about · email me · subscribe
Spurious correlation #3,546 · 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 State College, Pennsylvania and the second variable is Violent crime rates.  The chart goes from 1990 to 2022, and the two variables track closely in value over that time. Small Image

AI explanation

As air pollution decreased, people's brains were no longer clouded, leading to a reduction in impulsive and aggressive behavior. It turns out, when you can actually see blue skies, you're less likely to see red!

Model: dalle-3
Prompt: Generate an image of a serene, idyllic town in State College, Pennsylvania as if captured in a Polaroid photo. The sky is a clear, vibrant blue, and billowy clouds float gracefully overhead. Lush, green trees and colorful flowers adorn the streets, exuding a sense of natural beauty and vitality. People leisurely stroll through the peaceful town, their spirits uplifted by the clean, unpolluted air. The overall scene radiates a tranquil ambiance, where the absence of pollution fosters a sense of harmony and decreases the crime rate. 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 State College, Pennsylvania and Violent crime rates. 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: Vaporwave Surrealism inspired by bauhaus a Polaroid photo Cute 2D animation
ChatGPT: a Polaroid photo

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 State College, Pennsylvania and Violent crime rates, in the following situation: Decrease in air pollution led to decrease in violent crime rates in State College, Pennsylvania, because clean air made people less likely to Hulk out and smash things.. Keep the description simple.
ChatGPT: In State College, Pennsylvania, the clear sky stretches above the peaceful town. The air is fresh and clean as people stroll along the streets, enjoying the pleasant environment. The trees and flowers thrive in the pollution-free air, creating a vibrant, green landscape. Amidst this tranquility, the crime rate decreases. The absence of pollution seems to have a calming effect, making people less likely to resort to violent behavior. Instead of chaos and aggression, the town is filled with a sense of harmony and tranquility.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ a Polaroid photo ] and depicting this scene: In State College, Pennsylvania, the clear sky stretches above the peaceful town. The air is fresh and clean as people stroll along the streets, enjoying the pleasant environment. The trees and flowers thrive in the pollution-free air, creating a vibrant, green landscape. Amidst this tranquility, the crime rate decreases. The absence of pollution seems to have a calming effect, making people less likely to resort to violent behavior. Instead of chaos and aggression, the town is filled with a sense of harmony and tranquility. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a serene, idyllic town in State College, Pennsylvania as if captured in a Polaroid photo. The sky is a clear, vibrant blue, and billowy clouds float gracefully overhead. Lush, green trees and colorful flowers adorn the streets, exuding a sense of natural beauty and vitality. People leisurely stroll through the peaceful town, their spirits uplifted by the clean, unpolluted air. The overall scene radiates a tranquil ambiance, where the absence of pollution fosters a sense of harmony and decreases the crime rate.

*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 State College, Pennsylvania caused Violent crime rates to decrease. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

Journal of Ecological Anthropology and Urban Sociology

Jan 2024
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




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

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Include a pun in the title.

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 0.7122592 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]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.


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

Please make up the introduction section of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The relationship between environmental factors and human behavior has long been a topic of interest and debate in academia. From the impact of natural landscapes on mental health to the effect of urban sprawl on social interaction, researchers have endeavored to untangle the intricate web of connections between our surroundings and our actions. Amidst this scholarly pursuit, one often underestimated factor, namely air pollution, has taken center stage in our investigation.

The small, yet bustling college town of State College, Pennsylvania, home to the Pennsylvania State University, has served as the backdrop for our inquiry. Nestled in the picturesque landscape of central Pennsylvania, it is renowned for its vibrant community and spirited culture. However, beneath the facade of this idyllic setting lurks a tale of hidden influences, one that ties the quality of the air we breathe to the incidence of violent crime.

As we embark on our quest to uncover the mysteries of this seemingly incongruous relationship, we are mindful of the whimsical yet undeniable nature of our findings. It is indeed a breath of fresh air to bring attention to this overlooked connection between air pollution and aggressive behavior. While some may find our revelations as shocking as inhaling a lungful of smog, we press on in our pursuit of truth, armed with statistical rigor and a keen sense of the somewhat unexpected.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading the backs of shampoo bottles.

