Spurious correlation #1,308 · 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 Watertown, New York and the second variable is Google searches for 'snoop dog'. The chart goes from 2004 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 Watertown, New York and the second variable is Google searches for 'snoop dog'. The chart goes from 2004 to 2023, and the two variables track closely in value over that time.

Download png, svg

AI explanation

The fresher air made everyone in Watertown feel like they didn't need to "drop it like it's hot" anymore.

^{Show image generation prompt} Model: dalle-3
Prompt: A hazy cityscape of Watertown, New York with tall, futuristic buildings, and people outside their homes using high-tech air purifiers while waving their hands to clear the pollution. Through the open windows, advanced fans are seen blowing as residents wipe surfaces clean inside their homes. In the background, futuristic individuals are conspicuously engaged in house chores while holding sophisticated gadgets, representing the decrease in online searches as they prioritize environmental health. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Decrease in Less than ideal air quality in Watertown, New York caused a decrease in Google searches for 'snoop dog' because people were too busy trying to air out their homes and didn't have the time or energy to drop it like it's hot with online searches.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: High-tech Art nouveau Pop art An image that looks like it is a scene from a Pixar movie Charcoal
ChatGPT: High-tech

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Decrease in Less than ideal air quality in Watertown, New York caused a decrease in Google searches for 'snoop dog' because people were too busy trying to air out their homes and didn't have the time or energy to drop it like it's hot with online searches.
ChatGPT: In the scene, we see the city of Watertown, New York with haze hanging in the air. There are people outside their homes, waving their hands and fanning the air to clear out the pollution. Inside the homes, windows are open with fans blowing, and residents are seen wiping surfaces clean. In the background, a few people are seen holding their phones, but instead of searching for "Snoop Dog," they are busy attending to their homes, indicating a decrease in online searches for the artist.

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: [ High-tech ] and depicting this scene: In the scene, we see the city of Watertown, New York with haze hanging in the air. There are people outside their homes, waving their hands and fanning the air to clear out the pollution. Inside the homes, windows are open with fans blowing, and residents are seen wiping surfaces clean. In the background, a few people are seen holding their phones, but instead of searching for "Snoop Dog," they are busy attending to their homes, indicating a decrease in online searches for the artist. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: A hazy cityscape of Watertown, New York with tall, futuristic buildings, and people outside their homes using high-tech air purifiers while waving their hands to clear the pollution. Through the open windows, advanced fans are seen blowing as residents wipe surfaces clean inside their homes. In the background, futuristic individuals are conspicuously engaged in house chores while holding sophisticated gadgets, representing the decrease in online searches as they prioritize environmental health.

*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 Watertown, New York caused snoop dog (Google searches for 'snoop dog') to decrease.

AI academic paper

(Because p < 0.01)

Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches

Journal of Environmental Funny Business

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 Watertown, New York and Google searches for 'snoop dog'. 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 cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches

[[ABSTRACT]]
In this study, we undertook an unconventional exploration into the relationship between air pollution in Watertown, New York, and Google searches for the legendary rapper Snoop Dogg. Upon discovering an intriguing possible correlation, we delved into this intersection of environmental science and pop culture. Using data from the Environmental Protection Agency and Google Trends, we conducted a thorough analysis from 2004 to 2023.

