about · email me · subscribe
Spurious correlation #2,912 · 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 Lansing, Michigan 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

The dirty air had everyone feeling more revved up, leading to an increase in altercations. You could say the smog was really adding fuel to the fire of criminal activity. It seems like when it comes to pollution and violent crime in Lansing, there's just no 'clean' connection! But in all seriousness, the correlation is likely due to other factors, such as socioeconomic conditions and population density, rather than a direct causal link between air quality and criminal behavior.

Model: dalle-3
Prompt: Image Generation Prompt: Generate an image in the style of a TIME magazine cover, depicting the scene in Lansing, Michigan. The image should show a city street with gray smog hanging heavily in the air. People with frizzy hair should be walking outside, with frowns and frustrated expressions decorating their faces due to the bad hair days caused by the air pollution. In the background, there should be subtle hints of confrontations and conflicts, symbolizing the surge in violent crime rates. The overall mood should capture the tense atmosphere and the impact of air pollution on people's daily lives. 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 Lansing, Michigan 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: Psychedelic Cyberpunk A TIME magazine cover image An image that looks like it is a scene from 'Star Wars' A photo-realistic 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 Lansing, Michigan and Violent crime rates, in the following situation: Because the increase in air pollution caused everyone's hair to frizz, leading to bad hair days, causing irritability and resulting in a surge in violent crime rates.. Keep the description simple.
ChatGPT: In Lansing, Michigan, the gray smog hung heavily in the air as people walked outside, their frizzy hair blowing in the wind. Frowns and frustrated expressions decorated their faces, a result of the bad hair days caused by the air pollution. Amidst this atmosphere, the city witnessed a surge in violent crime rates, as the increasing irritability bubbled over into confrontations and conflicts.

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 Lansing, Michigan, the gray smog hung heavily in the air as people walked outside, their frizzy hair blowing in the wind. Frowns and frustrated expressions decorated their faces, a result of the bad hair days caused by the air pollution. Amidst this atmosphere, the city witnessed a surge in violent crime rates, as the increasing irritability bubbled over into confrontations and conflicts. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Image Generation Prompt: Generate an image in the style of a TIME magazine cover, depicting the scene in Lansing, Michigan. The image should show a city street with gray smog hanging heavily in the air. People with frizzy hair should be walking outside, with frowns and frustrated expressions decorating their faces due to the bad hair days caused by the air pollution. In the background, there should be subtle hints of confrontations and conflicts, symbolizing the surge in violent crime rates. The overall mood should capture the tense atmosphere and the impact of air pollution on people's daily lives.

*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 increases in Air pollution in Lansing, Michigan positively influenced Violent crime rates. Include one good pun.

AI academic paper

(Because p < 0.01)
Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan

Journal of Environmental Psychology

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 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Your research team used data from Environmental Protection Agency and FBI Criminal Justice Information Services to assess this nagging question. You found a correlation coefficient of 0.6651267 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]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Air quality and its potential impacts have been the subject of much research and discussion, akin to the act of breathing itself – often taken for granted until it becomes difficult. The effects of air pollution on physical health have been well-documented, but its potential influence on societal behaviors, specifically violent crime rates, has received less attention. However, our study aims to fill this gap by investigating the association between air pollution levels and violent crime rates in Lansing, Michigan.

It's no secret that air pollution can be a real breath-taker, but could it also be a crime sparker? *Badum tss.* This question led us to pore over decades of data, hoping to uncover any untold tales hidden within the hazy mist of statistical analysis. Our findings, like a gust of fresh air, stand to shed new light on the interconnectedness of environmental and societal well-being.

Lansing, Michigan, serves as our stage – a city known for its industrious spirit and vibrant community. Yet, beneath the surface lies a potential correlation between levels of air pollutants and instances of violent crime. So, just for the record, it's not all sunshine and roses in the capital of the Wolverine State.

As we delved into the data, we were struck by the starkness of our correlation coefficient – 0.6651267, to be precise. In layman's terms, this suggests a strong relationship between air pollution and violent crime rates, holding p < 0.01, which is not just a statistical fluke – it's a bona fide finding that demands attention. Our results are nothing to sneeze at, indicating that there is indeed something more than mere coincidence in the air.

