Spurious correlation #2,882 · 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 Americus, Georgia and the second variable is Sales of LP/Vinyl Albums. The chart goes from 1993 to 2006, 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 Americus, Georgia and the second variable is Sales of LP/Vinyl Albums. The chart goes from 1993 to 2006, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The poor air quality in Americus led more people to stay indoors. As a result, individuals rediscovered their old record collections, opting for analog music to "breathe new life" into their listening experience. This unexpected vinyl revival proves that even in smog-filled skies, there's always a silver lining spinning on a turntable.

^{Show image generation prompt} Model: dalle-3
Prompt: [ Concept art ] Generate an image showcasing a quaint, small-town scene in Americus, Georgia. The sky above the town is depicted with reduced air pollution, appearing crystal clear and serene. A group of people can be seen sitting on their charming front porches, framed by lush greenery. They are enjoying the clean air and casually spinning LP/Vinyl albums, creating a nostalgic and timeless atmosphere. The music emanating from the records forms a beautiful and protective bubble that contrasts with the once harmful pollution, symbolizing the transformative power of classic melodies. 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 Americus, Georgia and Sales of LP/Vinyl Albums. 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: Glitch art Psychedelic Scalar art Charcoal 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 Americus, Georgia and Sales of LP/Vinyl Albums, in the following situation: As air pollution decreased in Americus, Georgia, sales of LP/Vinyl albums increased because people were trying to create a protective barrier of good ol' classic tunes to shield themselves from the harmful effects of pollution.. Keep the description simple.
ChatGPT: In Americus, Georgia, as the air pollution decreased, the sales of LP/Vinyl albums soared. People, sitting on their front porch, enjoyed the clean air while spinning their favorite classic records, creating a protective bubble of timeless melodies against the once harmful pollution.

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 Americus, Georgia, as the air pollution decreased, the sales of LP/Vinyl albums soared. People, sitting on their front porch, enjoyed the clean air while spinning their favorite classic records, creating a protective bubble of timeless melodies against the once harmful pollution. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Concept art ] Generate an image showcasing a quaint, small-town scene in Americus, Georgia. The sky above the town is depicted with reduced air pollution, appearing crystal clear and serene. A group of people can be seen sitting on their charming front porches, framed by lush greenery. They are enjoying the clean air and casually spinning LP/Vinyl albums, creating a nostalgic and timeless atmosphere. The music emanating from the records forms a beautiful and protective bubble that contrasts with the once harmful pollution, symbolizing the transformative power of classic melodies.

*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 an increase in Air pollution in Americus, Georgia caused Sales of LP/Vinyl Albums to increase. Include one good pun.

AI academic paper

(Because p < 0.05)

Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums

The Journal of Eclectic Environmental Studies

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 Americus, Georgia and Sales of LP/Vinyl Albums. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums"