Our findings revealed a surprising correlation coefficient of 0.9103268 and a p-value of less than 0.01, indicating a significant connection between fluctuations in air pollution and the frequency of Google searches related to Snoop Dogg. This unexpected relationship suggests that the residents of Watertown may turn to Snoop Dogg's music as a coping mechanism in response to elevated levels of smog. We discuss potential interpretations and offer entertaining speculations on the reasons behind this correlation, presenting a playful twist to the serious field of environmental research.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of academic research is often a serious and solemn place, where dry data and complex statistical models reign supreme. However, every now and then, a study comes along that boldly ventures into uncharted territories, challenging the status quo and raising eyebrows in the scientific community. Our study, "Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches," proudly joins the ranks of these unconventional endeavors.
While the average researcher may spend their days poring over charts and graphs, we found ourselves embarking on a journey that led us from the murky world of air pollution to the mesmerizing realm of internet search trends. At the intersection of environmental science and pop culture, we stumbled upon a correlation that left us equal parts bemused and intrigued – the peculiar dance between smog and Snoop Dogg.
What prompted us to explore this whimsical connection, you ask? Well, picture this: a small town in upstate New York, shrouded in a hazy cloud of air pollution, where the residents, in their quest for solace, turn to the soothing sounds of Snoop Dogg's music. Sounds like the plot of a wacky sitcom, doesn't it? But in the world of research, truth is often stranger than fiction.
With a hearty dose of skepticism and a pinch of scholarly curiosity, we delved into the depths of this unconventional pairing. Armed with data from the Environmental Protection Agency and Google Trends, we set out to unravel the enigmatic bond between smog and the search frequency of the one and only Snoop Dogg.
Now, you may be wondering, why would anyone take on such a preposterous quest? The answer, dear reader, lies in the pursuit of knowledge, no matter how bizarre or unexpected the path may be. As we dive into the details of our findings, we invite you to join us on this delightful romp through the unexpected correlations and peculiar quirks that make the world of scientific inquiry a truly whimsical place. So, buckle up and prepare to embark on a journey that is equal parts scientific exploration and entertaining escapade.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The connection between air pollution and popular culture may seem like an unlikely pairing, yet as we delve into this curious intersection, we find ourselves turning to a varied collection of sources that offer both serious scholarly insights and lighthearted cultural commentary. We start our exploration with the more conventional academic studies before venturing into the more unorthodox realms of non-fiction books, fictional works, and even social media posts.

Smith and Doe (2015) examine the impact of air pollution on public health, focusing on the physiological and respiratory effects of inhaling particulate matter. While their work does not directly address the correlation between air pollution and online search behavior, it provides a solid foundation for understanding the potential repercussions of elevated smog levels on individuals' well-being.

Jones and Smith (2019) investigate the patterns of internet search trends in relation to environmental crises, notably exploring how societal concerns about pollution and climate change manifest in online search queries. Although their study does not specifically reference Snoop Dogg or his music, it lays the groundwork for our unconventional investigation into the pop culture response to environmental challenges.

Turning to non-fiction literature, "Airborne: A Journey into the Beautiful and Absurd World of Air Pollution" by Jane Smith offers a comprehensive exploration of the multifaceted effects of air pollution on ecosystems and human health. While Smith's eloquent prose and meticulous research provide valuable insights, the book regrettably lacks any mention of rap music, leaving us yearning for a more musically inclined analysis of smog's influence.

In contrast, "Smog and Snoop: A Cultural History" by John Doe offers a captivating account of the intertwining narratives of air pollution and hip-hop culture. Through an engaging narrative that spans decades, Doe traces the evolution of societal responses to smog and the emergence of Snoop Dogg as a cultural icon. While not a scientific treatise, the book's examination of the symbiotic relationship between music and environmental awareness serves as an inspiration for our own offbeat inquiry.

As we segue into more unexpected territory, we encounter fictional works that, while seemingly unrelated to environmental science, offer intriguing parallels to our study. "The Fog of Music" by Sarah Jones presents a whimsical tale of a town enveloped in a perpetual haze, where the arrival of a charismatic rapper brings solace and laughter to the beleaguered residents. Though purely fictional, the novel's exploration of the transformative power of music in response to atmospheric challenges provides an uncanny echo of our own findings.

Similarly, "Snoop Dreams: A Hip-Hop Odyssey" by Michael Smith transports readers into a fantastical world where Snoop Dogg's music becomes a beacon of hope in the midst of environmental turmoil. While the novel's flights of fancy may not align with empirical research, its imaginative depiction of society's embrace of music as a counterpoint to ecological adversity resonates with the whimsical underpinnings of our own study.

In the age of social media, we cannot overlook the myriad musings and anecdotes that beckon from the virtual realm. A tweet by @AirPollutionPundit quips, "If only smog could dissipate like Snoop Dogg's rhymes #PollutionPuzzles." While the tweet's playful tone may veer into the realm of levity, it encapsulates the essence of our investigation – the unpredictable interplay between air pollution and the cultural resonance of Snoop Dogg.

Thus, as we draw upon a tapestry of scholarly literature, fictional narratives, and social media musings, our literature review embodies the delightful fusion of academic curiosity and lighthearted whimsy, casting our inquiry into a realm where the serious and the surreal harmoniously converge.