Here is the title and abstract of the paper:
[[TITLE]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The relationship between environmental factors and human behavior has long been a topic of interest and debate in academia. From the impact of natural landscapes on mental health to the effect of urban sprawl on social interaction, researchers have endeavored to untangle the intricate web of connections between our surroundings and our actions. Amidst this scholarly pursuit, one often underestimated factor, namely air pollution, has taken center stage in our investigation.
The small, yet bustling college town of State College, Pennsylvania, home to the Pennsylvania State University, has served as the backdrop for our inquiry. Nestled in the picturesque landscape of central Pennsylvania, it is renowned for its vibrant community and spirited culture. However, beneath the facade of this idyllic setting lurks a tale of hidden influences, one that ties the quality of the air we breathe to the incidence of violent crime.
As we embark on our quest to uncover the mysteries of this seemingly incongruous relationship, we are mindful of the whimsical yet undeniable nature of our findings. It is indeed a breath of fresh air to bring attention to this overlooked connection between air pollution and aggressive behavior. While some may find our revelations as shocking as inhaling a lungful of smog, we press on in our pursuit of truth, armed with statistical rigor and a keen sense of the somewhat unexpected.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we traverse the labyrinthine landscape of literature on the interplay between air pollution and violent crime rates, we encounter a multitude of studies that attempt to elucidate this enigmatic relationship. Smith et al. (2015) contribute to this discourse by highlighting the potential impact of air pollution on cognitive functions, underscoring its potential role in shaping behavioral outcomes. Similarly, Doe and colleagues (2018) delve into the physiological effects of air pollution, shedding light on the potential mechanisms through which polluted air could influence aggressive tendencies.

In "The Air Pollutant's Dilemma" by Brown (2020), the author explores the societal implications of air pollution, drawing attention to its potential to disrupt the delicate balance of human interactions. Furthermore, Jones (2017) postulates that the psychological distress induced by exposure to polluted air may contribute to heightened levels of aggression, thereby offering a lens through which to view the link between air quality and violent behavior.

Navigating into the realm of fiction, the works of Dickens and Dostoevsky offer a curious insight into the human psyche, albeit in a metaphorical sense. "Bleak House" illustrated the bleakness that can permeate an environment clouded by the presence of pollution, while "Crime and Punishment" provides a window into the tumultuous inner world of individuals grappling with the impurities of their surroundings.

In the pursuit of a comprehensive understanding, we ventured into uncharted territories, perusing unconventional sources in a valiant attempt to capture the essence of this perplexing correlation. From the back of shampoo bottles to the whimsical musings of internet forums, we discovered an assortment of quixotic insights, each adding a peculiar tint to the kaleidoscopic tapestry of our investigation.

As we reflect on this diversity of perspectives, we cannot help but marvel at the breadth of influences that have shaped our understanding of this captivating nexus between air pollution and violent crime rates. Indeed, it is amidst this whimsical journey through literature that we gleaned valuable insights, dissolving the boundaries between the serious and the surreal in our quest for revelatory revelations.


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

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and 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]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

[[INTRODUCTION]]
The relationship between environmental factors and human behavior has long been a topic of interest and debate in academia. From the impact of natural landscapes on mental health to the effect of urban sprawl on social interaction, researchers have endeavored to untangle the intricate web of connections between our surroundings and our actions. Amidst this scholarly pursuit, one often underestimated factor, namely air pollution, has taken center stage in our investigation.
The small, yet bustling college town of State College, Pennsylvania, home to the Pennsylvania State University, has served as the backdrop for our inquiry. Nestled in the picturesque landscape of central Pennsylvania, it is renowned for its vibrant community and spirited culture. However, beneath the facade of this idyllic setting lurks a tale of hidden influences, one that ties the quality of the air we breathe to the incidence of violent crime.
As we embark on our quest to uncover the mysteries of this seemingly incongruous relationship, we are mindful of the whimsical yet undeniable nature of our findings. It is indeed a breath of fresh air to bring attention to this overlooked connection between air pollution and aggressive behavior. While some may find our revelations as shocking as inhaling a lungful of smog, we press on in our pursuit of truth, armed with statistical rigor and a keen sense of the somewhat unexpected.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Our research endeavor involved a multi-faceted approach that combined quantitative analysis with some mind-bending acrobatics. Our data collection process began with the retrieval of air pollution data from the Environmental Protection Agency (EPA) through a series of carefully-plotted clicks and judicious use of search strings. The air quality data encompassed various pollutants, including but not limited to ozone, particulate matter, sulfur dioxide, and nitrogen dioxide, spanning the years 1990 to 2022. We then skillfully navigated the labyrinthine pathways of the FBI Criminal Justice Information Services to obtain reported violent crime rates for the same timeframe in the State College, Pennsylvania region. Considering the surreptitious manner in which data can sometimes elude researchers, we made sure to double and triple-check our sources to ensure the accuracy and reliability of the information gathered.

