about · email me · subscribe
Spurious correlation #5,219 · 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 Cleveland 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. Small Image
Download png
, svg

AI explanation

As air pollution in Cleveland decreased, people's respiratory systems became more efficient, leading to an uptake in oxygen levels. This increase in oxygen prompted a shift in brain activity, specifically in the regions responsible for music and dance. The brain's newfound clarity and functionality redirected societal interest towards more sophisticated and varied forms of entertainment, causing a decline in the popularity of the iconic 'Gangnam Style' dance. It seems that cleaner air may have not only cleared their lungs, but also their dance floors.

Model: dalle-3
Prompt: Generate an image that resembles a setting from 'Star Wars' showcasing a futuristic and technologically advanced Cleveland skyline. The skyline is adorned with sleek buildings and digital screens, all set against a backdrop of crystal clear blue skies. People are seen enjoying the fresh and smog-free air, engaging in various activities. Meanwhile, the digital screens in the city display a decline in Google searches for 'Gangnam Style', indicating a shift in public interest towards a diverse range of entertainment options. 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 Cleveland 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: Pop art Futuristic Futuristic a Polaroid photo An image that looks like it is a scene from 'Star Wars'
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Cleveland and Google searches for 'Gangnam Style', in the following situation: As air pollution in Cleveland decreased, people's respiratory systems became more efficient, leading to an uptake in oxygen levels. This increase in oxygen prompted a shift in brain activity, specifically in the regions responsible for music and dance. The brain's newfound clarity and functionality redirected societal interest towards more sophisticated and varied forms of entertainment, causing a decline in the popularity of the iconic 'Gangnam Style' dance. It seems that cleaner air may have not only cleared their lungs, but also their dance floors.. Keep the description simple.
ChatGPT: A smog-free Cleveland skyline, with clear blue skies, and people breathing in the fresh air. Meanwhile, digital screens in the city show a decline in Google searches for 'Gangnam Style', as people's interest shifts towards more varied forms of entertainment.

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: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: A smog-free Cleveland skyline, with clear blue skies, and people breathing in the fresh air. Meanwhile, digital screens in the city show a decline in Google searches for 'Gangnam Style', as people's interest shifts towards more varied forms of entertainment. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that resembles a setting from 'Star Wars' showcasing a futuristic and technologically advanced Cleveland skyline. The skyline is adorned with sleek buildings and digital screens, all set against a backdrop of crystal clear blue skies. People are seen enjoying the fresh and smog-free air, engaging in various activities. Meanwhile, the digital screens in the city display a decline in Google searches for 'Gangnam Style', indicating a shift in public interest towards a diverse range of entertainment options.

*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.

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 Cleveland caused Gangnam Style (Google searches for 'Gangnam Style') to decrease.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches

The International Journal of Unlikely Correlations

Jan 2024

Reminder: This paper is AI-generated. Not real!
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 researcher writing an academic paper.You write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between Air pollution in Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8005456 and p < 0.01 for 2012 to 2023.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the introduction 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 introduction section of an academic research paper presenting the findings of the connection between Air pollution in Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

Air pollution is a pervasive problem with significant implications for public health, environmental quality, and the integrity of our atmosphere. The adverse effects of air pollution on respiratory health, cardiovascular function, and overall well-being are well-documented in the research literature (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019). Concurrently, the rise of internet culture and the dominance of search engines like Google have become integral to daily life, providing a window into the collective consciousness of society (Braun & Beck, 2015; Patel & Williams, 2018). In recent years, the meteoric spread of viral phenomena through online platforms has captured the imagination of the global populace, generating a plethora of data ripe for exploration.

It is against this backdrop that a seemingly incongruous connection surfaced – the relationship between air pollution in Cleveland, Ohio, and the surge of Google searches for the iconic "Gangnam Style" during the same period. The playful, exuberant nature of "Gangnam Style" is a stark contrast to the sobering statistics of air pollution levels, but as researchers, we recognize the importance of not dismissing unexpected correlations without due investigation. Thus, with a mix of curiosity and bewilderment, we embarked on an analytical journey to unearth the underlying mechanisms of this peculiar association.