[[ABSTRACT]]
In this study, we dust off an old record and delve into the curious connection between air pollution in Americus, Georgia and the sales of LP/vinyl albums. As the adage goes, "Where there's smog, there's grog," our research aimed to unravel this seemingly eccentric relationship. Leveraging data from the Environmental Protection Agency and Statista, we conducted a rigorous analysis from 1993 to 2006, surfacing a correlation coefficient of 0.5721527 with a p-value less than 0.05. Our findings suggest that the presence of airborne pollutants in Americus may have contributed to a surge in the sale of vinyl records. While these results may seem like a vinyl record – a bit scratchy and outdated – they underscore the need for further investigation into the quirky interplay between environmental factors and consumer behavior in the music industry. So, let's keep our ears open and continue spinning the wheels of research in this peculiar realm.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of research often spins us in unexpected directions, and our latest study surely takes that concept to a whole new level. As we dig into the peculiar relationship between air pollution in Americus, Georgia and the sales of LP/vinyl albums, we find ourselves on a unique and groovy journey – one that's as unpredictable as a record on a turntable.
In recent years, the resurgence of vinyl records has stunned many music enthusiasts and industry analysts alike. It's as if retro has become the new avant-garde, with sleek phonographs reclaiming their place in living rooms and hipster hangouts across the globe. Amidst this resurgence, we find ourselves pondering the curious notion: did the air in Americus play a role in the revival of vinyl's charm? This study aims to explore that very question and, in doing so, bring a breath of fresh air to the often-stuffy world of academic inquiry.
Harnessing the power of data and statistical analysis, our research seeks to bridge the gap between seemingly disparate realms – environmental science and music consumption. By examining the years 1993 to 2006, we aim to unravel the peculiar dynamics that tie Americus' air quality to the turntable tunes that captured the hearts of its residents. While the notion may sound like a symphony played on kazoos, the implications of our findings could strike a chord far beyond the borders of Georgia.
Buckle up, fellow researchers, for we're about to embark on a musical journey through the ozone layer, in search of the melodies that drift through the pollution. Our study is set to prove that sometimes, in the midst of the haze, remarkable discoveries await – even those that may seem as unlikely as a saxophone serenade in a heavy metal concert. So, without further ado, let's drop the needle and groove our way through this novel exploration.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The exploration of seemingly peculiar correlations has long captivated researchers across diverse disciplines. In the realm of environmental science and consumer behavior, the quest to uncover the influence of air quality on music preferences has led to an array of studies. Smith, in "A Breath of Fresh Air: The Impact of Environmental Factors on Consumer Choices," delves into the interplay between airborne pollutants and consumer behavior, shedding light on the potential ripple effects of pollution on cultural consumption. Similarly, Doe and Jones, in "Sounds of the City: Investigating Urban Air Quality and Musical Preferences," present a comprehensive analysis of how urban air quality has shaped the musical inclinations of city dwellers. These studies, among others, set the stage for our investigation into the intriguing relationship between air pollution in Americus, Georgia, and the sales of LP/vinyl albums.

Drawing from the rich tapestry of literature on environmental influences and consumer choices, our research takes a turn into uncharted territories, much like a record skipping unexpectedly. As our journey unfolds, we move beyond the realm of academic publications and delve into the wealth of knowledge embedded in books pertinent to our investigation. "The Air We Breathe" by John Green offers a poignant exploration of environmental issues, serving as a reminder of the profound impact of polluted air on human experiences. In a similar vein, "Vinyl Frontier: The Cultural Resurgence of Long-Playing Records" by Amanda Thompson provides insights into the revival of vinyl albums, hinting at the intersection of cultural nostalgia and consumer trends amidst a changing environmental landscape.

Venturing further into the realm of fiction, we encounter unexpected connections that mirror the quirkiness of our research endeavor. In "Scent of Vinyl: A Musical Mystery" by Arthur Conan Doyle, the protagonist navigates a perplexing case where air pollution intertwines with the enigmatic lure of vinyl records, offering a fictional yet thought-provoking narrative. Likewise, in "The Ozone Overture" by J.K. Rowling, the mystical realm of magic intertwines with ecological concerns, highlighting the potential consequences of tainted air on the enchanting melodies that captivate fictional characters and readers alike.

Amidst the eclectic mix of literary influences, our pursuit of understanding the interplay between air pollution and vinyl album sales takes an unexpected turn, akin to stumbling upon a treasure trove in unlikely places. As we seek to unravel the peculiar correlation that lies at the heart of our study, we must acknowledge the unconventional sources that have informed our exploration. Indeed, it is with a certain degree of jest and curiosity that we unveil the unorthodox canvases from which we have drawn inspiration – from fortune cookies with cryptic messages to the ubiquitous but perplexing CVS receipts that seem to hold within them the secrets of consumer behavior.

In the spirit of scholarly inquiry and a sprinkle of whimsy, our literature review embraces the unconventional, offering a nod to the idiosyncrasies of our research journey. As we set our sights on unraveling the curious connection between air pollution in Americus, Georgia, and the sales of LP/vinyl albums, we invite fellow scholars to join us in this whimsical expedition through the realms of music, environmental influences, and perhaps, a touch of absurdity. So, with a twirl of the turntable and a dash of mirth, let us continue our quest, eager to unearth the harmonies that resonate amidst the haze.

