about · email me · subscribe
Spurious correlation #3,116 · 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 St. Louis and the second variable is Violent crime rates.  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 quality improved, people could finally take deep breaths and calm down instead of being constantly irritable from smog inhalation. This led to a city-wide reduction in agitated behavior, ultimately lowering the overall violent crime rates. Who knew that all it took to pacify the population was some cleaner air!

Model: dalle-3
Prompt: Create an image of a TIME magazine cover featuring an iconic cityscape of St. Louis consumed by thick smog, with the skyline barely visible through the pollution. Below, depict two individuals engaged in a heated altercation on a crowded street, surrounded by onlookers and a sense of unease. The subtle details of the hazy air and the heightened tension in the atmosphere should be evident, portraying the impact of pollution on human behavior and the city's increasing crime rates. 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 St. Louis 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: Cybernetic art Art nouveau Oragami Psychedelic A TIME magazine cover image
ChatGPT: A TIME magazine cover image

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 St. Louis and Violent crime rates, in the following situation: Because the increase in air pollution in St. Louis led to a decrease in brain oxygen levels, causing people to make impulsive decisions and increasing the likelihood of violent behavior.. Keep the description simple.
ChatGPT: In St. Louis, thick smog hung over the city, a result of heavy air pollution. Despite the bustling streets, an uneasy atmosphere lingered, as the hazy air seemed to weigh heavily on the people. In the midst of this, a sudden altercation erupted between two individuals, highlighting the increasing violent crime rates. The altered brain oxygen levels due to the pollution seemed to fuel impulsive actions, adding to the tension in the city.

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 TIME magazine cover image ] and depicting this scene: In St. Louis, thick smog hung over the city, a result of heavy air pollution. Despite the bustling streets, an uneasy atmosphere lingered, as the hazy air seemed to weigh heavily on the people. In the midst of this, a sudden altercation erupted between two individuals, highlighting the increasing violent crime rates. The altered brain oxygen levels due to the pollution seemed to fuel impulsive actions, adding to the tension in the city. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a TIME magazine cover featuring an iconic cityscape of St. Louis consumed by thick smog, with the skyline barely visible through the pollution. Below, depict two individuals engaged in a heated altercation on a crowded street, surrounded by onlookers and a sense of unease. The subtle details of the hazy air and the heightened tension in the atmosphere should be evident, portraying the impact of pollution on human behavior and the city's increasing crime rates.

*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 St. Louis caused Violent crime rates to decrease.

AI academic paper

(Because p < 0.01)
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

The Journal of Ecological Criminology

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 St. Louis 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.

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

Your research team used data from Environmental Protection Agency and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.6596152 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]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.


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 St. Louis 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The proverbial haze surrounding the relationship between environmental factors and societal behavior has long captivated the minds of researchers and policymakers alike. Among the myriad environmental variables, air pollution stands out as a crucial yet often overlooked facet of urban life. While the deleterious effects of air pollution on physical health are well-documented, its potential influence on societal well-being and behavior remains a subject of ongoing inquiry. In this vein, the present study seeks to unravel the enigmatic connection between air pollution and violent crime rates in the city of St. Louis, Missouri.

As we embark on this academic odyssey, it is paramount to acknowledge the multifaceted nature of the variables at play. Air pollution, with its noxious concoction of particulate matter, nitrogen dioxide, and volatile organic compounds, permeates the urban atmosphere like an unwelcome guest at a dinner party. Meanwhile, violent crime rates, characterized by their statistical nonchalance towards the null hypothesis of societal tranquility, masquerade as the unruly cousins of more well-behaved social metrics. The intricate interplay between these variables mirrors a convoluted dance, where the steps taken by one partner may inadvertently influence the movements of the other.

Shedding light on the relationship between air pollution and violent crime rates is akin to untangling a proverbial ball of statistical yarn. Our endeavor involves sifting through decades of data, akin to archeologists excavating the remnants of Pangaea. Through the use of rigorous statistical analyses and dry mathematical incantations, we aim to extract meaning from the cacophony of numbers and symbols, much like deciphering an ancient code.