Our study is not without its quirks and challenges, much like a quest to solve a scientific mystery ripe for the silver screen. As we delved into the quantitative data, we encountered anomalies that necessitated thorough scrutiny – much like a detective sifting through clues at a crime scene. Our investigation led us to statistical analyses that raised more questions than answers, akin to a mathematician uncovering patterns in a sequence of prime numbers. The interconnectedness of the variables at play evoked a sense of intrigue, as if we were navigating a tangled web of connections in a digital labyrinth.

In this era of data-driven inquiry, where the lines between disciplines blur and unexpected discoveries await in the most unassuming places, our work demonstrates the value of embracing unconventional juxtapositions. The intertwining of atmospheric chemistry, public interest, and internet behavior uncovers a multidimensional narrative that transcends traditional disciplinary boundaries – akin to a fusion of scientific inquiry and digital anthropology.

With this backdrop in mind, we present our analysis of the correlation between air pollution levels in Cleveland and the ebb and flow of "Gangnam Style" searches on Google. Our findings not only shed light on the interplay between environmental factors and societal phenomena but also serve as a testament to the serendipitous discoveries that await those willing to venture beyond the confines of conventional research paradigms.

In the subsequent sections, we present the methodology, results, and implications of our exploration, inviting readers to join us on this whimsical quest for insight, and perhaps a few dance moves.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
Air pollution is a pervasive problem with significant implications for public health, environmental quality, and the integrity of our atmosphere. The adverse effects of air pollution on respiratory health, cardiovascular function, and overall well-being are well-documented in the research literature (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019). Concurrently, the rise of internet culture and the dominance of search engines like Google have become integral to daily life, providing a window into the collective consciousness of society (Braun & Beck, 2015; Patel & Williams, 2018). In recent years, the meteoric spread of viral phenomena through online platforms has captured the imagination of the global populace, generating a plethora of data ripe for exploration.
It is against this backdrop that a seemingly incongruous connection surfaced – the relationship between air pollution in Cleveland, Ohio, and the surge of Google searches for the iconic "Gangnam Style" during the same period. The playful, exuberant nature of "Gangnam Style" is a stark contrast to the sobering statistics of air pollution levels, but as researchers, we recognize the importance of not dismissing unexpected correlations without due investigation. Thus, with a mix of curiosity and bewilderment, we embarked on an analytical journey to unearth the underlying mechanisms of this peculiar association.
Our study is not without its quirks and challenges, much like a quest to solve a scientific mystery ripe for the silver screen. As we delved into the quantitative data, we encountered anomalies that necessitated thorough scrutiny – much like a detective sifting through clues at a crime scene. Our investigation led us to statistical analyses that raised more questions than answers, akin to a mathematician uncovering patterns in a sequence of prime numbers. The interconnectedness of the variables at play evoked a sense of intrigue, as if we were navigating a tangled web of connections in a digital labyrinth.
In this era of data-driven inquiry, where the lines between disciplines blur and unexpected discoveries await in the most unassuming places, our work demonstrates the value of embracing unconventional juxtapositions. The intertwining of atmospheric chemistry, public interest, and internet behavior uncovers a multidimensional narrative that transcends traditional disciplinary boundaries – akin to a fusion of scientific inquiry and digital anthropology.
With this backdrop in mind, we present our analysis of the correlation between air pollution levels in Cleveland and the ebb and flow of "Gangnam Style" searches on Google. Our findings not only shed light on the interplay between environmental factors and societal phenomena but also serve as a testament to the serendipitous discoveries that await those willing to venture beyond the confines of conventional research paradigms.
In the subsequent sections, we present the methodology, results, and implications of our exploration, inviting readers to join us on this whimsical quest for insight, and perhaps a few dance moves.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In exploring the peculiar correlation between air pollution in Cleveland, Ohio, and the frequency of Google searches for "Gangnam Style," we delved into a wide array of academic and non-academic sources that shed light on the intersection of environmental factors and cultural phenomena. While the literature predominantly focuses on the health ramifications of air pollution (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019), our search led us down an unexpected rabbit hole where the whimsical meets the scientific.

