Spurious correlation #3,468 · 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. Marys, Pennsylvania and the second variable is Motor vehicle thefts in Pennsylvania. The chart goes from 1990 to 2022, and the two variables track closely in value over that time.

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. Marys, Pennsylvania and the second variable is Motor vehicle thefts in Pennsylvania. The chart goes from 1990 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As air quality improved in St. Marys, Pennsylvania, residents experienced an unexpected boost in energy and clarity of thought. This led to a wave of amateur detective work as people could finally think clearly enough to track down and retrieve their stolen vehicles. With their newfound focus and determination, the community banded together to combat the ongoing issue of car theft, ultimately leading to a decrease in motor vehicle thefts across the state. Who knew that the key to solving car thefts lay not in fancy security systems, but in the simple clarity of clean, crisp air!

^{Show image generation prompt} Model: dalle-3
Prompt: [Concept art] Create an image of St. Marys, Pennsylvania, with beautiful, towering mountains in the background. The scene should be serene, with a clear, blue sky and fresh, clean air. Show a vigilant police officer standing in the foreground, overlooking the landscape. At a distance, a stolen vehicle should be partially obscured by lingering remnants of dissipating smog, giving the impression of the clear air aiding in its discovery. The overall atmosphere should evoke a sense of calm and clarity, with the focus on the contrast between the improved air quality and the swift resolution of the vehicle theft. 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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. 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: Steampunk High-tech Woodblock painting An image that looks like it is a scene from 'Star Wars' Concept art
ChatGPT: Concept art

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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania, in the following situation: Because with the decrease in air pollution, criminals found it harder to blend in with the smog, making it easier for law enforcement to spot stolen vehicles.. Keep the description simple.
ChatGPT: In St. Marys, Pennsylvania, the crisp, clean air carries a clear view of the picturesque mountains. As the air pollution decreases, a watchful police officer easily spots a stolen vehicle trying to disappear amongst the now-diminished smog, leading to a swift resolution.

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: [ Concept art ] and depicting this scene: In St. Marys, Pennsylvania, the crisp, clean air carries a clear view of the picturesque mountains. As the air pollution decreases, a watchful police officer easily spots a stolen vehicle trying to disappear amongst the now-diminished smog, leading to a swift resolution. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [Concept art] Create an image of St. Marys, Pennsylvania, with beautiful, towering mountains in the background. The scene should be serene, with a clear, blue sky and fresh, clean air. Show a vigilant police officer standing in the foreground, overlooking the landscape. At a distance, a stolen vehicle should be partially obscured by lingering remnants of dissipating smog, giving the impression of the clear air aiding in its discovery. The overall atmosphere should evoke a sense of calm and clarity, with the focus on the contrast between the improved air quality and the swift resolution of the vehicle theft.

*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.
^{Show prompt for explanation} 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. Marys, Pennsylvania caused Motor vehicle thefts in Pennsylvania to decrease.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys

The Journal of Ecological Criminology

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
"Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys"

[[ABSTRACT]]
The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.

Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
The nexus between environmental factors and societal trends has captivated the minds of scholars and policy-makers alike, prompting endeavors to untangle the web of connections between pollution and human behavior. Amidst the myriad ecological puzzles, the curious case of air pollution in St. Marys, Pennsylvania and its potential affiliation with motor vehicle thefts in the broader landscape of Pennsylvania beckons for closer scrutiny. As we embark on this scholarly expedition, we aim to shed light on the uncanny relationship between the quality of air in St. Marys and the vanishing presence of motor vehicles across Pennsylvania.
While the pursuit of interconnections between seemingly unrelated phenomena often yields surprising revelations, the prospect of air pollution influencing the predilections of car pilferers strikes a chord as particularly intriguing. Prior research has illuminated the far-reaching implications of environmental pollution on public health and economic landscapes, but the prospect of its insidious influence on criminal predilections opens a peculiar Pandora’s box of inquiry.
Drawing from the reservoir of data amassed by the Environmental Protection Agency and the FBI Criminal Justice Information Services, we endeavor to unravel the statistical threads that intertwine the ambient pollution levels in St. Marys with the ebb and flow of motor vehicle thefts. Our inquiry was steeped in the rigorous tenets of statistical analysis, yielding a correlation coefficient of 0.8855373 and p < 0.01 over the temporal expanse from 1990 to 2022. This staggering coefficient underscores a robust and startling association between the ethereal presence of air pollution in St. Marys and the tangible occurrence of motor vehicle thefts across Pennsylvania.
The ramifications of this brazen correlation resonate with implications that transcend the rote confines of statistical fascination, casting an inquisitive shadow on the intersection of environmental quality and propensities for property crimes. What mechanisms underpin this connection? Does the smog-laden air serve as a siren call for larcenous impulses, or is there an intricate ballet between atmospheric pollutants and criminal intent? While we diplomatically refrain from donning the garb of speculators, the implications of our findings beckon for an introspective appraisal of the whimsical ramifications of hazy skies on the impetus for automotive larceny.
In the annals of empirical inquiry, our study stakes a claim to a peculiar niche in the compendium of literature on air pollution. It beckons for an enigmatic consideration of the spillover effects of atmospheric malaise onto the behavioral inclinations of vehicular trespassers. As we embark on this expedition into the intriguing hinterlands of statistical analysis, we invite fellow scholars to partake in this whimsical expedition and unearth the peculiar nuances that underscore the correlation between air pollution and the enigma of the vanishing vehicles.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The correlation between air pollution and its impact on societal phenomena has been a subject of extensive scholarly exploration. Smith et al. (2015) expounded on the pervasive influence of air quality on public health, while Doe and Jones (2018) delved into the economic reverberations of environmental pollution. However, the idiosyncratic relationship between air pollution and motor vehicle thefts has thus far remained a curious enigma. In "Airborne Adversaries: The Grim Affair of Air Pollution and Crime" by Green, the authors delve into the potential connections between air quality and criminal activities, providing a foundation for our peculiar pursuit.

Turning to works of non-fiction, "Choked: Life and Breath in the Age of Air Pollution" by Beth Gardiner offers a comprehensive exposé of the insidious influence of air pollution on various facets of human existence, shedding light on the tentacular reach of atmospheric pollutants. On a less serious note, "The Air Affair: Mysteries of Atmospheric Mischief" by A. L. Foggy takes a whimsical dive into the quirky interactions between air quality and human behavior, blending scientific musings with a touch of levity.

In the realm of fiction, "The Smog Conspiracy" by R. E. Smogger spins a tale of intrigue and surreptitious plots set against the backdrop of a polluted metropolis, offering a fanciful exploration of the potential machinations brewing within hazy skies. In a similar vein, "Smokey and the Bandit" by Burnt Rubber introduces readers to a caper imbued with automotive shenanigans and a dash of environmental intrigue, albeit within a decidedly fictional landscape.

Furthermore, the researchers found themselves drawn to cinematic offerings that depict the thematic essence of air pollution and criminal capers. "Gone in 60 Seconds" and "The Italian Job" offered compelling visual narratives of grand larceny and vehicular escapades, intimating the potential influence of atmospheric vicissitudes on the art of motor vehicle theft.

As the researchers navigated through the labyrinthine corridors of literature, the interplay between air pollution and criminal predilections unveiled itself as a droll enigma, beckoning for a whimsical exploration. In the following sections, we shall delve into the empirical inquiries that have illuminated the curious connection between the atmospheric malaise in St. Marys, Pennsylvania and the enigmatic tendencies of vehicular trespassers.

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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and FBI Criminal Justice Information Services . You used data from 1990 to 2022

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys"

[[ABSTRACT]]
The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.

Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

[[INTRODUCTION]]
INTRODUCTION
The nexus between environmental factors and societal trends has captivated the minds of scholars and policy-makers alike, prompting endeavors to untangle the web of connections between pollution and human behavior. Amidst the myriad ecological puzzles, the curious case of air pollution in St. Marys, Pennsylvania and its potential affiliation with motor vehicle thefts in the broader landscape of Pennsylvania beckons for closer scrutiny. As we embark on this scholarly expedition, we aim to shed light on the uncanny relationship between the quality of air in St. Marys and the vanishing presence of motor vehicles across Pennsylvania.
While the pursuit of interconnections between seemingly unrelated phenomena often yields surprising revelations, the prospect of air pollution influencing the predilections of car pilferers strikes a chord as particularly intriguing. Prior research has illuminated the far-reaching implications of environmental pollution on public health and economic landscapes, but the prospect of its insidious influence on criminal predilections opens a peculiar Pandora’s box of inquiry.
Drawing from the reservoir of data amassed by the Environmental Protection Agency and the FBI Criminal Justice Information Services, we endeavor to unravel the statistical threads that intertwine the ambient pollution levels in St. Marys with the ebb and flow of motor vehicle thefts. Our inquiry was steeped in the rigorous tenets of statistical analysis, yielding a correlation coefficient of 0.8855373 and p < 0.01 over the temporal expanse from 1990 to 2022. This staggering coefficient underscores a robust and startling association between the ethereal presence of air pollution in St. Marys and the tangible occurrence of motor vehicle thefts across Pennsylvania.
The ramifications of this brazen correlation resonate with implications that transcend the rote confines of statistical fascination, casting an inquisitive shadow on the intersection of environmental quality and propensities for property crimes. What mechanisms underpin this connection? Does the smog-laden air serve as a siren call for larcenous impulses, or is there an intricate ballet between atmospheric pollutants and criminal intent? While we diplomatically refrain from donning the garb of speculators, the implications of our findings beckon for an introspective appraisal of the whimsical ramifications of hazy skies on the impetus for automotive larceny.
In the annals of empirical inquiry, our study stakes a claim to a peculiar niche in the compendium of literature on air pollution. It beckons for an enigmatic consideration of the spillover effects of atmospheric malaise onto the behavioral inclinations of vehicular trespassers. As we embark on this expedition into the intriguing hinterlands of statistical analysis, we invite fellow scholars to partake in this whimsical expedition and unearth the peculiar nuances that underscore the correlation between air pollution and the enigma of the vanishing vehicles.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between air pollution in St. Marys, Pennsylvania and the curious case of motor vehicle thefts in the Keystone State, our research team embarked on a methodological odyssey that combined rigorous statistical analysis with a touch of whimsical curiosity. The data underpinning this peculiar expedition were harvested from the venerable repositories of the Environmental Protection Agency and the FBI Criminal Justice Information Services, with temporal boundaries extending from 1990 to 2022.

We first sought to quantify the ethereal presence of air pollution in St. Marys, Pennsylvania, employing data on various atmospheric pollutants such as particulate matter, nitrogen dioxide, sulfur dioxide, and carbon monoxide. The medley of pollutant concentrations was gleaned from the Environmental Protection Agency's comprehensive database, capturing the ebb and flow of airborne contaminants over the designated temporal expanse. We then juxtaposed this atmospheric tapestry with the incidence of motor vehicle thefts across Pennsylvania, extracted from the FBI Criminal Justice Information Services, to ascertain the lurking correlations that may underpin this seemingly incongruous pairing.

Our statistical toolkit, finely honed through innumerable hours of caffeinated contemplation and spirited debates, included the revered Pearson correlation coefficient and its elusive comrade, the p-value. By subjecting the atmospheric malaise in St. Marys to the unblinking gaze of statistical scrutiny, we sought to discern the strength and significance of its association with the ebb and flow of motor vehicle thefts across Pennsylvania. The resultant correlation coefficient of 0.8855373, coupled with a p-value lower than 0.01, bore witness to the robust and resounding relationship between these seemingly disparate phenomena, lending an unexpected twist to the narrative of air pollution and illicit automotive escapades.

While the mystifying gap between air pollution and motor vehicle thefts compelled an introspective appraisal of the potential underlying mechanisms, our methodological voyage was regrettably bereft of a definitive elucidation of the causative pathways. Nevertheless, our methodological expedition stands as a testament to the interplay of scholarly intrigue and a touch of whimsy, as we ventured to unravel the enigmatic story of vanishing vehicles amidst the hazy environs of St. Marys, Pennsylvania.

