about · email me · subscribe
Spurious correlation #3,640 · 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 Ann Arbor and the second variable is Arson in Michigan.  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

As air pollution in Ann Arbor decreased, the smog particles became less effective kindling for would-be arsonists in Michigan. Without the air-pollution-enhanced fire capabilities, the arson rates naturally declined. Remember, only you can prevent smog-enhanced arson.

Model: dalle-3
Prompt: Generate an image of Ann Arbor's skyline under a heavy, dusky sky filled with smog. The air is thick, and the city is partially obscured by the haze. In the distance, there is a small blaze with billowing smoke rising. The scene should convey the environmental impact of air pollution and the consequences it has on the urban environment. The focus should be on capturing the eerie atmosphere created by the smog and the distant blaze. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Air pollution in Ann Arbor and Arson in Michigan. 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: Symbolism Celtic art Cyber folk Symbolism Realistic
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 Air pollution in Ann Arbor and Arson in Michigan, in the following situation: Because as air pollution in Ann Arbor increased, it caused a lingering smell which led to people lighting fires just to clear the air. You could say the pollution ignited a fiery passion for arson in Michigan!. Keep the description simple.
ChatGPT: In Ann Arbor, a hazy sky hangs heavy with smog, caused by the air pollution. The thick air carries the acrid scent of burning, as fires have been ignited in an attempt to disperse the lingering pollution. In the distance, billowing smoke rises from a small blaze, a result of the fiery passion for arson that has been sparked in Michigan due to the polluted air.

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 Ann Arbor, a hazy sky hangs heavy with smog, caused by the air pollution. The thick air carries the acrid scent of burning, as fires have been ignited in an attempt to disperse the lingering pollution. In the distance, billowing smoke rises from a small blaze, a result of the fiery passion for arson that has been sparked in Michigan due to the polluted air. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of Ann Arbor's skyline under a heavy, dusky sky filled with smog. The air is thick, and the city is partially obscured by the haze. In the distance, there is a small blaze with billowing smoke rising. The scene should convey the environmental impact of air pollution and the consequences it has on the urban environment. The focus should be on capturing the eerie atmosphere created by the smog and the distant blaze.

*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 Ann Arbor caused Arson in Michigan to decrease.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

The Journal of Environmental Misadventures

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Ann Arbor and Arson in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title an alliteration.

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 0.7288017 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Ann Arbor and Arson in Michigan. 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

When one thinks of the quaint, picturesque city of Ann Arbor, Michigan, one might conjure images of tree-lined streets, bustling college campuses, and a pervasive aroma of freshly roasted coffee. However, beneath this idyllic surface lies a burning question - could the quality of the air we breathe be igniting more than just our senses of curiosity?

Arson, the deliberate and malicious act of setting fires, has long been a matter of concern for law enforcement and fire prevention authorities. The implications of arson extend beyond the physical destruction of property, often resulting in immeasurable emotional and financial tolls on affected individuals and communities.

Meanwhile, air pollution, with its billowing haze and invisible particles, has been an ongoing subject of environmental scrutiny. From vehicular emissions to industrial effluents, the sources of air pollution are as diverse as the array of spicy hot sauces at a condiment convention.

In this study, we aim to bridge these seemingly disparate realms by examining the potential link between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. We understand that some may find the idea of this link to be a bit of a "stretch," but as researchers, we are not afraid to navigate the smoky corridors of investigative inquiry.

As we delve into the annals of environmental and criminal data, we recognize the importance of approaching this topic with the seriousness it deserves, while allowing for a lighthearted appreciation of the potential connections we may uncover. Air pollution and arson may seem to be as unrelated as a cat and a canary, but as the data will reveal, there may be more to these twin flames than meets the eye.

Through rigorous statistical analysis and a touch of dry wit, we embark on a journey to unravel the enigmatic relationship between the aerated atmosphere and accidental arson. Join us as we sift through the data-scorched landscape and follow the trail of evidence, all while striving to maintain a healthy balance of academic rigor and unabashed puns.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Arson in Michigan. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Speak in the present tense for this section (the authors find...), as is common in academic research paper literature reviews. Name the sources in a format similar to this: In "Book," the authors find lorem and ipsum.

Make up the lorem and ipsum part, but make it sound related to the topic at hand.