While it's tempting to jump to conclusions and assume that cleaner air equates to crime reduction, we treaded cautiously, knowing that correlation does not necessarily imply causation. Yet, it's hard to deny the allure of the idea that improving air quality could be a breath of fresh air for tackling crime rates. *Clean air, clean conscience, anyone?*

In the grand scheme of things, our study unveils a connection that has been lurking in the shadows, much like the lurking smog in an industrial city. The implications of our research transcend the atmospheric level, pointing to a potential avenue for crime prevention that is as straightforward as breathing in clean air. So, to wrap up this introduction with a joke befitting the occasion: What did the clean air say to the criminal? "You're under a fresh arrest!"


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Air quality and its potential impacts have been the subject of much research and discussion, akin to the act of breathing itself – often taken for granted until it becomes difficult. The effects of air pollution on physical health have been well-documented, but its potential influence on societal behaviors, specifically violent crime rates, has received less attention. However, our study aims to fill this gap by investigating the association between air pollution levels and violent crime rates in Lansing, Michigan.
It's no secret that air pollution can be a real breath-taker, but could it also be a crime sparker? *Badum tss.* This question led us to pore over decades of data, hoping to uncover any untold tales hidden within the hazy mist of statistical analysis. Our findings, like a gust of fresh air, stand to shed new light on the interconnectedness of environmental and societal well-being.
Lansing, Michigan, serves as our stage – a city known for its industrious spirit and vibrant community. Yet, beneath the surface lies a potential correlation between levels of air pollutants and instances of violent crime. So, just for the record, it's not all sunshine and roses in the capital of the Wolverine State.
As we delved into the data, we were struck by the starkness of our correlation coefficient – 0.6651267, to be precise. In layman's terms, this suggests a strong relationship between air pollution and violent crime rates, holding p < 0.01, which is not just a statistical fluke – it's a bona fide finding that demands attention. Our results are nothing to sneeze at, indicating that there is indeed something more than mere coincidence in the air.
While it's tempting to jump to conclusions and assume that cleaner air equates to crime reduction, we treaded cautiously, knowing that correlation does not necessarily imply causation. Yet, it's hard to deny the allure of the idea that improving air quality could be a breath of fresh air for tackling crime rates. *Clean air, clean conscience, anyone?*
In the grand scheme of things, our study unveils a connection that has been lurking in the shadows, much like the lurking smog in an industrial city. The implications of our research transcend the atmospheric level, pointing to a potential avenue for crime prevention that is as straightforward as breathing in clean air. So, to wrap up this introduction with a joke befitting the occasion: What did the clean air say to the criminal? "You're under a fresh arrest!"

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we embarked on our quest to unravel the relationship between air pollution and violent crime rates, we found ourselves wading through a fog of literature that addressed the intricacies of environmental factors and their impact on societal behavior. In "The Impact of Air Pollution on Health," Smith and Doe underscore the detrimental effects of air pollution on physical health, serving as a foundational backdrop for our investigation. *Looks like bad air isn't just a breath of fresh air.*

Furthermore, Jones, in "Pollution and Its Socioeconomic Impacts," delves into the intricate web of environmental and socioeconomic factors, shedding light on the interplay between pollution and societal well-being. These works set the stage for our exploration, prompting us to don our metaphorical detective hats and sniff out the potential link between air quality and violent crime rates. *Who knew we'd be air-ogant enough to take on both crime and pollution?*

Turning to non-fiction literature, "The End of Nature" by Bill McKibben and "The Omnivore's Dilemma" by Michael Pollan venture into the broader implications of environmental degradation, hinting at the sprawling ramifications of polluted air on human behaviors. *It's not just the trees and climate suffering, but maybe also our criminal tendencies?*

In the realm of fiction, works like "Fahrenheit 451" by Ray Bradbury and "Neuromancer" by William Gibson, while exploring vastly different themes, evoke dystopian settings influenced by environmental deterioration, prompting us to ponder the potential consequences of air pollution on behavioral patterns within societies. *A world without clean air and full of crime? Sounds like a breathless plot twist.*

Further expanding our sources beyond the traditional, we perused assorted receipts from CVS, hoping to capture snippets of wisdom hidden within the mundane purchases of everyday life. Alas, while the ink may have faded on these receipts, our spirits remained undampened in our pursuit of knowledge. *The lengths we'll go to for research – even if it means decoding grocery lists.*

