about · email me · subscribe
Spurious correlation #2,079 · 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 Wabash, Indiana and the second variable is Arson in United States.  The chart goes from 1990 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The cleaner air in Wabash meant there was less soot to go around, leaving arsonists without a suit-able accomplice for their fiery crimes. With no smog to mask their misdeeds, the arson rates went up in smoke!

Model: dalle-3
Prompt: Generate an image of a realistic scene in Wabash, Indiana, with thick clouds of smoke hanging low in the air, creating a hazy and unhealthy atmosphere. Within the haze, depict firefighters actively working to extinguish a blaze caused by an act of arson in a nearby building. Capture the intensity and urgency of their efforts amidst the smoke and fire. 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 Wabash, Indiana 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: Realistic Woodblock painting Parallax art Steampunk Vaporwave
ChatGPT: Realistic

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 Wabash, Indiana and Arson in United States together. Keep the description simple.
ChatGPT: In Wabash, Indiana, thick clouds of smoke hang low in the air, creating a hazy and unhealthy atmosphere. Amongst the haze, firefighters work tirelessly to extinguish a blaze caused by an act of arson in a nearby building.

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: [ Realistic ] and depicting this scene: In Wabash, Indiana, thick clouds of smoke hang low in the air, creating a hazy and unhealthy atmosphere. Amongst the haze, firefighters work tirelessly to extinguish a blaze caused by an act of arson in a nearby building. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a realistic scene in Wabash, Indiana, with thick clouds of smoke hanging low in the air, creating a hazy and unhealthy atmosphere. Within the haze, depict firefighters actively working to extinguish a blaze caused by an act of arson in a nearby building. Capture the intensity and urgency of their efforts amidst the smoke and fire.

*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 Wabash, Indiana caused Arson in United States to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

The Journal of Atmospheric and Arson 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 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 Wabash, Indiana 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 punny if you can come up with clever pun. If not, just make it sound clever.

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 0.7246561 and p < 0.01 for 1990 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]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.


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 Wabash, Indiana 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. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The study of environmental and criminal phenomena has often been confined to separate spheres of academic inquiry, with the former typically falling within the purview of environmental science and the latter under the domain of criminology. However, as our understanding of the intricate web of causation in human behavior continues to evolve, it becomes increasingly imperative to examine potential connections between seemingly disparate variables. In this research, we aim to scrutinize the relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The motivation behind this investigation stems from a desire to explore the oft-ignored intersection between air quality and criminal behavior, as well as to determine whether there is indeed fire where there's smoke, both literally and metaphorically.

The seemingly unlikely pairing of air pollution and arson may initially appear as implausible as a cloudless day in Seattle, yet there are compelling reasons to consider the potential influence of environmental factors on criminal activities. As the old adage goes, "Where there's smoke, there's fire," and our research endeavors to elucidate whether this expression holds true not just in the literal sense, but also in terms of the figurative smoggy relationship between air quality and arson incidents. While it may seem like a tall order to establish a connection between a silent, invisible assailant like air pollution and the deliberate, visible act of arson, our findings may well challenge preconceived notions and kindle new perspectives on the interplay between environmental conditions and criminal conduct.

The town of Wabash, Indiana, serves as a focal point of our investigation due to its unique combination of industrial activity and environmental factors, which create a microcosm of air pollution dynamics. The town's historical prominence as a manufacturing hub, coupled with its geographical location and meteorological characteristics, provides an intriguing backdrop for studying the potential impacts of air pollution on criminal behavior. Given the idiosyncrasies of Wabash and the broader implications for arson across the United States, this research holds promise in unraveling the enigmatic relationship between smog and pyromania.

Consequently, the overarching objective of this study is to contribute to a nuanced understanding of the multifaceted influences on criminal behavior by venturing into uncharted territory – or in this case, unfiltered air. By examining the empirical evidence surrounding air quality and arson, we endeavor to not only stir the embers of inquiry but also to fan the flames of discourse concerning the unexpected and, dare we say, incendiary connections between environmental variables and criminal acts.


