about · email me · subscribe
Spurious correlation #1,424 · 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 New York City and the second variable is Arson in United States.  The chart goes from 1985 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in New York City meant arsonists' lighters were no longer getting clogged with soot, leading to fewer successful arson attempts nationwide.

Model: dalle-3
Prompt: Generate an image of the New York City skyline, where tall skyscrapers disappear into a thick layer of smog, almost shrouded by the dense, gray atmosphere. In the foreground, a building is ablaze, with flames shooting out of its windows and smoke billowing into the sky. Firefighters, distinguishable by their protective gear and helmets, are depicted rushing towards the burning structure, their silhouette prominent against the backdrop of the city. The entire scene is recreated as a striking black-and-white newspaper illustration. 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: Unhealthy air quality in New York City and Arson 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: A black-and-white newspaper illustration High-tech Cyberpunk Cute 2D animation An image that looks like it is a scene from 'Star Wars'
ChatGPT: A black-and-white newspaper illustration

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 Unhealthy air quality in New York City and Arson in United States together. Keep the description simple.
ChatGPT: Thick smog clouds hang over the New York City skyline as flames engulf a building, with firefighters rushing to extinguish the fire.

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 black-and-white newspaper illustration ] and depicting this scene: Thick smog clouds hang over the New York City skyline as flames engulf a building, with firefighters rushing to extinguish the fire. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of the New York City skyline, where tall skyscrapers disappear into a thick layer of smog, almost shrouded by the dense, gray atmosphere. In the foreground, a building is ablaze, with flames shooting out of its windows and smoke billowing into the sky. Firefighters, distinguishable by their protective gear and helmets, are depicted rushing towards the burning structure, their silhouette prominent against the backdrop of the city. The entire scene is recreated as a striking black-and-white newspaper illustration.

*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 New York City caused Arson in United States to decrease.

AI academic paper

(Because p < 0.01)
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

Journal of Environmental Criminology and Atmospheric Studies

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 silly researcher writing an academic paper.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 New York City and Arson 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 a clever pun.

Your research team used data from Environmental Protection Agency and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.8722697 and p < 0.01 for 1985 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]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

Air pollution has been a topic of heated debate in the scientific community for many years. Researchers have long been burning the midnight oil in search of answers to the questions surrounding the impacts of air pollution on various aspects of human life. In this paper, we add fuel to the fire by investigating the potential relationship between air pollution in the bustling metropolis of New York City and the occurrence of arson incidents across the United States.

The notion of connecting the dots between air pollution and arson might seem like trying to catch smoke with a butterfly net. However, armed with statistical tools and a keen eye for unexpected correlations, our research team set out to sift through the data and see if we could fan the flames of insight into this peculiar link.

The Environmental Protection Agency, with its arsenal of air quality measurements, and the FBI Criminal Justice Information Services, with its trove of arson incident records, provided us with the fuel for our investigation. We gathered data spanning nearly four decades, from 1985 to 2022, to ensure that our analysis did not go up in smoke due to a limited time frame.

Our findings, as we reveal in this paper, sparked our curiosity and left us gasping for breath. We uncovered a correlation coefficient of 0.8722697 - a figure that flickered like a candle in the wind, signaling a potential association between air pollution in New York City and the occurrence of arson incidents across the United States. Furthermore, with a p-value of less than 0.01, our results were hotter than a jalapeño pepper, indicating a statistically significant relationship.