In our pursuit of understanding, we couldn't help but inhale the wisdom present in unexpected places, reinforcing the notion that there's always something to be learned, even in places where the air is, shall we say, rather thin. *The air may be hazy, but our findings are crystal clear – there's more to air pollution than meets the eye.*


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

[[INTRODUCTION]]
Air quality and its potential impacts have been the subject of much research and discussion, akin to the act of breathing itself – often taken for granted until it becomes difficult. The effects of air pollution on physical health have been well-documented, but its potential influence on societal behaviors, specifically violent crime rates, has received less attention. However, our study aims to fill this gap by investigating the association between air pollution levels and violent crime rates in Lansing, Michigan.
It's no secret that air pollution can be a real breath-taker, but could it also be a crime sparker? *Badum tss.* This question led us to pore over decades of data, hoping to uncover any untold tales hidden within the hazy mist of statistical analysis. Our findings, like a gust of fresh air, stand to shed new light on the interconnectedness of environmental and societal well-being.
Lansing, Michigan, serves as our stage – a city known for its industrious spirit and vibrant community. Yet, beneath the surface lies a potential correlation between levels of air pollutants and instances of violent crime. So, just for the record, it's not all sunshine and roses in the capital of the Wolverine State.
As we delved into the data, we were struck by the starkness of our correlation coefficient – 0.6651267, to be precise. In layman's terms, this suggests a strong relationship between air pollution and violent crime rates, holding p < 0.01, which is not just a statistical fluke – it's a bona fide finding that demands attention. Our results are nothing to sneeze at, indicating that there is indeed something more than mere coincidence in the air.
While it's tempting to jump to conclusions and assume that cleaner air equates to crime reduction, we treaded cautiously, knowing that correlation does not necessarily imply causation. Yet, it's hard to deny the allure of the idea that improving air quality could be a breath of fresh air for tackling crime rates. *Clean air, clean conscience, anyone?*
In the grand scheme of things, our study unveils a connection that has been lurking in the shadows, much like the lurking smog in an industrial city. The implications of our research transcend the atmospheric level, pointing to a potential avenue for crime prevention that is as straightforward as breathing in clean air. So, to wrap up this introduction with a joke befitting the occasion: What did the clean air say to the criminal? "You're under a fresh arrest!"

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To dissect the potential relationship between air pollution and violent crime rates in Lansing, Michigan, we adopted a multi-faceted approach that would make even the most intricate jigsaw puzzle blush. First, we gathered air quality data from the Environmental Protection Agency, from various monitoring sites throughout Lansing, spanning the years from 1985 to 2022. This data included levels of pollutants such as ozone, particulate matter, carbon monoxide, nitrogen dioxide, and sulfur dioxide. We then put our heads together, or rather, our noses to the grindstone, to ensure the accuracy and reliability of the air quality data. Our dedication to precision was nothing to sneeze at, believe me.

Simultaneously, we obtained information on violent crime rates from the FBI's Uniform Crime Reporting (UCR) Program via the Criminal Justice Information Services Division. This encompassed reported incidents of murder, non-negligent manslaughter, rape, robbery, and aggravated assault from local law enforcement agencies in Lansing over the same time period. We double-checked the crime data, just to be sure there wasn't anything fishy in the data that might have escaped our notice. We certainly didn't want any criminal discrepancies to slip through the cracks.

In order to breathe new life into the data and uncover any hidden connections, we meticulously correlated the air quality metrics with violent crime rates. We relied on advanced statistical techniques, including regression analysis and time-series modeling, to provide a robust framework for our investigation. This methodology allowed us to tease out any potential associations between air pollution and violent crime, steering clear of any statistical pitfalls that might have left us gasping for air.

Furthermore, we took a cue from Sherlock Holmes and carefully considered potential confounding variables, such as demographic factors, economic conditions, and population density, to ensure that our findings didn't run the risk of being overshadowed by lurking covariates. We also conducted sensitivity analyses to gauge the stability of our results, ensuring that our conclusions were as steady as a rock in the face of potential turbulence. After all, we didn't want to leave any stone unturned in our pursuit of research excellence.

To provide a comprehensive analysis of the data, we employed both temporal and spatial analyses, examining not only the trends over time but also variations across different geographical locations within Lansing. This approach allowed us to peel back the layers of complexity and gain a nuanced understanding of how air pollution might intertwine with violent crime at different points in time and across various neighborhoods. In the end, our research methodology was as intricate as a spider's web, but without the entrapment - unless you count ensnaring noteworthy findings!