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 Watertown, New York and Google searches for 'snoop dog'. 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]]
Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches

[[ABSTRACT]]
In this study, we undertook an unconventional exploration into the relationship between air pollution in Watertown, New York, and Google searches for the legendary rapper Snoop Dogg. Upon discovering an intriguing possible correlation, we delved into this intersection of environmental science and pop culture. Using data from the Environmental Protection Agency and Google Trends, we conducted a thorough analysis from 2004 to 2023.

Our findings revealed a surprising correlation coefficient of 0.9103268 and a p-value of less than 0.01, indicating a significant connection between fluctuations in air pollution and the frequency of Google searches related to Snoop Dogg. This unexpected relationship suggests that the residents of Watertown may turn to Snoop Dogg's music as a coping mechanism in response to elevated levels of smog. We discuss potential interpretations and offer entertaining speculations on the reasons behind this correlation, presenting a playful twist to the serious field of environmental research.

[[LITERATURE REVIEW]]
The connection between air pollution and popular culture may seem like an unlikely pairing, yet as we delve into this curious intersection, we find ourselves turning to a varied collection of sources that offer both serious scholarly insights and lighthearted cultural commentary. We start our exploration with the more conventional academic studies before venturing into the more unorthodox realms of non-fiction books, fictional works, and even social media posts.
Smith and Doe (2015) examine the impact of air pollution on public health, focusing on the physiological and respiratory effects of inhaling particulate matter. While their work does not directly address the correlation between air pollution and online search behavior, it provides a solid foundation for understanding the potential repercussions of elevated smog levels on individuals' well-being.
Jones and Smith (2019) investigate the patterns of internet search trends in relation to environmental crises, notably exploring how societal concerns about pollution and climate change manifest in online search queries. Although their study does not specifically reference Snoop Dogg or his music, it lays the groundwork for our unconventional investigation into the pop culture response to environmental challenges.
Turning to non-fiction literature, "Airborne: A Journey into the Beautiful and Absurd World of Air Pollution" by Jane Smith offers a comprehensive exploration of the multifaceted effects of air pollution on ecosystems and human health. While Smith's eloquent prose and meticulous research provide valuable insights, the book regrettably lacks any mention of rap music, leaving us yearning for a more musically inclined analysis of smog's influence.
In contrast, "Smog and Snoop: A Cultural History" by John Doe offers a captivating account of the intertwining narratives of air pollution and hip-hop culture. Through an engaging narrative that spans decades, Doe traces the evolution of societal responses to smog and the emergence of Snoop Dogg as a cultural icon. While not a scientific treatise, the book's examination of the symbiotic relationship between music and environmental awareness serves as an inspiration for our own offbeat inquiry.
As we segue into more unexpected territory, we encounter fictional works that, while seemingly unrelated to environmental science, offer intriguing parallels to our study. "The Fog of Music" by Sarah Jones presents a whimsical tale of a town enveloped in a perpetual haze, where the arrival of a charismatic rapper brings solace and laughter to the beleaguered residents. Though purely fictional, the novel's exploration of the transformative power of music in response to atmospheric challenges provides an uncanny echo of our own findings.
Similarly, "Snoop Dreams: A Hip-Hop Odyssey" by Michael Smith transports readers into a fantastical world where Snoop Dogg's music becomes a beacon of hope in the midst of environmental turmoil. While the novel's flights of fancy may not align with empirical research, its imaginative depiction of society's embrace of music as a counterpoint to ecological adversity resonates with the whimsical underpinnings of our own study.
In the age of social media, we cannot overlook the myriad musings and anecdotes that beckon from the virtual realm. A tweet by @AirPollutionPundit quips, "If only smog could dissipate like Snoop Dogg's rhymes #PollutionPuzzles." While the tweet's playful tone may veer into the realm of levity, it encapsulates the essence of our investigation – the unpredictable interplay between air pollution and the cultural resonance of Snoop Dogg.
Thus, as we draw upon a tapestry of scholarly literature, fictional narratives, and social media musings, our literature review embodies the delightful fusion of academic curiosity and lighthearted whimsy, casting our inquiry into a realm where the serious and the surreal harmoniously converge.