As we embark on this journey to unravel the mysteries of air pollution and arson, we acknowledge the smoke and mirrors that often shroud such investigations. Nonetheless, we hope that our efforts will set the stage for further research, igniting a blaze of interest in understanding the interplay between environmental and criminal factors. Just as a spark can ignite a wildfire, we aim to ignite the flames of curiosity and inquiry in the scientific community and beyond with our findings.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson 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 name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
Air pollution has been a topic of heated debate in the scientific community for many years. Researchers have long been burning the midnight oil in search of answers to the questions surrounding the impacts of air pollution on various aspects of human life. In this paper, we add fuel to the fire by investigating the potential relationship between air pollution in the bustling metropolis of New York City and the occurrence of arson incidents across the United States.
The notion of connecting the dots between air pollution and arson might seem like trying to catch smoke with a butterfly net. However, armed with statistical tools and a keen eye for unexpected correlations, our research team set out to sift through the data and see if we could fan the flames of insight into this peculiar link.
The Environmental Protection Agency, with its arsenal of air quality measurements, and the FBI Criminal Justice Information Services, with its trove of arson incident records, provided us with the fuel for our investigation. We gathered data spanning nearly four decades, from 1985 to 2022, to ensure that our analysis did not go up in smoke due to a limited time frame.
Our findings, as we reveal in this paper, sparked our curiosity and left us gasping for breath. We uncovered a correlation coefficient of 0.8722697 - a figure that flickered like a candle in the wind, signaling a potential association between air pollution in New York City and the occurrence of arson incidents across the United States. Furthermore, with a p-value of less than 0.01, our results were hotter than a jalapeño pepper, indicating a statistically significant relationship.
As we embark on this journey to unravel the mysteries of air pollution and arson, we acknowledge the smoke and mirrors that often shroud such investigations. Nonetheless, we hope that our efforts will set the stage for further research, igniting a blaze of interest in understanding the interplay between environmental and criminal factors. Just as a spark can ignite a wildfire, we aim to ignite the flames of curiosity and inquiry in the scientific community and beyond with our findings.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The link between air pollution and criminal behavior has garnered significant attention in recent years. Smith et al. (2015) explored the impact of air pollution on various health and social outcomes, but their study did not directly address its potential connection to criminal acts. Doe and Jones (2018) investigated the environmental factors influencing criminal behavior, yet they did not delve into the specific relationship between air pollution and arson.

Turning the page to non-fiction books, "The Air Pollution Prevention Act" and "Crime and the Urban Environment" provide valuable insights into the individual components of our research. However, when turning to fiction, "Smoke Gets in Your Eyes" and "Playing with Fire" offer a more imaginative perspective on the subject matter. As the authors illuminated their narratives with vivid descriptions, we found ourselves entranced by the fictional portrayal of the smoky urban landscape and the allure of arson.

In our quest for a deeper understanding, we turned our attention to TV shows with potential relevance. "Breaking Bad" and "Mindhunter" provided intriguing glimpses into criminal psychology and motivations, eliciting a burning desire to explore the nuances of arson incidents in the context of air pollution.

As we sifted through this body of literature and media, it became increasingly clear that the connection between air pollution in New York City and arson across the United States warranted further investigation. The existing research, while enlightening in its own right, failed to fan the flames of inquiry into this specific intersection. Thus, our study seeks to bridge this gap and shed light on a distinctly smoldering correlation, igniting sparks of curiosity within the scientific community.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services . You used data from 1985 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]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

[[INTRODUCTION]]
INTRODUCTION
Air pollution has been a topic of heated debate in the scientific community for many years. Researchers have long been burning the midnight oil in search of answers to the questions surrounding the impacts of air pollution on various aspects of human life. In this paper, we add fuel to the fire by investigating the potential relationship between air pollution in the bustling metropolis of New York City and the occurrence of arson incidents across the United States.
The notion of connecting the dots between air pollution and arson might seem like trying to catch smoke with a butterfly net. However, armed with statistical tools and a keen eye for unexpected correlations, our research team set out to sift through the data and see if we could fan the flames of insight into this peculiar link.
The Environmental Protection Agency, with its arsenal of air quality measurements, and the FBI Criminal Justice Information Services, with its trove of arson incident records, provided us with the fuel for our investigation. We gathered data spanning nearly four decades, from 1985 to 2022, to ensure that our analysis did not go up in smoke due to a limited time frame.
Our findings, as we reveal in this paper, sparked our curiosity and left us gasping for breath. We uncovered a correlation coefficient of 0.8722697 - a figure that flickered like a candle in the wind, signaling a potential association between air pollution in New York City and the occurrence of arson incidents across the United States. Furthermore, with a p-value of less than 0.01, our results were hotter than a jalapeño pepper, indicating a statistically significant relationship.
As we embark on this journey to unravel the mysteries of air pollution and arson, we acknowledge the smoke and mirrors that often shroud such investigations. Nonetheless, we hope that our efforts will set the stage for further research, igniting a blaze of interest in understanding the interplay between environmental and criminal factors. Just as a spark can ignite a wildfire, we aim to ignite the flames of curiosity and inquiry in the scientific community and beyond with our findings.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unearth the potential link between air pollution in New York City and arson incidents in the United States, our research team employed a combination of rigorous data collection, advanced statistical analysis, and a dash of scientific ingenuity.

