Spurious correlation #4,697 · 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 Deming, New Mexico and the second variable is Google searches for 'Gangnam Style'. The chart goes from 2012 to 2023, 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 Deming, New Mexico and the second variable is Google searches for 'Gangnam Style'. The chart goes from 2012 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

Breathable air led to a lack of interest in 'Gangnam Style' as people no longer needed a catchy, opp-air-ational tune to help them breathe easy! As the pollution cleared, so did the desire to saddle up and dance Gangnam Style. The correlation is as clear as fresh mountain air - when the skies are cleaner, the dance crazes leaner! It seems like in Deming, New Mexico, as the air quality improved, so did the musical taste - the Gangnam Style fad just couldn't air-take the change!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a low poly landscape of Deming, New Mexico under a clear sky. The scene should show content people walking outside, enjoying the fresh air. Rather than a bustle of activity, the town is quiet, with low poly figures in the distance. A subtle nod to the decline of "Gangnam Style" can be represented by a minimalistic visual element that conveys the absence of the once popular dance craze in the town, perhaps through the representation of quiet streets and a serene 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 Deming, New Mexico and Google searches for 'Gangnam Style'. 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: a Polaroid photo Cyber folk Low poly Surrealism Cyber folk
ChatGPT: Low poly

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 Deming, New Mexico and Google searches for 'Gangnam Style', in the following situation: Breathable air led to a lack of interest in 'Gangnam Style' as people no longer needed a catchy, opp-air-ational tune to help them breathe easy! As the pollution cleared, so did the desire to saddle up and dance Gangnam Style. The correlation is as clear as fresh mountain air - when the skies are cleaner, the dance crazes leaner! It seems like in Deming, New Mexico, as the air quality improved, so did the musical taste - the Gangnam Style fad just couldn't air-take the change!. Keep the description simple.
ChatGPT: In Deming, New Mexico, the sky was clear and the air was fresh. People were seen walking outside, taking in deep, easy breaths. They appeared content and at ease. Meanwhile, the Google searches for "Gangnam Style" were noticeably low, as the town seemed to have outgrown the once popular dance craze. The streets were quiet, and instead of hearing the familiar tune of "Gangnam Style", the sound of gentle, clean air filled the atmosphere.

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: [ Low poly ] and depicting this scene: In Deming, New Mexico, the sky was clear and the air was fresh. People were seen walking outside, taking in deep, easy breaths. They appeared content and at ease. Meanwhile, the Google searches for "Gangnam Style" were noticeably low, as the town seemed to have outgrown the once popular dance craze. The streets were quiet, and instead of hearing the familiar tune of "Gangnam Style", the sound of gentle, clean air filled the atmosphere. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a low poly landscape of Deming, New Mexico under a clear sky. The scene should show content people walking outside, enjoying the fresh air. Rather than a bustle of activity, the town is quiet, with low poly figures in the distance. A subtle nod to the decline of "Gangnam Style" can be represented by a minimalistic visual element that conveys the absence of the once popular dance craze in the town, perhaps through the representation of quiet streets and a serene 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 Deming, New Mexico caused Gangnam Style (Google searches for 'Gangnam Style') to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)

Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'

Journal of Unusual Correlations

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 Deming, New Mexico and Google searches for 'Gangnam Style'. 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 name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delve into the unexpected correlation between air pollution levels in Deming, New Mexico, and the seemingly unrelated phenomenon of Google searches for the iconic hit 'Gangnam Style'. Our research team embarked on this journey with curious minds and a love for an academic riddle that's as elusive as a clean air day in a bustling city.

After meticulously analyzing data from the Environmental Protection Agency and Google Trends, we unearthed a startling correlation coefficient of 0.9318336 and p < 0.01 for the years 2012 to 2023. This statistically significant association had us dancing with joy, even if we had to do it Gangnam Style.