However, as with any research pursuit, navigating the labyrinthine realm of statistical analysis is not without its pitfalls. The ever-looming specter of confounding variables, lurking in the shadows like mischievous sprites, threatens to obfuscate the clarity of our findings. Thus, our quest to elucidate the relationship between air pollution and violent crime rates in St. Louis is not merely an academic exercise, but a valiant odyssey fraught with statistical perils and unexpected twists.

In the pages that follow, we will navigate this scientific odyssey with the tenacity of intrepid explorers and the wit of seasoned jesters, as we seek to unravel the hazy connection between air pollution and violent crime rates in St. Louis.


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 St. Louis 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 CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The proverbial haze surrounding the relationship between environmental factors and societal behavior has long captivated the minds of researchers and policymakers alike. Among the myriad environmental variables, air pollution stands out as a crucial yet often overlooked facet of urban life. While the deleterious effects of air pollution on physical health are well-documented, its potential influence on societal well-being and behavior remains a subject of ongoing inquiry. In this vein, the present study seeks to unravel the enigmatic connection between air pollution and violent crime rates in the city of St. Louis, Missouri.
As we embark on this academic odyssey, it is paramount to acknowledge the multifaceted nature of the variables at play. Air pollution, with its noxious concoction of particulate matter, nitrogen dioxide, and volatile organic compounds, permeates the urban atmosphere like an unwelcome guest at a dinner party. Meanwhile, violent crime rates, characterized by their statistical nonchalance towards the null hypothesis of societal tranquility, masquerade as the unruly cousins of more well-behaved social metrics. The intricate interplay between these variables mirrors a convoluted dance, where the steps taken by one partner may inadvertently influence the movements of the other.
Shedding light on the relationship between air pollution and violent crime rates is akin to untangling a proverbial ball of statistical yarn. Our endeavor involves sifting through decades of data, akin to archeologists excavating the remnants of Pangaea. Through the use of rigorous statistical analyses and dry mathematical incantations, we aim to extract meaning from the cacophony of numbers and symbols, much like deciphering an ancient code.
However, as with any research pursuit, navigating the labyrinthine realm of statistical analysis is not without its pitfalls. The ever-looming specter of confounding variables, lurking in the shadows like mischievous sprites, threatens to obfuscate the clarity of our findings. Thus, our quest to elucidate the relationship between air pollution and violent crime rates in St. Louis is not merely an academic exercise, but a valiant odyssey fraught with statistical perils and unexpected twists.
In the pages that follow, we will navigate this scientific odyssey with the tenacity of intrepid explorers and the wit of seasoned jesters, as we seek to unravel the hazy connection between air pollution and violent crime rates in St. Louis.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The literature on the relationship between air pollution and violent crime rates in urban areas comprises a diverse body of work, ranging from rigorous empirical studies to more speculative explorations. Smith et al. (2015) conducted a seminal study examining the potential link between air pollution and aggressive behaviors, highlighting a positive association between particulate matter exposure and instances of interpersonal conflict. Similarly, Doe's (2018) comprehensive review of environmental determinants of crime elucidated the complex interplay between air quality and criminal behavior, positing air pollution as a potential catalyst for heightened aggression.

Moving beyond the realm of academic research, popular non-fiction works such as "Air Pollution and Its Socioeconomic Impacts" by Jones (2009) and "Crime and the Urban Environment" by White (2013) offer insightful perspectives on the intersection of environmental factors and societal well-being. These seminal works serve as touchstones for understanding the intricate dynamics at play in the urban milieu, although their readability may lack the page-turning excitement found in a Dan Brown thriller.

Speaking of thrillers, an intriguing line of inquiry emerges when considering fictional literature that may indirectly shed light on the air pollution-crime rate nexus. In "The Poisoned Air Affair" by Mystery Author (2020) and "Smog: A Noir Tale" by Fictional Writer (2017), the protagonists navigate treacherous urban landscapes tainted by pollution, intertwining their sleuthing escapades with the murky underbelly of crime. While these novels may not offer empirical evidence, they do lend a sense of intrigue to the intersection of environmental hazards and criminal activity.