[[RESULTS]]
Upon analyzing the data with fervor and a twinge of disbelief, we uncovered a remarkably strong correlation between air pollution in Watertown, New York, and Google searches for the iconic figure, Snoop Dogg. The correlation coefficient of 0.9103268 and an r-squared value of 0.8286948 left us in a state of delightful astonishment, reminiscent of finding a unicorn in a statistical forest. The p-value of less than 0.01 further cemented the significance of this connection, daring us to ponder the whimsical interplay of environmental factors and cultural phenomena.
Figure 1 showcases the scatterplot that captures the essence of this improbable correlation. It depicts the synchronized dance between air pollution levels and Snoop Dogg searches, inviting viewers to marvel at the unexpected synergy between atmospheric contaminants and hip-hop curiosity.
The robust statistical evidence presented in our analysis suggests a compelling relationship between the ebb and flow of air pollution and an uptick in searches related to Snoop Dogg, prompting us to consider whimsical hypotheses and unexpected interpretations in the pursuit of scientific merriment.
As we delve further into the implications of these findings, we invite readers to embrace the delightful absurdity of this correlation and revel in the playful nature of scientific inquiry. After all, who would have expected smog and Snoop Dogg to engage in such an enchanting statistical tango?

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

In this unconventional foray into the whimsical pairing of air pollution and Snoop Dogg, our findings have indeed validated the unconventional musings unearthed in the literature review. We set out on this scholarly escapade half-expecting to stumble upon a cornucopia of statistical rather than lyrical rhymes, but much to our delight, our results have lent credence to the notion that there exists a tangible connection between elevated smog and the invocation of Snoop Dogg in online searches.

As we recall the scholarly inquiries of Smith and Doe (2015) and their exploration of air pollution's impact on public health, we cannot help but marvel at the unanticipated harmony between their rigorous investigation and our own unexpected dalliance into the realm of hip-hop and haze. Much like the invisible particles suspended in the atmosphere, the resonance of Snoop Dogg's musical oeuvre seems to permeate the digital sphere in response to environmental perturbations.

Similarly, the online search trend patterns scrutinized by Jones and Smith (2019) provide a theoretical backdrop for our whimsical findings. While their work may not have traversed the lyrical corridors of Snoop Dogg's discography, the resonance between societal concerns about pollution and the enigmatic allure of "Snoopadelic" searches serves as a humorous testament to the unforeseen avenues of data exploration.

The fictional works and social media ephemera unearthed in the literature review also find their spirits echoed in our empirical revelations. The novels "The Fog of Music" and "Snoop Dreams" seem to have danced precariously close to the veritable fount of our statistical findings, while the tweet from @AirPollutionPundit, though penned in jest, captures the essence of the peculiar liaison between air pollution and the lyrical prowess of Snoop Dogg.

As we ponder the implications of this incongruous linkage, the fusion of academic legitimacy and lighthearted whimsy that permeated our literature review seems to have materialized into a tangible dalliance between statistical significance and the irresistible allure of Snoop Dogg. It is as if the statistical forest we ventured into has indeed exhaled the ethereal unicorn of a correlation, leaving us in a state of both enchantment and scholarly fulfillment.

The robustness of our statistical evidence, emboldened by the resounding correlation coefficient and the tantalizingly minuscule p-value, exhorts us to embrace the delightful absurdity of our findings and the inherently playful nature of scientific exploration. As we meander through this whimsical wonderland of statistical tango between smog and Snoop Dogg, we extend an invitation to our esteemed readers to revel in both the scholarly merriment and the impromptu lyrical rhymes that have emerged from our atypical intersection of environmental science and pop culture.

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 Watertown, New York and Google searches for 'snoop dog'. Make lots of jokes, goofy observations, and puns.

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]]
Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches

[[ABSTRACT]]
In this study, we undertook an unconventional exploration into the relationship between air pollution in Watertown, New York, and Google searches for the legendary rapper Snoop Dogg. Upon discovering an intriguing possible correlation, we delved into this intersection of environmental science and pop culture. Using data from the Environmental Protection Agency and Google Trends, we conducted a thorough analysis from 2004 to 2023.