Overall, our methodology was aimed at airring out any potential biases and ensuring that our conclusions were based on sound, methodologically-sound analyses: the kind that would leave no room for doubt – a breath of fresh air in the world of scientific inquiry, you could say.


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1985 to 2022, you found a correlation 0.6651267, r-squared of 0.4423935, 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]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Air quality and its potential impacts have been the subject of much research and discussion, akin to the act of breathing itself – often taken for granted until it becomes difficult. The effects of air pollution on physical health have been well-documented, but its potential influence on societal behaviors, specifically violent crime rates, has received less attention. However, our study aims to fill this gap by investigating the association between air pollution levels and violent crime rates in Lansing, Michigan.
It's no secret that air pollution can be a real breath-taker, but could it also be a crime sparker? *Badum tss.* This question led us to pore over decades of data, hoping to uncover any untold tales hidden within the hazy mist of statistical analysis. Our findings, like a gust of fresh air, stand to shed new light on the interconnectedness of environmental and societal well-being.
Lansing, Michigan, serves as our stage – a city known for its industrious spirit and vibrant community. Yet, beneath the surface lies a potential correlation between levels of air pollutants and instances of violent crime. So, just for the record, it's not all sunshine and roses in the capital of the Wolverine State.
As we delved into the data, we were struck by the starkness of our correlation coefficient – 0.6651267, to be precise. In layman's terms, this suggests a strong relationship between air pollution and violent crime rates, holding p < 0.01, which is not just a statistical fluke – it's a bona fide finding that demands attention. Our results are nothing to sneeze at, indicating that there is indeed something more than mere coincidence in the air.
While it's tempting to jump to conclusions and assume that cleaner air equates to crime reduction, we treaded cautiously, knowing that correlation does not necessarily imply causation. Yet, it's hard to deny the allure of the idea that improving air quality could be a breath of fresh air for tackling crime rates. *Clean air, clean conscience, anyone?*
In the grand scheme of things, our study unveils a connection that has been lurking in the shadows, much like the lurking smog in an industrial city. The implications of our research transcend the atmospheric level, pointing to a potential avenue for crime prevention that is as straightforward as breathing in clean air. So, to wrap up this introduction with a joke befitting the occasion: What did the clean air say to the criminal? "You're under a fresh arrest!"

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation into the relationship between air pollution levels and violent crime rates in Lansing, Michigan from 1985 to 2022 left us breathless. The correlation coefficient of 0.6651267 revealed a strong positive association between the two variables, with an r-squared value of 0.4423935 that accounted for a substantial portion of the variance. The p-value of less than 0.01 indicated that this relationship was unlikely to be due to mere chance, as rare as a blue moon on a clear night.

Fig. 1 displays a striking scatterplot that visually captures the robust correlation we uncovered, much like catching a whiff of the aroma of a homemade apple pie. *But beware – this correlation is no pie in the sky!*

Our findings provide compelling evidence that air pollution has a tangible impact on violent crime rates in Lansing, Michigan. It seems that the connection between noxious fumes and unseemly behaviors may not just be up in the air after all. *Talk about a gasp-worthy revelation!*

By adjusting for various confounding factors such as socioeconomic conditions and population density, we ensured that our results didn't dissipate into thin air like a puff of smoke. These efforts bolster the notion that the relationship we've unveiled is as sturdy as a well-built house – a breath-taking finding, indeed.

In conclusion, our research uncovers a significant correlation between air pollution levels and violent crime rates in Lansing, Michigan. This unexpected relationship between atmospheric quality and human behavior breathes new life into the discourse surrounding crime prevention strategies. *Looks like freshening up the air might just freshen up the city's crime rates, too!*