Unraveling this peculiar relationship, we discovered that as air pollution levels in Deming, New Mexico rose, so did the frequency of Google searches for 'Gangnam Style'. It's almost as if the residents, in the face of environmental challenges, sought refuge in the catchy beats and whimsical dance moves of Psy's global hit. It's like they said, "If the air's not clean, at least our dance moves can be!"

Our findings shed light on the mysterious ways in which human behavior is influenced by environmental factors, even when it comes to the seemingly frivolous world of internet searches. With this study, we pave the way for future research into the quirky connections between air quality and pop culture phenomena, showing that even in the realm of academic research, there's always room for a little Gangnam flair.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the old adage goes, "When the air quality's low, the Gangnam Style searches will grow." Okay, maybe that's not an old adage, but the unexpected correlation between air pollution levels and Google searches for 'Gangnam Style' has left the scientific community scratching their heads almost as vigorously as Psy's infamous horse-riding dance moves.
Air pollution, often seen as a villain in the environmental narrative, has taken an unexpected turn in our study. It seems that the residents of Deming, New Mexico have found a unique coping mechanism for the perils of polluted air, and it involves donning invisible horse reins and busting out their best Gangnam Style moves. It's almost as if they're saying, "If we can't breathe clean air, we might as well breathe in the infectious energy of K-pop."
In the realm of scientific inquiry, one must be prepared for the unexpected connections that arise from data analysis. In this case, we were prepared for air pollution to affect respiratory health, but how could we have foreseen its influence on internet search trends for a song that had seemingly galloped into the sunset of pop culture obscurity? It just goes to show that research can take us on unexpected, vibrant, and sometimes downright quirky rides.
Delving into the depths of environmental data from the Environmental Protection Agency and the digital echo chamber of Google searches, we found ourselves riding the statistical horse of correlation. With a correlation coefficient of 0.9318336 and a p-value that made statisticians do a double-take, we had to admit that this connection was as clear as a day with zero particulate matter in the air – which, in Deming, may be as rare as finding someone who doesn't secretly want to join a Gangnam Style flash mob.
But fear not, dear readers, for our statistical journey doesn't end there. With a dance in our step and a twinkle in our eye, we waltzed into the realm of cultural psychology, where we pondered the human penchant for seeking solace in unexpected places. After all, who would have thought that air pollution could also serve as a catalyst for a community-wide virtual dance party through online search queries?
In the following sections, we will dissect the nuances of this correlation, explore its implications, and perhaps even dive into the psyche of a populace who turns to a whimsical K-pop sensation in the face of environmental adversity. Join us as we embark on a scientific adventure that's as unpredictable and toe-tappingly delightful as a viral dance craze.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In their seminal work, Smith and Doe (2015) explored the intricate relationship between air pollution and human behavior, uncovering unexpected connections that had researchers raising their eyebrows higher than a Google Trends spike for 'Gangnam Style'. The authors found that as air quality diminished, individuals exhibited increased tendencies to seek out unconventional sources of joy and entertainment. It's almost as if they were saying, "If we can't have fresh air, at least we can have fresh dance moves."

Diving deeper into the realm of environmental psychology, Jones (2018) expanded on this notion, delving into the subconscious coping mechanisms employed by communities in the face of environmental challenges. These coping mechanisms, it turns out, often involve turning to seemingly unrelated cultural phenomena, such as viral dance crazes, for a much-needed dose of levity. It's like the old saying, "When the going gets tough, the tough start doing the Gangnam Style shuffle."

In "The Air We Breathe" (2016), the authors delve into the effects of air pollution on human cognitive processes, shedding light on how pollution can influence decision-making and behavior. Little did they know that their findings would extend to the realm of internet searches, with the siren call of 'Gangnam Style' beckoning in the digital haze like a whimsical mirage in a polluted desert.

Turning to the realm of pop culture and its influence on human behavior, "Pop Goes the Culture" (2017) by Poppy Le Pew examines the unexpected and often inexplicable ways in which popular culture seeps into the collective consciousness. But even Poppy may have been left flabbergasted by the idea that air pollution levels in Deming, New Mexico could spark a resurgence of interest in a dance sensation from across the globe. It's almost as if the air pollution whispered, "Oppan Gangnam Style" to the residents of Deming, and they couldn't help but oblige.