Beginning with seminal works such as "Air Pollution and Human Health" by Brown and "Polluted Air: We All Suffer" by Green, we familiarized ourselves with the grave implications of air pollution on human respiratory systems and overall well-being. As we delved deeper into the research, however, we stumbled upon less conventional sources that bordered on the absurdly relevant, such as "The Economics of Clean Air" by Clearman and "Breathe Easy: A Practical Guide to Air Purification" by Airington.

Transitioning into the realm of internet culture and viral phenomena, our foray into non-fiction works led us to insightful readings like "Global Impact of Internet Culture" by Webber and "The Art of Virality: Unraveling Online Phenomena" by Trendinson. Nevertheless, our journey took a turn towards the unexpected as we chanced upon fictional narratives with an uncanny resemblance to our investigation, including "The Scent of Serendipity" by Page-Turner and "The Search for Gangnam" by Song-Seeker.

Venturing further into uncharted territory, we let our explorations intersect with the world of cinema, where tangentially related films such as "Gangnam Dreams: A Musical Odyssey" and "Air Pollution and the City: A Tale of Respiring Woes" piqued our interest. These cinematic experiences, while not firsthand research, provided a delightful diversion and a fresh perspective on the whimsical aspects of our study.

For our specific inquiry, the literature provided a rich tapestry of information, encapsulating the gravity of air pollution's impact on health and the playful ebullience of internet phenomena. This multidimensional narrative, akin to a literary fusion of environmental exposé and digital escapades, served as a valuable backdrop for our offbeat exploration. As we unveil our own findings, we invite readers to join us on this off-kilter odyssey, where the serious meets the absurd and the unexpected takes center stage.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between Air pollution in Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Google Trends . You used data from 2012 to 2023

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

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

[[INTRODUCTION]]
INTRODUCTION
Air pollution is a pervasive problem with significant implications for public health, environmental quality, and the integrity of our atmosphere. The adverse effects of air pollution on respiratory health, cardiovascular function, and overall well-being are well-documented in the research literature (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019). Concurrently, the rise of internet culture and the dominance of search engines like Google have become integral to daily life, providing a window into the collective consciousness of society (Braun & Beck, 2015; Patel & Williams, 2018). In recent years, the meteoric spread of viral phenomena through online platforms has captured the imagination of the global populace, generating a plethora of data ripe for exploration.
It is against this backdrop that a seemingly incongruous connection surfaced – the relationship between air pollution in Cleveland, Ohio, and the surge of Google searches for the iconic "Gangnam Style" during the same period. The playful, exuberant nature of "Gangnam Style" is a stark contrast to the sobering statistics of air pollution levels, but as researchers, we recognize the importance of not dismissing unexpected correlations without due investigation. Thus, with a mix of curiosity and bewilderment, we embarked on an analytical journey to unearth the underlying mechanisms of this peculiar association.
Our study is not without its quirks and challenges, much like a quest to solve a scientific mystery ripe for the silver screen. As we delved into the quantitative data, we encountered anomalies that necessitated thorough scrutiny – much like a detective sifting through clues at a crime scene. Our investigation led us to statistical analyses that raised more questions than answers, akin to a mathematician uncovering patterns in a sequence of prime numbers. The interconnectedness of the variables at play evoked a sense of intrigue, as if we were navigating a tangled web of connections in a digital labyrinth.
In this era of data-driven inquiry, where the lines between disciplines blur and unexpected discoveries await in the most unassuming places, our work demonstrates the value of embracing unconventional juxtapositions. The intertwining of atmospheric chemistry, public interest, and internet behavior uncovers a multidimensional narrative that transcends traditional disciplinary boundaries – akin to a fusion of scientific inquiry and digital anthropology.
With this backdrop in mind, we present our analysis of the correlation between air pollution levels in Cleveland and the ebb and flow of "Gangnam Style" searches on Google. Our findings not only shed light on the interplay between environmental factors and societal phenomena but also serve as a testament to the serendipitous discoveries that await those willing to venture beyond the confines of conventional research paradigms.
In the subsequent sections, we present the methodology, results, and implications of our exploration, inviting readers to join us on this whimsical quest for insight, and perhaps a few dance moves.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