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 Americus, Georgia and Sales of LP/Vinyl Albums. Make lots of jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums"

[[ABSTRACT]]
In this study, we dust off an old record and delve into the curious connection between air pollution in Americus, Georgia and the sales of LP/vinyl albums. As the adage goes, "Where there's smog, there's grog," our research aimed to unravel this seemingly eccentric relationship. Leveraging data from the Environmental Protection Agency and Statista, we conducted a rigorous analysis from 1993 to 2006, surfacing a correlation coefficient of 0.5721527 with a p-value less than 0.05. Our findings suggest that the presence of airborne pollutants in Americus may have contributed to a surge in the sale of vinyl records. While these results may seem like a vinyl record – a bit scratchy and outdated – they underscore the need for further investigation into the quirky interplay between environmental factors and consumer behavior in the music industry. So, let's keep our ears open and continue spinning the wheels of research in this peculiar realm.

[[LITERATURE REVIEW]]
The exploration of seemingly peculiar correlations has long captivated researchers across diverse disciplines. In the realm of environmental science and consumer behavior, the quest to uncover the influence of air quality on music preferences has led to an array of studies. Smith, in "A Breath of Fresh Air: The Impact of Environmental Factors on Consumer Choices," delves into the interplay between airborne pollutants and consumer behavior, shedding light on the potential ripple effects of pollution on cultural consumption. Similarly, Doe and Jones, in "Sounds of the City: Investigating Urban Air Quality and Musical Preferences," present a comprehensive analysis of how urban air quality has shaped the musical inclinations of city dwellers. These studies, among others, set the stage for our investigation into the intriguing relationship between air pollution in Americus, Georgia, and the sales of LP/vinyl albums.
Drawing from the rich tapestry of literature on environmental influences and consumer choices, our research takes a turn into uncharted territories, much like a record skipping unexpectedly. As our journey unfolds, we move beyond the realm of academic publications and delve into the wealth of knowledge embedded in books pertinent to our investigation. "The Air We Breathe" by John Green offers a poignant exploration of environmental issues, serving as a reminder of the profound impact of polluted air on human experiences. In a similar vein, "Vinyl Frontier: The Cultural Resurgence of Long-Playing Records" by Amanda Thompson provides insights into the revival of vinyl albums, hinting at the intersection of cultural nostalgia and consumer trends amidst a changing environmental landscape.
Venturing further into the realm of fiction, we encounter unexpected connections that mirror the quirkiness of our research endeavor. In "Scent of Vinyl: A Musical Mystery" by Arthur Conan Doyle, the protagonist navigates a perplexing case where air pollution intertwines with the enigmatic lure of vinyl records, offering a fictional yet thought-provoking narrative. Likewise, in "The Ozone Overture" by J.K. Rowling, the mystical realm of magic intertwines with ecological concerns, highlighting the potential consequences of tainted air on the enchanting melodies that captivate fictional characters and readers alike.
Amidst the eclectic mix of literary influences, our pursuit of understanding the interplay between air pollution and vinyl album sales takes an unexpected turn, akin to stumbling upon a treasure trove in unlikely places. As we seek to unravel the peculiar correlation that lies at the heart of our study, we must acknowledge the unconventional sources that have informed our exploration. Indeed, it is with a certain degree of jest and curiosity that we unveil the unorthodox canvases from which we have drawn inspiration – from fortune cookies with cryptic messages to the ubiquitous but perplexing CVS receipts that seem to hold within them the secrets of consumer behavior.
In the spirit of scholarly inquiry and a sprinkle of whimsy, our literature review embraces the unconventional, offering a nod to the idiosyncrasies of our research journey. As we set our sights on unraveling the curious connection between air pollution in Americus, Georgia, and the sales of LP/vinyl albums, we invite fellow scholars to join us in this whimsical expedition through the realms of music, environmental influences, and perhaps, a touch of absurdity. So, with a twirl of the turntable and a dash of mirth, let us continue our quest, eager to unearth the harmonies that resonate amidst the haze.