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 Wabash, Indiana 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 some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The study of environmental and criminal phenomena has often been confined to separate spheres of academic inquiry, with the former typically falling within the purview of environmental science and the latter under the domain of criminology. However, as our understanding of the intricate web of causation in human behavior continues to evolve, it becomes increasingly imperative to examine potential connections between seemingly disparate variables. In this research, we aim to scrutinize the relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The motivation behind this investigation stems from a desire to explore the oft-ignored intersection between air quality and criminal behavior, as well as to determine whether there is indeed fire where there's smoke, both literally and metaphorically.
The seemingly unlikely pairing of air pollution and arson may initially appear as implausible as a cloudless day in Seattle, yet there are compelling reasons to consider the potential influence of environmental factors on criminal activities. As the old adage goes, "Where there's smoke, there's fire," and our research endeavors to elucidate whether this expression holds true not just in the literal sense, but also in terms of the figurative smoggy relationship between air quality and arson incidents. While it may seem like a tall order to establish a connection between a silent, invisible assailant like air pollution and the deliberate, visible act of arson, our findings may well challenge preconceived notions and kindle new perspectives on the interplay between environmental conditions and criminal conduct.
The town of Wabash, Indiana, serves as a focal point of our investigation due to its unique combination of industrial activity and environmental factors, which create a microcosm of air pollution dynamics. The town's historical prominence as a manufacturing hub, coupled with its geographical location and meteorological characteristics, provides an intriguing backdrop for studying the potential impacts of air pollution on criminal behavior. Given the idiosyncrasies of Wabash and the broader implications for arson across the United States, this research holds promise in unraveling the enigmatic relationship between smog and pyromania.
Consequently, the overarching objective of this study is to contribute to a nuanced understanding of the multifaceted influences on criminal behavior by venturing into uncharted territory – or in this case, unfiltered air. By examining the empirical evidence surrounding air quality and arson, we endeavor to not only stir the embers of inquiry but also to fan the flames of discourse concerning the unexpected and, dare we say, incendiary connections between environmental variables and criminal acts.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find that air pollution has been a subject of growing concern in both the academic and public spheres, with a multitude of studies attributing adverse health effects and environmental degradation to atmospheric contaminants. This body of literature underscores the pressing need to address air quality issues, not only for the well-being of human and ecological systems but also for the broader social implications. Meanwhile, "Doe and Jones" delve into the complexities of criminal behavior, highlighting the myriad factors that contribute to deviant acts within society. Their analysis illuminates the intricate web of causation in criminal phenomena, underscoring the multifaceted nature of criminal conduct and the paramount importance of understanding its underlying drivers.

Venturing into the realm of less conventional sources, "Fumes and Felonies: The Correlation Coefficient Chronicles" by Lorem Ipsum dissects the smoggy relationship between air pollution and arson, offering a curious exploration of the potential links between environmental factors and fire-related crimes. The unexpected juxtaposition of environmental science and criminology in this work certainly piques one's curiosity, much like stumbling upon a rare gem amidst a pile of statistical rubble.

Turning to the realm of non-fiction books, "The Big Burn: Teddy Roosevelt and the Fire that Saved America" by Timothy Egan provides a historical perspective on the impact of wildfires, examining the far-reaching consequences of infernos on landscapes and communities. Conversely, "Smoke Gets in Your Eyes: And Other Lessons from the Crematory" by Caitlin Doughty offers a macabre yet strangely fascinating account of the funeral industry, albeit tangentially linked to the subject at hand. A more whimsical addition to the literature is "The Arsonist's Guide to Writers' Homes in New England" by Brock Clarke, which, despite its fictional nature, presents an offbeat take on the world of arsonists and their unusual escapades.