Taking a whimsical turn, we can't help but draw parallels between the unexpected correlation we've uncovered and the "Harry Potter" series by J.K. Rowling. Just as Harry and his friends stumbled upon enchanted connections and hidden corridors in Hogwarts, we've stumbled upon an enchanted correlation between air pollution and 'Gangnam Style' searches in our digital labyrinth. Who knew that the search for clean air in Deming, New Mexico would lead us down a rabbit hole straight into Psy's stylish Gangnam world?

Speaking of unexpected discoveries, let's not forget the influence of internet memes on contemporary culture. The viral spread of memes like "This is Fine" and the "Distracted Boyfriend" perfectly encapsulate how internet culture reflects and refracts the quirks of human behavior. Similarly, the surge in 'Gangnam Style' searches mirrors the internet's ability to amplify and propagate unexpected phenomena, much like the way air pollutants can disperse into the atmosphere. It's a digital whirlwind as unpredictable as a gust of wind in the midst of an air quality advisory.

As we wade through the literature, we find ourselves enveloped in a whirlwind of unexpected connections and whimsical turns, much like a rollercoaster ride through a cultural amusement park. With each study and reference, we uncover a treasure trove of insights that show us just how delightfully unpredictable the intersection of air pollution, internet searches, and pop culture can truly be. It's a wild ride, but as they say, "Life's a rollercoaster – just make sure to do the Gangnam Style dance at the peaks and valleys."

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 Deming, New Mexico and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delve into the unexpected correlation between air pollution levels in Deming, New Mexico, and the seemingly unrelated phenomenon of Google searches for the iconic hit 'Gangnam Style'. Our research team embarked on this journey with curious minds and a love for an academic riddle that's as elusive as a clean air day in a bustling city.

After meticulously analyzing data from the Environmental Protection Agency and Google Trends, we unearthed a startling correlation coefficient of 0.9318336 and p < 0.01 for the years 2012 to 2023. This statistically significant association had us dancing with joy, even if we had to do it Gangnam Style.

Unraveling this peculiar relationship, we discovered that as air pollution levels in Deming, New Mexico rose, so did the frequency of Google searches for 'Gangnam Style'. It's almost as if the residents, in the face of environmental challenges, sought refuge in the catchy beats and whimsical dance moves of Psy's global hit. It's like they said, "If the air's not clean, at least our dance moves can be!"

Our findings shed light on the mysterious ways in which human behavior is influenced by environmental factors, even when it comes to the seemingly frivolous world of internet searches. With this study, we pave the way for future research into the quirky connections between air quality and pop culture phenomena, showing that even in the realm of academic research, there's always room for a little Gangnam flair.

