Spurious correlation #5,433 · 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 Green Bay, Wisconsin and the second variable is Carjackings in the US. The chart goes from 1995 to 2021, 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 Green Bay, Wisconsin and the second variable is Carjackings in the US. The chart goes from 1995 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The connection is crystal clear - as the air in Green Bay got cleaner, it seems the car-jackers nationwide couldn't handle the fresh heist that blowing their way! It's like they say, when the smog lifts, so does the urge to commit grand theft auto. Who knew that all it took to reduce carjackings was a breath of fresh air from Green Bay? Looks like we can add 'pollution' to the list of criminal repellents - right alongside security alarms and steering wheel locks!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image macro of a surreal scenario: Unsuccessful Carjackers. Create a scene where the skies over Green Bay, Wisconsin are vibrant and clear, in stark contrast to the smoggy skies previously shown. In various locations across the US, depict carjackers scratching their heads in confusion, surrounded by a surreal, hazy atmosphere. The carjackers should appear bewildered, symbolizing the incapacity to carry out their heists due to the unexpected change in the environment. The visuals should emphasize the comical dynamic between the thwarted criminals and the unexpected turn of events in the atmosphere. 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 Green Bay, Wisconsin and Carjackings in the US. 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: Celtic art Woodblock painting Low poly Charcoal a funny image macro
ChatGPT: a funny image macro

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 Green Bay, Wisconsin and Carjackings in the US, in the following situation: The connection is crystal clear - as the air in Green Bay got cleaner, it seems the car-jackers nationwide couldn't handle the fresh heist that blowing their way! It's like they say, when the smog lifts, so does the urge to commit grand theft auto. Who knew that all it took to reduce carjackings was a breath of fresh air from Green Bay? Looks like we can add 'pollution' to the list of criminal repellents - right alongside security alarms and steering wheel locks!. Keep the description simple.
ChatGPT: In Green Bay, Wisconsin, the air is visibly cleaner as the smog dissipates, revealing bright blue skies. Nearby, a group of carjackers in various locations across the US stand bewildered, scratching their heads as they seem unable to carry out their planned heists, looking around at the clear air in confusion.

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 funny image macro ] and depicting this scene: In Green Bay, Wisconsin, the air is visibly cleaner as the smog dissipates, revealing bright blue skies. Nearby, a group of carjackers in various locations across the US stand bewildered, scratching their heads as they seem unable to carry out their planned heists, looking around at the clear air in confusion. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image macro of a surreal scenario: Unsuccessful Carjackers. Create a scene where the skies over Green Bay, Wisconsin are vibrant and clear, in stark contrast to the smoggy skies previously shown. In various locations across the US, depict carjackers scratching their heads in confusion, surrounded by a surreal, hazy atmosphere. The carjackers should appear bewildered, symbolizing the incapacity to carry out their heists due to the unexpected change in the environment. The visuals should emphasize the comical dynamic between the thwarted criminals and the unexpected turn of events in the atmosphere.

*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 Green Bay, Wisconsin caused Carjackings in the US to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US

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 dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Green Bay, Wisconsin and Carjackings in the US. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
"Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US"

[[ABSTRACT]]
This research paper delves into the potentially gasping relationship between air pollution levels in Green Bay, Wisconsin, and the incidence of carjackings across the United States. Our analysis, based on data obtained from the Environmental Protection Agency and the Bureau of Justice Statistics spanning from 1995 to 2021, reveals a surprising correlation between these seemingly unrelated phenomena.

In our findings, we have uncovered a remarkably high and statistically significant correlation coefficient of 0.8148871 (p < 0.01) between air pollution in Green Bay and the occurrence of carjackings nationwide. This unlikely association prompts a quip about "taking a breath of fresh air" to avoid car theft, adding a theoretical dimension to the phrase.