Once the treasure trove of data was in our possession, we engaged in some statistical wizardry to derive meaningful insights. Employing the formidable powers of correlation analysis and regression modeling, we sought to uncover the hidden relationship between air pollution and violent crime rates. Our analysis included a variety of statistical tests, all performed with the dexterity and precision of a juggler handling flaming torches, albeit without the potential for catastrophe.

In order to account for potential confounding variables that could cloud our results like a haze of uncertainty, we included demographic and socioeconomic indicators in our models. These were sourced from reputable demographic databases, sparing no effort in ensuring the completeness and accuracy of our adjustments.

To add a touch of whimsy to our methodology, we also conducted a qualitative analysis through interviews with local residents and law enforcement officials. Their perspectives provided valuable contextual insights and added a splash of colorful anecdotes to our otherwise data-driven narrative.

At the heart of our methodology lies a deep appreciation for the interplay of serious scientific inquiry and the occasional moment of levity. We approached our research with the earnestness of a scholar and the playful curiosity of a child discovering a particularly intriguing toy. This synthesis of rigor and light-heartedness defined our journey through the aether of empirical investigation, and we hope it lends a delightful charm to our scholarly pursuits.


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

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 1990 to 2022, you found a correlation 0.7122592, r-squared of 0.5073131, 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]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The relationship between environmental factors and human behavior has long been a topic of interest and debate in academia. From the impact of natural landscapes on mental health to the effect of urban sprawl on social interaction, researchers have endeavored to untangle the intricate web of connections between our surroundings and our actions. Amidst this scholarly pursuit, one often underestimated factor, namely air pollution, has taken center stage in our investigation.
The small, yet bustling college town of State College, Pennsylvania, home to the Pennsylvania State University, has served as the backdrop for our inquiry. Nestled in the picturesque landscape of central Pennsylvania, it is renowned for its vibrant community and spirited culture. However, beneath the facade of this idyllic setting lurks a tale of hidden influences, one that ties the quality of the air we breathe to the incidence of violent crime.
As we embark on our quest to uncover the mysteries of this seemingly incongruous relationship, we are mindful of the whimsical yet undeniable nature of our findings. It is indeed a breath of fresh air to bring attention to this overlooked connection between air pollution and aggressive behavior. While some may find our revelations as shocking as inhaling a lungful of smog, we press on in our pursuit of truth, armed with statistical rigor and a keen sense of the somewhat unexpected.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]
In analyzing the extensive dataset encompassing three decades of air pollution and violent crime data in State College, Pennsylvania, a robust correlation coefficient of 0.7122592 and an r-squared value of 0.5073131 have been uncovered, indicating a statistically significant association between air pollution levels and violent crime rates. The p-value of less than 0.01 offers compelling evidence to support the strength of this correlation, suggesting that the relationship between air pollution and violent crime rates is not merely a product of chance.

Our findings are visually encapsulated in Figure 1, which exhibits a compelling scatterplot depicting the strong positive correlation between air pollution and violent crime rates. The clear trend in the data points serves as a visual testament to the poignant connection between the quality of the air and the propensity for aggressive behaviors in the context of State College, Pennsylvania.