[[LITERATURE REVIEW]]
In their seminal work, Smith and Doe (2015) explored the intricate relationship between air pollution and human behavior, uncovering unexpected connections that had researchers raising their eyebrows higher than a Google Trends spike for 'Gangnam Style'. The authors found that as air quality diminished, individuals exhibited increased tendencies to seek out unconventional sources of joy and entertainment. It's almost as if they were saying, "If we can't have fresh air, at least we can have fresh dance moves."
Diving deeper into the realm of environmental psychology, Jones (2018) expanded on this notion, delving into the subconscious coping mechanisms employed by communities in the face of environmental challenges. These coping mechanisms, it turns out, often involve turning to seemingly unrelated cultural phenomena, such as viral dance crazes, for a much-needed dose of levity. It's like the old saying, "When the going gets tough, the tough start doing the Gangnam Style shuffle."
In "The Air We Breathe" (2016), the authors delve into the effects of air pollution on human cognitive processes, shedding light on how pollution can influence decision-making and behavior. Little did they know that their findings would extend to the realm of internet searches, with the siren call of 'Gangnam Style' beckoning in the digital haze like a whimsical mirage in a polluted desert.
Turning to the realm of pop culture and its influence on human behavior, "Pop Goes the Culture" (2017) by Poppy Le Pew examines the unexpected and often inexplicable ways in which popular culture seeps into the collective consciousness. But even Poppy may have been left flabbergasted by the idea that air pollution levels in Deming, New Mexico could spark a resurgence of interest in a dance sensation from across the globe. It's almost as if the air pollution whispered, "Oppan Gangnam Style" to the residents of Deming, and they couldn't help but oblige.
Taking a whimsical turn, we can't help but draw parallels between the unexpected correlation we've uncovered and the "Harry Potter" series by J.K. Rowling. Just as Harry and his friends stumbled upon enchanted connections and hidden corridors in Hogwarts, we've stumbled upon an enchanted correlation between air pollution and 'Gangnam Style' searches in our digital labyrinth. Who knew that the search for clean air in Deming, New Mexico would lead us down a rabbit hole straight into Psy's stylish Gangnam world?
Speaking of unexpected discoveries, let's not forget the influence of internet memes on contemporary culture. The viral spread of memes like "This is Fine" and the "Distracted Boyfriend" perfectly encapsulate how internet culture reflects and refracts the quirks of human behavior. Similarly, the surge in 'Gangnam Style' searches mirrors the internet's ability to amplify and propagate unexpected phenomena, much like the way air pollutants can disperse into the atmosphere. It's a digital whirlwind as unpredictable as a gust of wind in the midst of an air quality advisory.
As we wade through the literature, we find ourselves enveloped in a whirlwind of unexpected connections and whimsical turns, much like a rollercoaster ride through a cultural amusement park. With each study and reference, we uncover a treasure trove of insights that show us just how delightfully unpredictable the intersection of air pollution, internet searches, and pop culture can truly be. It's a wild ride, but as they say, "Life's a rollercoaster – just make sure to do the Gangnam Style dance at the peaks and valleys."

[[RESULTS]]
Our analysis of the data revealed a remarkably strong correlation between air pollution levels in Deming, New Mexico and Google searches for 'Gangnam Style' over the period from 2012 to 2023. The correlation coefficient of 0.9318336 indicated a highly positive relationship, which, much like a catchy song, was hard to get out of our heads. It seems that when the air quality dropped, the search interest in Psy's horse-riding anthem went up, proving that even in the world of statistics, opposites can attract – just like the magnetic pull of a chart-topping K-pop melody.
The r-squared value of 0.8683138 further solidified the strength of this connection, leaving us with a result as clear as the panoramic views from Gangnam district in Seoul, South Korea – the very birthplace of the global dance phenomenon. It's almost as if the statistical stars aligned to reveal this unexpected relationship, making us wonder if the air pollution itself was longing for a taste of Gangnam Style and decided to nudge the residents toward the nearest internet connection.
Additionally, the p-value of less than 0.01 left us in awe, much like stumbling upon a hidden dance floor in the midst of a bustling city – statistically, we were grooving to a significant beat. The likelihood of this correlation occurring by chance was as rare as finding someone who hasn't heard of 'Gangnam Style' – a statistical anomaly that got our pulses racing faster than a viral dance challenge.
Fig. 1 presents a visual representation of this striking correlation, showcasing the undeniable trend of increasing 'Gangnam Style' searches with rising levels of air pollution in Deming, New Mexico. It's as though the residents, faced with the haze of airborne particles, turned to the dance-based infectious rhythm for a breath of fresh, albeit metaphorical, air. If nothing else, it's proof that in the realm of scientific exploration, there's always room for a little'air-y' influence on pop culture phenomena.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

Our study has unearthed a compelling correlation between air pollution in Deming, New Mexico, and Google searches for 'Gangnam Style', shedding light on the fascinating and unexpected ways in which environmental factors can influence human behavior. As we delved into this peculiar relationship, we couldn't help but be reminded of the old adage: when the air gets hazy, the search interest gets jazzy - a real statistical twist on the classic dad joke format, if you will.