METHODOLOGY

Data Collection

Our research team embarked on a whimsical quest through the digital labyrinth of data to uncover the enigmatic link between air pollution in Cleveland and the pulsating rhythms of "Gangnam Style" searches on Google. Leveraging resources from the Environmental Protection Agency (EPA) and Google Trends, we gathered a trove of information spanning the years 2012 to 2023. With the precision of a conductor orchestrating a symphony, we harmonized these disparate datasets to tease out the melody of correlation lurking within.

Air Pollution Measurement

To capture the atmospheric dance of pollutants in Cleveland, we harnessed the EPA's Air Quality System (AQS) database, immersing ourselves in a flurry of readings on particulate matter, ozone, carbon monoxide, and sulfur dioxide. We sifted through this virtual smorgasbord of chemical compositions, endeavoring to decipher the symphony of pollutants that permeated Cleveland's atmosphere. These gusts of data propelled us into a scientific waltz, where each pollutant waltzed its way into our analytical embrace, revealing the intricate choreography of atmospheric composition.

Google Trends Analysis

In our pursuit of the digital zeitgeist, we delved into the vaults of Google Trends, where the echoes of "Gangnam Style" reverberated across the digital landscape. With the precision of digital archaeologists, we excavated the temporal footprint of "Gangnam Style" searches, capturing the crescendos and diminuendos of public curiosity with mathematical finesse. Each flurry of search activity painted a digital canvas, recounting the enigmatic dance of relevance and recollection within the collective consciousness of internet denizens.

Statistical Analysis

Armed with our arsenal of data, we waded into the waters of statistical analysis. Employing rigorous tools and techniques, we danced on the precipice of significance, teasing apart the nuances of correlation with the finesse of statistical troubadours. The tango of regression models and correlation coefficients illuminated the stage of our analysis, casting a spotlight on the unlikely pas de deux between air pollution and "Gangnam Style" searches. As the curtains rose on the dynamics of significance testing, we reveled in the theatrics of p-values and confidence intervals, painting a portrait of empirical intrigue that defied conventional expectations.

In summary, our methodology blended scientific rigor with a touch of whimsy, navigating the convoluted pathways of atmospheric chemistry and digital footprints. Our dances with data, statistics, and digital echoes wove a narrative that invites readers to take a spin on the empyrean dance floor of interdisciplinary exploration. The results of our endeavor, as we shall elucidate in the subsequent section, illuminate a serendipitous waltz between traditionally disparate domains, offering a glimpse into the unexpected crescendos that await those daring enough to peer beyond the ordinary.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between Air pollution in Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Google Trends .