Venturing into unconventional territories, the present study also draws inspiration from an array of unexpected sources. From perusing the cryptic engravings on Stone Age cave walls to decoding the esoteric wisdom conveyed in supermarket tabloids, our quest for knowledge has left no stone unturned, no parchment unread, and no CVS receipt unexamined. In the spirit of unorthodox inquiry, we have embraced the untold wisdom that lies beyond the confines of traditional academia, for after all, insights into the human condition may be found in the unlikeliest of places.

The overarching narrative that emerges from this diverse array of literature underscores the intricate nature of the air pollution-violent crime relationship, weaving a tapestry of scholarly discourse, fictional intrigue, and unconventional wisdom. As we delve deeper into the empirical underpinnings of this phenomenon, it becomes increasingly clear that the hazy connection between air pollution and violent crime rates in St. Louis is not merely a matter of statistical correlation, but a complex web of interwoven factors awaiting elucidation.


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 St. Louis 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services . You used data from 1985 to 2022

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

[[INTRODUCTION]]
The proverbial haze surrounding the relationship between environmental factors and societal behavior has long captivated the minds of researchers and policymakers alike. Among the myriad environmental variables, air pollution stands out as a crucial yet often overlooked facet of urban life. While the deleterious effects of air pollution on physical health are well-documented, its potential influence on societal well-being and behavior remains a subject of ongoing inquiry. In this vein, the present study seeks to unravel the enigmatic connection between air pollution and violent crime rates in the city of St. Louis, Missouri.
As we embark on this academic odyssey, it is paramount to acknowledge the multifaceted nature of the variables at play. Air pollution, with its noxious concoction of particulate matter, nitrogen dioxide, and volatile organic compounds, permeates the urban atmosphere like an unwelcome guest at a dinner party. Meanwhile, violent crime rates, characterized by their statistical nonchalance towards the null hypothesis of societal tranquility, masquerade as the unruly cousins of more well-behaved social metrics. The intricate interplay between these variables mirrors a convoluted dance, where the steps taken by one partner may inadvertently influence the movements of the other.
Shedding light on the relationship between air pollution and violent crime rates is akin to untangling a proverbial ball of statistical yarn. Our endeavor involves sifting through decades of data, akin to archeologists excavating the remnants of Pangaea. Through the use of rigorous statistical analyses and dry mathematical incantations, we aim to extract meaning from the cacophony of numbers and symbols, much like deciphering an ancient code.
However, as with any research pursuit, navigating the labyrinthine realm of statistical analysis is not without its pitfalls. The ever-looming specter of confounding variables, lurking in the shadows like mischievous sprites, threatens to obfuscate the clarity of our findings. Thus, our quest to elucidate the relationship between air pollution and violent crime rates in St. Louis is not merely an academic exercise, but a valiant odyssey fraught with statistical perils and unexpected twists.
In the pages that follow, we will navigate this scientific odyssey with the tenacity of intrepid explorers and the wit of seasoned jesters, as we seek to unravel the hazy connection between air pollution and violent crime rates in St. Louis.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

Sampling Procedure:

The selection of data for this study involved an elaborate and meticulous process akin to a chef meticulously selecting the finest ingredients for a gourmet dish. We sourced air pollution data from the Environmental Protection Agency, where we indulged in a veritable buffet of pollutants such as particulate matter, sulfur dioxide, and carbon monoxide – a tantalizing menu for any discerning environmental researcher. Meanwhile, the FBI Criminal Justice Information Services provided us with delectable crime data, a smorgasbord of criminal activities ranging from arson to homicide, each adding a unique flavor to our statistical stew.

Data Analysis:

To unravel the complex relationship between air pollution and violent crime rates, we employed an arsenal of statistical methods that would make even the most ardent mathematician do a little dance of statistical joy. We conducted a robust correlation analysis, akin to a matchmaking service for environmental variables and criminal activity, to determine the strength and direction of the relationship. Additionally, we employed a multiple regression analysis, weaving together the threads of air pollution and crime data into a statistical tapestry of unparalleled complexity. It was a bit like conducting an intricate symphony, with air pollution and crime rates serving as the errant notes in a melodious cacophony of statistical significance.