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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

For the time period 1990 to 2022, you found a correlation 0.8855373, r-squared of 0.7841763, 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]]
"Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys"

[[ABSTRACT]]
The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.

Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
The nexus between environmental factors and societal trends has captivated the minds of scholars and policy-makers alike, prompting endeavors to untangle the web of connections between pollution and human behavior. Amidst the myriad ecological puzzles, the curious case of air pollution in St. Marys, Pennsylvania and its potential affiliation with motor vehicle thefts in the broader landscape of Pennsylvania beckons for closer scrutiny. As we embark on this scholarly expedition, we aim to shed light on the uncanny relationship between the quality of air in St. Marys and the vanishing presence of motor vehicles across Pennsylvania.
While the pursuit of interconnections between seemingly unrelated phenomena often yields surprising revelations, the prospect of air pollution influencing the predilections of car pilferers strikes a chord as particularly intriguing. Prior research has illuminated the far-reaching implications of environmental pollution on public health and economic landscapes, but the prospect of its insidious influence on criminal predilections opens a peculiar Pandora’s box of inquiry.
Drawing from the reservoir of data amassed by the Environmental Protection Agency and the FBI Criminal Justice Information Services, we endeavor to unravel the statistical threads that intertwine the ambient pollution levels in St. Marys with the ebb and flow of motor vehicle thefts. Our inquiry was steeped in the rigorous tenets of statistical analysis, yielding a correlation coefficient of 0.8855373 and p < 0.01 over the temporal expanse from 1990 to 2022. This staggering coefficient underscores a robust and startling association between the ethereal presence of air pollution in St. Marys and the tangible occurrence of motor vehicle thefts across Pennsylvania.
The ramifications of this brazen correlation resonate with implications that transcend the rote confines of statistical fascination, casting an inquisitive shadow on the intersection of environmental quality and propensities for property crimes. What mechanisms underpin this connection? Does the smog-laden air serve as a siren call for larcenous impulses, or is there an intricate ballet between atmospheric pollutants and criminal intent? While we diplomatically refrain from donning the garb of speculators, the implications of our findings beckon for an introspective appraisal of the whimsical ramifications of hazy skies on the impetus for automotive larceny.
In the annals of empirical inquiry, our study stakes a claim to a peculiar niche in the compendium of literature on air pollution. It beckons for an enigmatic consideration of the spillover effects of atmospheric malaise onto the behavioral inclinations of vehicular trespassers. As we embark on this expedition into the intriguing hinterlands of statistical analysis, we invite fellow scholars to partake in this whimsical expedition and unearth the peculiar nuances that underscore the correlation between air pollution and the enigma of the vanishing vehicles.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data revealed a striking correlation between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across Pennsylvania. The correlation coefficient of 0.8855373 and the r-squared of 0.7841763 suggested a remarkably strong relationship between these two seemingly disparate phenomena. Furthermore, the p-value of less than 0.01 indicated the statistical significance of this connection, which certainly made us sit up and take notice; after all, it's not every day that you expect to find a link between smog and stolen cars.

Figure 1 depicts the scatterplot illustrating this robust correlation, showcasing the clear trend of increasing motor vehicle thefts coinciding with elevated levels of air pollution in St. Marys. Look at those points; they practically tell a story, don't they? A tale of murky skies and miscreant maneuvers, if you will.

The implications of this correlation extend beyond the sterile domain of statistical associations, beckoning for a deeper contemplation of the whimsical interplay between environmental quality and criminal predilections. While we resist the temptation to embark on flights of fancy about the precise mechanisms underpinning this correlation, it's difficult not to wonder just what it is about polluted air that might tempt the thieving fingers of car bandits. Could it be the haze itself that serves as a cloak for nefarious activities? Or perhaps there's a more subtle dance at work here, a clandestine waltz between atmospheric pollutants and criminal intent that would make even the most experienced sleuth scratch their head in bewilderment.

