our urban centers.
The city of Boston, with its rich historical significance and vibrant urban landscape, provides an intriguing backdrop for our investigation. Known for its diverse population and atmospheric conditions that are sometimes as unpredictable as a New England winter, Boston offers an ideal setting for examining the intricate interplay between human activities and atmospheric phenomena. Through our rigorous analysis of air pollution data in Boston and kerosene consumption patterns across the United States, we aim to bring this relationship to the forefront - effectively dragging kerosene out of the shadows and into the spotlight, if you will.
Our pursuit of this connection is not purely for academic intrigue; rather, it stems from the inherent necessity to understand and mitigate the factors contributing to air pollution. By unraveling the potential association between kerosene usage and air quality, we endeavor to pave the way for more informed policy decisions and targeted interventions to address this looming environmental concern. Let's hope that our findings shed some light on this issue, much like a well-lit kerosene lamp on a dark, stormy night - minus the fumes, of course!
As we embark on this endeavor, we invite the reader to join us on this scientific journey, where we transition from merely flickering a match in the darkness to illuminating the underexplored corridors of environmental research. So, let's roll up our sleeves and dive into the data, armed with a spirit of inquiry and perhaps a dash of humor, as we uncover the possible relationship between air pollution in Boston and the unassuming yet potentially influential kerosene consumption across the United States.
Stay tuned for our findings, as we aim to reveal the hidden connections and dispel the haze surrounding this intriguing association.

[[RESULTS]]
We discovered a significant correlation between air pollution levels in Boston and kerosene consumption in the United States over the 42-year period from 1980 to 2022. Our analysis of the data obtained from the Environmental Protection Agency and the Energy Information Administration revealed a correlation coefficient of 0.8650919, indicating a strong positive association between these two seemingly disparate variables. With an r-squared value of 0.7483841, we found that approximately 74.8% of the variability in air pollution levels in Boston can be explained by the variability in kerosene consumption across the United States. The p-value of less than 0.01 further emphasizes the statistical significance of this relationship, affirming that this connection is no mere statistical fluke.
Notably, Fig. 1 visually encapsulates the compelling correlation we observed, illustrating how kerosene consumption across the United States aligns with air pollution levels in Boston. The scatterplot showcases the tight clustering of data points, indicating a strong linear relationship between the two variables. It seems that kerosene might not only be lighting up homes but also lighting up the pollution levels in Boston – talk about a multi-talented fuel!
Our findings lend credence to the notion that seemingly unrelated environmental factors can intermingle in ways that might surprise even the keenest observers. This study underscores the importance of delving into unconventional relationships, reminding us that there's more to the environmental puzzle than meets the eye. Our hope is that this revelation will ignite further interest in untangling the complex web of connections shaping our environmental landscape - though preferably without adding any more pollutants to the mix!

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In concluding our investigation, we assert that this study has illuminated a substantial correlation between air pollution in Boston and kerosene consumption in the United States. The remarkably robust correlation coefficient of 0.8650919 and the r-squared value of 0.7483841 unequivocally establish the significance of this association. It appears that kerosene, long overshadowed by its flashier counterparts in the pollution game, is indeed a key player in the environmental arena. Who would have thought that this unassuming fuel could have such an impact? It seems that when it comes to air pollution, kerosene is a real "lightweight" - in more ways than one!

Our analysis also underscores the need to recognize the interconnectedness of seemingly disparate variables in shaping environmental outcomes. This newfound understanding sheds light on the complex dynamics at play in our atmosphere, emphasizing the need for holistic approaches to tackling air quality issues. It's clear that our study has sparked new insights into the multifaceted nature of environmental factors – much like the flicker of a kerosene lamp in the still of the night.

It is our firm belief that this study serves as a catalyst for further exploration of the intricate web of relationships woven into the fabric of air pollution dynamics. However, perhaps it's time to dim the spotlight on this particular topic. After all, how much more can be uncovered about the unlikely link between Boston's pollution and kerosene use nationwide? It's not rocket science; the data speaks for itself. It's time to extinguish the flames of curiosity on this specific correlation and redirect our research efforts toward other intriguing environmental mysteries. This study has shed ample light on the subject, and it's high time we turn our attention to other dimly lit corners of environmental research.


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 Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Environmental Quirks and Quandaries


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 Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States. Respond only with the name of a fictional organization.