Data Collection:
Our primary source of air pollution data stemmed from the Environmental Protection Agency's vast repository of air quality measurements. We selected specific air quality indices (AQI) related to pollutants like particulate matter (PM2.5 and PM10), carbon monoxide (CO), sulfur dioxide (SO2), nitrogen dioxide (NO2), and o-zone (O3). This multipollutant approach aimed to prevent any potential gaslighting of our findings by a single pollutant and capture the full spectrum of air quality dynamics in New York City.

For the arson incidents across the United States, we relied on the FBI Criminal Justice Information Services, where we extracted data related to the number and locations of reported arson cases. We wanted to ensure that our analysis was not firewalled by a narrow scope, so we collected data from urban and rural areas, acknowledging that arson incidents can ignite anywhere.

Data Analysis:
To analyze the collected data, we donned our statistical firefighter helmets and wielded a variety of analytical tools. Firstly, we conducted descriptive statistics to better understand the central tendency and dispersion of the variables. This allowed us to gauge the smoldering intensity of air pollution levels and arson incidents over the years.

Next, we applied correlation analysis, akin to inspecting the kindling that might spark a fire. This involved calculating Pearson's correlation coefficient to quantify the strength and direction of the relationship between air pollution and arson. We also performed multivariate regression analysis, kindling the flames of excitement as we delved into the potential predictive power of air pollution on arson incidents, controlling for other potential confounding factors.

Furthermore, we employed time series analysis to examine the temporal patterns in both air pollution and arson incidents. This approach aimed to capture the ebb and flow, much like the flickering flames of a roaring fire, of these variables over the years.

Conclusion:
In conclusion, our methodology aimed to kindle a comprehensive understanding of the potential relationship between air pollution in New York City and arson incidents across the United States. By utilizing a myriad of analytical techniques, we endeavored to not only fan the flames of insight but also prevent our findings from going up in smoke due to incomplete or inadequate analysis. With our approach, we hope to illuminate the debate surrounding the impact of air pollution on criminal behavior and ignite further research interest in this unexplored intersection of environmental and criminal factors.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services .

For the time period 1985 to 2022, you found a correlation 0.8722697, r-squared of 0.7608544, 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]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
Air pollution has been a topic of heated debate in the scientific community for many years. Researchers have long been burning the midnight oil in search of answers to the questions surrounding the impacts of air pollution on various aspects of human life. In this paper, we add fuel to the fire by investigating the potential relationship between air pollution in the bustling metropolis of New York City and the occurrence of arson incidents across the United States.
The notion of connecting the dots between air pollution and arson might seem like trying to catch smoke with a butterfly net. However, armed with statistical tools and a keen eye for unexpected correlations, our research team set out to sift through the data and see if we could fan the flames of insight into this peculiar link.
The Environmental Protection Agency, with its arsenal of air quality measurements, and the FBI Criminal Justice Information Services, with its trove of arson incident records, provided us with the fuel for our investigation. We gathered data spanning nearly four decades, from 1985 to 2022, to ensure that our analysis did not go up in smoke due to a limited time frame.
Our findings, as we reveal in this paper, sparked our curiosity and left us gasping for breath. We uncovered a correlation coefficient of 0.8722697 - a figure that flickered like a candle in the wind, signaling a potential association between air pollution in New York City and the occurrence of arson incidents across the United States. Furthermore, with a p-value of less than 0.01, our results were hotter than a jalapeño pepper, indicating a statistically significant relationship.
As we embark on this journey to unravel the mysteries of air pollution and arson, we acknowledge the smoke and mirrors that often shroud such investigations. Nonetheless, we hope that our efforts will set the stage for further research, igniting a blaze of interest in understanding the interplay between environmental and criminal factors. Just as a spark can ignite a wildfire, we aim to ignite the flames of curiosity and inquiry in the scientific community and beyond with our findings.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis of the data collected from the Environmental Protection Agency and the FBI Criminal Justice Information Services revealed an intriguing relationship between air pollution in New York City and the incidence of arson across the United States. The correlation coefficient of 0.8722697 suggests a strong positive association between these two variables, while the r-squared value of 0.7608544 indicates that approximately 76.1% of the variability in arson incidents can be explained by changes in air pollution levels. With a p-value of less than 0.01, our results provide strong evidence of a significant relationship, hotter than the flames of a campfire on a chilly night.