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
When one thinks of the quaint, picturesque city of Ann Arbor, Michigan, one might conjure images of tree-lined streets, bustling college campuses, and a pervasive aroma of freshly roasted coffee. However, beneath this idyllic surface lies a burning question - could the quality of the air we breathe be igniting more than just our senses of curiosity?
Arson, the deliberate and malicious act of setting fires, has long been a matter of concern for law enforcement and fire prevention authorities. The implications of arson extend beyond the physical destruction of property, often resulting in immeasurable emotional and financial tolls on affected individuals and communities.
Meanwhile, air pollution, with its billowing haze and invisible particles, has been an ongoing subject of environmental scrutiny. From vehicular emissions to industrial effluents, the sources of air pollution are as diverse as the array of spicy hot sauces at a condiment convention.
In this study, we aim to bridge these seemingly disparate realms by examining the potential link between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. We understand that some may find the idea of this link to be a bit of a "stretch," but as researchers, we are not afraid to navigate the smoky corridors of investigative inquiry.
As we delve into the annals of environmental and criminal data, we recognize the importance of approaching this topic with the seriousness it deserves, while allowing for a lighthearted appreciation of the potential connections we may uncover. Air pollution and arson may seem to be as unrelated as a cat and a canary, but as the data will reveal, there may be more to these twin flames than meets the eye.
Through rigorous statistical analysis and a touch of dry wit, we embark on a journey to unravel the enigmatic relationship between the aerated atmosphere and accidental arson. Join us as we sift through the data-scorched landscape and follow the trail of evidence, all while striving to maintain a healthy balance of academic rigor and unabashed puns.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

Air Pollution and Arson: A Flaming Connection?

Smith et al. (2010) examined the impact of air pollution on various social and environmental outcomes, including but not limited to respiratory illnesses, climate change, and perhaps most importantly for our purposes, arson incidents. Their study, conducted in urban areas, reported a positive association between air pollution levels and the occurrence of arson, providing preliminary evidence for our own investigation.

Doe and Jones (2015) delved into the intricacies of criminal behavior and environmental stressors, shedding light on the potential pathways through which air pollution may stoke the embers of arson. Their thorough exploration of psychosocial and ecological factors sets the stage for our own exploration, igniting the curiosity of readers who dare to venture into the smog-choked arena of atmospheric influences on incendiary behaviors.

Transitioning from the academic realm to the public domain, "The Air We Breathe: A Comprehensive Guide to Environmental Pollution" by Environmental Expert (2018) offers a comprehensive overview of air quality issues and their effects on human health and well-being. While the book does not explicitly delve into the link between air pollution and arson, it certainly fans the flames of interest in the broader context of atmospheric impacts on human behavior.

On the fictional front, "Smoke Signals: The Arsonist's Alibi" by Mystery Author (2019) dabbles in the realm of criminal intrigue, intertwining the enigma of atmospheric conditions with the enigmatic motives of arsonists. Though purely speculative in nature, the novel beckons readers into a world where smoke and conspiracy intertwine, fanning the flames of imagination and suspicion.

And who can forget the social media sphere, where fiery debates and incendiary opinions abound? On a post by @AirandCrimeWatch (2021), a netizen posits a tongue-in-cheek theory linking air pollution levels in urban centers to the propensity for arson, sparking a flurry of comments and emoji-laden reactions. While such musings may dance on the edge of whimsical speculation, they underscore the public's fascination with uncovering hidden connections in the atmospheric ether.

As we make our way through the smokescreen of literature and popular discourse, it becomes clear that the link between air pollution and arson is not just a "hot topic" but one that ignites curiosity and sparks a desire for deeper investigation. The stage is set, and the time has come to breathe life into our own analysis of this fiery relationship.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Arson in Michigan. 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 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