In any case, our findings offer a curious twist to the existing literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the proclivities for automotive larceny. It's as if the very air in St. Marys is whispering secrets to the car thieves, coaxing them into action with promises of concealment amidst the haze. Quite the enigmatic tale, isn't it?

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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys"

[[ABSTRACT]]
The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.

Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

[[LITERATURE REVIEW]]
The correlation between air pollution and its impact on societal phenomena has been a subject of extensive scholarly exploration. Smith et al. (2015) expounded on the pervasive influence of air quality on public health, while Doe and Jones (2018) delved into the economic reverberations of environmental pollution. However, the idiosyncratic relationship between air pollution and motor vehicle thefts has thus far remained a curious enigma. In "Airborne Adversaries: The Grim Affair of Air Pollution and Crime" by Green, the authors delve into the potential connections between air quality and criminal activities, providing a foundation for our peculiar pursuit.
Turning to works of non-fiction, "Choked: Life and Breath in the Age of Air Pollution" by Beth Gardiner offers a comprehensive exposé of the insidious influence of air pollution on various facets of human existence, shedding light on the tentacular reach of atmospheric pollutants. On a less serious note, "The Air Affair: Mysteries of Atmospheric Mischief" by A. L. Foggy takes a whimsical dive into the quirky interactions between air quality and human behavior, blending scientific musings with a touch of levity.
In the realm of fiction, "The Smog Conspiracy" by R. E. Smogger spins a tale of intrigue and surreptitious plots set against the backdrop of a polluted metropolis, offering a fanciful exploration of the potential machinations brewing within hazy skies. In a similar vein, "Smokey and the Bandit" by Burnt Rubber introduces readers to a caper imbued with automotive shenanigans and a dash of environmental intrigue, albeit within a decidedly fictional landscape.
Furthermore, the researchers found themselves drawn to cinematic offerings that depict the thematic essence of air pollution and criminal capers. "Gone in 60 Seconds" and "The Italian Job" offered compelling visual narratives of grand larceny and vehicular escapades, intimating the potential influence of atmospheric vicissitudes on the art of motor vehicle theft.
As the researchers navigated through the labyrinthine corridors of literature, the interplay between air pollution and criminal predilections unveiled itself as a droll enigma, beckoning for a whimsical exploration. In the following sections, we shall delve into the empirical inquiries that have illuminated the curious connection between the atmospheric malaise in St. Marys, Pennsylvania and the enigmatic tendencies of vehicular trespassers.

[[RESULTS]]
The analysis of the data revealed a striking correlation between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across Pennsylvania. The correlation coefficient of 0.8855373 and the r-squared of 0.7841763 suggested a remarkably strong relationship between these two seemingly disparate phenomena. Furthermore, the p-value of less than 0.01 indicated the statistical significance of this connection, which certainly made us sit up and take notice; after all, it's not every day that you expect to find a link between smog and stolen cars.
Figure 1 depicts the scatterplot illustrating this robust correlation, showcasing the clear trend of increasing motor vehicle thefts coinciding with elevated levels of air pollution in St. Marys. Look at those points; they practically tell a story, don't they? A tale of murky skies and miscreant maneuvers, if you will.
The implications of this correlation extend beyond the sterile domain of statistical associations, beckoning for a deeper contemplation of the whimsical interplay between environmental quality and criminal predilections. While we resist the temptation to embark on flights of fancy about the precise mechanisms underpinning this correlation, it's difficult not to wonder just what it is about polluted air that might tempt the thieving fingers of car bandits. Could it be the haze itself that serves as a cloak for nefarious activities? Or perhaps there's a more subtle dance at work here, a clandestine waltz between atmospheric pollutants and criminal intent that would make even the most experienced sleuth scratch their head in bewilderment.
In any case, our findings offer a curious twist to the existing literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the proclivities for automotive larceny. It's as if the very air in St. Marys is whispering secrets to the car thieves, coaxing them into action with promises of concealment amidst the haze. Quite the enigmatic tale, isn't it?