Furthermore, the scatterplot (Fig. 1) included in this paper visually demonstrates the robust correlation between air pollution in New York City and arson incidents in the United States. The data points exhibit a clear pattern, resembling the erratic dance of sparks in a campfire, further supporting our statistical findings.

Overall, our research provides compelling evidence that the level of air pollution in New York City is positively associated with the occurrence of arson across the United States. While the specific mechanisms underlying this relationship remain a bit hazy, our results kindle the flame of curiosity and warrant further investigation into the complex interplay between environmental and criminal factors. Just as a smoldering ember has the potential to ignite a raging inferno, our findings ignite the need for additional studies to fully understand the firestorm of factors at play in this curious association.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

[[LITERATURE REVIEW]]
The link between air pollution and criminal behavior has garnered significant attention in recent years. Smith et al. (2015) explored the impact of air pollution on various health and social outcomes, but their study did not directly address its potential connection to criminal acts. Doe and Jones (2018) investigated the environmental factors influencing criminal behavior, yet they did not delve into the specific relationship between air pollution and arson.
Turning the page to non-fiction books, "The Air Pollution Prevention Act" and "Crime and the Urban Environment" provide valuable insights into the individual components of our research. However, when turning to fiction, "Smoke Gets in Your Eyes" and "Playing with Fire" offer a more imaginative perspective on the subject matter. As the authors illuminated their narratives with vivid descriptions, we found ourselves entranced by the fictional portrayal of the smoky urban landscape and the allure of arson.
In our quest for a deeper understanding, we turned our attention to TV shows with potential relevance. "Breaking Bad" and "Mindhunter" provided intriguing glimpses into criminal psychology and motivations, eliciting a burning desire to explore the nuances of arson incidents in the context of air pollution.
As we sifted through this body of literature and media, it became increasingly clear that the connection between air pollution in New York City and arson across the United States warranted further investigation. The existing research, while enlightening in its own right, failed to fan the flames of inquiry into this specific intersection. Thus, our study seeks to bridge this gap and shed light on a distinctly smoldering correlation, igniting sparks of curiosity within the scientific community.

[[RESULTS]]
Our analysis of the data collected from the Environmental Protection Agency and the FBI Criminal Justice Information Services revealed an intriguing relationship between air pollution in New York City and the incidence of arson across the United States. The correlation coefficient of 0.8722697 suggests a strong positive association between these two variables, while the r-squared value of 0.7608544 indicates that approximately 76.1% of the variability in arson incidents can be explained by changes in air pollution levels. With a p-value of less than 0.01, our results provide strong evidence of a significant relationship, hotter than the flames of a campfire on a chilly night.
Furthermore, the scatterplot (Fig. 1) included in this paper visually demonstrates the robust correlation between air pollution in New York City and arson incidents in the United States. The data points exhibit a clear pattern, resembling the erratic dance of sparks in a campfire, further supporting our statistical findings.
Overall, our research provides compelling evidence that the level of air pollution in New York City is positively associated with the occurrence of arson across the United States. While the specific mechanisms underlying this relationship remain a bit hazy, our results kindle the flame of curiosity and warrant further investigation into the complex interplay between environmental and criminal factors. Just as a smoldering ember has the potential to ignite a raging inferno, our findings ignite the need for additional studies to fully understand the firestorm of factors at play in this curious association.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

The scorching results of our research have laid bare the fiery connection between air pollution in New York City and arson incidents across the United States. Our findings not only breathe fresh air into the field of environmental criminology but also stoke the flames of curiosity for future investigations. The sizzling correlation coefficient of 0.8722697 and a p-value of less than 0.01 provide robust support for our hypothesis, igniting excitement among researchers like a well-fueled bonfire.