Delving deeper into the terrain of popular culture, cartoons and children's shows such as "Paw Patrol" and "Fireman Sam" subtly instill the notion of fire safety and prevention in young audiences, albeit through the lens of anthropomorphic pups and a daring firefighter in the fictional town of Pontypandy. While these animated series may not provide direct insights into the scholarly discourse on air pollution and arson, they undeniably contribute to the collective consciousness surrounding fire-related themes, albeit in a lighthearted and whimsical manner.

In summary, the eclectic array of literature and cultural references pertaining to air pollution and arson spans a spectrum from the scholarly to the imaginative, offering a multifaceted tapestry of insights and entertainment. With this diverse landscape of sources as our backdrop, we embark on a scholarly endeavor to illuminate the smoggy relationship between air quality and arson, weaving together threads of empirical evidence and unexpected analogies to unravel the enigmatic connections between environmental variables and criminal behavior.


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 Wabash, Indiana 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. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services . You used data from 1990 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]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

[[INTRODUCTION]]
The study of environmental and criminal phenomena has often been confined to separate spheres of academic inquiry, with the former typically falling within the purview of environmental science and the latter under the domain of criminology. However, as our understanding of the intricate web of causation in human behavior continues to evolve, it becomes increasingly imperative to examine potential connections between seemingly disparate variables. In this research, we aim to scrutinize the relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The motivation behind this investigation stems from a desire to explore the oft-ignored intersection between air quality and criminal behavior, as well as to determine whether there is indeed fire where there's smoke, both literally and metaphorically.
The seemingly unlikely pairing of air pollution and arson may initially appear as implausible as a cloudless day in Seattle, yet there are compelling reasons to consider the potential influence of environmental factors on criminal activities. As the old adage goes, "Where there's smoke, there's fire," and our research endeavors to elucidate whether this expression holds true not just in the literal sense, but also in terms of the figurative smoggy relationship between air quality and arson incidents. While it may seem like a tall order to establish a connection between a silent, invisible assailant like air pollution and the deliberate, visible act of arson, our findings may well challenge preconceived notions and kindle new perspectives on the interplay between environmental conditions and criminal conduct.
The town of Wabash, Indiana, serves as a focal point of our investigation due to its unique combination of industrial activity and environmental factors, which create a microcosm of air pollution dynamics. The town's historical prominence as a manufacturing hub, coupled with its geographical location and meteorological characteristics, provides an intriguing backdrop for studying the potential impacts of air pollution on criminal behavior. Given the idiosyncrasies of Wabash and the broader implications for arson across the United States, this research holds promise in unraveling the enigmatic relationship between smog and pyromania.
Consequently, the overarching objective of this study is to contribute to a nuanced understanding of the multifaceted influences on criminal behavior by venturing into uncharted territory – or in this case, unfiltered air. By examining the empirical evidence surrounding air quality and arson, we endeavor to not only stir the embers of inquiry but also to fan the flames of discourse concerning the unexpected and, dare we say, incendiary connections between environmental variables and criminal acts.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the potential relationship between air pollution in Wabash, Indiana, and incidents of arson in the United States, a comprehensive and, dare we say, "fire-resistant" methodology was employed. Data spanning the years 1990 to 2022 were gathered from the venerable repositories of knowledge, namely the Environmental Protection Agency (EPA) and the FBI Criminal Justice Information Services. Our research team spared no expense in ensuring that the data were exhaustively collected and rigorously analyzed – much like a diligent firefighter methodically extinguishing embers.

Firstly, the air quality data for Wabash, Indiana, was obtained from the EPA's Air Quality System database, which encompasses measurements of various pollutants such as particulate matter, carbon monoxide, sulfur dioxide, and nitrogen dioxide. These data acted as the smoke signals guiding our inquiry into the potential impact of air pollution on criminal activity.

Simultaneously, the FBI's Uniform Crime Reporting (UCR) program provided the central repository of arson incidents across the United States. This comprehensive dataset allowed us to identify and examine arson incidents at both the national and state levels, akin to meticulously cataloging the spread of flames across a geographical landscape.