Control Variables:

In our pursuit of truth amidst the statistical labyrinth, we diligently considered the influence of potential confounding variables that could covertly sway our findings. Like detectives on the trail of elusive suspects, we scrutinized demographic factors, socioeconomic status, and urban development, diligently ensuring that our findings were not unduly influenced by these sneaky interlopers.

Statistical Software:

The analysis was conducted using state-of-the-art statistical software, which acted as the trusty sidekick to our intrepid band of researchers. This software became the Harry to our research Potter, carefully crafting and casting statistical spells that unveiled the hidden patterns and relationships within the data.

Ethical Considerations:

Throughout the data collection and analysis process, we maintained the utmost ethical standards, tiptoeing delicately through the minefield of research ethics like a pair of cautious spelunkers in an academic cave. The privacy and confidentiality of individuals represented in the data were safeguarded with the diligence of a wise wizard guarding ancient scrolls, ensuring that our research was conducted with the highest regard for ethical principles.

Limitations:

No research endeavor is without its limitations, and our study is no exception. The use of secondary data from public sources introduces the potential for measurement error and reporting biases, akin to navigating a scientific maze with a few unexpected twists and turns. Additionally, the ecological nature of our study restricts the ability to infer causality, leaving us in a state of statistical limbo where correlation does not necessarily imply causation.

In summary, the methodology adopted for this study involved a meticulous gathering and analysis of data, coupled with a deep-seated commitment to ethical research practices. The findings of this study will shed light on the tangled web of connections between air pollution and violent crime rates, providing valuable insights into the complex interplay of environmental and societal factors.


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 St. Louis 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 1985 to 2022, you found a correlation 0.6596152, r-squared of 0.4350922, 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 Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The proverbial haze surrounding the relationship between environmental factors and societal behavior has long captivated the minds of researchers and policymakers alike. Among the myriad environmental variables, air pollution stands out as a crucial yet often overlooked facet of urban life. While the deleterious effects of air pollution on physical health are well-documented, its potential influence on societal well-being and behavior remains a subject of ongoing inquiry. In this vein, the present study seeks to unravel the enigmatic connection between air pollution and violent crime rates in the city of St. Louis, Missouri.
As we embark on this academic odyssey, it is paramount to acknowledge the multifaceted nature of the variables at play. Air pollution, with its noxious concoction of particulate matter, nitrogen dioxide, and volatile organic compounds, permeates the urban atmosphere like an unwelcome guest at a dinner party. Meanwhile, violent crime rates, characterized by their statistical nonchalance towards the null hypothesis of societal tranquility, masquerade as the unruly cousins of more well-behaved social metrics. The intricate interplay between these variables mirrors a convoluted dance, where the steps taken by one partner may inadvertently influence the movements of the other.
Shedding light on the relationship between air pollution and violent crime rates is akin to untangling a proverbial ball of statistical yarn. Our endeavor involves sifting through decades of data, akin to archeologists excavating the remnants of Pangaea. Through the use of rigorous statistical analyses and dry mathematical incantations, we aim to extract meaning from the cacophony of numbers and symbols, much like deciphering an ancient code.
However, as with any research pursuit, navigating the labyrinthine realm of statistical analysis is not without its pitfalls. The ever-looming specter of confounding variables, lurking in the shadows like mischievous sprites, threatens to obfuscate the clarity of our findings. Thus, our quest to elucidate the relationship between air pollution and violent crime rates in St. Louis is not merely an academic exercise, but a valiant odyssey fraught with statistical perils and unexpected twists.
In the pages that follow, we will navigate this scientific odyssey with the tenacity of intrepid explorers and the wit of seasoned jesters, as we seek to unravel the hazy connection between air pollution and violent crime rates in St. Louis.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The robust statistical analysis revealed a correlation coefficient of 0.6596152 between air pollution levels and violent crime rates in St. Louis from 1985 to 2022. This coefficient indicates a moderately strong positive relationship between these two variables. In simpler terms, as air pollution levels increased, so did the violent crime rates. It's like they were holding hands skipping merrily along the dataset, hand in hand, polluting both the air and the statistical model.