Speaking of bonfires, let's circle back to our literature review. While we might have whimsically mentioned the subtle influence of "Breaking Bad" and "Mindhunter" on our research, the significance of these contributions cannot be underestimated. After all, who would have thought that TV shows would provide sparks of inspiration for our scientific inquiry? Similarly, while we may have initially chuckled at the mention of "Smoke Gets in Your Eyes" and "Playing with Fire," these fictional works inadvertently kindled our interest in the subject matter, reminding us that even in the world of academic research, truth can sometimes be stranger than fiction.

Our results have corroborated and expanded upon the existing literature, fanning the flames of understanding in a field that has traditionally been dimly lit. This illuminating research provides a breath of fresh air and sets the stage for further exploration into the complex relationship between environmental factors and criminal behavior.

As we draw our discussion to a close, it's worth highlighting that just as the sparks of curiosity from our findings continue to smolder, this paper may serve as a guiding light for future studies. After all, in the world of research, it often takes just a single flame to ignite a veritable inferno of discovery.


Model: gpt-3.5-turbo-1106
System prompt: You are a silly researcher writing an academic paper.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 New York City and Arson in United States. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States

[[ABSTRACT]]
This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

[[INTRDUCTION]]
INTRODUCTION
Air pollution has been a topic of heated debate in the scientific community for many years. Researchers have long been burning the midnight oil in search of answers to the questions surrounding the impacts of air pollution on various aspects of human life. In this paper, we add fuel to the fire by investigating the potential relationship between air pollution in the bustling metropolis of New York City and the occurrence of arson incidents across the United States.
The notion of connecting the dots between air pollution and arson might seem like trying to catch smoke with a butterfly net. However, armed with statistical tools and a keen eye for unexpected correlations, our research team set out to sift through the data and see if we could fan the flames of insight into this peculiar link.
The Environmental Protection Agency, with its arsenal of air quality measurements, and the FBI Criminal Justice Information Services, with its trove of arson incident records, provided us with the fuel for our investigation. We gathered data spanning nearly four decades, from 1985 to 2022, to ensure that our analysis did not go up in smoke due to a limited time frame.
Our findings, as we reveal in this paper, sparked our curiosity and left us gasping for breath. We uncovered a correlation coefficient of 0.8722697 - a figure that flickered like a candle in the wind, signaling a potential association between air pollution in New York City and the occurrence of arson incidents across the United States. Furthermore, with a p-value of less than 0.01, our results were hotter than a jalapeño pepper, indicating a statistically significant relationship.
As we embark on this journey to unravel the mysteries of air pollution and arson, we acknowledge the smoke and mirrors that often shroud such investigations. Nonetheless, we hope that our efforts will set the stage for further research, igniting a blaze of interest in understanding the interplay between environmental and criminal factors. Just as a spark can ignite a wildfire, we aim to ignite the flames of curiosity and inquiry in the scientific community and beyond with our findings.

[[RESULTS]]
Our analysis of the data collected from the Environmental Protection Agency and the FBI Criminal Justice Information Services revealed an intriguing relationship between air pollution in New York City and the incidence of arson across the United States. The correlation coefficient of 0.8722697 suggests a strong positive association between these two variables, while the r-squared value of 0.7608544 indicates that approximately 76.1% of the variability in arson incidents can be explained by changes in air pollution levels. With a p-value of less than 0.01, our results provide strong evidence of a significant relationship, hotter than the flames of a campfire on a chilly night.
Furthermore, the scatterplot (Fig. 1) included in this paper visually demonstrates the robust correlation between air pollution in New York City and arson incidents in the United States. The data points exhibit a clear pattern, resembling the erratic dance of sparks in a campfire, further supporting our statistical findings.
Overall, our research provides compelling evidence that the level of air pollution in New York City is positively associated with the occurrence of arson across the United States. While the specific mechanisms underlying this relationship remain a bit hazy, our results kindle the flame of curiosity and warrant further investigation into the complex interplay between environmental and criminal factors. Just as a smoldering ember has the potential to ignite a raging inferno, our findings ignite the need for additional studies to fully understand the firestorm of factors at play in this curious association.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has brought to light a compelling connection between air pollution in New York City and arson incidents across the United States. The statistically significant correlation coefficient of 0.8722697 and the p-value of less than 0.01 provide strong evidence for this fiery association. While the precise mechanisms underlying this relationship may still be shrouded in a bit of smog, our findings kindle the flames of curiosity and prompt further investigation into the interplay of environmental and criminal factors.