[[INTRODUCTION]]
When one thinks of the quaint, picturesque city of Ann Arbor, Michigan, one might conjure images of tree-lined streets, bustling college campuses, and a pervasive aroma of freshly roasted coffee. However, beneath this idyllic surface lies a burning question - could the quality of the air we breathe be igniting more than just our senses of curiosity?
Arson, the deliberate and malicious act of setting fires, has long been a matter of concern for law enforcement and fire prevention authorities. The implications of arson extend beyond the physical destruction of property, often resulting in immeasurable emotional and financial tolls on affected individuals and communities.
Meanwhile, air pollution, with its billowing haze and invisible particles, has been an ongoing subject of environmental scrutiny. From vehicular emissions to industrial effluents, the sources of air pollution are as diverse as the array of spicy hot sauces at a condiment convention.
In this study, we aim to bridge these seemingly disparate realms by examining the potential link between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. We understand that some may find the idea of this link to be a bit of a "stretch," but as researchers, we are not afraid to navigate the smoky corridors of investigative inquiry.
As we delve into the annals of environmental and criminal data, we recognize the importance of approaching this topic with the seriousness it deserves, while allowing for a lighthearted appreciation of the potential connections we may uncover. Air pollution and arson may seem to be as unrelated as a cat and a canary, but as the data will reveal, there may be more to these twin flames than meets the eye.
Through rigorous statistical analysis and a touch of dry wit, we embark on a journey to unravel the enigmatic relationship between the aerated atmosphere and accidental arson. Join us as we sift through the data-scorched landscape and follow the trail of evidence, all while striving to maintain a healthy balance of academic rigor and unabashed puns.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To investigate the potential correlation between air pollution and the occurrence of arson, we employed a multifaceted research approach that blended traditional statistical analyses with some unconventional investigative tactics. Our data were primarily sourced from the Environmental Protection Agency's Air Quality System database and the FBI Criminal Justice Information Services' Uniform Crime Reporting database. This comprehensive dataset spanned from 1985 to 2022, allowing for a longitudinal exploration of the relationship between atmospheric pollutants and fiery felonies.

First, we conducted a thorough review of air pollution levels in Ann Arbor, Michigan, focusing on key pollutants such as particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), and carbon monoxide (CO). These pollutants were selected based on their potential to serve as incendiary co-conspirators, with an emphasis on the wayward behavior of volatile organic compounds (VOCs) and their potential to spark nefarious activities.

Simultaneously, we diligently parsed through the arson data for the entire state of Michigan, sifting through reports of intentionally ignited infernos while maintaining a keen eye for any suspicious smoke signals. The spatial and temporal distribution of arson incidents were subsequently scrutinized to identify any potential synchronicity with the fluctuations in air pollution levels, akin to seeking out patterns in a haze of ambiguity.

To quantify the strength of the relationship between air pollution and arson, we employed a series of robust statistical analyses, including but not limited to correlation coefficients, time-series analysis, and spatial econometric models. Our statistical exploration allowed us to unearth any hidden connections lurking beneath the surface, akin to the satisfaction of finding the last slice of pizza at a crowded party.

Furthermore, we employed a novel technique incorporating geographic information systems (GIS) to spatially visualize the distribution of both air pollution and arson incidents across Michigan. This approach not only added a layer of spatial context to our analysis but also offered a fanciful opportunity to create maps reminiscent of a treasure hunt, albeit with smoldering implications.

In addition to our quantitative analyses, we also engaged in qualitative assessments, gathering anecdotal accounts and interviews from atmospheric scientists, law enforcement officers, and perhaps even a famous candlemaker or two. These qualitative insights added depth to our understanding of the nuanced interplay between atmospheric conditions and incendiary tendencies, providing a rich tapestry of contextual understanding that transcends mere data points.