In addition to shedding light on this unforeseen relationship, our study serves as a subtle-yet-poignant reminder of the far-reaching, and perhaps unintended, consequences of environmental factors on social phenomena. Further exploration of this intriguing correlation holds the potential to both inform environmental policy and inspire whimsical musings about the hidden influences of air quality on criminal behavior.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Carjackings, a crime that leaves victims feeling "exhausted" in more ways than one, pose a significant threat to public safety and vehicle security in the United States. The alarming frequency of these incidents has prompted researchers to explore the factors contributing to this vehicular theft epidemic. In a similar vein, air pollution, particularly in the industrious city of Green Bay, Wisconsin, has been a concerning environmental issue, leaving citizens yearning for a "breath of fresh air."
As these two disparate matters converge in the realm of empirical investigation, the aim of this study is to untangle the web of connections between air pollution in Green Bay and the occurrence of carjackings nationwide. Our analysis endeavors to inject fresh air into the discourse surrounding both environmental health and criminal behavior. A "punny" correlation has emerged, suggesting that perhaps "letting off steam" from air pollution might prevent the "hot pursuit" of stolen vehicles.
By leveraging data from the Environmental Protection Agency and the Bureau of Justice Statistics, covering a span from 1995 to 2021, we have embarked on a whimsical journey to demystify the intricate relationship between these seemingly disparate phenomena. The unveiling of this correlation challenges traditional assumptions and breathes new life into the fields of environmental and criminological research. It also provides ample opportunity for air pollution puns, which are nothing to sneeze at.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In "Smith and Doe", the authors find a modest correlation between air pollution and certain types of crime. They describe a mediating effect, suggesting that pollutants may impair cognitive function, thereby increasing the likelihood of criminal behavior. While this offers some insight into the potential mechanisms at play, it fails to capture the specific nuances of the relationship between air pollution in Green Bay, Wisconsin, and carjackings across the United States. One might say their findings "smog the issue" at hand, leaving a hazy understanding of the true connection.

Moving on, "Jones et al." delve into the psychological ramifications of living in an environmentally compromised area. Their research posits that prolonged exposure to air pollution can lead to increased stress and irritability, potentially contributing to criminal impulses. However, this study lacks a comprehensive analysis of nationwide data and fails to establish a direct link to carjackings. It's as if they've left us stranded on the side of the road without a clear route to understanding.

As we venture further into the literature, "The Air We Breathe" by Lungs McGee discusses the tangible effects of air pollution on public health, but does not directly address its impact on criminal behavior. Similarly, "The Wheels of Misfortune" by Car Lockington chronicles the gripping tales of carjackings but offers no exploration into the potential environmental factors shaping this phenomenon. One might humorously ponder if these two genres could collide in a literary vehicular heist thriller, titled "The Diesel Dilemma: A Tale of Tubular Carjackings".

A surprising diversion into unconventional sources leads us to consider the educational value of animated television series. Taking inspiration from children's show "Captain Planet" and its environmental messaging, one might envision a crossover episode where the eco-friendly superhero thwarts air pollution-induced carjackings with the power of wind, earth, fire, water, and heart. After all, a little whimsy can breathe life into even the most serious of inquiries.

In conclusion, while existing literature has touched on the intersections of air pollution and criminal behavior, none have directly scrutinized the specific correlation between air pollution in Green Bay, Wisconsin, and carjackings in the United States. This leaves the field open for our innovative inquiry, an investigation that breathes in fresh, crisp air and exhales long-debated theories in a puff of clarity. And if nothing else, it has allowed for a breath of fresh, albeit somewhat punny, air in academic discourse.

Model: gpt-3.5-turbo-1106
System prompt: You are a dry but witty academic researcher. You speak in the passive voice, and your writing sounds like it belongs in a medical or economics journal.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 Green Bay, Wisconsin and Carjackings in the US. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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]]
"Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US"

[[ABSTRACT]]
This research paper delves into the potentially gasping relationship between air pollution levels in Green Bay, Wisconsin, and the incidence of carjackings across the United States. Our analysis, based on data obtained from the Environmental Protection Agency and the Bureau of Justice Statistics spanning from 1995 to 2021, reveals a surprising correlation between these seemingly unrelated phenomena.

In our findings, we have uncovered a remarkably high and statistically significant correlation coefficient of 0.8148871 (p < 0.01) between air pollution in Green Bay and the occurrence of carjackings nationwide. This unlikely association prompts a quip about "taking a breath of fresh air" to avoid car theft, adding a theoretical dimension to the phrase.

In addition to shedding light on this unforeseen relationship, our study serves as a subtle-yet-poignant reminder of the far-reaching, and perhaps unintended, consequences of environmental factors on social phenomena. Further exploration of this intriguing correlation holds the potential to both inform environmental policy and inspire whimsical musings about the hidden influences of air quality on criminal behavior.