To assess the relationship between air pollution and arson, a series of rigorous statistical analyses were conducted. These analyses involved the use of regression models to tease apart the potential influence of air quality on arson incidents, taking into account various control variables to ensure a robust examination. The examination method mirrored the meticulous inspection of a fire scene by an experienced investigator, leaving no stone unturned in uncovering the potential connections between environmental factors and criminal behavior.

Furthermore, spatial and temporal analyses were deployed to unravel any underlying patterns or trends in the data – akin to the discerning eye of a seasoned fire marshal scanning the scene for telltale signs of arson. Geographic Information System (GIS) software was employed to map the spatial distribution of arson incidents and air pollution levels, providing a visual representation of the interplay between these variables.

As with any rigorous scientific inquiry, careful consideration was given to controlling for confounding variables and potential sources of bias. Multivariate analyses were conducted to account for various demographic, socio-economic, and environmental factors that could potentially influence the relationship between air pollution and arson. This thorough approach allowed us to sift through the statistical smoke and mirrors to uncover any substantive connections between air quality and fiery criminal activities.

In summary, the methodology employed in this research strived to be as comprehensive and meticulous as a well-designed fire safety plan. The convergence of data collection, robust statistical analyses, and thorough consideration of potential confounders enabled us to sift through the smoke and uncover compelling insights into the smoggy relationship between air pollution in Wabash, Indiana, and arson incidents across the United States.


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 Wabash, Indiana 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. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1990 to 2022, you found a correlation 0.7246561, r-squared of 0.5251265, 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]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The study of environmental and criminal phenomena has often been confined to separate spheres of academic inquiry, with the former typically falling within the purview of environmental science and the latter under the domain of criminology. However, as our understanding of the intricate web of causation in human behavior continues to evolve, it becomes increasingly imperative to examine potential connections between seemingly disparate variables. In this research, we aim to scrutinize the relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The motivation behind this investigation stems from a desire to explore the oft-ignored intersection between air quality and criminal behavior, as well as to determine whether there is indeed fire where there's smoke, both literally and metaphorically.
The seemingly unlikely pairing of air pollution and arson may initially appear as implausible as a cloudless day in Seattle, yet there are compelling reasons to consider the potential influence of environmental factors on criminal activities. As the old adage goes, "Where there's smoke, there's fire," and our research endeavors to elucidate whether this expression holds true not just in the literal sense, but also in terms of the figurative smoggy relationship between air quality and arson incidents. While it may seem like a tall order to establish a connection between a silent, invisible assailant like air pollution and the deliberate, visible act of arson, our findings may well challenge preconceived notions and kindle new perspectives on the interplay between environmental conditions and criminal conduct.
The town of Wabash, Indiana, serves as a focal point of our investigation due to its unique combination of industrial activity and environmental factors, which create a microcosm of air pollution dynamics. The town's historical prominence as a manufacturing hub, coupled with its geographical location and meteorological characteristics, provides an intriguing backdrop for studying the potential impacts of air pollution on criminal behavior. Given the idiosyncrasies of Wabash and the broader implications for arson across the United States, this research holds promise in unraveling the enigmatic relationship between smog and pyromania.
Consequently, the overarching objective of this study is to contribute to a nuanced understanding of the multifaceted influences on criminal behavior by venturing into uncharted territory – or in this case, unfiltered air. By examining the empirical evidence surrounding air quality and arson, we endeavor to not only stir the embers of inquiry but also to fan the flames of discourse concerning the unexpected and, dare we say, incendiary connections between environmental variables and criminal acts.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The data analysis revealed a striking correlation coefficient of 0.7246561 between air pollution in Wabash, Indiana, and incidents of arson across the United States. This significant association was supported by an r-squared value of 0.5251265, indicating that approximately 52.51% of the variability in arson incidents could be explained by variations in air pollution levels. The statistical significance of the correlation was further underscored by a p-value of less than 0.01, lending credence to the robustness of the observed relationship.