Ultimately, our methodology encompassed a judicious blend of conventional statistical rigor, innovative spatial analysis, and a sprinkle of whimsy, ensuring that our investigation unfolded with the precision of a well-crafted arsonist's plot. The calculated fusion of methodology allowed us to navigate the convoluted corridors of data, all while maintaining a firm grip on the fire extinguisher of academic objectivity.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the 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 Ann Arbor and Arson in Michigan. 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 1985 to 2022, you found a correlation 0.7288017, r-squared of 0.5311519, 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
When one thinks of the quaint, picturesque city of Ann Arbor, Michigan, one might conjure images of tree-lined streets, bustling college campuses, and a pervasive aroma of freshly roasted coffee. However, beneath this idyllic surface lies a burning question - could the quality of the air we breathe be igniting more than just our senses of curiosity?
Arson, the deliberate and malicious act of setting fires, has long been a matter of concern for law enforcement and fire prevention authorities. The implications of arson extend beyond the physical destruction of property, often resulting in immeasurable emotional and financial tolls on affected individuals and communities.
Meanwhile, air pollution, with its billowing haze and invisible particles, has been an ongoing subject of environmental scrutiny. From vehicular emissions to industrial effluents, the sources of air pollution are as diverse as the array of spicy hot sauces at a condiment convention.
In this study, we aim to bridge these seemingly disparate realms by examining the potential link between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. We understand that some may find the idea of this link to be a bit of a "stretch," but as researchers, we are not afraid to navigate the smoky corridors of investigative inquiry.
As we delve into the annals of environmental and criminal data, we recognize the importance of approaching this topic with the seriousness it deserves, while allowing for a lighthearted appreciation of the potential connections we may uncover. Air pollution and arson may seem to be as unrelated as a cat and a canary, but as the data will reveal, there may be more to these twin flames than meets the eye.
Through rigorous statistical analysis and a touch of dry wit, we embark on a journey to unravel the enigmatic relationship between the aerated atmosphere and accidental arson. Join us as we sift through the data-scorched landscape and follow the trail of evidence, all while striving to maintain a healthy balance of academic rigor and unabashed puns.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Upon conducting our analysis, we found a strong positive correlation between air pollution levels in Ann Arbor and the incidence of arson in Michigan, with a correlation coefficient of 0.7288017. This suggests a moderately strong linear relationship between these two variables. The r-squared value of 0.5311519 indicates that approximately 53% of the variance in arson incidents can be explained by changes in air pollution levels.

In other words, it seems that as the air gets "hotter," the incidence of arson "fires up." Now, before you start frantically checking your thermostat for arson-related conspiracy theories, it's important to remind ourselves that correlation does not imply causation. While our findings do indeed point to a notable association, we must resist the temptation to leap to fiery conclusions. After all, it would be rather flammable of us to ignite unwarranted assumptions based solely on correlation.

The p-value of less than 0.01 further supports our conclusion, indicating that the observed relationship between air pollution and arson incidents is indeed statistically significant. It seems that the link between polluted air and fire-related mischief is more than just smoke and mirrors; it's statistically grounded.

Lastly, to visually elucidate the captivating relationship we've uncovered, we present Figure 1, a scatterplot demonstrating the strong positive correlation between air pollution levels and arson incidents. Behold, the smoldering evidence of this intriguing connection. But before you find yourself getting too fired up about these results, let's remember that our analysis merely scratches the surface of this complex association.

In conclusion, while our findings point to a compelling link between air pollution levels in Ann Arbor and the incidence of arson in Michigan, we must approach these results with cautious optimism and a hint of whimsy. Our research leaves us with a tantalizing question: could atmospheric pollutants be stoking unintended flames in ways we never suspected? As we contemplate this possibility, remember that a good scientific inquiry should always have a dash of curiosity and a sprinkle of humor to keep things from going up in smoke.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Arson in Michigan. 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

[[LITERATURE REVIEW]]
Air Pollution and Arson: A Flaming Connection?
Smith et al. (2010) examined the impact of air pollution on various social and environmental outcomes, including but not limited to respiratory illnesses, climate change, and perhaps most importantly for our purposes, arson incidents. Their study, conducted in urban areas, reported a positive association between air pollution levels and the occurrence of arson, providing preliminary evidence for our own investigation.
Doe and Jones (2015) delved into the intricacies of criminal behavior and environmental stressors, shedding light on the potential pathways through which air pollution may stoke the embers of arson. Their thorough exploration of psychosocial and ecological factors sets the stage for our own exploration, igniting the curiosity of readers who dare to venture into the smog-choked arena of atmospheric influences on incendiary behaviors.
Transitioning from the academic realm to the public domain, "The Air We Breathe: A Comprehensive Guide to Environmental Pollution" by Environmental Expert (2018) offers a comprehensive overview of air quality issues and their effects on human health and well-being. While the book does not explicitly delve into the link between air pollution and arson, it certainly fans the flames of interest in the broader context of atmospheric impacts on human behavior.
On the fictional front, "Smoke Signals: The Arsonist's Alibi" by Mystery Author (2019) dabbles in the realm of criminal intrigue, intertwining the enigma of atmospheric conditions with the enigmatic motives of arsonists. Though purely speculative in nature, the novel beckons readers into a world where smoke and conspiracy intertwine, fanning the flames of imagination and suspicion.
And who can forget the social media sphere, where fiery debates and incendiary opinions abound? On a post by @AirandCrimeWatch (2021), a netizen posits a tongue-in-cheek theory linking air pollution levels in urban centers to the propensity for arson, sparking a flurry of comments and emoji-laden reactions. While such musings may dance on the edge of whimsical speculation, they underscore the public's fascination with uncovering hidden connections in the atmospheric ether.
As we make our way through the smokescreen of literature and popular discourse, it becomes clear that the link between air pollution and arson is not just a "hot topic" but one that ignites curiosity and sparks a desire for deeper investigation. The stage is set, and the time has come to breathe life into our own analysis of this fiery relationship.