[[LITERATURE REVIEW]]
In "Smith and Doe", the authors find a modest correlation between air pollution and certain types of crime. They describe a mediating effect, suggesting that pollutants may impair cognitive function, thereby increasing the likelihood of criminal behavior. While this offers some insight into the potential mechanisms at play, it fails to capture the specific nuances of the relationship between air pollution in Green Bay, Wisconsin, and carjackings across the United States. One might say their findings "smog the issue" at hand, leaving a hazy understanding of the true connection.
Moving on, "Jones et al." delve into the psychological ramifications of living in an environmentally compromised area. Their research posits that prolonged exposure to air pollution can lead to increased stress and irritability, potentially contributing to criminal impulses. However, this study lacks a comprehensive analysis of nationwide data and fails to establish a direct link to carjackings. It's as if they've left us stranded on the side of the road without a clear route to understanding.
As we venture further into the literature, "The Air We Breathe" by Lungs McGee discusses the tangible effects of air pollution on public health, but does not directly address its impact on criminal behavior. Similarly, "The Wheels of Misfortune" by Car Lockington chronicles the gripping tales of carjackings but offers no exploration into the potential environmental factors shaping this phenomenon. One might humorously ponder if these two genres could collide in a literary vehicular heist thriller, titled "The Diesel Dilemma: A Tale of Tubular Carjackings".
A surprising diversion into unconventional sources leads us to consider the educational value of animated television series. Taking inspiration from children's show "Captain Planet" and its environmental messaging, one might envision a crossover episode where the eco-friendly superhero thwarts air pollution-induced carjackings with the power of wind, earth, fire, water, and heart. After all, a little whimsy can breathe life into even the most serious of inquiries.
In conclusion, while existing literature has touched on the intersections of air pollution and criminal behavior, none have directly scrutinized the specific correlation between air pollution in Green Bay, Wisconsin, and carjackings in the United States. This leaves the field open for our innovative inquiry, an investigation that breathes in fresh, crisp air and exhales long-debated theories in a puff of clarity. And if nothing else, it has allowed for a breath of fresh, albeit somewhat punny, air in academic discourse.

[[RESULTS]]
The data analysis revealed a statistically significant positive correlation between air pollution levels in Green Bay, Wisconsin, and the incidence of carjackings across the United States. The correlation coefficient of 0.8148871 indicated a strong relationship between these variables, prompting the quip that maybe "clean air isn't the only thing being stolen in Green Bay."
The r-squared value of 0.6640411 suggested that approximately 66.4% of the variation in carjackings could be explained by the variation in air pollution levels. One might say that this correlation isn't just blowing hot air.
The p-value of less than 0.01 further confirmed the significance of the relationship between air pollution in Green Bay and carjackings nationwide, providing evidence that this association is not just a "whiff of speculation."
The scatterplot (Fig. 1) visually depicts the strong positive correlation between air pollution in Green Bay and carjackings in the US, illustrating a clear and conspicuous pattern that makes it difficult to "brush off" this unexpected relationship.
In summary, our findings highlight the unexpected and puzzling connection between air pollution in Green Bay and carjackings nationwide, presenting a delightful surprise for researchers interested in the intersection of environmental and criminological factors. These results offer a breath of fresh air in the study of crime and environmental influences, serving as a refreshing departure from traditional research in these domains.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study support and extend previous literature examining the relationship between air pollution and criminal behavior. Our statistical analysis revealed a robust and statistically significant positive correlation between air pollution levels in Green Bay, Wisconsin, and the incidence of carjackings across the United States. This correlation coefficient, which we affectionately refer to as the "smoggy score," not only aligns with prior research but also deepens our understanding of the potential impact of environmental factors on criminal activities.

The observed correlation prompts the amusing yet thought-provoking notion that perhaps individuals are hot-wiring cars to escape the smog-laden air in Green Bay, seeking out fresher environments for their illicit activities. This unexpected relationship, while certainly surprising, underscores the need for further exploration into the multifaceted interactions between environmental quality and criminal behavior. Our study serves as a vehicle for shedding light on these intricate dynamics, driving us toward a clearer understanding of the nuanced influences at play.

Additionally, our results contribute to the burgeoning literature on the broader implications of air pollution, demonstrating its far-reaching consequences on societal well-being and safety. The substantial portion of the variation in carjackings explained by air pollution levels underscores the significance of environmental conditions in shaping criminal phenomena. It's as if pollutants are not just affecting visibility but also steering individuals toward criminal behavior.

Moreover, the significance of the relationship confirmed by the p-value adds weight to the argument that this association is not a mere figment of statistical noise. This finding eliminates any lingering doubt about the substantial impact of air pollution in Green Bay on the occurrence of carjackings across the country, dispelling any notions that this correlation is just a "fume of imagination."

Our study's contributions, though lighthearted in tone, mark a significant stride in understanding the interplay between environmental and criminological factors. The unexpected and puzzling connection between air pollution in Green Bay and carjackings nationwide injects a breath of fresh air into the study of crime and its environmental underpinnings. As the old saying goes, "Where there's smog, there's fire" – and our findings ignite a newfound interest in exploring the interwoven fabric of environmental conditions and criminal activities.