Fig. 1 depicts the scatterplot illustrating the compelling correlation between air pollution levels in Wabash, Indiana, and incidents of arson across the United States. The figure unequivocally portrays the alignment of these variables, making it abundantly clear that where there’s pollution, there’s a higher propensity for combustion – a fiery testament to the interplay between environmental conditions and criminal behavior.

These findings not only provide quantitative support for the notion that smog may serve as more than just a backdrop to criminal activities but also spark contemplation on the potential mechanisms underlying this intriguing relationship. The results challenge traditional perspectives and salvage the often-overlooked idea that air pollution does more than just dimming the view; it may also stoke the flames of arson - quite literally and figuratively, if you will. This unexpected revelation ignites novel inquiries into the web of causality between environmental factors and criminal conduct, setting ablaze the discourse on the unseen influences on fiery felonies.

In sum, this study unearths a compelling correlation between air pollution in Wabash, Indiana, and incidents of arson in the United States, lighting the way for further investigation into the smoggy entanglement of environmental variables and criminal behavior. These results not only illuminate the need for a more comprehensive understanding of the multifaceted influences on criminal activities but also kindle a newfound appreciation for the potential impact of haze on unlawful blazes – offering a fresh perspective on the burning question of the relationship between environmental factors and criminal conduct.


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 Wabash, Indiana 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. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find that air pollution has been a subject of growing concern in both the academic and public spheres, with a multitude of studies attributing adverse health effects and environmental degradation to atmospheric contaminants. This body of literature underscores the pressing need to address air quality issues, not only for the well-being of human and ecological systems but also for the broader social implications. Meanwhile, "Doe and Jones" delve into the complexities of criminal behavior, highlighting the myriad factors that contribute to deviant acts within society. Their analysis illuminates the intricate web of causation in criminal phenomena, underscoring the multifaceted nature of criminal conduct and the paramount importance of understanding its underlying drivers.
Venturing into the realm of less conventional sources, "Fumes and Felonies: The Correlation Coefficient Chronicles" by Lorem Ipsum dissects the smoggy relationship between air pollution and arson, offering a curious exploration of the potential links between environmental factors and fire-related crimes. The unexpected juxtaposition of environmental science and criminology in this work certainly piques one's curiosity, much like stumbling upon a rare gem amidst a pile of statistical rubble.
Turning to the realm of non-fiction books, "The Big Burn: Teddy Roosevelt and the Fire that Saved America" by Timothy Egan provides a historical perspective on the impact of wildfires, examining the far-reaching consequences of infernos on landscapes and communities. Conversely, "Smoke Gets in Your Eyes: And Other Lessons from the Crematory" by Caitlin Doughty offers a macabre yet strangely fascinating account of the funeral industry, albeit tangentially linked to the subject at hand. A more whimsical addition to the literature is "The Arsonist's Guide to Writers' Homes in New England" by Brock Clarke, which, despite its fictional nature, presents an offbeat take on the world of arsonists and their unusual escapades.
Delving deeper into the terrain of popular culture, cartoons and children's shows such as "Paw Patrol" and "Fireman Sam" subtly instill the notion of fire safety and prevention in young audiences, albeit through the lens of anthropomorphic pups and a daring firefighter in the fictional town of Pontypandy. While these animated series may not provide direct insights into the scholarly discourse on air pollution and arson, they undeniably contribute to the collective consciousness surrounding fire-related themes, albeit in a lighthearted and whimsical manner.
In summary, the eclectic array of literature and cultural references pertaining to air pollution and arson spans a spectrum from the scholarly to the imaginative, offering a multifaceted tapestry of insights and entertainment. With this diverse landscape of sources as our backdrop, we embark on a scholarly endeavor to illuminate the smoggy relationship between air quality and arson, weaving together threads of empirical evidence and unexpected analogies to unravel the enigmatic connections between environmental variables and criminal behavior.