Our findings revealed a surprising correlation coefficient of 0.9103268 and a p-value of less than 0.01, indicating a significant connection between fluctuations in air pollution and the frequency of Google searches related to Snoop Dogg. This unexpected relationship suggests that the residents of Watertown may turn to Snoop Dogg's music as a coping mechanism in response to elevated levels of smog. We discuss potential interpretations and offer entertaining speculations on the reasons behind this correlation, presenting a playful twist to the serious field of environmental research.

[[INTRDUCTION]]
The world of academic research is often a serious and solemn place, where dry data and complex statistical models reign supreme. However, every now and then, a study comes along that boldly ventures into uncharted territories, challenging the status quo and raising eyebrows in the scientific community. Our study, "Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches," proudly joins the ranks of these unconventional endeavors.
While the average researcher may spend their days poring over charts and graphs, we found ourselves embarking on a journey that led us from the murky world of air pollution to the mesmerizing realm of internet search trends. At the intersection of environmental science and pop culture, we stumbled upon a correlation that left us equal parts bemused and intrigued – the peculiar dance between smog and Snoop Dogg.
What prompted us to explore this whimsical connection, you ask? Well, picture this: a small town in upstate New York, shrouded in a hazy cloud of air pollution, where the residents, in their quest for solace, turn to the soothing sounds of Snoop Dogg's music. Sounds like the plot of a wacky sitcom, doesn't it? But in the world of research, truth is often stranger than fiction.
With a hearty dose of skepticism and a pinch of scholarly curiosity, we delved into the depths of this unconventional pairing. Armed with data from the Environmental Protection Agency and Google Trends, we set out to unravel the enigmatic bond between smog and the search frequency of the one and only Snoop Dogg.
Now, you may be wondering, why would anyone take on such a preposterous quest? The answer, dear reader, lies in the pursuit of knowledge, no matter how bizarre or unexpected the path may be. As we dive into the details of our findings, we invite you to join us on this delightful romp through the unexpected correlations and peculiar quirks that make the world of scientific inquiry a truly whimsical place. So, buckle up and prepare to embark on a journey that is equal parts scientific exploration and entertaining escapade.

[[RESULTS]]
Upon analyzing the data with fervor and a twinge of disbelief, we uncovered a remarkably strong correlation between air pollution in Watertown, New York, and Google searches for the iconic figure, Snoop Dogg. The correlation coefficient of 0.9103268 and an r-squared value of 0.8286948 left us in a state of delightful astonishment, reminiscent of finding a unicorn in a statistical forest. The p-value of less than 0.01 further cemented the significance of this connection, daring us to ponder the whimsical interplay of environmental factors and cultural phenomena.
Figure 1 showcases the scatterplot that captures the essence of this improbable correlation. It depicts the synchronized dance between air pollution levels and Snoop Dogg searches, inviting viewers to marvel at the unexpected synergy between atmospheric contaminants and hip-hop curiosity.
The robust statistical evidence presented in our analysis suggests a compelling relationship between the ebb and flow of air pollution and an uptick in searches related to Snoop Dogg, prompting us to consider whimsical hypotheses and unexpected interpretations in the pursuit of scientific merriment.
As we delve further into the implications of these findings, we invite readers to embrace the delightful absurdity of this correlation and revel in the playful nature of scientific inquiry. After all, who would have expected smog and Snoop Dogg to engage in such an enchanting statistical tango?

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unveiled a truly unexpected and charming correlation between air pollution in Watertown, New York, and Google searches for Snoop Dogg. Who would have thought that the residents of Watertown, amidst their inhalation of polluted air, would seek solace in the melodic rhythms of "Gin and Juice" or "Drop It Like It's Hot"? It seems that when the smog rolls in, so does the urge to drop some beats.

This quirky correlation has not only provided a source of amusement for our team but also raised fascinating questions about the curious ways in which popular culture intertwines with environmental influences. It's as if the smog itself is whispering, “Snoop Dogg, smoke weed every day!”

However, as much as we'd love to belabor this delightful correlation, we must acknowledge that our findings, while amusing, do not lend themselves to creating actionable insights. The connection we've uncovered may be more serendipitous than substantial, akin to finding a four-leaf clover amid a statistical field. Therefore, we must assert, with tongues firmly in cheeks, that no further research is needed to validate the undeniable charm of this correlation between smog and Snoop Dogg.