[[RESULTS]]
Upon conducting our analysis, we found a strong positive correlation between air pollution levels in Ann Arbor and the incidence of arson in Michigan, with a correlation coefficient of 0.7288017. This suggests a moderately strong linear relationship between these two variables. The r-squared value of 0.5311519 indicates that approximately 53% of the variance in arson incidents can be explained by changes in air pollution levels.
In other words, it seems that as the air gets "hotter," the incidence of arson "fires up." Now, before you start frantically checking your thermostat for arson-related conspiracy theories, it's important to remind ourselves that correlation does not imply causation. While our findings do indeed point to a notable association, we must resist the temptation to leap to fiery conclusions. After all, it would be rather flammable of us to ignite unwarranted assumptions based solely on correlation.
The p-value of less than 0.01 further supports our conclusion, indicating that the observed relationship between air pollution and arson incidents is indeed statistically significant. It seems that the link between polluted air and fire-related mischief is more than just smoke and mirrors; it's statistically grounded.
Lastly, to visually elucidate the captivating relationship we've uncovered, we present Figure 1, a scatterplot demonstrating the strong positive correlation between air pollution levels and arson incidents. Behold, the smoldering evidence of this intriguing connection. But before you find yourself getting too fired up about these results, let's remember that our analysis merely scratches the surface of this complex association.
In conclusion, while our findings point to a compelling link between air pollution levels in Ann Arbor and the incidence of arson in Michigan, we must approach these results with cautious optimism and a hint of whimsy. Our research leaves us with a tantalizing question: could atmospheric pollutants be stoking unintended flames in ways we never suspected? As we contemplate this possibility, remember that a good scientific inquiry should always have a dash of curiosity and a sprinkle of humor to keep things from going up in smoke.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our investigation into the relationship between air pollution and arson incidents in Michigan has set the stage for a fiery discussion, one that fans the flames of curiosity while cautioning against jumping to sizzling conclusions. The significant positive correlation we unearthed aligns with previous research, breathing life into the notion that pollutants lingering in the air may be inadvertently kindling the spark of arson incidents across the state.

Smith et al.'s (2010) findings, akin to our own, highlight the intriguing dance between air pollution and arson, while Doe and Jones (2015) offer a nuanced perspective on the potential pathways through which atmospheric stressors might feed into the fiery antics of arsonists. It's fascinating to see how these serious academic discussions blaze a trail of inquiry, ultimately shedding light on the smoldering connection between atmospheric composition and incendiary behavior. Even the lighthearted musings found in "Smoke Signals: The Arsonist's Alibi" by Mystery Author (2019) or the spicy debates in the social media sphere serve to remind us that the relationship between air pollution and arson is not just hot air but a topic that inflames the imagination of both scholars and the wider public.

Our results, depicted in Figure 1, provide a striking visual portrayal of the robust association we've uncovered. The statistically significant p-value further bolsters the credibility of this ignited connection, reinforcing the notion that the link between polluted air and fire-related mischief is no mere wispy speculation but a solid, inferno-tinged reality.

Of course, we must keep our feet firmly planted in the realm of cautious interpretation and avoid turning this discussion into a blazing inferno of overzealous conclusions. As tempting as it might be to succumb to the allure of sensational headlines proclaiming "Air Pollution Sets Michigan Ablaze," we must resist the urge to fuel unwarranted assumptions based solely on correlation. Instead, our findings beckon us to dive deeper into the inferno of atmospheric influences on human behavior, wielding a curious spirit and a touch of wry humor to navigate the murky smoke of scientific inquiry.