For the time period 2012 to 2023, you found a correlation 0.8005456, r-squared of 0.6408733, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
Air pollution is a pervasive problem with significant implications for public health, environmental quality, and the integrity of our atmosphere. The adverse effects of air pollution on respiratory health, cardiovascular function, and overall well-being are well-documented in the research literature (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019). Concurrently, the rise of internet culture and the dominance of search engines like Google have become integral to daily life, providing a window into the collective consciousness of society (Braun & Beck, 2015; Patel & Williams, 2018). In recent years, the meteoric spread of viral phenomena through online platforms has captured the imagination of the global populace, generating a plethora of data ripe for exploration.
It is against this backdrop that a seemingly incongruous connection surfaced – the relationship between air pollution in Cleveland, Ohio, and the surge of Google searches for the iconic "Gangnam Style" during the same period. The playful, exuberant nature of "Gangnam Style" is a stark contrast to the sobering statistics of air pollution levels, but as researchers, we recognize the importance of not dismissing unexpected correlations without due investigation. Thus, with a mix of curiosity and bewilderment, we embarked on an analytical journey to unearth the underlying mechanisms of this peculiar association.
Our study is not without its quirks and challenges, much like a quest to solve a scientific mystery ripe for the silver screen. As we delved into the quantitative data, we encountered anomalies that necessitated thorough scrutiny – much like a detective sifting through clues at a crime scene. Our investigation led us to statistical analyses that raised more questions than answers, akin to a mathematician uncovering patterns in a sequence of prime numbers. The interconnectedness of the variables at play evoked a sense of intrigue, as if we were navigating a tangled web of connections in a digital labyrinth.
In this era of data-driven inquiry, where the lines between disciplines blur and unexpected discoveries await in the most unassuming places, our work demonstrates the value of embracing unconventional juxtapositions. The intertwining of atmospheric chemistry, public interest, and internet behavior uncovers a multidimensional narrative that transcends traditional disciplinary boundaries – akin to a fusion of scientific inquiry and digital anthropology.
With this backdrop in mind, we present our analysis of the correlation between air pollution levels in Cleveland and the ebb and flow of "Gangnam Style" searches on Google. Our findings not only shed light on the interplay between environmental factors and societal phenomena but also serve as a testament to the serendipitous discoveries that await those willing to venture beyond the confines of conventional research paradigms.
In the subsequent sections, we present the methodology, results, and implications of our exploration, inviting readers to join us on this whimsical quest for insight, and perhaps a few dance moves.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

RESULTS

Our analysis of the data revealed a strong positive correlation between air pollution levels in Cleveland, Ohio, and Google searches for "Gangnam Style" from 2012 to 2023. The correlation coefficient of 0.8005456 indicates a robust relationship between these seemingly disconnected variables, suggesting that as air pollution levels rose, searches for "Gangnam Style" also experienced a surge.

The relationship is further validated by an r-squared value of 0.6408733, indicating that approximately 64.08% of the variability in "Gangnam Style" searches can be explained by variations in air pollution levels. This substantial proportion of explained variance underscores the compelling connection between these two disparate phenomena.

Additionally, the statistical significance of this relationship is underscored by the p-value being less than 0.01, providing strong evidence against the null hypothesis that there is no correlation between air pollution levels and "Gangnam Style" searches.

Furthermore, our findings are visually encapsulated in Figure 1, which displays a scatterplot illustrating the striking correlation between air pollution levels and the frequency of "Gangnam Style" searches. The scatterplot showcases the consistent pattern of increasing search frequencies as air pollution levels elevate, affirming the robustness of our statistical findings.

In essence, our results illuminate a noteworthy association that transcends traditional boundaries, inviting researchers to pirouette across disciplinary landscapes and embrace the unexpected partnerships that scientific inquiry has to offer.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

[[LITERATURE REVIEW]]
In exploring the peculiar correlation between air pollution in Cleveland, Ohio, and the frequency of Google searches for "Gangnam Style," we delved into a wide array of academic and non-academic sources that shed light on the intersection of environmental factors and cultural phenomena. While the literature predominantly focuses on the health ramifications of air pollution (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019), our search led us down an unexpected rabbit hole where the whimsical meets the scientific.
Beginning with seminal works such as "Air Pollution and Human Health" by Brown and "Polluted Air: We All Suffer" by Green, we familiarized ourselves with the grave implications of air pollution on human respiratory systems and overall well-being. As we delved deeper into the research, however, we stumbled upon less conventional sources that bordered on the absurdly relevant, such as "The Economics of Clean Air" by Clearman and "Breathe Easy: A Practical Guide to Air Purification" by Airington.
Transitioning into the realm of internet culture and viral phenomena, our foray into non-fiction works led us to insightful readings like "Global Impact of Internet Culture" by Webber and "The Art of Virality: Unraveling Online Phenomena" by Trendinson. Nevertheless, our journey took a turn towards the unexpected as we chanced upon fictional narratives with an uncanny resemblance to our investigation, including "The Scent of Serendipity" by Page-Turner and "The Search for Gangnam" by Song-Seeker.
Venturing further into uncharted territory, we let our explorations intersect with the world of cinema, where tangentially related films such as "Gangnam Dreams: A Musical Odyssey" and "Air Pollution and the City: A Tale of Respiring Woes" piqued our interest. These cinematic experiences, while not firsthand research, provided a delightful diversion and a fresh perspective on the whimsical aspects of our study.
For our specific inquiry, the literature provided a rich tapestry of information, encapsulating the gravity of air pollution's impact on health and the playful ebullience of internet phenomena. This multidimensional narrative, akin to a literary fusion of environmental exposé and digital escapades, served as a valuable backdrop for our offbeat exploration. As we unveil our own findings, we invite readers to join us on this off-kilter odyssey, where the serious meets the absurd and the unexpected takes center stage.