The results of this study, while undoubtedly compelling, should be approached with equal parts skepticism and intrigue. Our team has carefully navigated the complex and winding road of environmental and behavioral data, ultimately arriving at a juncture where the impact of air pollution on violent crime rates cannot be dismissed as inconsequential. Thus, we invite our readers to take a deep breath and contemplate the multifaceted influences that inhabit the air we breathe and the behaviors we exhibit. For, in the curious tapestry of human experiences, the role of air pollution in shaping human actions may be more than just a puff of smoke.


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

Please make up the discussion section of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

[[LITERATURE REVIEW]]
As we traverse the labyrinthine landscape of literature on the interplay between air pollution and violent crime rates, we encounter a multitude of studies that attempt to elucidate this enigmatic relationship. Smith et al. (2015) contribute to this discourse by highlighting the potential impact of air pollution on cognitive functions, underscoring its potential role in shaping behavioral outcomes. Similarly, Doe and colleagues (2018) delve into the physiological effects of air pollution, shedding light on the potential mechanisms through which polluted air could influence aggressive tendencies.
In "The Air Pollutant's Dilemma" by Brown (2020), the author explores the societal implications of air pollution, drawing attention to its potential to disrupt the delicate balance of human interactions. Furthermore, Jones (2017) postulates that the psychological distress induced by exposure to polluted air may contribute to heightened levels of aggression, thereby offering a lens through which to view the link between air quality and violent behavior.
Navigating into the realm of fiction, the works of Dickens and Dostoevsky offer a curious insight into the human psyche, albeit in a metaphorical sense. "Bleak House" illustrated the bleakness that can permeate an environment clouded by the presence of pollution, while "Crime and Punishment" provides a window into the tumultuous inner world of individuals grappling with the impurities of their surroundings.
In the pursuit of a comprehensive understanding, we ventured into uncharted territories, perusing unconventional sources in a valiant attempt to capture the essence of this perplexing correlation. From the back of shampoo bottles to the whimsical musings of internet forums, we discovered an assortment of quixotic insights, each adding a peculiar tint to the kaleidoscopic tapestry of our investigation.
As we reflect on this diversity of perspectives, we cannot help but marvel at the breadth of influences that have shaped our understanding of this captivating nexus between air pollution and violent crime rates. Indeed, it is amidst this whimsical journey through literature that we gleaned valuable insights, dissolving the boundaries between the serious and the surreal in our quest for revelatory revelations.

[[RESULTS]]
In analyzing the extensive dataset encompassing three decades of air pollution and violent crime data in State College, Pennsylvania, a robust correlation coefficient of 0.7122592 and an r-squared value of 0.5073131 have been uncovered, indicating a statistically significant association between air pollution levels and violent crime rates. The p-value of less than 0.01 offers compelling evidence to support the strength of this correlation, suggesting that the relationship between air pollution and violent crime rates is not merely a product of chance.
Our findings are visually encapsulated in Figure 1, which exhibits a compelling scatterplot depicting the strong positive correlation between air pollution and violent crime rates. The clear trend in the data points serves as a visual testament to the poignant connection between the quality of the air and the propensity for aggressive behaviors in the context of State College, Pennsylvania.
The results of this study, while undoubtedly compelling, should be approached with equal parts skepticism and intrigue. Our team has carefully navigated the complex and winding road of environmental and behavioral data, ultimately arriving at a juncture where the impact of air pollution on violent crime rates cannot be dismissed as inconsequential. Thus, we invite our readers to take a deep breath and contemplate the multifaceted influences that inhabit the air we breathe and the behaviors we exhibit. For, in the curious tapestry of human experiences, the role of air pollution in shaping human actions may be more than just a puff of smoke.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

In navigating the tangled web of literature concerning the interplay between air pollution and violent crime rates, we stumbled upon an intriguing assortment of insights that added unexpected hues to our understanding of this perplexing correlation. The works of Dickens and Dostoevsky, which we whimsically intertwined with our more conventional research sources, provide a curious metaphorical lens through which to view the obscured link between the quality of the air and proclivity for aggressive behavior.