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study have unearthed a rather unexpected, yet remarkably robust association between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across Pennsylvania. Our findings not only corroborate the works of Smith et al. and Doe and Jones on the profound impact of air quality on societal phenomena, but they also provide a quirky twist to the literature, in line with the thematic essence celebrated by A. L. Foggy and R. E. Smogger. We find ourselves pondering, much like the author A. L. Foggy, the potential musings and mischievous whispers that pervade the polluted air.

Our statistical analyses have lent support to the notion that the atmosphere in St. Marys may indeed harbor enigmatic secrets that beckon to the miscreant maneuverings of car thieves across the state. The remarkably strong correlation coefficient we uncovered certainly adds a curious twist to the existing body of research, evoking a whimsical consideration of the implications of hazy skies on the proclivities for automotive mischief. Perhaps there is, as R. E. Smogger fancifully spins in "The Smog Conspiracy," a clandestine waltz between atmospheric pollutants and criminal intent, a dance of evanescent allure that we are only beginning to decipher.

While we refrain from speculating on the precise mechanisms underpinning this correlation, the results of our study invite a playful exploration of the potential influence of atmospheric malaise on the behaviors of vehicle thieves. One cannot help but ponder whether the very air in St. Marys is whispering secrets to the car thieves, coaxing them into action with promises of concealment amidst the haze. As Beth Gardiner's sobering exposé "Choked" reminds us, the insidious influence of air pollution extends far beyond the realms of public health and environmental concern, intertwining with the intricate fabric of societal dynamics in ways that captivate the scholarly mind.

In essence, our study adds a quirky chapter to the evolving narrative of the influence of air pollution on societal phenomena. Much like a caper imbued with both intrigue and levity, our findings beckon for a whimsical contemplation of the potential theatrics playing out amidst the hazy skies of St. Marys. The scientific musings inspired by our research carry with them a touch of the unexpected, inviting scholars and enthusiasts alike to delve into the whimsical enigma of the interplay between atmospheric pollutants and criminal predilections. After all, in the intricate dance of research and discovery, who's to say that a touch of whimsy isn't the key to unraveling the mysteries hidden within the haze?

(Feel free to insert a statement about whether the results are in line with or contradict existing research, depending on the actual findings of the study)

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. Marys, Pennsylvania and Motor vehicle thefts in Pennsylvania. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys"

[[ABSTRACT]]
The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.

Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

[[INTRDUCTION]]
INTRODUCTION
The nexus between environmental factors and societal trends has captivated the minds of scholars and policy-makers alike, prompting endeavors to untangle the web of connections between pollution and human behavior. Amidst the myriad ecological puzzles, the curious case of air pollution in St. Marys, Pennsylvania and its potential affiliation with motor vehicle thefts in the broader landscape of Pennsylvania beckons for closer scrutiny. As we embark on this scholarly expedition, we aim to shed light on the uncanny relationship between the quality of air in St. Marys and the vanishing presence of motor vehicles across Pennsylvania.
While the pursuit of interconnections between seemingly unrelated phenomena often yields surprising revelations, the prospect of air pollution influencing the predilections of car pilferers strikes a chord as particularly intriguing. Prior research has illuminated the far-reaching implications of environmental pollution on public health and economic landscapes, but the prospect of its insidious influence on criminal predilections opens a peculiar Pandora’s box of inquiry.
Drawing from the reservoir of data amassed by the Environmental Protection Agency and the FBI Criminal Justice Information Services, we endeavor to unravel the statistical threads that intertwine the ambient pollution levels in St. Marys with the ebb and flow of motor vehicle thefts. Our inquiry was steeped in the rigorous tenets of statistical analysis, yielding a correlation coefficient of 0.8855373 and p < 0.01 over the temporal expanse from 1990 to 2022. This staggering coefficient underscores a robust and startling association between the ethereal presence of air pollution in St. Marys and the tangible occurrence of motor vehicle thefts across Pennsylvania.
The ramifications of this brazen correlation resonate with implications that transcend the rote confines of statistical fascination, casting an inquisitive shadow on the intersection of environmental quality and propensities for property crimes. What mechanisms underpin this connection? Does the smog-laden air serve as a siren call for larcenous impulses, or is there an intricate ballet between atmospheric pollutants and criminal intent? While we diplomatically refrain from donning the garb of speculators, the implications of our findings beckon for an introspective appraisal of the whimsical ramifications of hazy skies on the impetus for automotive larceny.
In the annals of empirical inquiry, our study stakes a claim to a peculiar niche in the compendium of literature on air pollution. It beckons for an enigmatic consideration of the spillover effects of atmospheric malaise onto the behavioral inclinations of vehicular trespassers. As we embark on this expedition into the intriguing hinterlands of statistical analysis, we invite fellow scholars to partake in this whimsical expedition and unearth the peculiar nuances that underscore the correlation between air pollution and the enigma of the vanishing vehicles.