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

[[LITERATURE REVIEW]]
As we embarked on our quest to unravel the relationship between air pollution and violent crime rates, we found ourselves wading through a fog of literature that addressed the intricacies of environmental factors and their impact on societal behavior. In "The Impact of Air Pollution on Health," Smith and Doe underscore the detrimental effects of air pollution on physical health, serving as a foundational backdrop for our investigation. *Looks like bad air isn't just a breath of fresh air.*
Furthermore, Jones, in "Pollution and Its Socioeconomic Impacts," delves into the intricate web of environmental and socioeconomic factors, shedding light on the interplay between pollution and societal well-being. These works set the stage for our exploration, prompting us to don our metaphorical detective hats and sniff out the potential link between air quality and violent crime rates. *Who knew we'd be air-ogant enough to take on both crime and pollution?*
Turning to non-fiction literature, "The End of Nature" by Bill McKibben and "The Omnivore's Dilemma" by Michael Pollan venture into the broader implications of environmental degradation, hinting at the sprawling ramifications of polluted air on human behaviors. *It's not just the trees and climate suffering, but maybe also our criminal tendencies?*
In the realm of fiction, works like "Fahrenheit 451" by Ray Bradbury and "Neuromancer" by William Gibson, while exploring vastly different themes, evoke dystopian settings influenced by environmental deterioration, prompting us to ponder the potential consequences of air pollution on behavioral patterns within societies. *A world without clean air and full of crime? Sounds like a breathless plot twist.*
Further expanding our sources beyond the traditional, we perused assorted receipts from CVS, hoping to capture snippets of wisdom hidden within the mundane purchases of everyday life. Alas, while the ink may have faded on these receipts, our spirits remained undampened in our pursuit of knowledge. *The lengths we'll go to for research – even if it means decoding grocery lists.*
In our pursuit of understanding, we couldn't help but inhale the wisdom present in unexpected places, reinforcing the notion that there's always something to be learned, even in places where the air is, shall we say, rather thin. *The air may be hazy, but our findings are crystal clear – there's more to air pollution than meets the eye.*

[[RESULTS]]
The results of our investigation into the relationship between air pollution levels and violent crime rates in Lansing, Michigan from 1985 to 2022 left us breathless. The correlation coefficient of 0.6651267 revealed a strong positive association between the two variables, with an r-squared value of 0.4423935 that accounted for a substantial portion of the variance. The p-value of less than 0.01 indicated that this relationship was unlikely to be due to mere chance, as rare as a blue moon on a clear night.
Fig. 1 displays a striking scatterplot that visually captures the robust correlation we uncovered, much like catching a whiff of the aroma of a homemade apple pie. *But beware – this correlation is no pie in the sky!*
Our findings provide compelling evidence that air pollution has a tangible impact on violent crime rates in Lansing, Michigan. It seems that the connection between noxious fumes and unseemly behaviors may not just be up in the air after all. *Talk about a gasp-worthy revelation!*
By adjusting for various confounding factors such as socioeconomic conditions and population density, we ensured that our results didn't dissipate into thin air like a puff of smoke. These efforts bolster the notion that the relationship we've unveiled is as sturdy as a well-built house – a breath-taking finding, indeed.
In conclusion, our research uncovers a significant correlation between air pollution levels and violent crime rates in Lansing, Michigan. This unexpected relationship between atmospheric quality and human behavior breathes new life into the discourse surrounding crime prevention strategies. *Looks like freshening up the air might just freshen up the city's crime rates, too!*

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study provide further support for previous research indicating a robust association between air pollution levels and violent crime rates. Our findings echo the sentiments expressed in Smith and Doe's work on the detrimental effects of air pollution on physical health, as well as Jones' exploration of the complex interplay between pollution and societal well-being. It appears that our study is not just blowing hot air but rather building upon a solid foundation of existing knowledge. *Who knew that the air in Lansing could turn out to be such a crime partner?*

Moreover, our results align with the broader implications of environmental degradation as hinted at in "The End of Nature" by Bill McKibben and "The Omnivore's Dilemma" by Michael Pollan, shedding light on the potential influence of polluted air on human behaviors. It seems that the impact of air pollution extends beyond mere health concerns and spills over into the realm of societal conduct. *Looks like the air in Lansing might be breathing life into criminal activities!*

Our discovery of a substantial correlation between air pollution levels and violent crime rates also provides a tangible link between fiction and reality, reminiscent of dystopian settings as portrayed in "Fahrenheit 451" by Ray Bradbury and "Neuromancer" by William Gibson. It appears that the notion of air pollution affecting behavioral patterns within societies is not merely a fanciful literary trope but rather a plausible reality. *Who'd have thought that the air in Lansing could serve as the inspiration for a dystopian crime novel?*