As we bid adieu to this discussion, let us remember that scientific inquiry – like an errant campfire – should be approached with both caution and a twinkle in the eye. After all, it's not every day that we get to unravel the enigmatic dance between air pollution and accidental arson, and we must savor this academic adventure with a healthy dose of whimsy.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in Ann Arbor and Arson in Michigan. 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]]
Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan

[[ABSTRACT]]
In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.

While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

[[INTRDUCTION]]
When one thinks of the quaint, picturesque city of Ann Arbor, Michigan, one might conjure images of tree-lined streets, bustling college campuses, and a pervasive aroma of freshly roasted coffee. However, beneath this idyllic surface lies a burning question - could the quality of the air we breathe be igniting more than just our senses of curiosity?
Arson, the deliberate and malicious act of setting fires, has long been a matter of concern for law enforcement and fire prevention authorities. The implications of arson extend beyond the physical destruction of property, often resulting in immeasurable emotional and financial tolls on affected individuals and communities.
Meanwhile, air pollution, with its billowing haze and invisible particles, has been an ongoing subject of environmental scrutiny. From vehicular emissions to industrial effluents, the sources of air pollution are as diverse as the array of spicy hot sauces at a condiment convention.
In this study, we aim to bridge these seemingly disparate realms by examining the potential link between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. We understand that some may find the idea of this link to be a bit of a "stretch," but as researchers, we are not afraid to navigate the smoky corridors of investigative inquiry.
As we delve into the annals of environmental and criminal data, we recognize the importance of approaching this topic with the seriousness it deserves, while allowing for a lighthearted appreciation of the potential connections we may uncover. Air pollution and arson may seem to be as unrelated as a cat and a canary, but as the data will reveal, there may be more to these twin flames than meets the eye.
Through rigorous statistical analysis and a touch of dry wit, we embark on a journey to unravel the enigmatic relationship between the aerated atmosphere and accidental arson. Join us as we sift through the data-scorched landscape and follow the trail of evidence, all while striving to maintain a healthy balance of academic rigor and unabashed puns.

[[RESULTS]]
Upon conducting our analysis, we found a strong positive correlation between air pollution levels in Ann Arbor and the incidence of arson in Michigan, with a correlation coefficient of 0.7288017. This suggests a moderately strong linear relationship between these two variables. The r-squared value of 0.5311519 indicates that approximately 53% of the variance in arson incidents can be explained by changes in air pollution levels.
In other words, it seems that as the air gets "hotter," the incidence of arson "fires up." Now, before you start frantically checking your thermostat for arson-related conspiracy theories, it's important to remind ourselves that correlation does not imply causation. While our findings do indeed point to a notable association, we must resist the temptation to leap to fiery conclusions. After all, it would be rather flammable of us to ignite unwarranted assumptions based solely on correlation.
The p-value of less than 0.01 further supports our conclusion, indicating that the observed relationship between air pollution and arson incidents is indeed statistically significant. It seems that the link between polluted air and fire-related mischief is more than just smoke and mirrors; it's statistically grounded.
Lastly, to visually elucidate the captivating relationship we've uncovered, we present Figure 1, a scatterplot demonstrating the strong positive correlation between air pollution levels and arson incidents. Behold, the smoldering evidence of this intriguing connection. But before you find yourself getting too fired up about these results, let's remember that our analysis merely scratches the surface of this complex association.
In conclusion, while our findings point to a compelling link between air pollution levels in Ann Arbor and the incidence of arson in Michigan, we must approach these results with cautious optimism and a hint of whimsy. Our research leaves us with a tantalizing question: could atmospheric pollutants be stoking unintended flames in ways we never suspected? As we contemplate this possibility, remember that a good scientific inquiry should always have a dash of curiosity and a sprinkle of humor to keep things from going up in smoke.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In summary, our investigation has illuminated a significant correlation between air pollution levels in Ann Arbor and the incidence of arson throughout Michigan, suggesting that pollutants in the air may indeed be fanning the flames of unintended ignition. While our findings kindle intriguing possibilities, we must exercise caution not to let our interpretations go up in smoke. It's critical to maintain a balanced perspective as we navigate this still-fresh landscape of research.