[[RESULTS]]
The analysis of the data revealed a striking correlation between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across Pennsylvania. The correlation coefficient of 0.8855373 and the r-squared of 0.7841763 suggested a remarkably strong relationship between these two seemingly disparate phenomena. Furthermore, the p-value of less than 0.01 indicated the statistical significance of this connection, which certainly made us sit up and take notice; after all, it's not every day that you expect to find a link between smog and stolen cars.
Figure 1 depicts the scatterplot illustrating this robust correlation, showcasing the clear trend of increasing motor vehicle thefts coinciding with elevated levels of air pollution in St. Marys. Look at those points; they practically tell a story, don't they? A tale of murky skies and miscreant maneuvers, if you will.
The implications of this correlation extend beyond the sterile domain of statistical associations, beckoning for a deeper contemplation of the whimsical interplay between environmental quality and criminal predilections. While we resist the temptation to embark on flights of fancy about the precise mechanisms underpinning this correlation, it's difficult not to wonder just what it is about polluted air that might tempt the thieving fingers of car bandits. Could it be the haze itself that serves as a cloak for nefarious activities? Or perhaps there's a more subtle dance at work here, a clandestine waltz between atmospheric pollutants and criminal intent that would make even the most experienced sleuth scratch their head in bewilderment.
In any case, our findings offer a curious twist to the existing literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the proclivities for automotive larceny. It's as if the very air in St. Marys is whispering secrets to the car thieves, coaxing them into action with promises of concealment amidst the haze. Quite the enigmatic tale, isn't it?

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

CONCLUSION

In conclusion, our study has uncovered a robust correlation between air pollution in St. Marys, Pennsylvania, and motor vehicle thefts across the broader landscape of Pennsylvania. The statistically significant correlation coefficient and p-value suggest a remarkably strong association, much to our surprise. It seems that the murky skies of St. Marys may indeed be casting a mysterious allure for car thieves, luring them into their larcenous escapades amidst the haze. Our findings offer a whimsical twist to the existing literature on air pollution, tempting one to envision a clandestine waltz between atmospheric pollutants and criminal intent.

Given the compelling nature of our results, it appears that no further research is needed in this area – unless, of course, one is particularly interested in the romanticism of smog-invoked criminal inclinations. It may be time to acknowledge that even the air has secrets, some of which may lead to the disappearance of vehicles in ways we never quite imagined.

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 Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys. 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 Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Eco-Transportation Studies

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 Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys with an abstract of The correlation between air pollution and various societal ills has long been a topic of interest for researchers, policymakers, and concerned citizens. In this study, we delve into the enigmatic relationship between air pollution in St. Marys, Pennsylvania and motor vehicle thefts across the state. Employing data from the Environmental Protection Agency and the FBI Criminal Justice Information Services, we set out to uncover whether the atmospheric malaise in St. Marys may have an unexpected impact on the frequency of motor vehicle thefts in the broader Pennsylvania landscape.
Through rigorous statistical analysis, we observed a staggering correlation coefficient of 0.8855373 and p < 0.01 for the period spanning from 1990 to 2022, indicating a remarkably robust association between these ostensibly unrelated phenomena. The implications of this correlation extend beyond mere statistical fascination, raising profound questions about the potential influence of air quality on behavioral patterns related to property crimes. How exactly does the presence of pollutants in the air catalyze the malfeasance of vehicle thieves? While we refrain from speculating on the mechanism underlying this correlation, this finding impels further investigation into the intricate interplay of environmental factors and criminal activities. Our study contributes a peculiar twist to the literature on air pollution, inviting a whimsical consideration of the implications of hazy skies on the propensity for automotive larceny.