While our investigation did not yield any groundbreaking revelations from our perusal of assorted receipts from CVS, it's clear that our findings have expanded the understanding of the potential impact of air pollution on societal behaviors, reinforcing the notion that knowledge can be gleaned from unexpected sources. Our study serves as a testament to the notion that there's always a whiff of truth to be found in the most unlikely of places – even in the aisles of a pharmacy. *They say crime doesn't pay, but who knew that receipts could still hold valuable insights?*

In sum, our study contributes to a growing body of evidence supporting the notion that air quality exerts a significant influence on violent crime rates. Our findings not only emphasize the need for stringent air quality regulations but also suggest that a breath of fresh air might just be the key to reducing criminal activities in urban areas. *It appears that the fight against crime may need a little less hot air and a lot more fresh breeze!*


Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Lansing, Michigan and Violent crime rates. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan"

[[ABSTRACT]]
In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.

But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.

To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

[[INTRDUCTION]]
Air quality and its potential impacts have been the subject of much research and discussion, akin to the act of breathing itself – often taken for granted until it becomes difficult. The effects of air pollution on physical health have been well-documented, but its potential influence on societal behaviors, specifically violent crime rates, has received less attention. However, our study aims to fill this gap by investigating the association between air pollution levels and violent crime rates in Lansing, Michigan.
It's no secret that air pollution can be a real breath-taker, but could it also be a crime sparker? *Badum tss.* This question led us to pore over decades of data, hoping to uncover any untold tales hidden within the hazy mist of statistical analysis. Our findings, like a gust of fresh air, stand to shed new light on the interconnectedness of environmental and societal well-being.
Lansing, Michigan, serves as our stage – a city known for its industrious spirit and vibrant community. Yet, beneath the surface lies a potential correlation between levels of air pollutants and instances of violent crime. So, just for the record, it's not all sunshine and roses in the capital of the Wolverine State.
As we delved into the data, we were struck by the starkness of our correlation coefficient – 0.6651267, to be precise. In layman's terms, this suggests a strong relationship between air pollution and violent crime rates, holding p < 0.01, which is not just a statistical fluke – it's a bona fide finding that demands attention. Our results are nothing to sneeze at, indicating that there is indeed something more than mere coincidence in the air.
While it's tempting to jump to conclusions and assume that cleaner air equates to crime reduction, we treaded cautiously, knowing that correlation does not necessarily imply causation. Yet, it's hard to deny the allure of the idea that improving air quality could be a breath of fresh air for tackling crime rates. *Clean air, clean conscience, anyone?*
In the grand scheme of things, our study unveils a connection that has been lurking in the shadows, much like the lurking smog in an industrial city. The implications of our research transcend the atmospheric level, pointing to a potential avenue for crime prevention that is as straightforward as breathing in clean air. So, to wrap up this introduction with a joke befitting the occasion: What did the clean air say to the criminal? "You're under a fresh arrest!"

[[RESULTS]]
The results of our investigation into the relationship between air pollution levels and violent crime rates in Lansing, Michigan from 1985 to 2022 left us breathless. The correlation coefficient of 0.6651267 revealed a strong positive association between the two variables, with an r-squared value of 0.4423935 that accounted for a substantial portion of the variance. The p-value of less than 0.01 indicated that this relationship was unlikely to be due to mere chance, as rare as a blue moon on a clear night.
Fig. 1 displays a striking scatterplot that visually captures the robust correlation we uncovered, much like catching a whiff of the aroma of a homemade apple pie. *But beware – this correlation is no pie in the sky!*
Our findings provide compelling evidence that air pollution has a tangible impact on violent crime rates in Lansing, Michigan. It seems that the connection between noxious fumes and unseemly behaviors may not just be up in the air after all. *Talk about a gasp-worthy revelation!*
By adjusting for various confounding factors such as socioeconomic conditions and population density, we ensured that our results didn't dissipate into thin air like a puff of smoke. These efforts bolster the notion that the relationship we've unveiled is as sturdy as a well-built house – a breath-taking finding, indeed.
In conclusion, our research uncovers a significant correlation between air pollution levels and violent crime rates in Lansing, Michigan. This unexpected relationship between atmospheric quality and human behavior breathes new life into the discourse surrounding crime prevention strategies. *Looks like freshening up the air might just freshen up the city's crime rates, too!*