Our findings, capturing a robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, cast a captivating spotlight on the underappreciated relationship between air pollution levels and violent crime rates. This stark statistical evidence undoubtedly lends credence to prior research positing the potential impact of polluted air on cognitive function and physiological well-being, underscoring the intricate mechanisms through which environmental factors could influence behavioral outcomes. Hence, our results not only substantiate but also amplify the validity of previous scholarly endeavors, inviting the reader to take a deep breath and contemplate the multifaceted influences that inhabit the air we breathe and the behaviors we exhibit.

In unraveling this complex nexus, we must also pay homage to the lighthearted detours we took into unconventional sources. From the whimsical musings of internet forums to the somewhat tongue-in-cheek reflections found on the back of shampoo bottles, each quixotic insight added a peculiar tint to the kaleidoscope of our investigation. It is amidst this whimsical journey that we gleaned valuable insights, dissolving the boundaries between the serious and the surreal in our quest for revelatory revelations.

As we carefully scrutinize the compelling scatterplot in Figure 1, which vividly encapsulates the potent relationship between air pollution and violent crime rates, we cannot help but speculate on the potential depth of this correlation. The succulent statistical fruits of our labor evoke a cocktail of skepticism and intrigue, prompting us to ponder the significance of air pollution in shaping human actions. Thus, let us keep our eyes wide open, for in the curious tapestry of human experiences, the role of air pollution in influencing our behaviors may be more than just a puff of smoke.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Air pollution in State College, Pennsylvania and Violent crime rates. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania

[[ABSTRACT]]
This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

[[INTRDUCTION]]
The relationship between environmental factors and human behavior has long been a topic of interest and debate in academia. From the impact of natural landscapes on mental health to the effect of urban sprawl on social interaction, researchers have endeavored to untangle the intricate web of connections between our surroundings and our actions. Amidst this scholarly pursuit, one often underestimated factor, namely air pollution, has taken center stage in our investigation.
The small, yet bustling college town of State College, Pennsylvania, home to the Pennsylvania State University, has served as the backdrop for our inquiry. Nestled in the picturesque landscape of central Pennsylvania, it is renowned for its vibrant community and spirited culture. However, beneath the facade of this idyllic setting lurks a tale of hidden influences, one that ties the quality of the air we breathe to the incidence of violent crime.
As we embark on our quest to uncover the mysteries of this seemingly incongruous relationship, we are mindful of the whimsical yet undeniable nature of our findings. It is indeed a breath of fresh air to bring attention to this overlooked connection between air pollution and aggressive behavior. While some may find our revelations as shocking as inhaling a lungful of smog, we press on in our pursuit of truth, armed with statistical rigor and a keen sense of the somewhat unexpected.

[[RESULTS]]
In analyzing the extensive dataset encompassing three decades of air pollution and violent crime data in State College, Pennsylvania, a robust correlation coefficient of 0.7122592 and an r-squared value of 0.5073131 have been uncovered, indicating a statistically significant association between air pollution levels and violent crime rates. The p-value of less than 0.01 offers compelling evidence to support the strength of this correlation, suggesting that the relationship between air pollution and violent crime rates is not merely a product of chance.
Our findings are visually encapsulated in Figure 1, which exhibits a compelling scatterplot depicting the strong positive correlation between air pollution and violent crime rates. The clear trend in the data points serves as a visual testament to the poignant connection between the quality of the air and the propensity for aggressive behaviors in the context of State College, Pennsylvania.
The results of this study, while undoubtedly compelling, should be approached with equal parts skepticism and intrigue. Our team has carefully navigated the complex and winding road of environmental and behavioral data, ultimately arriving at a juncture where the impact of air pollution on violent crime rates cannot be dismissed as inconsequential. Thus, we invite our readers to take a deep breath and contemplate the multifaceted influences that inhabit the air we breathe and the behaviors we exhibit. For, in the curious tapestry of human experiences, the role of air pollution in shaping human actions may be more than just a puff of smoke.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unveiled a compelling association between air pollution levels and violent crime rates in State College, Pennsylvania. The robust correlation coefficient and statistically significant p-value leave little room for doubt regarding the influence of air quality on aggressive behaviors. It appears that the air in State College is not just thin, but also inciting some less than savory actions - a revelation as unexpected as finding a needle in a haystack or a breath of fresh air on a smoggy day.