In line with prior research by Smith and Doe (2015) and Jones (2018), our findings support the notion that as air quality diminishes, individuals seek out unconventional sources of joy and entertainment – in this case, turning to the infectious beats and quirky dance moves of Psy's iconic hit. It's almost as if the residents of Deming were saying, "If the air's not clear, at least our internet search history can be," a sentiment that resonates even in the whimsical land of statistical analysis.

The strength of the correlation coefficient (0.9318336) echoes the resounding rhythm of 'Gangnam Style', affirming the robustness of this unexpected connection. It's as if the data itself couldn't resist doing the popular dance – a statistical phenomenon that left us chuckling in the midst of our rigorous analysis.

The r-squared value of 0.8683138 further reinforced the solidity of this relationship, much like the sturdy heels of a dancer executing the famed Gangnam horse-riding move. It seems that statistically, the allure of 'Gangnam Style' was as magnetic as a well-designed research study, drawing in the residents of Deming amidst the haze of air pollution.

Our study's findings, supported by the p-value of less than 0.01, paint an unmistakable picture – when it comes to the influence of air pollution on internet searches, the beat of 'Gangnam Style' rises to the forefront with a significance as striking as a well-timed dance break in a bustling city. This statistical significance had us meandering through the corridors of academia with the grace of Psy himself.

Our visualization of the correlation in Fig. 1 showcases the undeniable trend of increasing 'Gangnam Style' searches with rising air pollution levels, akin to a dance floor emerging from the smog as a virtual refuge in the haze. As we present these results, we can't help but think that even in the world of scientific inquiry, a little 'air-y' influence can lead to a dance with unexpected statistical significance.

In sum, our study illuminates the captivating interplay between environmental factors and human behavior, reminding us that even in the most unexpected corners of research, there's always room for a little Gangnam flair. As we conclude our discussion, we invite fellow academics to join us in embracing the delightful unpredictability of academic inquiry, and perhaps indulge in a spontaneous rendition of a certain iconic dance move – for the sake of statistics, of course.

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 Deming, New Mexico and Google searches for 'Gangnam Style'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'

[[ABSTRACT]]
In this study, we delve into the unexpected correlation between air pollution levels in Deming, New Mexico, and the seemingly unrelated phenomenon of Google searches for the iconic hit 'Gangnam Style'. Our research team embarked on this journey with curious minds and a love for an academic riddle that's as elusive as a clean air day in a bustling city.

After meticulously analyzing data from the Environmental Protection Agency and Google Trends, we unearthed a startling correlation coefficient of 0.9318336 and p < 0.01 for the years 2012 to 2023. This statistically significant association had us dancing with joy, even if we had to do it Gangnam Style.

Unraveling this peculiar relationship, we discovered that as air pollution levels in Deming, New Mexico rose, so did the frequency of Google searches for 'Gangnam Style'. It's almost as if the residents, in the face of environmental challenges, sought refuge in the catchy beats and whimsical dance moves of Psy's global hit. It's like they said, "If the air's not clean, at least our dance moves can be!"

Our findings shed light on the mysterious ways in which human behavior is influenced by environmental factors, even when it comes to the seemingly frivolous world of internet searches. With this study, we pave the way for future research into the quirky connections between air quality and pop culture phenomena, showing that even in the realm of academic research, there's always room for a little Gangnam flair.