As we reflect on the smoke signals emanating from our data, it's clear that further research is warranted to delve deeper into the mechanisms underlying this association and to extinguish any doubts about causation. However, approaching this topic with a twinkle in our eyes and a spark of humor may just ignite the flames of discovery.

In conclusion, this study ignites a compelling conversation about the intricacies of atmospheric influences on incendiary events. Ultimately, the smoke from our investigation clears the air and leaves us with the unassailable conclusion that no more research is needed in this area. After all, we wouldn't want to fan the flames unnecessarily, would we?


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 Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Environmental Misadventures


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 Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Advanced Atmospheric Anomalies


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 Aerated Atmosphere and Accidental Arson: An Analysis of Air Pollution's Influence on Incendiary Incidents in Michigan with an abstract of In this study, we investigate the potential relationship between air pollution levels in Ann Arbor and the incidence of arson throughout the state of Michigan. Utilizing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we conducted a longitudinal analysis spanning from 1985 to 2022. Our analysis yielded a correlation coefficient of 0.7288017 and a statistically significant p-value of less than 0.01, suggesting a strong association between air pollution and arson occurrences.
While the results point to a compelling connection, it is important to approach the findings with caution and humorously not jump to burning conclusions. Although correlation does not necessarily imply causation, it is intriguing to ponder the idea that pollutants lingering in the air could be heating things up in unintentional ways. Future research endeavors in this area could undoubtedly benefit from a more comprehensive investigation into the mechanisms underlying this association and elucidate the fiery dynamics between atmospheric composition and incendiary behavior.

ChatGPT:

air pollution levels, arson incidents, Michigan, Ann Arbor, atmospheric composition, incendiary incidents, Environmental Protection Agency data, FBI Criminal Justice Information Services, longitudinal analysis, correlation coefficient, causation vs correlation, incendiary behavior dynamics

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

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

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

Correlation r = 0.7288017 (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 = 0.5311519 (Coefficient of determination)
This means 53.1% of the change in the one variable (i.e., Arson in Michigan) is predictable based on the change in the other (i.e., Air pollution in Ann Arbor) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.1E-7. 0.0000002124008623569850800000
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 0.73 in 2.1E-5% of random cases. Said differently, if you correlated 4,708,079 random variables You don't actually need 4 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 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.

[ 0.53, 0.85 ] 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 Ann Arbor (Bad air quality days)4.819283.030313.145520.560710.79817.142869.722224.670333.021984.941867.835826.909093.846159.510099.340663.561647.627128.493156.145251.99436.371192.747254.945061.098900.2762431.960786.043960.2747251.0958901.639340.8219181.6438401.6393400.273973
Arson in Michigan (Arson rate)43.160.759.855.149.64850.647.844.943.541.947.155.65146.323.442.548.840.736.931.832.129.728.626.830.42724.520.217.220.417.919.617.716.818.414.913




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.
  4. Outlandish outliers: There are "outliers" in this data. In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

    For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

    (This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
    They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.




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([4.81928,3.0303,13.1455,20.5607,10.7981,7.14286,9.72222,4.67033,3.02198,4.94186,7.83582,6.90909,3.84615,9.51009,9.34066,3.56164,7.62712,8.49315,6.14525,1.9943,6.37119,2.74725,4.94506,1.0989,0,0.276243,1.96078,6.04396,0.274725,1.09589,0,1.63934,0.821918,1.64384,0,1.63934,0,0.273973,])
array_2 = np.array([43.1,60.7,59.8,55.1,49.6,48,50.6,47.8,44.9,43.5,41.9,47.1,55.6,51,46.3,23.4,42.5,48.8,40.7,36.9,31.8,32.1,29.7,28.6,26.8,30.4,27,24.5,20.2,17.2,20.4,17.9,19.6,17.7,16.8,18.4,14.9,13,])
array_1_name = "Air pollution in Ann Arbor"
array_2_name = "Arson in Michigan"

# 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 rating guru we've been waiting for!


Correlation ID: 3640 · Black Variable ID: 20271 · Red Variable ID: 20050
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0