The r-squared value of 0.4350922 suggests that approximately 43.5% of the variation in violent crime rates can be explained by changes in air pollution levels. The remaining 56.5% of the variation may be attributed to other factors, such as socioeconomic conditions, population demographics, or the capricious nature of human behavior. It's as if a mischievous statistical imp has been playing with our model, leaving more than half of the variation unaccounted for.

Moreover, the statistically significant p-value of less than 0.01 indicates that the observed relationship between air pollution and violent crime rates is unlikely to be a mere fluke or the result of random chance. It's so statistically significant, even the most skeptical of statistical gurus would have to do a double take. If the p-value were a celebrity, it would be strutting down the statistical runway, commanding attention and adoration from fellow p-values.

Fig. 1 displays the captivating scatterplot illustrating the pronounced correlation between air pollution levels and violent crime rates in St. Louis. Like two peas in a pod, each data point seems to whisper a tale of environmental haziness and criminal mischief, painting a vivid picture of their intertwined destinies.

These results illuminate the intricate relationship between air pollution and violent crime rates in the urban landscape of St. Louis, teasingly hinting at the potential impact of environmental factors on societal behavior. As we continue to scrutinize this intriguing connection, it becomes clear that the cloud of air pollution may cast more than just a shadow on the city; it may leave its mark in the annals of statistical inquiry as well.


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 St. Louis 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

[[LITERATURE REVIEW]]
The literature on the relationship between air pollution and violent crime rates in urban areas comprises a diverse body of work, ranging from rigorous empirical studies to more speculative explorations. Smith et al. (2015) conducted a seminal study examining the potential link between air pollution and aggressive behaviors, highlighting a positive association between particulate matter exposure and instances of interpersonal conflict. Similarly, Doe's (2018) comprehensive review of environmental determinants of crime elucidated the complex interplay between air quality and criminal behavior, positing air pollution as a potential catalyst for heightened aggression.
Moving beyond the realm of academic research, popular non-fiction works such as "Air Pollution and Its Socioeconomic Impacts" by Jones (2009) and "Crime and the Urban Environment" by White (2013) offer insightful perspectives on the intersection of environmental factors and societal well-being. These seminal works serve as touchstones for understanding the intricate dynamics at play in the urban milieu, although their readability may lack the page-turning excitement found in a Dan Brown thriller.
Speaking of thrillers, an intriguing line of inquiry emerges when considering fictional literature that may indirectly shed light on the air pollution-crime rate nexus. In "The Poisoned Air Affair" by Mystery Author (2020) and "Smog: A Noir Tale" by Fictional Writer (2017), the protagonists navigate treacherous urban landscapes tainted by pollution, intertwining their sleuthing escapades with the murky underbelly of crime. While these novels may not offer empirical evidence, they do lend a sense of intrigue to the intersection of environmental hazards and criminal activity.
Venturing into unconventional territories, the present study also draws inspiration from an array of unexpected sources. From perusing the cryptic engravings on Stone Age cave walls to decoding the esoteric wisdom conveyed in supermarket tabloids, our quest for knowledge has left no stone unturned, no parchment unread, and no CVS receipt unexamined. In the spirit of unorthodox inquiry, we have embraced the untold wisdom that lies beyond the confines of traditional academia, for after all, insights into the human condition may be found in the unlikeliest of places.
The overarching narrative that emerges from this diverse array of literature underscores the intricate nature of the air pollution-violent crime relationship, weaving a tapestry of scholarly discourse, fictional intrigue, and unconventional wisdom. As we delve deeper into the empirical underpinnings of this phenomenon, it becomes increasingly clear that the hazy connection between air pollution and violent crime rates in St. Louis is not merely a matter of statistical correlation, but a complex web of interwoven factors awaiting elucidation.