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study illuminates the interplay between air pollution and violent crime rates in Lansing, Michigan, revealing a robust correlation that demands attention. Our findings not only add depth to the discourse on the societal impacts of environmental quality but also hint at intriguing possibilities for crime prevention strategies. It seems that the invisible hand of air pollution may be more tangible in shaping human behavior than previously assumed. *Who would've thought that the air we breathe could have such a stirring effect on crime rates – talk about a breath-taking revelation!*

By carefully considering and controlling for confounding variables, we've ensured that our results aren't just a fleeting puff of statistical significance. This research may serve as a breath of fresh air for policymakers and urban planners, offering a new perspective on the factors that influence community safety and well-being. *You could say our findings are nothing to sneeze at!*

However, while our findings point to an undeniable correlation, it's essential to remember that correlation doesn't imply causation. So, we must approach these results with cautious optimism, like taking a deep breath in an unfamiliar environment. And speaking of breath, I recently read a study about air pollution – it took my breath away!

In light of our findings, it's clear that further research into the mechanisms underlying the relationship between air pollution and violent crime is warranted. Yet, for now, we can confidently assert that our investigation has provided substantial evidence of a connection between air quality and violent crime rates in Lansing, Michigan. *You could even say it's a slam-dunk case!* Therefore, it's safe to say that no further research is needed in this area. *Let's give this topic some room to breathe.*




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 Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Environmental Psychology


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 Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Environmental Anthropology and Urban 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 Breath of the Wild: Unearthing the Impact of Air Pollution on Violent Crime Rates in Lansing, Michigan with an abstract of In this study, we turn our attention to the air quality in Lansing, Michigan and its potential impact on violent crime rates, but not before taking a breath and diving headfirst into the data. With our noses in the books – and occasionally out of joint due to the less-than-pleasant aroma of statistical analysis – we examined the relationship between air pollution levels and violent crime rates from 1985 to 2022. Our findings reveal a correlation coefficient that might just take your breath away at 0.6651267, with a p < 0.01, suggesting that there's more than just hot air when it comes to the link between air pollution and violent crime.
But hold your noses! Before jumping to conclusions, we were keenly aware that correlation does not always imply causation. We accounted for various confounding variables, such as socioeconomic factors and population density, to ensure that our findings didn't just float away like a gasp in the wind. Our results are a breath of fresh air in the field, shedding light on a pressing issue that's been overlooked in the past. So, in the end, it looks like the air quality in Lansing may very well have a tangible impact on the city's violent crime rates.
To wrap up this "air"resistible research, as we unraveled the tangled web of statistical analysis, it became clear that improving air quality might just be a breath of fresh air for reducing violent crime in Lansing. After all, who knew that cleaning up the air could also freshen up the crime rates? It seems that in the battle against crime, cleaner air could very well be a breath-taking ally.

ChatGPT:

air quality, air pollution, violent crime rates, Lansing Michigan, correlation coefficient, socioeconomic factors, population density, statistical analysis, causation, environmental impact, crime prevention, pollution control

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

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 = 0.6651267 (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 = 0.4423935 (Coefficient of determination)
This means 44.2% 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 Lansing, Michigan) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.2E-6. 0.0000052281661200643820000000
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 0.67 in 0.00052% of random cases. Said differently, if you correlated 191,272 random variables You don't actually need 191 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.

[ 0.44, 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 Lansing, Michigan (Bad air quality days)0.3968255.263168.1784416.38668.407087.9439314.01877.103834.371585.464488.743178.743175.4644815.30059.6153945.705719.958516.611571.2511.11112.892565.857741.229510.4115230.3289470.8241763.878120.2762430.2739730.5494511.9125701.0958900.27322400
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([0.396825,5.26316,8.17844,16.3866,8.40708,7.94393,14.0187,7.10383,4.37158,5.46448,8.74317,8.74317,5.46448,15.3005,9.61539,4,5.70571,9.95851,6.61157,1.25,11.1111,2.89256,5.85774,1.22951,0.411523,0.328947,0.824176,3.87812,0.276243,0.273973,0.549451,1.91257,0,1.09589,0,0.273224,0,0,])
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 Lansing, Michigan"
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?

I'm genuinely thankful for your rating!


Correlation ID: 2912 · Black Variable ID: 20801 · Red Variable ID: 20220
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0