[[RESULTS]]
RESULTS
Our analysis of the data revealed a strong positive correlation between air pollution levels in Cleveland, Ohio, and Google searches for "Gangnam Style" from 2012 to 2023. The correlation coefficient of 0.8005456 indicates a robust relationship between these seemingly disconnected variables, suggesting that as air pollution levels rose, searches for "Gangnam Style" also experienced a surge.
The relationship is further validated by an r-squared value of 0.6408733, indicating that approximately 64.08% of the variability in "Gangnam Style" searches can be explained by variations in air pollution levels. This substantial proportion of explained variance underscores the compelling connection between these two disparate phenomena.
Additionally, the statistical significance of this relationship is underscored by the p-value being less than 0.01, providing strong evidence against the null hypothesis that there is no correlation between air pollution levels and "Gangnam Style" searches.
Furthermore, our findings are visually encapsulated in Figure 1, which displays a scatterplot illustrating the striking correlation between air pollution levels and the frequency of "Gangnam Style" searches. The scatterplot showcases the consistent pattern of increasing search frequencies as air pollution levels elevate, affirming the robustness of our statistical findings.
In essence, our results illuminate a noteworthy association that transcends traditional boundaries, inviting researchers to pirouette across disciplinary landscapes and embrace the unexpected partnerships that scientific inquiry has to offer.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings present a curious dance between air pollution in Cleveland and Google searches for "Gangnam Style," revealing an unexpected duet that harmonizes two seemingly discordant elements. The significant positive correlation observed between air pollution levels and "Gangnam Style" queries provides robust evidence supporting our initial hypothesis. This unanticipated correlation, reminiscent of a scientific serendipity, aligns with previous literature that has emphasized the multifaceted nature of environmental and cultural interactions.

Drawing from the literature review, our offbeat journey through the diverse landscape of academic and non-academic sources illuminated the serious health implications of air pollution and simultaneously unearthed the quirky underbelly of internet culture. It is within this eccentric intellectual sphere that we uncovered parallels between our seemingly disparate variables, akin to a cosmic collision between serious environmental concerns and the whimsical resonances of internet memes.

Our results offer a symphony of statistical evidence, with a correlation coefficient of 0.8005456 orchestrating a compelling concerto, indicating a strong positive relationship between air pollution and "Gangnam Style" searches. This statistical harmony echoes the findings of previous scholarly works, albeit in a refreshingly peculiar context, underlining the inseparable bond between the gravity of environmental influence and the lighthearted buoyancy of cultural phenomena.

The implications of our study extend beyond mere statistical curiosity, invoking an invitation for researchers to waltz beyond conventional disciplinary confines and embrace the unexpected partnerships that scientific inquiry may yield. This whimsical tango between air pollution and "Gangnam Style" searches serves as a testament to the serendipitous nature of research, proving that even in the most unlikely pairings, an intricate dance of statistical significance can be orchestrated.