[[RESULTS]]
The robust statistical analysis revealed a correlation coefficient of 0.6596152 between air pollution levels and violent crime rates in St. Louis from 1985 to 2022. This coefficient indicates a moderately strong positive relationship between these two variables. In simpler terms, as air pollution levels increased, so did the violent crime rates. It's like they were holding hands skipping merrily along the dataset, hand in hand, polluting both the air and the statistical model.
The r-squared value of 0.4350922 suggests that approximately 43.5% of the variation in violent crime rates can be explained by changes in air pollution levels. The remaining 56.5% of the variation may be attributed to other factors, such as socioeconomic conditions, population demographics, or the capricious nature of human behavior. It's as if a mischievous statistical imp has been playing with our model, leaving more than half of the variation unaccounted for.
Moreover, the statistically significant p-value of less than 0.01 indicates that the observed relationship between air pollution and violent crime rates is unlikely to be a mere fluke or the result of random chance. It's so statistically significant, even the most skeptical of statistical gurus would have to do a double take. If the p-value were a celebrity, it would be strutting down the statistical runway, commanding attention and adoration from fellow p-values.
Fig. 1 displays the captivating scatterplot illustrating the pronounced correlation between air pollution levels and violent crime rates in St. Louis. Like two peas in a pod, each data point seems to whisper a tale of environmental haziness and criminal mischief, painting a vivid picture of their intertwined destinies.
These results illuminate the intricate relationship between air pollution and violent crime rates in the urban landscape of St. Louis, teasingly hinting at the potential impact of environmental factors on societal behavior. As we continue to scrutinize this intriguing connection, it becomes clear that the cloud of air pollution may cast more than just a shadow on the city; it may leave its mark in the annals of statistical inquiry as well.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

These results support and extend prior research, shedding further light on the intriguing relationship between air pollution and violent crime rates. Our findings concur with the work of Smith et al. (2015) and Doe (2018), affirming the notion that heightened levels of air pollution may indeed be linked to increased instances of criminal behavior. Just as a good detective builds upon the clues of those who came before, our study adds another piece to the puzzle of environmental influence on human conduct, showcasing how the haze of pollution may hang not just in the air, but also in the statistical corridors of research.

The moderately strong positive correlation coefficient of 0.6596152 aligns with the anticipated direction of the relationship posited in prior literature, akin to a puzzle piece fitting snugly into place with a satisfying click. It reinforces the notion that as air pollution levels rise, so do the violent crime rates, a connection as tight as the lid on a jam jar. Furthermore, the r-squared value of 0.4350922 highlights the substantial proportion of variation in violent crime rates that can be elucidated by changes in air pollution levels, painting a picture of statistical sleuthing akin to meticulously unraveling a gripping mystery novel.

The statistically significant p-value, akin to a noteworthy protagonist in the statistical drama, serves as a compelling testament to the robustness of the connection uncovered. Much like a finely crafted plot twist, the p-value propels the narrative of the air pollution-crime rate relationship forward, dispelling any lingering uncertainty with its resounding significance. The scatterplot further crystallizes these inextricable ties, offering a visual narrative as vivid and captivating as a crime scene diorama meticulously laid out at the scene of statistical inquiry.

Our study adds another chapter to the ongoing discourse, indicating that the web of causation linking air pollution and violent crime rates is not merely a figment of statistical happenstance, but a tangible thread weaving through the urban fabric of St. Louis. As we continue to unravel these complex relationships, we are reminded that the labyrinth of science is peppered not only with rigorous methodology and theoretical frameworks but also with a dash of whimsy and wonder, akin to a captivating plot twist in an unexpected genre.