[[RESULTS]]
The results of our analysis unveiled a correlation coefficient of 0.5721527 between air pollution levels in Americus, Georgia and the sales of LP/vinyl albums during the period of 1993 to 2006. The coefficient of determination (r-squared) was calculated to be 0.3273587, and the p-value was found to be less than 0.05. In other words, there's a statistically significant relationship between the two variables, and it's as clear as when your favorite vinyl has been cleaned with a top-notch record brush.
As depicted in Figure 1, the scatterplot showcases the robust correlation between air pollution and LP/vinyl album sales. It's as if the data points are dancing to the tunes of an invisible DJ, with the air pollution levels setting the tempo for the vinyl sales. The relationship is so striking that one might wonder if the vinyl records were acting as a filter, capturing the essence of the polluted air and transforming it into musical gold.
This finding may seem reminiscent of a vinyl record itself – old-fashioned and a bit crackly – but its significance is not to be underestimated. The link between air pollution and the resurgence of vinyl records in Americus, Georgia hints at a melody of environmental influence on consumer behavior. It's as if the polluted skies were whispering a siren song, luring the residents to seek solace in the nostalgic crackles and pops of vinyl tunes. One might even say that in Americus, the sound of music is in the air, both literally and figuratively.
The unexpected harmony between these seemingly unrelated variables underscores the need for further investigation into the peculiar interplay of environmental factors and consumer choices. After all, who would have thought that pollution and vinyl records could harmonize in such an unexpected duet? In the grand symphony of scientific discoveries, this uncanny coupling strikes a chord that resonates beyond the boundaries of Americus, echoing through the halls of academia and the groovy dance floors of music aficionados worldwide. As we uncover more about the idiosyncrasies of this relationship, it's clear that the airwaves of research hold more surprises than a vinyl treasure hunt at a flea market.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The perplexing yet intriguing correlation between air pollution in Americus, Georgia and the sales of LP/vinyl albums, as unearthed in our study, mirrors the unexpected harmonies that one might stumble upon in a vinyl record store. Our findings not only aligned with prior research, but they also offered a melodic cadence to the chorus of scholarly inquiry into seemingly peculiar connections.

Drawing from the literary tapestry we highlighted in our literature review, it becomes evident that the resonance of our results was indeed in tune with previous investigations. Smith's "A Breath of Fresh Air" and Doe and Jones' "Sounds of the City" may have set the stage for our exploration, but it is our study that adds the groovy riff to the symphony of air pollution and consumer behavior research. Just like John Green's "The Air We Breathe" and Amanda Thompson's "Vinyl Frontier," our findings hit the right notes, hinting at the lyrical dance between environmental influences and musical preferences.

The statistically significant correlation coefficient and p-value, akin to a catchy rhythm and hook, not only supported the potential influence of air pollution on vinyl album sales but also echoed the findings of past studies, much like a familiar tune that reappears unexpectedly. Our results, much like the twists in "Scent of Vinyl" and the allegorical resonance of "The Ozone Overture," lend credence to the notion that the murkiness of polluted air could indeed entwine with the allure of vinyl melodies.

The robust relationship illustrated in our scatterplot, akin to a visual representation of an improvised jazz session, showcased the unmistakable synchrony between air pollution and vinyl sales. It's as if the hazy air of Americus was choreographing a dance of consumer choices, where vinyl records took center stage in an unlikely pas de deux with pollutants. This discovery fit seamlessly into the evolving narrative of environmental influence on artistic consumption, adding a whimsical yet substantial verse to the ballad of interdisciplinary research.

Our study, much like the cryptic messages in fortune cookies and the enigmatic CVS receipts, brought an element of jest and curiosity to the scholarly discourse, perhaps akin to a playful xylophone interlude in a grand orchestral performance. As we beckon fellow scholars to join us on this quirky expedition, the unorthodox orchestration of air pollution, vinyl albums, and scholarly inquiry promises a symphony of enlightenment and amusement, where the unexpected yet harmonious connections serve as the delightful refrains in the melody of academic exploration.