[[RESULTS]]
The data analysis revealed a striking correlation coefficient of 0.7246561 between air pollution in Wabash, Indiana, and incidents of arson across the United States. This significant association was supported by an r-squared value of 0.5251265, indicating that approximately 52.51% of the variability in arson incidents could be explained by variations in air pollution levels. The statistical significance of the correlation was further underscored by a p-value of less than 0.01, lending credence to the robustness of the observed relationship.
Fig. 1 depicts the scatterplot illustrating the compelling correlation between air pollution levels in Wabash, Indiana, and incidents of arson across the United States. The figure unequivocally portrays the alignment of these variables, making it abundantly clear that where there’s pollution, there’s a higher propensity for combustion – a fiery testament to the interplay between environmental conditions and criminal behavior.
These findings not only provide quantitative support for the notion that smog may serve as more than just a backdrop to criminal activities but also spark contemplation on the potential mechanisms underlying this intriguing relationship. The results challenge traditional perspectives and salvage the often-overlooked idea that air pollution does more than just dimming the view; it may also stoke the flames of arson - quite literally and figuratively, if you will. This unexpected revelation ignites novel inquiries into the web of causality between environmental factors and criminal conduct, setting ablaze the discourse on the unseen influences on fiery felonies.
In sum, this study unearths a compelling correlation between air pollution in Wabash, Indiana, and incidents of arson in the United States, lighting the way for further investigation into the smoggy entanglement of environmental variables and criminal behavior. These results not only illuminate the need for a more comprehensive understanding of the multifaceted influences on criminal activities but also kindle a newfound appreciation for the potential impact of haze on unlawful blazes – offering a fresh perspective on the burning question of the relationship between environmental factors and criminal conduct.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings of our study have produced a combustion of thought-provoking implications, shedding light on the unexpected relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. Our results not only fan the flames of the existing body of literature but also kindle a fiery discussion on the interplay between environmental factors and criminal behavior.

The correlation coefficient of 0.7246561, with a significance level of p < 0.01, markedly reinforces the prior research on the potential linkage between air pollution and arson. These results are akin to discovering hidden embers amidst a smoggy landscape, serving as a testament to the unforeseen influences of atmospheric contaminants on criminal activities. Our findings not only stoke the flame of curiosity regarding the mechanisms underlying this intriguing association but also breathe new life into the discourse on the unseen influences on fiery felonies.

In a whimsical echo of Lorem Ipsum's "Fumes and Felonies: The Correlation Coefficient Chronicles," our study has indeed voyaged into the uncharted territory of the smoggy relationship between air pollution and arson, uncovering a surprising convergence of environmental variables and criminal conduct. The unexpected nature of this connection is reminiscent of stumbling upon a rare gem amidst a pile of statistical rubble, underscoring the serendipitous nature of empirical inquiry.

Furthermore, our results offer a fiery testament to the unpredictability of statistical relationships, much like a smoldering flame that defies conventional expectations. The r-squared value of 0.5251265 serves as a beacon of statistical significance, illuminating the substantial variability in arson incidents that can be explained by variations in air pollution levels. This statistical prowess not only fans the flames of empirical rigor but also sets ablaze the need for a more comprehensive understanding of the multifaceted influences on criminal activities.

In summary, our study has sparked a fiery dialogue on the smoggy entanglement of environmental variables and criminal behavior, encouraging further investigation into the unexpected intersections of air quality and arson. Our research not only adds fuel to the fire of empirical inquiry but also kindles a newfound appreciation for the potential impact of haze on unlawful blazes. As we extinguish the embers of this discussion section, the smoky remnants of our findings linger, igniting novel inquiries into the enigmatic connections between environmental factors and criminal conduct.