This research adds to the growing body of evidence on the nuanced connections between our environment and human behavior. While some may find our findings as shocking as inhaling a lungful of smog, it is important to recognize the potential impact of air pollution on the behaviors we exhibit. It seems that in the curious tapestry of human experiences, the role of air pollution in shaping human actions may be more than just a puff of smoke.

But alas, despite our delightful findings, it seems that no more research is needed in this area. After all, we’ve already taken a deep breath and contemplated the multifaceted influences that inhabit the air we breathe and the behaviors we exhibit. It’s time to clear the air and move on to new, less airy endeavors.


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 The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Ecological Anthropology and Urban Sociology


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 The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania. Respond only with the name of a fictional organization.

ChatGPT:

Society for Environmental Justice Research and Advocacy


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 The Polluted Truth: Unveiling the Air Pollution-Violent Crime Connection in State College, Pennsylvania with an abstract of This study delves into the often-overlooked relationship between air pollution and violent crime rates in the quaint college town of State College, Pennsylvania. Using a comprehensive analysis of data from the Environmental Protection Agency and the FBI Criminal Justice Information Services spanning over three decades, we sought to unravel the obscured links between the quality of the air we breathe and the propensity for aggressive behavior. Our findings reveal a surprisingly robust correlation coefficient of 0.7122592 and a p-value of less than 0.01, suggesting a statistically significant association between air pollution levels and violent crime rates. While our results may astound some, we must lament the unfortunate reality that the air in State College may not just be thin, but also inciting some less than savory actions. This study aims to shed light on this often-ignored factor in the complex web of influences on human behavior.

ChatGPT:

air pollution, violent crime, correlation, State College, Pennsylvania, environmental protection agency, FBI criminal justice information services, statistical analysis, aggressive behavior, air quality, human behavior, pollution effects

*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 State College, Pennsylvania
Detailed data title: Percentage of days 'unhealthy' or worse air quality in State College, PA
Source: Environmental Protection Agency
See what else correlates with Air pollution in State College, Pennsylvania

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

Correlation r = 0.7122592 (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 = 0.5073131 (Coefficient of determination)
This means 50.7% of the change in the one variable (i.e., Violent crime rates) is predictable based on the change in the other (i.e., Air pollution in State College, Pennsylvania) over the 33 years from 1990 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.3E-6. 0.0000033340249406497065000000
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 0.71 in 0.00033% of random cases. Said differently, if you correlated 299,938 random variables You don't actually need 299 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.

[ 0.49, 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.
199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in State College, Pennsylvania (Bad air quality days)0.02222220.03672320.01381220.031250.01373630.01694920.005509640.02472530.02523660.02747250.008196720.01643840.04109590.010958900.008219180000000.002732240000000000
Violent crime rates (Violent crime)729.6758.2757.7747.1713.6684.5636.6611567.6523506.5504.5494.4475.8463.2469479.3471.8458.6431.9404.5387.1387.8369.1361.6373.7397.5394.9383.4380.8398.5387380.7




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. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([0.0222222,0.0367232,0.0138122,0.03125,0.0137363,0.0169492,0.00550964,0.0247253,0.0252366,0.0274725,0.00819672,0.0164384,0.0410959,0.0109589,0,0.00821918,0,0,0,0,0,0,0.00273224,0,0,0,0,0,0,0,0,0,0,])
array_2 = np.array([729.6,758.2,757.7,747.1,713.6,684.5,636.6,611,567.6,523,506.5,504.5,494.4,475.8,463.2,469,479.3,471.8,458.6,431.9,404.5,387.1,387.8,369.1,361.6,373.7,397.5,394.9,383.4,380.8,398.5,387,380.7,])
array_1_name = "Air pollution in State College, Pennsylvania"
array_2_name = "Violent crime rates"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your dedication to rating warms my heart!


Correlation ID: 3546 · Black Variable ID: 22254 · Red Variable ID: 20220
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0