With our research serving as the kindling for future inquiries, we hope to ignite the interest of researchers in delving deeper into this puzzling yet intriguing association. However, it may be wise not to jump into conclusions like a hare-brained hare into a bonfire, as more studies are needed to fully understand the combustible dynamics at play.

In the spirit of scientific inquiry, we urge caution in interpreting these results as anything more than a spark of insight into the complex relationship between air pollution and arson. Just as a well-tended fire requires careful attention, additional research should proceed with diligence and thorough investigation, fanning the flames of knowledge without getting burned.

Ultimately, our findings add fuel to the fire of scientific curiosity but underscore the need for more structured and controlled investigation into this phenomenon. On the bright side, it is safe to say that for now, no further research is needed in this area - at least until we're ready to light the match for the next round of investigations!


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 A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Environmental Criminology and Atmospheric Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States. Respond only with the name of a fictional organization.

ChatGPT:

Institute for Urban Environmental Health and Safety


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 A Breath of Fresh Air: Unearthing the Link Between Air Pollution in New York City and Arson in the United States with an abstract of This paper examines the intriguing relationship between air pollution in New York City and arson incidents across the United States. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning the years 1985 to 2022, our research team found a startling correlation coefficient of 0.8722697 and a p-value of less than 0.01. While the connection may not be as clear as a smog-free day, our findings suggest a potentially fiery interaction between these two variables. In uncovering this association, we not only shed light on the interplay of environmental and criminal factors but also fan the flames of curiosity for future investigations.

ChatGPT:

air pollution, New York City, arson, United States, correlation coefficient, Environmental Protection Agency, FBI Criminal Justice Information Services, correlation between air pollution and arson

*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 New York City
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in New York-Newark-Jersey City, NY-NJ-PA
Source: Environmental Protection Agency
See what else correlates with Air pollution in New York City

Arson in United States
Detailed data title: The arson rate per 100,000 residents in United States
Source: FBI Criminal Justice Information Services
See what else correlates with Arson in United States

Correlation r = 0.8722697 (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 = 0.7608544 (Coefficient of determination)
This means 76.1% of the change in the one variable (i.e., Arson in United States) is predictable based on the change in the other (i.e., Air pollution in New York City) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 9.8E-13. 0.0000000000009829252978485174
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 9.8E-11% of random cases. Said differently, if you correlated 1,017,371,312,132 random variables You don't actually need 1 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 37 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 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.

[ 0.77, 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.
19851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in New York City (Bad air quality days)52.054844.109640.821931.420830.13724.383629.041116.939923.013723.287719.72618.30617.808222.191822.739717.759624.383623.561616.712313.934419.452117.808218.082214.20779.5890416.71239.041110.65575.753424.3835610.4118.196725.205487.397264.383563.005465.753423.0137
Arson in United States (Arson rate)43.646.342.54141.441.74140.837.339.636.734.632.629.728.824.727.726.82523.623.124.422.621.619.518.117.517.614.914.513.714.113.2121113.98.911.6




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([52.0548,44.1096,40.8219,31.4208,30.137,24.3836,29.0411,16.9399,23.0137,23.2877,19.726,18.306,17.8082,22.1918,22.7397,17.7596,24.3836,23.5616,16.7123,13.9344,19.4521,17.8082,18.0822,14.2077,9.58904,16.7123,9.0411,10.6557,5.75342,4.38356,10.411,8.19672,5.20548,7.39726,4.38356,3.00546,5.75342,3.0137,])
array_2 = np.array([43.6,46.3,42.5,41,41.4,41.7,41,40.8,37.3,39.6,36.7,34.6,32.6,29.7,28.8,24.7,27.7,26.8,25,23.6,23.1,24.4,22.6,21.6,19.5,18.1,17.5,17.6,14.9,14.5,13.7,14.1,13.2,12,11,13.9,8.9,11.6,])
array_1_name = "Air pollution in New York City"
array_2_name = "Arson 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?

You're the correlation whisperer we needed!


Correlation ID: 1424 · Black Variable ID: 20976 · Red Variable ID: 20038
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0