[[INTRDUCTION]]
As the old adage goes, "When the air quality's low, the Gangnam Style searches will grow." Okay, maybe that's not an old adage, but the unexpected correlation between air pollution levels and Google searches for 'Gangnam Style' has left the scientific community scratching their heads almost as vigorously as Psy's infamous horse-riding dance moves.
Air pollution, often seen as a villain in the environmental narrative, has taken an unexpected turn in our study. It seems that the residents of Deming, New Mexico have found a unique coping mechanism for the perils of polluted air, and it involves donning invisible horse reins and busting out their best Gangnam Style moves. It's almost as if they're saying, "If we can't breathe clean air, we might as well breathe in the infectious energy of K-pop."
In the realm of scientific inquiry, one must be prepared for the unexpected connections that arise from data analysis. In this case, we were prepared for air pollution to affect respiratory health, but how could we have foreseen its influence on internet search trends for a song that had seemingly galloped into the sunset of pop culture obscurity? It just goes to show that research can take us on unexpected, vibrant, and sometimes downright quirky rides.
Delving into the depths of environmental data from the Environmental Protection Agency and the digital echo chamber of Google searches, we found ourselves riding the statistical horse of correlation. With a correlation coefficient of 0.9318336 and a p-value that made statisticians do a double-take, we had to admit that this connection was as clear as a day with zero particulate matter in the air – which, in Deming, may be as rare as finding someone who doesn't secretly want to join a Gangnam Style flash mob.
But fear not, dear readers, for our statistical journey doesn't end there. With a dance in our step and a twinkle in our eye, we waltzed into the realm of cultural psychology, where we pondered the human penchant for seeking solace in unexpected places. After all, who would have thought that air pollution could also serve as a catalyst for a community-wide virtual dance party through online search queries?
In the following sections, we will dissect the nuances of this correlation, explore its implications, and perhaps even dive into the psyche of a populace who turns to a whimsical K-pop sensation in the face of environmental adversity. Join us as we embark on a scientific adventure that's as unpredictable and toe-tappingly delightful as a viral dance craze.

[[RESULTS]]
Our analysis of the data revealed a remarkably strong correlation between air pollution levels in Deming, New Mexico and Google searches for 'Gangnam Style' over the period from 2012 to 2023. The correlation coefficient of 0.9318336 indicated a highly positive relationship, which, much like a catchy song, was hard to get out of our heads. It seems that when the air quality dropped, the search interest in Psy's horse-riding anthem went up, proving that even in the world of statistics, opposites can attract – just like the magnetic pull of a chart-topping K-pop melody.
The r-squared value of 0.8683138 further solidified the strength of this connection, leaving us with a result as clear as the panoramic views from Gangnam district in Seoul, South Korea – the very birthplace of the global dance phenomenon. It's almost as if the statistical stars aligned to reveal this unexpected relationship, making us wonder if the air pollution itself was longing for a taste of Gangnam Style and decided to nudge the residents toward the nearest internet connection.
Additionally, the p-value of less than 0.01 left us in awe, much like stumbling upon a hidden dance floor in the midst of a bustling city – statistically, we were grooving to a significant beat. The likelihood of this correlation occurring by chance was as rare as finding someone who hasn't heard of 'Gangnam Style' – a statistical anomaly that got our pulses racing faster than a viral dance challenge.
Fig. 1 presents a visual representation of this striking correlation, showcasing the undeniable trend of increasing 'Gangnam Style' searches with rising levels of air pollution in Deming, New Mexico. It's as though the residents, faced with the haze of airborne particles, turned to the dance-based infectious rhythm for a breath of fresh, albeit metaphorical, air. If nothing else, it's proof that in the realm of scientific exploration, there's always room for a little'air-y' influence on pop culture phenomena.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unraveled a connection between air pollution in Deming, New Mexico and Google searches for 'Gangnam Style' that's as undeniable as a dad trying to impress his kids with his dance moves at a family gathering. Our findings highlight the intricate ways in which environmental factors can steer human behavior in unexpectedly catchy directions. It's almost as if the polluted air whispered to the residents, "Hey, why breathe when you can groove?"
This intriguing correlation has opened doors to a whole new avenue of research, albeit a slightly whimsical one. It's like stumbling upon a scientific treasure map that leads to Gangnam-style dance-offs instead of buried gold. However, as much as our academic hearts might want to dive into more 'entertaining' correlations, we must resist the siren call of K-pop-infused statistical analysis. As much fun as it has been, we can confidently say that no further research is needed in this area. Let's let Gangnam Air have its moment in the research spotlight, and who knows, maybe it'll inspire a dance revolution in the world of science. But for now, we'll gracefully bow out, leaving the statistical dance floor open for other pressing inquiries. As Psy himself would say, "Oppan research style!"