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 Wabash, Indiana 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. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States

[[ABSTRACT]]
This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

[[INTRDUCTION]]
The study of environmental and criminal phenomena has often been confined to separate spheres of academic inquiry, with the former typically falling within the purview of environmental science and the latter under the domain of criminology. However, as our understanding of the intricate web of causation in human behavior continues to evolve, it becomes increasingly imperative to examine potential connections between seemingly disparate variables. In this research, we aim to scrutinize the relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The motivation behind this investigation stems from a desire to explore the oft-ignored intersection between air quality and criminal behavior, as well as to determine whether there is indeed fire where there's smoke, both literally and metaphorically.
The seemingly unlikely pairing of air pollution and arson may initially appear as implausible as a cloudless day in Seattle, yet there are compelling reasons to consider the potential influence of environmental factors on criminal activities. As the old adage goes, "Where there's smoke, there's fire," and our research endeavors to elucidate whether this expression holds true not just in the literal sense, but also in terms of the figurative smoggy relationship between air quality and arson incidents. While it may seem like a tall order to establish a connection between a silent, invisible assailant like air pollution and the deliberate, visible act of arson, our findings may well challenge preconceived notions and kindle new perspectives on the interplay between environmental conditions and criminal conduct.
The town of Wabash, Indiana, serves as a focal point of our investigation due to its unique combination of industrial activity and environmental factors, which create a microcosm of air pollution dynamics. The town's historical prominence as a manufacturing hub, coupled with its geographical location and meteorological characteristics, provides an intriguing backdrop for studying the potential impacts of air pollution on criminal behavior. Given the idiosyncrasies of Wabash and the broader implications for arson across the United States, this research holds promise in unraveling the enigmatic relationship between smog and pyromania.
Consequently, the overarching objective of this study is to contribute to a nuanced understanding of the multifaceted influences on criminal behavior by venturing into uncharted territory – or in this case, unfiltered air. By examining the empirical evidence surrounding air quality and arson, we endeavor to not only stir the embers of inquiry but also to fan the flames of discourse concerning the unexpected and, dare we say, incendiary connections between environmental variables and criminal acts.

[[RESULTS]]
The data analysis revealed a striking correlation coefficient of 0.7246561 between air pollution in Wabash, Indiana, and incidents of arson across the United States. This significant association was supported by an r-squared value of 0.5251265, indicating that approximately 52.51% of the variability in arson incidents could be explained by variations in air pollution levels. The statistical significance of the correlation was further underscored by a p-value of less than 0.01, lending credence to the robustness of the observed relationship.
Fig. 1 depicts the scatterplot illustrating the compelling correlation between air pollution levels in Wabash, Indiana, and incidents of arson across the United States. The figure unequivocally portrays the alignment of these variables, making it abundantly clear that where there’s pollution, there’s a higher propensity for combustion – a fiery testament to the interplay between environmental conditions and criminal behavior.
These findings not only provide quantitative support for the notion that smog may serve as more than just a backdrop to criminal activities but also spark contemplation on the potential mechanisms underlying this intriguing relationship. The results challenge traditional perspectives and salvage the often-overlooked idea that air pollution does more than just dimming the view; it may also stoke the flames of arson - quite literally and figuratively, if you will. This unexpected revelation ignites novel inquiries into the web of causality between environmental factors and criminal conduct, setting ablaze the discourse on the unseen influences on fiery felonies.
In sum, this study unearths a compelling correlation between air pollution in Wabash, Indiana, and incidents of arson in the United States, lighting the way for further investigation into the smoggy entanglement of environmental variables and criminal behavior. These results not only illuminate the need for a more comprehensive understanding of the multifaceted influences on criminal activities but also kindle a newfound appreciation for the potential impact of haze on unlawful blazes – offering a fresh perspective on the burning question of the relationship between environmental factors and criminal conduct.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shed light on the intriguing relationship between air pollution in Wabash, Indiana, and incidents of arson across the United States. The statistically significant correlation coefficient and r-squared value suggest that there is indeed a fiery connection between these seemingly disparate variables. The scatterplot vividly illustrates the alignment of air pollution levels and arson incidents, providing empirical support for the smoggy relationship we have uncovered. It seems that where there's pollution, there's potential for combustion – a revelation that may spark further inquiry into the mechanisms underlying this unexpected association.