As we revel in the synchronized rhythm of our findings, we encourage fellow scientists to embark on their own offbeat odysseys, daring to explore the uncharted territories where science and absurdity collide. This intricate dance of statistical significance encourages us to ponder the humor of scientific serendipity and emblemizes the inexhaustible breadth of intellectual exploration. So, let us continue to waltz, wiggling our research tattoos to the rhythm of statistical innovation and discovery, as we pirouette through the peculiar pathways of scientific endeavor.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 Cleveland and Google searches for 'Gangnam Style'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
"Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches"

[[ABSTRACT]]
This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

[[INTRDUCTION]]
INTRODUCTION
Air pollution is a pervasive problem with significant implications for public health, environmental quality, and the integrity of our atmosphere. The adverse effects of air pollution on respiratory health, cardiovascular function, and overall well-being are well-documented in the research literature (Smith et al., 2014; Jones & Black, 2017; Wang & Hunter, 2019). Concurrently, the rise of internet culture and the dominance of search engines like Google have become integral to daily life, providing a window into the collective consciousness of society (Braun & Beck, 2015; Patel & Williams, 2018). In recent years, the meteoric spread of viral phenomena through online platforms has captured the imagination of the global populace, generating a plethora of data ripe for exploration.
It is against this backdrop that a seemingly incongruous connection surfaced – the relationship between air pollution in Cleveland, Ohio, and the surge of Google searches for the iconic "Gangnam Style" during the same period. The playful, exuberant nature of "Gangnam Style" is a stark contrast to the sobering statistics of air pollution levels, but as researchers, we recognize the importance of not dismissing unexpected correlations without due investigation. Thus, with a mix of curiosity and bewilderment, we embarked on an analytical journey to unearth the underlying mechanisms of this peculiar association.
Our study is not without its quirks and challenges, much like a quest to solve a scientific mystery ripe for the silver screen. As we delved into the quantitative data, we encountered anomalies that necessitated thorough scrutiny – much like a detective sifting through clues at a crime scene. Our investigation led us to statistical analyses that raised more questions than answers, akin to a mathematician uncovering patterns in a sequence of prime numbers. The interconnectedness of the variables at play evoked a sense of intrigue, as if we were navigating a tangled web of connections in a digital labyrinth.
In this era of data-driven inquiry, where the lines between disciplines blur and unexpected discoveries await in the most unassuming places, our work demonstrates the value of embracing unconventional juxtapositions. The intertwining of atmospheric chemistry, public interest, and internet behavior uncovers a multidimensional narrative that transcends traditional disciplinary boundaries – akin to a fusion of scientific inquiry and digital anthropology.
With this backdrop in mind, we present our analysis of the correlation between air pollution levels in Cleveland and the ebb and flow of "Gangnam Style" searches on Google. Our findings not only shed light on the interplay between environmental factors and societal phenomena but also serve as a testament to the serendipitous discoveries that await those willing to venture beyond the confines of conventional research paradigms.
In the subsequent sections, we present the methodology, results, and implications of our exploration, inviting readers to join us on this whimsical quest for insight, and perhaps a few dance moves.

[[RESULTS]]
RESULTS
Our analysis of the data revealed a strong positive correlation between air pollution levels in Cleveland, Ohio, and Google searches for "Gangnam Style" from 2012 to 2023. The correlation coefficient of 0.8005456 indicates a robust relationship between these seemingly disconnected variables, suggesting that as air pollution levels rose, searches for "Gangnam Style" also experienced a surge.
The relationship is further validated by an r-squared value of 0.6408733, indicating that approximately 64.08% of the variability in "Gangnam Style" searches can be explained by variations in air pollution levels. This substantial proportion of explained variance underscores the compelling connection between these two disparate phenomena.
Additionally, the statistical significance of this relationship is underscored by the p-value being less than 0.01, providing strong evidence against the null hypothesis that there is no correlation between air pollution levels and "Gangnam Style" searches.
Furthermore, our findings are visually encapsulated in Figure 1, which displays a scatterplot illustrating the striking correlation between air pollution levels and the frequency of "Gangnam Style" searches. The scatterplot showcases the consistent pattern of increasing search frequencies as air pollution levels elevate, affirming the robustness of our statistical findings.
In essence, our results illuminate a noteworthy association that transcends traditional boundaries, inviting researchers to pirouette across disciplinary landscapes and embrace the unexpected partnerships that scientific inquiry has to offer.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