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 St. Louis 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. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis

[[ABSTRACT]]
The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

[[INTRDUCTION]]
The proverbial haze surrounding the relationship between environmental factors and societal behavior has long captivated the minds of researchers and policymakers alike. Among the myriad environmental variables, air pollution stands out as a crucial yet often overlooked facet of urban life. While the deleterious effects of air pollution on physical health are well-documented, its potential influence on societal well-being and behavior remains a subject of ongoing inquiry. In this vein, the present study seeks to unravel the enigmatic connection between air pollution and violent crime rates in the city of St. Louis, Missouri.
As we embark on this academic odyssey, it is paramount to acknowledge the multifaceted nature of the variables at play. Air pollution, with its noxious concoction of particulate matter, nitrogen dioxide, and volatile organic compounds, permeates the urban atmosphere like an unwelcome guest at a dinner party. Meanwhile, violent crime rates, characterized by their statistical nonchalance towards the null hypothesis of societal tranquility, masquerade as the unruly cousins of more well-behaved social metrics. The intricate interplay between these variables mirrors a convoluted dance, where the steps taken by one partner may inadvertently influence the movements of the other.
Shedding light on the relationship between air pollution and violent crime rates is akin to untangling a proverbial ball of statistical yarn. Our endeavor involves sifting through decades of data, akin to archeologists excavating the remnants of Pangaea. Through the use of rigorous statistical analyses and dry mathematical incantations, we aim to extract meaning from the cacophony of numbers and symbols, much like deciphering an ancient code.
However, as with any research pursuit, navigating the labyrinthine realm of statistical analysis is not without its pitfalls. The ever-looming specter of confounding variables, lurking in the shadows like mischievous sprites, threatens to obfuscate the clarity of our findings. Thus, our quest to elucidate the relationship between air pollution and violent crime rates in St. Louis is not merely an academic exercise, but a valiant odyssey fraught with statistical perils and unexpected twists.
In the pages that follow, we will navigate this scientific odyssey with the tenacity of intrepid explorers and the wit of seasoned jesters, as we seek to unravel the hazy connection between air pollution and violent crime rates in St. Louis.

[[RESULTS]]
The robust statistical analysis revealed a correlation coefficient of 0.6596152 between air pollution levels and violent crime rates in St. Louis from 1985 to 2022. This coefficient indicates a moderately strong positive relationship between these two variables. In simpler terms, as air pollution levels increased, so did the violent crime rates. It's like they were holding hands skipping merrily along the dataset, hand in hand, polluting both the air and the statistical model.
The r-squared value of 0.4350922 suggests that approximately 43.5% of the variation in violent crime rates can be explained by changes in air pollution levels. The remaining 56.5% of the variation may be attributed to other factors, such as socioeconomic conditions, population demographics, or the capricious nature of human behavior. It's as if a mischievous statistical imp has been playing with our model, leaving more than half of the variation unaccounted for.
Moreover, the statistically significant p-value of less than 0.01 indicates that the observed relationship between air pollution and violent crime rates is unlikely to be a mere fluke or the result of random chance. It's so statistically significant, even the most skeptical of statistical gurus would have to do a double take. If the p-value were a celebrity, it would be strutting down the statistical runway, commanding attention and adoration from fellow p-values.
Fig. 1 displays the captivating scatterplot illustrating the pronounced correlation between air pollution levels and violent crime rates in St. Louis. Like two peas in a pod, each data point seems to whisper a tale of environmental haziness and criminal mischief, painting a vivid picture of their intertwined destinies.
These results illuminate the intricate relationship between air pollution and violent crime rates in the urban landscape of St. Louis, teasingly hinting at the potential impact of environmental factors on societal behavior. As we continue to scrutinize this intriguing connection, it becomes clear that the cloud of air pollution may cast more than just a shadow on the city; it may leave its mark in the annals of statistical inquiry as well.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our rigorous statistical analysis has unveiled a compelling relationship between air pollution levels and violent crime rates in St. Louis. The robust correlation coefficient and statistically significant p-value paint a vivid picture of the intertwining destinies of these variables. It's as if they were engaging in a tango of statistical significance, twirling and swirling through the data with undeniable flair.

However, we must acknowledge that our findings merely scratch the surface of this enigmatic connection. Like detectives in a statistical mystery novel, we have uncovered tantalizing clues, but the full story remains shrouded in statistical fog. Untangling the web of causation and untoward influences demands further inquiry. We hope future researchers will unravel this enigmatic relationship, armed with statistical magnifying glasses, and a healthy dose of scientific curiosity.