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 Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Unusual Correlations

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 Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Whimsical Environmental Research (CWER)

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 Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style' with an abstract of In this study, we delve into the unexpected correlation between air pollution levels in Deming, New Mexico, and the seemingly unrelated phenomenon of Google searches for the iconic hit 'Gangnam Style'. Our research team embarked on this journey with curious minds and a love for an academic riddle that's as elusive as a clean air day in a bustling city.
After meticulously analyzing data from the Environmental Protection Agency and Google Trends, we unearthed a startling correlation coefficient of 0.9318336 and p < 0.01 for the years 2012 to 2023. This statistically significant association had us dancing with joy, even if we had to do it Gangnam Style.
Unraveling this peculiar relationship, we discovered that as air pollution levels in Deming, New Mexico rose, so did the frequency of Google searches for 'Gangnam Style'. It's almost as if the residents, in the face of environmental challenges, sought refuge in the catchy beats and whimsical dance moves of Psy's global hit. It's like they said, "If the air's not clean, at least our dance moves can be!"
Our findings shed light on the mysterious ways in which human behavior is influenced by environmental factors, even when it comes to the seemingly frivolous world of internet searches. With this study, we pave the way for future research into the quirky connections between air quality and pop culture phenomena, showing that even in the realm of academic research, there's always room for a little Gangnam flair.

ChatGPT:

air pollution, Deming New Mexico, Google searches, Gangnam Style, correlation, Environmental Protection Agency, Google Trends, correlation coefficient, human behavior, environmental factors, internet searches, air quality, pop culture phenomena, academic research

*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 Deming, New Mexico
Detailed data title: Percentage of days with moderate or worse air quality in Deming, NM
Source: Environmental Protection Agency
See what else correlates with Air pollution in Deming, New Mexico

Google searches for 'Gangnam Style'
Detailed data title: Relative volume of Google searches for 'Gangnam Style' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'Gangnam Style'

Correlation r = 0.9318336 (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 = 0.8683138 (Coefficient of determination)
This means 86.8% of the change in the one variable (i.e., Google searches for 'Gangnam Style') is predictable based on the change in the other (i.e., Air pollution in Deming, New Mexico) over the 12 years from 2012 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.03E-5.^Show 0.0000103302989299936520000000
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 0.93 in 0.00103% of random cases. Said differently, if you correlated 96,803 random variables^Note You don't actually need 96 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 11 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 11 because we have two variables measured over a period of 12 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.

[ 0.77, 0.98 ] 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.

	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Air pollution in Deming, New Mexico (Bad air quality days)	0.384615	0.339726	0.162088	0.0112676	0.0611111	0.0555556	0.0392157	0.033241	0.0536723	0.0635359	0.114525	0.0747126
Google searches for 'Gangnam Style' (Rel. search volume)	36.9	20.3333	4.66667	2.83333	1.33333	1	1	1	1	1	1	1

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([0.384615,0.339726,0.162088,0.0112676,0.0611111,0.0555556,0.0392157,0.033241,0.0536723,0.0635359,0.114525,0.0747126,])
array_2 = np.array([36.9,20.3333,4.66667,2.83333,1.33333,1,1,1,1,1,1,1,])
array_1_name = "Air pollution in Deming, New Mexico"
array_2_name = "Google searches for 'Gangnam Style'"

# 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 Deming, New Mexico
Line chart for only Google searches for 'Gangnam Style'
AI-generated correlation image
The spurious research paper: Gangnam Air: A Study on the Correlation between Air Pollution in Deming, New Mexico and Google Searches for 'Gangnam Style'

View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!

Correlation ID: 4697 · Black Variable ID: 21805 · Red Variable ID: 1442


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