ChatGPT:

The International Institute for Environmental Economics and Policy Research


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 Clearing the Air: Analyzing the Relationship between Air Pollution in Boston and Kerosene Consumption in the United States with an abstract of In this study, we scrutinize the correlation between air pollution levels in Boston and kerosene usage across the United States over a period of 42 years from 1980 to 2022. Leveraging data from the Environmental Protection Agency and the Energy Information Administration, our research team meticulously analyzed the relationship between these two seemingly disparate factors. Our findings revealed a remarkably robust correlation coefficient of 0.8650919, with a p-value of less than 0.01, indicating a significant association between air pollution in Boston and kerosene consumption in the United States. So, it seems that in addition to lighting up homes, kerosene might also be lighting up the pollution levels in Boston! This study contributes to our understanding of the interconnectedness of environmental factors and underscores the need for further investigation into the intricate web of relationships between seemingly unrelated variables. Our hope is that shedding light on this association - not kerosene light, mind you - will fuel future research into the complex dynamics at play in our atmosphere.

ChatGPT:

air pollution, Boston, kerosene consumption, United States, correlation, Environmental Protection Agency, Energy Information Administration, pollution levels, correlation coefficient, p-value, environmental factors, interconnectedness, relationships, variables, atmosphere dynamics

*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 Boston
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Boston-Cambridge-Newton, MA-NH
Source: Environmental Protection Agency
See what else correlates with Air pollution in Boston

Kerosene used in United States
Detailed data title: Volume of kerosene used consumed in United States in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in United States

Correlation r = 0.8650919 (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 = 0.7483841 (Coefficient of determination)
This means 74.8% of the change in the one variable (i.e., Kerosene used in United States) is predictable based on the change in the other (i.e., Air pollution in Boston) over the 43 years from 1980 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.4E-14. 0.0000000000000737284439103759
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

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

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.87 in 7.4E-12% of random cases. Said differently, if you correlated 13,563,286,392,096 random variables You don't actually need 13 trillion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

p-value calculations are useful for understanding the probability of a result happening by chance. They are most useful when used to highlight the risk of a fluke outcome. For example, if you calculate a p-value of 0.30, the risk that the result is a fluke is high. It is good to know that! But there are lots of ways to get a p-value of less than 0.01, as evidenced by this project.

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 42 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 42 because we have two variables measured over a period of 43 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.

[ 0.76, 0.93 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

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


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

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
1980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in Boston (Bad air quality days)20.491812.876717.534221.917827.049212.054812.328812.054814.20778.493158.493159.315078.196728.493158.219189.04117.377057.397267.6712311.50684.918039.5890415.89047.671234.098369.315078.767129.589044.644811.917812.739731.917813.551912.465751.369861.095891.912571.369861.369860.27397301.369861.64384
Kerosene used in United States (Million Barrels/Day)158126.882128.559127.008115.123113.83698.358994.569996.117584.142542.567146.369941.423549.646649.032954.06361.789666.030178.098673.112367.327972.290443.347954.627464.295169.808353.682632.139114.228617.547419.929212.24085.275915.197138.996046.385858.670625.177475.412616.771427.493625.943435.25028




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([20.4918,12.8767,17.5342,21.9178,27.0492,12.0548,12.3288,12.0548,14.2077,8.49315,8.49315,9.31507,8.19672,8.49315,8.21918,9.0411,7.37705,7.39726,7.67123,11.5068,4.91803,9.58904,15.8904,7.67123,4.09836,9.31507,8.76712,9.58904,4.64481,1.91781,2.73973,1.91781,3.55191,2.46575,1.36986,1.09589,1.91257,1.36986,1.36986,0.273973,0,1.36986,1.64384,])
array_2 = np.array([158,126.882,128.559,127.008,115.123,113.836,98.3589,94.5699,96.1175,84.1425,42.5671,46.3699,41.4235,49.6466,49.0329,54.063,61.7896,66.0301,78.0986,73.1123,67.3279,72.2904,43.3479,54.6274,64.2951,69.8083,53.6826,32.1391,14.2286,17.5474,19.9292,12.2408,5.27591,5.19713,8.99604,6.38585,8.67062,5.17747,5.41261,6.77142,7.49362,5.94343,5.25028,])
array_1_name = "Air pollution in Boston"
array_2_name = "Kerosene used in United States"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!


Correlation ID: 4740 · Black Variable ID: 20376 · Red Variable ID: 25053
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0