While the cloud of air pollution may cast a shadow on both the city and our statistical models, it is imperative to recognize that correlation does not imply causation. There may be lurking confounders ready to pounce on our elegant statistical dance, so caution is warranted. As enigmatic as the relationship between air pollution and violent crime rates may be, for now, it appears our quest has quenched the statistical thirst for this particular conundrum. It's time to close the statistical case on this hazy connection. No more research needed, folks. We've blown this case wide open!


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 Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Criminology


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 Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Atmospheric Psychosocial Dynamics


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 Hazy Connection: Air Pollution and Violent Crime Rates in St. Louis with an abstract of The relationship between air pollution and violent crime rates in urban areas has long been a topic of discourse. This study examines the association between air pollution levels and violent crime rates in St. Louis, Missouri. Utilizing data from the Environmental Protection Agency and FBI Criminal Justice Information Services, we conducted a comprehensive analysis from 1985 to 2022. The findings reveal a robust correlation coefficient of 0.6596152 and a statistically significant p-value of less than 0.01, indicating a significant relationship between air pollution and violent crime rates in St. Louis. The implications of these findings shed light on the complex interplay between environmental factors and societal behavior, prompting further investigation to elucidate potential causative mechanisms. While it seems air pollution may cloud more than just the atmosphere, it is imperative to engage in further research to tease apart the nuances of this relationship and discern the underlying mechanisms driving this association.

ChatGPT:

air pollution, violent crime rates, St. Louis, Missouri, environmental factors, societal behavior, correlation coefficient, causative mechanisms, air pollution levels, FBI Criminal Justice Information Services, Environmental Protection Agency, urban areas, atmospheric pollution

*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 St. Louis
Detailed data title: Percentage of days 'unhealthy' or worse air quality in St. Louis, MO-IL
Source: Environmental Protection Agency
See what else correlates with Air pollution in St. Louis

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 = 0.6596152 (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 = 0.4350922 (Coefficient of determination)
This means 43.5% 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 St. Louis) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 6.7E-6. 0.0000066570630669745426000000
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 0.66 in 0.00067% of random cases. Said differently, if you correlated 150,216 random variables You don't actually need 150 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 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.

[ 0.43, 0.81 ] 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 St. Louis (Bad air quality days)6.02746.849329.8630113.93446.301376.849328.493153.551912.191788.7671211.23296.010933.561646.575347.945214.644814.109598.493153.01370.5464487.671234.657536.301370.2732240.2739731.917813.01375.464480.54794500.5479450.5464480.2739730.5479450.5479450.2732240.5479450
Violent crime rates (Violent crime)558.1620.1612.5640.6666.9729.6758.2757.7747.1713.6684.5636.6611567.6523506.5504.5494.4475.8463.2469479.3471.8458.6431.9404.5387.1387.8369.1361.6373.7397.5394.9383.4380.8398.5387380.7




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([6.0274,6.84932,9.86301,13.9344,6.30137,6.84932,8.49315,3.55191,2.19178,8.76712,11.2329,6.01093,3.56164,6.57534,7.94521,4.64481,4.10959,8.49315,3.0137,0.546448,7.67123,4.65753,6.30137,0.273224,0.273973,1.91781,3.0137,5.46448,0.547945,0,0.547945,0.546448,0.273973,0.547945,0.547945,0.273224,0.547945,0,])
array_2 = np.array([558.1,620.1,612.5,640.6,666.9,729.6,758.2,757.7,747.1,713.6,684.5,636.6,611,567.6,523,506.5,504.5,494.4,475.8,463.2,469,479.3,471.8,458.6,431.9,404.5,387.1,387.8,369.1,361.6,373.7,397.5,394.9,383.4,380.8,398.5,387,380.7,])
array_1_name = "Air pollution in St. Louis"
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 rating skills are top-notch!


Correlation ID: 3116 · Black Variable ID: 21309 · Red Variable ID: 20220
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0