CONCLUSION

In conclusion, our study has unearthed a fascinating correlation between air pollution in Cleveland, Ohio, and the frequency of Google searches for the iconic "Gangnam Style." The robust positive correlation coefficient of 0.8005456, along with a p-value less than 0.01, highlights the unexpected interconnectedness of these seemingly disparate phenomena. While our findings may leave some scratching their heads, much like a mathematician encountering a perplexing proof, they underscore the serendipitous discoveries that await researchers willing to waltz into uncharted territories of inquiry.

The substantial proportion of explained variance, as reflected in the r-squared value of 0.6408733, emphasizes the compelling nature of this association, beckoning researchers to tango between the realms of atmospheric science and digital culture. Our results, encapsulated in the visually enlightening Figure 1, serve as an invitation for fellow researchers to cha-cha across disciplinary boundaries and embrace the enigmatic dance of statistical relationships.

As we take our final bow, it is clear that our findings demand reflection and contemplation, much like a mysterious riddle waiting to be solved. We hope this study encourages researchers to tap into the trove of unconventional connections that science and data have to offer, and perhaps even inspires a few impromptu dance moves in the process.

In light of these revelatory findings, we confidently assert that no further research is needed to verify the correlation between air pollution levels in Cleveland and Google searches for "Gangnam Style." This peculiar dance between air quality and viral internet phenomena has been meticulously examined, leaving the scholarly community with a celebration of statistical serendipity and a symphony of data-driven discovery.


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 Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Unlikely 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 Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Urban Environmental Research and Analysis


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 Gasping for Air: Unearthing the Correlation Between Air Pollution in Cleveland and 'Gangnam Style' Google Searches with an abstract of This research paper delves into the unusual correlation between air pollution levels in Cleveland, Ohio and the frequency of Google searches for the globally viral "Gangnam Style" phenomenon. Leveraging extensive data from the Environmental Protection Agency and Google Trends, our study uncovers an unexpected link between the two seemingly disparate elements. With a striking correlation coefficient of 0.8005456 and a p-value less than 0.01 for the period spanning 2012 to 2023, our findings demand attention and reflection from the academic and research realms. We invite readers to breathe in this revelation and perhaps dance to the rhythm of our analytical exploration.

ChatGPT:

air pollution Cleveland, Gangnam Style, Google searches correlation, Cleveland Ohio air quality data, google trends analysis, correlation coefficient analysis, air pollution effects on online behavior, environmental data analysis

*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 Cleveland
Detailed data title: Percentage of days with moderate or worse air quality in Cleveland-Elyria, OH
Source: Environmental Protection Agency
See what else correlates with Air pollution in Cleveland

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

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

Correlation r = 0.8005456 (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 = 0.6408733 (Coefficient of determination)
This means 64.1% 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 Cleveland) over the 12 years from 2012 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0018. 0.0017593968498729933000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. 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 0.8 in 0.18% of random cases. Said differently, if you correlated 568 random variables Which I absolutely did.
with the same 11 degrees of freedom, 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.

[ 0.42, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
201220132014201520162017201820192020202120222023
Air pollution in Cleveland (Bad air quality days)71.038358.356250.684957.260344.535542.191844.383649.315139.617552.602743.013756.5574
Google searches for 'Gangnam Style' (Rel. search volume)36.920.33334.666672.833331.333331111111




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 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.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. 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([71.0383,58.3562,50.6849,57.2603,44.5355,42.1918,44.3836,49.3151,39.6175,52.6027,43.0137,56.5574,])
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 Cleveland"
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. 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:


View another random correlation

How fun was this correlation?

Thanks for shining a light on this correlation!


Correlation ID: 5219 · Black Variable ID: 20475 · Red Variable ID: 1442
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0