While our findings may initially appear as improbable as finding a needle in a haystack (or a firefly in a fog), they beckon us to consider the profound and, dare I say, burning implications of our results. The data not only challenge traditional paradigms but also invite us to contemplate the unseen influences of environmental conditions on criminal behavior. It appears that air pollution does more than just cloud our vision; it may also fan the flames of felonious activities – a notion that ignites novel inquiries into the enigmatic web of causality between smog and pyromania.

As we put a lid on this investigation, we are confident in asserting that further research in this area is as unnecessary as a snowplow in the Sahara. The sparks of knowledge generated by this study illuminate the need for a more nuanced understanding of the multifaceted influences on criminal activities but also provoke a newfound appreciation for the potential impact of haze on unlawful blazes. It is our hope that this research not only smolders in the annals of academia but also kindles a renewed interest in the unexpected intersections of environmental and criminal phenomena.


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 Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Atmospheric and Arson 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 Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Air Quality and Fire Dynamics 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 Up in Smoke: Examining the Smoggy Relationship Between Air Pollution in Wabash, Indiana, and Arson in the United States with an abstract of This research paper presents an analysis of the potential link between air pollution in Wabash, Indiana, and incidents of arson across the United States. Using data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, our study delves into the hazy connection between environmental factors and criminal behavior. Our findings reveal a surprisingly strong correlation coefficient of 0.7246561 with a significance level of p < 0.01 for the period spanning 1990 to 2022. The results suggest that perhaps there's more than meets the eye when it comes to the impact of smog on fire-related crimes. This research not only sheds light on the fiery relationship between air quality and arson but also ignites further discussions on the unexpected intersections of environmental and criminal phenomena.

ChatGPT:

air pollution, Wabash Indiana, arson, United States, EPA data, FBI Criminal Justice Information Services, correlation coefficient, significance level, environmental factors, criminal behavior, smog impact, fire-related crimes, air quality, unexpected intersections, environmental phenomena, criminal phenomena

*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 Wabash, Indiana
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Wabash, IN
Source: Environmental Protection Agency
See what else correlates with Air pollution in Wabash, Indiana

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 = 0.7246561 (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 = 0.5251265 (Coefficient of determination)
This means 52.5% 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 Wabash, Indiana) over the 33 years from 1990 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.9E-6. 0.0000018550875374568797000000
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 0.72 in 0.00019% of random cases. Said differently, if you correlated 539,058 random variables You don't actually need 539 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 32 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 32 because we have two variables measured over a period of 33 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.

[ 0.51, 0.86 ] 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.
199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in Wabash, Indiana (Bad air quality days)0.08732390.1218840.047222200.1002870.1412640.1267610.07202220.08169010.1191140.03591160.03305780.08011050.02873560.01146130.0474860.0030030.05898880.0029411800.005602240.02083330.06760560.005665720.005952380.005586590.01440920.003012050.0138122000.002762430.00276243
Arson in United States (Arson rate)41.74140.837.339.636.734.632.629.728.824.727.726.82523.623.124.422.621.619.518.117.517.614.914.513.714.113.2121113.98.911.6




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([0.0873239,0.121884,0.0472222,0,0.100287,0.141264,0.126761,0.0720222,0.0816901,0.119114,0.0359116,0.0330578,0.0801105,0.0287356,0.0114613,0.047486,0.003003,0.0589888,0.00294118,0,0.00560224,0.0208333,0.0676056,0.00566572,0.00595238,0.00558659,0.0144092,0.00301205,0.0138122,0,0,0.00276243,0.00276243,])
array_2 = np.array([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 Wabash, Indiana"
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?

Cheers to you for rating this correlation!


Correlation ID: 2079 · Black Variable ID: 22271 · Red Variable ID: 20038
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0