In the grand refrain of scientific discovery, our findings teeter on the brink of a delightful surprise, much like stumbling upon a treasure trove amid the unlikely nooks of research. The melodic interplay between air pollution and vinyl records not only adds a whimsical allure to our understanding of environmental influences on consumer behavior but also hints at the potential for more surprising discoveries in the realms of air quality and cultural inclinations.

So, as we swivel the turntable of curiosity and mirth, let us continue to uncover the enigmatic melodies that resonate amidst the haze, embracing the offbeat harmonies and idiosyncratic symphonies that enrich our scholarly pursuits. After all, who knew that the atmospheric musings of Americus could ring through in the nostalgic crackles of vinyl records with such unexpected harmony?

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 Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Environmental Studies

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 Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Ethnomusicological Air Quality 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 Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums with an abstract of In this study, we dust off an old record and delve into the curious connection between air pollution in Americus, Georgia and the sales of LP/vinyl albums. As the adage goes, "Where there's smog, there's grog," our research aimed to unravel this seemingly eccentric relationship. Leveraging data from the Environmental Protection Agency and Statista, we conducted a rigorous analysis from 1993 to 2006, surfacing a correlation coefficient of 0.5721527 with a p-value less than 0.05. Our findings suggest that the presence of airborne pollutants in Americus may have contributed to a surge in the sale of vinyl records. While these results may seem like a vinyl record – a bit scratchy and outdated – they underscore the need for further investigation into the quirky interplay between environmental factors and consumer behavior in the music industry. So, let's keep our ears open and continue spinning the wheels of research in this peculiar realm.

ChatGPT:

air pollution, Americus Georgia, LP sales, vinyl albums, correlation, Environmental Protection Agency data, Statista, consumer behavior, music industry, airborne pollutants

*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 Americus, Georgia
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Americus, GA
Source: Environmental Protection Agency
See what else correlates with Air pollution in Americus, Georgia

Sales of LP/Vinyl Albums
Source: Statista
See what else correlates with Sales of LP/Vinyl Albums

Correlation r = 0.5721527 (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 = 0.3273587 (Coefficient of determination)
This means 32.7% of the change in the one variable (i.e., Sales of LP/Vinyl Albums) is predictable based on the change in the other (i.e., Air pollution in Americus, Georgia) over the 14 years from 1993 through 2006.

p < 0.05, which statistically significant(Null hypothesis significance test)
The p-value is 0.033.^Show 0.0325166854532829560000000000
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 0.57 in 3.3% of random cases. Said differently, if you correlated 31 random variables^Note Which I absolutely did.
with the same 13 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 13 because we have two variables measured over a period of 14 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.

[ 0.06, 0.85 ] 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.

	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006
Air pollution in Americus, Georgia (Bad air quality days)	0	0.00274725	0	0	0.00970874	0.00469484	0.00970874	0.0204082	0.00411523	0.00454545	0.0047619	0	0	0.00411523
Sales of LP/Vinyl Albums (Units)	300000	600000	800000	1100000	1100000	1400000	1400000	1500000	1200000	1300000	1400000	1200000	900000	900000

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([0,0.00274725,0,0,0.00970874,0.00469484,0.00970874,0.0204082,0.00411523,0.00454545,0.0047619,0,0,0.00411523,])
array_2 = np.array([300000,600000,800000,1100000,1100000,1400000,1400000,1500000,1200000,1300000,1400000,1200000,900000,900000,])
array_1_name = "Air pollution in Americus, Georgia"
array_2_name = "Sales of LP/Vinyl Albums"

# 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 Americus, Georgia
Line chart for only Sales of LP/Vinyl Albums
AI-generated correlation image
The spurious research paper: Spin Me Round: The Vinyl Frontier – Exploring the Correlation between Air Pollution in Americus, Georgia and Sales of LP/Vinyl Albums

View another random correlation

How fun was this correlation?

Your rating is stellar!

Correlation ID: 2882 · Black Variable ID: 21969 · Red Variable ID: 25


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