In summary, our research not only solidifies existing knowledge but also invites further scholarly pursuits into the intricate web of relationships between air quality and criminal behavior. This study sets the wheels in motion for future investigations to uncover the mechanisms through which air pollution may potentially serve as a catalyst for car-related crimes. By taking this road less traveled, we pave the way for a richer understanding of the unexpected intersections between environmental factors and criminal conduct.

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 Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US. Respond only with the name of a fictional academic journal.

ChatGPT:

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 Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Environmental Criminology and Air Quality Research

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 Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US with an abstract of This research paper delves into the potentially gasping relationship between air pollution levels in Green Bay, Wisconsin, and the incidence of carjackings across the United States. Our analysis, based on data obtained from the Environmental Protection Agency and the Bureau of Justice Statistics spanning from 1995 to 2021, reveals a surprising correlation between these seemingly unrelated phenomena.
In our findings, we have uncovered a remarkably high and statistically significant correlation coefficient of 0.8148871 (p < 0.01) between air pollution in Green Bay and the occurrence of carjackings nationwide. This unlikely association prompts a quip about "taking a breath of fresh air" to avoid car theft, adding a theoretical dimension to the phrase.
In addition to shedding light on this unforeseen relationship, our study serves as a subtle-yet-poignant reminder of the far-reaching, and perhaps unintended, consequences of environmental factors on social phenomena. Further exploration of this intriguing correlation holds the potential to both inform environmental policy and inspire whimsical musings about the hidden influences of air quality on criminal behavior.

ChatGPT:

air pollution, carjackings, Green Bay, Wisconsin, correlation, environmental factors, crime, EPA data, Bureau of Justice Statistics, United States, social phenomena, criminal behavior

*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 Green Bay, Wisconsin
Detailed data title: Percentage of days with air quality at 'unhealthy for sensitive groups' or worse in Green Bay, WI
Source: Environmental Protection Agency
See what else correlates with Air pollution in Green Bay, Wisconsin

Carjackings in the US
Detailed data title: Rate of nonfatal carjacking victimization per 1,000 persons age 16 or older (3-year moving averages)
Source: Bureau of Justice Statistics
See what else correlates with Carjackings in the US

Correlation r = 0.8148871 (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 = 0.6640411 (Coefficient of determination)
This means 66.4% of the change in the one variable (i.e., Carjackings in the US) is predictable based on the change in the other (i.e., Air pollution in Green Bay, Wisconsin) over the 27 years from 1995 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.3E-7.^Show 0.0000002281892503834420300000
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 0.81 in 2.3E-5% of random cases. Said differently, if you correlated 4,382,327 random variables^Note You don't actually need 4 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 26 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 26 because we have two variables measured over a period of 27 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.

[ 0.63, 0.91 ] 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.

	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
Air pollution in Green Bay, Wisconsin (Bad air quality days)	12.5	9.83607	8.15217	11.9565	9.7561	3.22581	7.34694	7.78689	5.46218	2.7451	9.92064	4.04858	5.89888	2.27273	3.3241	3.37079	2.1978	4.91803	0.547945	0.821918	0.828729	1.36612	0.555556	1.66667	0	0.273224	1.36986
Carjackings in the US (Carjackings)	0.53	0.48	0.4	0.3	0.35	0.31	0.31	0.19	0.23	0.19	0.22	0.185	0.185	0.185	0.15	0.13	0.09	0.09	0.12	0.15	0.14	0.11	0.09	0.1	0.1	0.1	0.12

Why this works

Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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([12.5,9.83607,8.15217,11.9565,9.7561,3.22581,7.34694,7.78689,5.46218,2.7451,9.92064,4.04858,5.89888,2.27273,3.3241,3.37079,2.1978,4.91803,0.547945,0.821918,0.828729,1.36612,0.555556,1.66667,0,0.273224,1.36986,])
array_2 = np.array([0.53,0.48,0.4,0.3,0.35,0.31,0.31,0.19,0.23,0.19,0.22,0.185,0.185,0.185,0.15,0.13,0.09,0.09,0.12,0.15,0.14,0.11,0.09,0.1,0.1,0.1,0.12,])
array_1_name = "Air pollution in Green Bay, Wisconsin"
array_2_name = "Carjackings in the US"

# 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 Green Bay, Wisconsin
Line chart for only Carjackings in the US
AI-generated correlation image
The spurious research paper: Breathless in Green Bay: The Smoggy Link Between Air Pollution and Carjackings in the US

View another random correlation

How fun was this correlation?

Big thanks for reviewing!

Correlation ID: 5433 · Black Variable ID: 20686 · Red Variable ID: 1200


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