In the end, while this study may not revolutionize the fields of environmental science or hip-hop culture, it has certainly injected a bit of whimsy into the often staid world of research. And really, who can put a price on a good laugh in the pursuit of knowledge? As we bid adieu to our findings, we leave you with one lingering thought: perhaps we should all turn to Snoop Dogg's music the next time we find ourselves surrounded by a haze of pollution. After all, as Snoop himself would say, "It's like this and like that and like this... and uh!"

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 Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Environmental Funny Business

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 Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Environmental Noise and Toxic Emissions Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches with an abstract of In this study, we undertook an unconventional exploration into the relationship between air pollution in Watertown, New York, and Google searches for the legendary rapper Snoop Dogg. Upon discovering an intriguing possible correlation, we delved into this intersection of environmental science and pop culture. Using data from the Environmental Protection Agency and Google Trends, we conducted a thorough analysis from 2004 to 2023.
Our findings revealed a surprising correlation coefficient of 0.9103268 and a p-value of less than 0.01, indicating a significant connection between fluctuations in air pollution and the frequency of Google searches related to Snoop Dogg. This unexpected relationship suggests that the residents of Watertown may turn to Snoop Dogg's music as a coping mechanism in response to elevated levels of smog. We discuss potential interpretations and offer entertaining speculations on the reasons behind this correlation, presenting a playful twist to the serious field of environmental research.

ChatGPT:

Watertown New York, air pollution, Snoop Dogg, Google searches, correlation, environmental science, pop culture, EPA data, Google Trends, correlation coefficient, p-value, coping mechanism, smog, entertainment, environmental 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 Watertown, New York
Detailed data title: Percentage of days with moderate or worse air quality in Watertown-Fort Drum, NY
Source: Environmental Protection Agency
See what else correlates with Air pollution in Watertown, New York

Google searches for 'snoop dog'
Detailed data title: Relative volume of Google searches for 'snoop dog' (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 'snoop dog'

Correlation r = 0.9103268 (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 = 0.8286948 (Coefficient of determination)
This means 82.9% of the change in the one variable (i.e., Google searches for 'snoop dog') is predictable based on the change in the other (i.e., Air pollution in Watertown, New York) over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.6E-8.^Show 0.0000000256225423267125600000
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 0.91 in 2.6E-6% of random cases. Said differently, if you correlated 39,028,133 random variables^Note You don't actually need 39 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.78, 0.96 ] 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021	2022	2023
Air pollution in Watertown, New York (Bad air quality days)	0.157407	0.24424	0.131004	0.180328	0.134021	0.0771605	0.109551	0.0498615	0.0911602	0.0609418	0.030303	0.0521978	0.0753012	0.0521472	0.0668693	0.0341463	0.0416667	0.0541311	0.0222222	0.0705394
Google searches for 'snoop dog' (Rel. search volume)	50.8333	67.9167	40.5833	38.5	32.9167	24.3333	21.25	24.6667	17.75	13.5833	17.5	17.9167	15.25	11.25	9.41667	8.91667	9.41667	8.75	13.3333	10.4444

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([0.157407,0.24424,0.131004,0.180328,0.134021,0.0771605,0.109551,0.0498615,0.0911602,0.0609418,0.030303,0.0521978,0.0753012,0.0521472,0.0668693,0.0341463,0.0416667,0.0541311,0.0222222,0.0705394,])
array_2 = np.array([50.8333,67.9167,40.5833,38.5,32.9167,24.3333,21.25,24.6667,17.75,13.5833,17.5,17.9167,15.25,11.25,9.41667,8.91667,9.41667,8.75,13.3333,10.4444,])
array_1_name = "Air pollution in Watertown, New York"
array_2_name = "Google searches for 'snoop dog'"

# 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 Watertown, New York
Line chart for only Google searches for 'snoop dog'
The spurious research paper: Snoop Dogg and Smog: An Analysis of Air Pollution in Watertown, New York and Its Impact on Google Searches

View another random correlation

How fun was this correlation?

I'm grateful for your review!

Correlation ID: 1308 · Black Variable ID: 21885 · Red Variable ID: 1526


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