ChatGPT:

air pollution, motor vehicle thefts, Pennsylvania, St. Marys, correlation, statistical analysis, environmental factors, criminal activities, atmospheric malaise, property crimes, air quality, pollutants, behavioral patterns

*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. Marys, Pennsylvania
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in St. Marys, PA
Source: Environmental Protection Agency
See what else correlates with Air pollution in St. Marys, Pennsylvania

Motor vehicle thefts in Pennsylvania
Detailed data title: The motor vehicle theft rate per 100,000 residents in Pennsylvania
Source: FBI Criminal Justice Information Services
See what else correlates with Motor vehicle thefts in Pennsylvania

Correlation r = 0.8855373 (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 = 0.7841763 (Coefficient of determination)
This means 78.4% of the change in the one variable (i.e., Motor vehicle thefts in Pennsylvania) is predictable based on the change in the other (i.e., Air pollution in St. Marys, Pennsylvania) over the 33 years from 1990 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.6E-12.^Show 0.0000000000075950932247236740
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.89 in 7.6E-10% of random cases. Said differently, if you correlated 131,663,953,346 random variables^Note You don't actually need 131 billion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 32 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 32 because we have two variables measured over a period of 33 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.78, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022
Air pollution in St. Marys, Pennsylvania (Bad air quality days)	0.0660377	0.0916667	0.0498615	0.0853659	0.0443213	0.0722433	0.0528846	0.0397112	0.077381	0.0606061	0.0368272	0.0736544	0.0589888	0.0194986	0.0169492	0.0319767	0.0169014	0.0221607	0.0145349	0.00291545	0.00558659	0.0027933	0.0138122	0.00277008	0.00274725	0.00288184	0.00867052	0	0	0	0	0	0.00275482
Motor vehicle thefts in Pennsylvania (Motor Vehicle Theft rate)	505.5	481.5	467.7	440.2	449.3	412.7	404.2	367.8	355.5	327.1	295.8	290.3	266.2	270.3	249.9	236.9	238.8	213.2	180.7	141.4	131.5	132.4	118.4	107.7	102	94.8	102.2	101.3	102.6	97	121	132.9	163

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. ^{Show the steps to do this.} 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([0.0660377,0.0916667,0.0498615,0.0853659,0.0443213,0.0722433,0.0528846,0.0397112,0.077381,0.0606061,0.0368272,0.0736544,0.0589888,0.0194986,0.0169492,0.0319767,0.0169014,0.0221607,0.0145349,0.00291545,0.00558659,0.0027933,0.0138122,0.00277008,0.00274725,0.00288184,0.00867052,0,0,0,0,0,0.00275482,])
array_2 = np.array([505.5,481.5,467.7,440.2,449.3,412.7,404.2,367.8,355.5,327.1,295.8,290.3,266.2,270.3,249.9,236.9,238.8,213.2,180.7,141.4,131.5,132.4,118.4,107.7,102,94.8,102.2,101.3,102.6,97,121,132.9,163,])
array_1_name = "Air pollution in St. Marys, Pennsylvania"
array_2_name = "Motor vehicle thefts in Pennsylvania"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Air pollution in St. Marys, Pennsylvania
Line chart for only Motor vehicle thefts in Pennsylvania
AI-generated correlation image
The spurious research paper: Air Pollution and the Case of the Vanishing Vehicles: A Correlational Study on Motor Vehicle Thefts in Pennsylvania and Air Pollution in St. Marys

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 3468 · Black Variable ID: 22251 · Red Variable ID: 20158


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: