about · email me · subscribe
Spurious correlation #1,937 · 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 Wichita and the second variable is Google searches for 'titanic'.  The chart goes from 2004 to 2016, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The higher levels of pollution in Wichita led to a thick haze in the air, prompting people to reminisce about the iconic scene from Titanic where Jack and Rose are standing at the bow of the ship. As the smog rolled in, so did the urge to Google search for everything Titanic-related, from the movie quotes to Celine Dion's 'My Heart Will Go On'. It's like the pollution created a 'fog of nostalgia' for the film, proving that even Leonardo DiCaprio's smoldering gaze can't escape the reach of air pollutants!

Model: dalle-3
Prompt: Generate an image of a futuristic cityscape with towering skyscrapers against a backdrop of hazy, pollution-filled air. The city streets are filled with people with furrowed brows, illuminated by the glow of their smartphones as they search for "titanic" on Google. The scene should capture the cyberpunk ambiance of a polluted urban environment juxtaposed with the cyber connectivity of its inhabitants. 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: Poor air quality in Wichita and Google searches for 'titanic'. 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: Brutalism Voxel art Magic realism Photorealism Data cyber art
ChatGPT: Data cyber art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Poor air quality in Wichita and Google searches for 'titanic' together. Keep the description simple.
ChatGPT: In Wichita, the skyline was hazy as thick smog filled the air. Along the bustling streets, people were seen furrowing their brows and pulling out their smartphones to search for "titanic" on Google, their faces lit up by the screens in the dimly lit city.

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: [ Data cyber art ] and depicting this scene: In Wichita, the skyline was hazy as thick smog filled the air. Along the bustling streets, people were seen furrowing their brows and pulling out their smartphones to search for "titanic" on Google, their faces lit up by the screens in the dimly lit city. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a futuristic cityscape with towering skyscrapers against a backdrop of hazy, pollution-filled air. The city streets are filled with people with furrowed brows, illuminated by the glow of their smartphones as they search for "titanic" on Google. The scene should capture the cyberpunk ambiance of a polluted urban environment juxtaposed with the cyber connectivity of its inhabitants.

*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 an increase in Air pollution in Wichita caused titanic (Google searches for 'titanic') to increase. Make it feel plausible.

AI academic paper

(Because p < 0.01)
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

The Journal of Ecological Entertainment Research

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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8957514 and p < 0.01 for 2004 to 2016.

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]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.


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 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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

In the annals of academic research, it is not often that one encounters a study that seeks to unravel the enigmatic connection between air pollution and Google searches for 'Titanic'. However, as the saying goes, "Where there’s smog, there’s a Google search for Leo DiCaprio," or something along those lines. While this seemingly peculiar correlation may evoke skepticism or amusement, our research team approached it with the utmost seriousness and a dash of whimsy.

The allure of the RMS Titanic, a symbol of both tragic demise and enduring fascination, has transcended generations and captured the intrigue of movie enthusiasts worldwide. Likewise, air pollution, a perennial specter looming over urban environments, has been the subject of rigorous scientific inquiry and the occasional exasperated muttering from asthmatic individuals. The convergence of these two seemingly disparate phenomena in the context of Google searches invites a playful curiosity, not dissimilar to a Titanic-themed game of "Six Degrees of Kevin Bacon" played on a smoggy evening.

The city of Wichita, Kansas, where the wheat fields whisper tales of yesteryear and the winds carry the echo of '90s blockbusters, provided an intriguing setting for this investigation. Here, a city known for its aviation legacy and convivial Midwestern charm, we sought to decipher the subtle dance between the atmospheric particles and online pursuits of maritime tragedy aficionados.

With access to comprehensive air quality data from the Environmental Protection Agency and the voluminous records of Google search queries through the aptly named Google Trends, we embarked on an academic journey rife with statistical analyses, perplexing correlations, and a deep-seated appreciation for the idiosyncrasies of human behavior. The fruits of our labor revealed a robust correlation coefficient of 0.8957514, which beckoned us to peer through the haze of air pollution and discern patterns in the digital footprints left by those in pursuit of cinematic nostalgia.

As we unravel the nuances of this unusual connection, it is our fervent belief that our findings will not only expand the boundaries of interdisciplinary inquiry but also elicit a chuckle or two from readers who are willing to indulge in this lighthearted exploration. So, buckle up and prepare to navigate the curious realms of air pollution and cinematic wistfulness, where the mist of scholarly rigor converges with the buoyancy of good-natured banter. Let the journey begin.


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 Wichita and Google searches for 'titanic'. 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 name some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
In the annals of academic research, it is not often that one encounters a study that seeks to unravel the enigmatic connection between air pollution and Google searches for 'Titanic'. However, as the saying goes, "Where there’s smog, there’s a Google search for Leo DiCaprio," or something along those lines. While this seemingly peculiar correlation may evoke skepticism or amusement, our research team approached it with the utmost seriousness and a dash of whimsy.
The allure of the RMS Titanic, a symbol of both tragic demise and enduring fascination, has transcended generations and captured the intrigue of movie enthusiasts worldwide. Likewise, air pollution, a perennial specter looming over urban environments, has been the subject of rigorous scientific inquiry and the occasional exasperated muttering from asthmatic individuals. The convergence of these two seemingly disparate phenomena in the context of Google searches invites a playful curiosity, not dissimilar to a Titanic-themed game of "Six Degrees of Kevin Bacon" played on a smoggy evening.
The city of Wichita, Kansas, where the wheat fields whisper tales of yesteryear and the winds carry the echo of '90s blockbusters, provided an intriguing setting for this investigation. Here, a city known for its aviation legacy and convivial Midwestern charm, we sought to decipher the subtle dance between the atmospheric particles and online pursuits of maritime tragedy aficionados.
With access to comprehensive air quality data from the Environmental Protection Agency and the voluminous records of Google search queries through the aptly named Google Trends, we embarked on an academic journey rife with statistical analyses, perplexing correlations, and a deep-seated appreciation for the idiosyncrasies of human behavior. The fruits of our labor revealed a robust correlation coefficient of 0.8957514, which beckoned us to peer through the haze of air pollution and discern patterns in the digital footprints left by those in pursuit of cinematic nostalgia.
As we unravel the nuances of this unusual connection, it is our fervent belief that our findings will not only expand the boundaries of interdisciplinary inquiry but also elicit a chuckle or two from readers who are willing to indulge in this lighthearted exploration. So, buckle up and prepare to navigate the curious realms of air pollution and cinematic wistfulness, where the mist of scholarly rigor converges with the buoyancy of good-natured banter. Let the journey begin.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
LITERATURE REVIEW

The authors sought to position their study within the broader context of environmental influences on human behavior and interests. As such, this review encompasses a spectrum of research, ranging from the earnest and scholarly to the whimsical and imaginative, mirroring the duality of the study at hand.

Smith, in "The Impact of Environmental Factors on Information Seeking Behavior," explores the subtle ways in which external environmental variables can shape online search patterns. Doe et al., in "Atmospheric Conditions and Popular Culture: An Unlikely Symbiosis," delves into the correlation between weather patterns and entertainment preferences, laying the groundwork for the present investigation.

At this juncture, the literature takes a turn toward less traditional, more light-hearted sources. "Cloudy with a Chance of Search Queries" by Chris Cumulonimbus, while not a formal academic text, provides a whimsical take on the intersection of weather conditions and digital pursuits, offering a meteorological perspective on internet browsing.

Transitioning to the realm of fictional works that might offer insight, "Gone with the Smog" by Margaret Airpollutant plunges readers into a dystopian world where air pollution dictates cultural predilections, as humanity clings to nostalgic artifacts amidst the murky haze.

Adding to the eclectic mix of sources, "The Search for Titanic: A Cinematic Odyssey" by James Cameron, although a work of fiction, offers a cinematic lens through which to contemplate the enduring allure of the RMS Titanic and its potential entanglement with environmental factors.

The researchers also draw inspiration from their own popular culture experiences, including repeated viewings of "An Inconvenient Truth" and "The Day After Tomorrow," which, albeit not directly focused on maritime tragedies, underscore the impact of environmental concerns on public consciousness and, in a more tangential sense, the substantial influence of blockbuster films on societal fascination with global phenomena.

As the scholarly inquiry rubs elbows with the whimsically imaginative, this wide-ranging review sets the stage for the singular fusion of environmental inquiry and entertainment intrigue, all while maintaining a sense of scholarly rigor and a healthy dose of intellectual levity.


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 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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 2004 to 2016

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]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

[[INTRODUCTION]]
INTRODUCTION
In the annals of academic research, it is not often that one encounters a study that seeks to unravel the enigmatic connection between air pollution and Google searches for 'Titanic'. However, as the saying goes, "Where there’s smog, there’s a Google search for Leo DiCaprio," or something along those lines. While this seemingly peculiar correlation may evoke skepticism or amusement, our research team approached it with the utmost seriousness and a dash of whimsy.
The allure of the RMS Titanic, a symbol of both tragic demise and enduring fascination, has transcended generations and captured the intrigue of movie enthusiasts worldwide. Likewise, air pollution, a perennial specter looming over urban environments, has been the subject of rigorous scientific inquiry and the occasional exasperated muttering from asthmatic individuals. The convergence of these two seemingly disparate phenomena in the context of Google searches invites a playful curiosity, not dissimilar to a Titanic-themed game of "Six Degrees of Kevin Bacon" played on a smoggy evening.
The city of Wichita, Kansas, where the wheat fields whisper tales of yesteryear and the winds carry the echo of '90s blockbusters, provided an intriguing setting for this investigation. Here, a city known for its aviation legacy and convivial Midwestern charm, we sought to decipher the subtle dance between the atmospheric particles and online pursuits of maritime tragedy aficionados.
With access to comprehensive air quality data from the Environmental Protection Agency and the voluminous records of Google search queries through the aptly named Google Trends, we embarked on an academic journey rife with statistical analyses, perplexing correlations, and a deep-seated appreciation for the idiosyncrasies of human behavior. The fruits of our labor revealed a robust correlation coefficient of 0.8957514, which beckoned us to peer through the haze of air pollution and discern patterns in the digital footprints left by those in pursuit of cinematic nostalgia.
As we unravel the nuances of this unusual connection, it is our fervent belief that our findings will not only expand the boundaries of interdisciplinary inquiry but also elicit a chuckle or two from readers who are willing to indulge in this lighthearted exploration. So, buckle up and prepare to navigate the curious realms of air pollution and cinematic wistfulness, where the mist of scholarly rigor converges with the buoyancy of good-natured banter. Let the journey begin.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

METHODOLOGY

Data Collection:
To unravel the entangled web of air pollution and 'Titanic' searches, our research team embarked on a quest for digital breadcrumbs scattered across the virtual expanse of the internet. Our primary sources of data included the Environmental Protection Agency's comprehensive records of air quality measurements and Google Trends, the virtual oracle that retrieves and organizes the zeitgeist-capturing queries of curious netizens. We spent countless hours wading through the virtual morass, dodging clickbait and resisting the siren call of viral memes to extract the requisite data from the years 2004 to 2016. Much like intrepid deep-sea explorers, we surfaced with a bounty of data shimmering with potential insights, albeit without the requisite nautical facial hair.

Air Pollution Measures:
Armed with the troves of information from the Environmental Protection Agency, we meticulously documented the levels of various air pollutants, including particulate matter, nitrogen dioxide, ozone, and sulfur dioxide, among others. Our measurements transcended the mundane realm of mere numerical values, capturing the ambient aura of pollutants as they mingled with the atmosphere, forming a tapestry of pollution that garnered begrudging respect from even the most fastidious of particulate connoisseurs. These data were then distilled into a palatable format for statistical analysis, leaving behind the scent of chemical equations and the unmistakable whiff of scholarly rigor.

Google Searches for 'Titanic':
In parallel, we harnessed the powerful tool of Google Trends to discern patterns in the ebb and flow of public interest in the cinematic marvel that is 'Titanic'. The search queries, often tinged with earnest curiosity and occasional fleeting whimsy, were scrutinized for trends, fluctuations, and potentially cryptic indications of environmental influence. We meticulously charted the rise and fall of 'Titanic' searches, akin to mapping the undulating waves of digital fascination that mirrored the uncontrollable tides of the Atlantic, albeit in a more figurative sense.

Statistical Analysis:
Armed with our arsenal of data, we launched headlong into the foray of statistical analyses. We employed the venerable spear of correlation analysis to discern the invisible threads binding air pollution and 'Titanic' searches. Our trusty ally, the Pearson correlation coefficient, laid bare the strength of association between the two variables, each data point whispering secrets of interdependence like a clandestine rendezvous in a crowded ballroom. Additionally, the p-value, that elusive arbiter of statistical significance, cast its discerning gaze upon our findings, confirming the legitimacy of our detected association and validating our quest for scholarly enlightenment.

Limitations:
As with any academic expedition, we encountered a few hurdles along the way. The limitations of our study include potential confounding variables, such as concurrent major events in pop culture or meteorological anomalies that may have influenced both air pollution levels and 'Titanic' searches. Furthermore, the localized nature of our study in Wichita may limit the generalizability of our findings to other regions, where the whims of curiosity and the capricious gusts of pollution may dance to a different, albeit equally captivating, tune.

In conclusion, our methodology, though fraught with the perilous seas of data collection and the treacherous shoals of statistical analyses, ultimately guided us to a treasure trove of insights. The fusion of environmental vigilance and cinematic intrigue has yielded unexpected revelations, beckoning us to ponder the subtle symphony of human behavior orchestrated by the unseen maestros of air pollution. With the rigors of scholarly inquiry as our compass and the lighthearted spirit of whimsy as our guiding star, we charted a course through uncharted waters seldom traversed in the annals of academic research.


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 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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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 2004 to 2016, you found a correlation 0.8957514, r-squared of 0.8023706, 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]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
In the annals of academic research, it is not often that one encounters a study that seeks to unravel the enigmatic connection between air pollution and Google searches for 'Titanic'. However, as the saying goes, "Where there’s smog, there’s a Google search for Leo DiCaprio," or something along those lines. While this seemingly peculiar correlation may evoke skepticism or amusement, our research team approached it with the utmost seriousness and a dash of whimsy.
The allure of the RMS Titanic, a symbol of both tragic demise and enduring fascination, has transcended generations and captured the intrigue of movie enthusiasts worldwide. Likewise, air pollution, a perennial specter looming over urban environments, has been the subject of rigorous scientific inquiry and the occasional exasperated muttering from asthmatic individuals. The convergence of these two seemingly disparate phenomena in the context of Google searches invites a playful curiosity, not dissimilar to a Titanic-themed game of "Six Degrees of Kevin Bacon" played on a smoggy evening.
The city of Wichita, Kansas, where the wheat fields whisper tales of yesteryear and the winds carry the echo of '90s blockbusters, provided an intriguing setting for this investigation. Here, a city known for its aviation legacy and convivial Midwestern charm, we sought to decipher the subtle dance between the atmospheric particles and online pursuits of maritime tragedy aficionados.
With access to comprehensive air quality data from the Environmental Protection Agency and the voluminous records of Google search queries through the aptly named Google Trends, we embarked on an academic journey rife with statistical analyses, perplexing correlations, and a deep-seated appreciation for the idiosyncrasies of human behavior. The fruits of our labor revealed a robust correlation coefficient of 0.8957514, which beckoned us to peer through the haze of air pollution and discern patterns in the digital footprints left by those in pursuit of cinematic nostalgia.
As we unravel the nuances of this unusual connection, it is our fervent belief that our findings will not only expand the boundaries of interdisciplinary inquiry but also elicit a chuckle or two from readers who are willing to indulge in this lighthearted exploration. So, buckle up and prepare to navigate the curious realms of air pollution and cinematic wistfulness, where the mist of scholarly rigor converges with the buoyancy of good-natured banter. Let the journey begin.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analyses conducted in this study revealed a remarkably strong correlation between air pollution levels and Google searches for 'Titanic' in Wichita, Kansas. The correlation coefficient of 0.8957514 signifies a robust relationship between these seemingly incongruous variables. This correlation indicates that as air pollution levels in Wichita increased, so did the frequency of searches for information related to the iconic film 'Titanic' on Google.
The coefficient of determination, with a value of 0.8023706, suggests that approximately 80.24% of the variation in 'Titanic' searches can be explained by changes in air pollution levels. This finding underscores the substantial influence of air pollution on the public's interest in the cinematic masterpiece.
Importantly, the p-value of less than 0.01 points to the statistical significance of this relationship. This indicates that the observed correlation is highly unlikely to have occurred by random chance, further substantiating the validity of the association.

The scatterplot in Figure 1 visually depicts the strong positive correlation between air pollution levels and Google searches for 'Titanic' in Wichita. Each data point on the plot represents the pairing of air pollution levels and the corresponding volume of 'Titanic' searches, displaying a clear trend of increased searches coinciding with higher levels of air pollution.

These results underscore the unexpected but compelling relationship between environmental quality and popular culture, prompting consideration of the potential impact of air pollution on individual behavior and interests. The implications of these findings extend beyond the realms of environmental science and information technology, offering a whimsical window into the subtle ways in which external factors influence societal preferences and activities.


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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

[[LITERATURE REVIEW]]
LITERATURE REVIEW
The authors sought to position their study within the broader context of environmental influences on human behavior and interests. As such, this review encompasses a spectrum of research, ranging from the earnest and scholarly to the whimsical and imaginative, mirroring the duality of the study at hand.
Smith, in "The Impact of Environmental Factors on Information Seeking Behavior," explores the subtle ways in which external environmental variables can shape online search patterns. Doe et al., in "Atmospheric Conditions and Popular Culture: An Unlikely Symbiosis," delves into the correlation between weather patterns and entertainment preferences, laying the groundwork for the present investigation.
At this juncture, the literature takes a turn toward less traditional, more light-hearted sources. "Cloudy with a Chance of Search Queries" by Chris Cumulonimbus, while not a formal academic text, provides a whimsical take on the intersection of weather conditions and digital pursuits, offering a meteorological perspective on internet browsing.
Transitioning to the realm of fictional works that might offer insight, "Gone with the Smog" by Margaret Airpollutant plunges readers into a dystopian world where air pollution dictates cultural predilections, as humanity clings to nostalgic artifacts amidst the murky haze.
Adding to the eclectic mix of sources, "The Search for Titanic: A Cinematic Odyssey" by James Cameron, although a work of fiction, offers a cinematic lens through which to contemplate the enduring allure of the RMS Titanic and its potential entanglement with environmental factors.
The researchers also draw inspiration from their own popular culture experiences, including repeated viewings of "An Inconvenient Truth" and "The Day After Tomorrow," which, albeit not directly focused on maritime tragedies, underscore the impact of environmental concerns on public consciousness and, in a more tangential sense, the substantial influence of blockbuster films on societal fascination with global phenomena.
As the scholarly inquiry rubs elbows with the whimsically imaginative, this wide-ranging review sets the stage for the singular fusion of environmental inquiry and entertainment intrigue, all while maintaining a sense of scholarly rigor and a healthy dose of intellectual levity.

[[RESULTS]]
The statistical analyses conducted in this study revealed a remarkably strong correlation between air pollution levels and Google searches for 'Titanic' in Wichita, Kansas. The correlation coefficient of 0.8957514 signifies a robust relationship between these seemingly incongruous variables. This correlation indicates that as air pollution levels in Wichita increased, so did the frequency of searches for information related to the iconic film 'Titanic' on Google.
The coefficient of determination, with a value of 0.8023706, suggests that approximately 80.24% of the variation in 'Titanic' searches can be explained by changes in air pollution levels. This finding underscores the substantial influence of air pollution on the public's interest in the cinematic masterpiece.
Importantly, the p-value of less than 0.01 points to the statistical significance of this relationship. This indicates that the observed correlation is highly unlikely to have occurred by random chance, further substantiating the validity of the association.
The scatterplot in Figure 1 visually depicts the strong positive correlation between air pollution levels and Google searches for 'Titanic' in Wichita. Each data point on the plot represents the pairing of air pollution levels and the corresponding volume of 'Titanic' searches, displaying a clear trend of increased searches coinciding with higher levels of air pollution.
These results underscore the unexpected but compelling relationship between environmental quality and popular culture, prompting consideration of the potential impact of air pollution on individual behavior and interests. The implications of these findings extend beyond the realms of environmental science and information technology, offering a whimsical window into the subtle ways in which external factors influence societal preferences and activities.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of this study lend credence to the notion that air pollution has an unexpected influence on the public's search interests, particularly in relation to the classic film 'Titanic.' Our findings align with the prior research by Smith and Doe et al., who explored the impact of external environmental variables on online search patterns and entertainment preferences. While their work was grounded in more traditional scholarly endeavors, our study delved into a more lighthearted exploration of the potential effects of air pollution on movie curiosity, drawing inspiration from sources both serious and whimsical.

Our robust correlation coefficient and statistically significant p-value echo the sentiments expressed in the seemingly fanciful works of Margaret Airpollutant, who envisioned a world where air pollution steers cultural predilections. The statistical significance of our findings reaffirms the potential for environmental factors, such as air pollution, to shape public interests and behaviors, even leading individuals to seek out information about cinematic masterpieces amid a smoggy backdrop.

While some may initially dismiss the connection between air pollution and 'Titanic' searches as a mere coincidence, the substantial influence evinced by our coefficient of determination emphasizes the genuine impact of air pollution on movie curiosity. It seems that as the air quality in Wichita deteriorates, residents are not only confronting environmental challenges but also seeking solace in the familiarity of a tragic love story set against the backdrop of a sinking ship.

Our study not only contributes to the growing body of research on environmental influences on human behavior but also injects a sense of whimsy and wonder into the scholarly discourse. By embracing the unexpected connections between environmental quality and popular culture, we open the door to a more imaginative and playful approach to understanding the nuanced interplay of external factors on societal interests.

In conclusion, our findings invite further exploration into the delightful and often peculiar ways in which environmental conditions could leave an indelible imprint on human inclinations, prompting a reconsideration of the multifaceted impact of air pollution and an acknowledgment of its potential to stir the winds of curiosity.


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 Wichita and Google searches for 'titanic'. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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]]
Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity

[[ABSTRACT]]
The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

[[INTRDUCTION]]
INTRODUCTION
In the annals of academic research, it is not often that one encounters a study that seeks to unravel the enigmatic connection between air pollution and Google searches for 'Titanic'. However, as the saying goes, "Where there’s smog, there’s a Google search for Leo DiCaprio," or something along those lines. While this seemingly peculiar correlation may evoke skepticism or amusement, our research team approached it with the utmost seriousness and a dash of whimsy.
The allure of the RMS Titanic, a symbol of both tragic demise and enduring fascination, has transcended generations and captured the intrigue of movie enthusiasts worldwide. Likewise, air pollution, a perennial specter looming over urban environments, has been the subject of rigorous scientific inquiry and the occasional exasperated muttering from asthmatic individuals. The convergence of these two seemingly disparate phenomena in the context of Google searches invites a playful curiosity, not dissimilar to a Titanic-themed game of "Six Degrees of Kevin Bacon" played on a smoggy evening.
The city of Wichita, Kansas, where the wheat fields whisper tales of yesteryear and the winds carry the echo of '90s blockbusters, provided an intriguing setting for this investigation. Here, a city known for its aviation legacy and convivial Midwestern charm, we sought to decipher the subtle dance between the atmospheric particles and online pursuits of maritime tragedy aficionados.
With access to comprehensive air quality data from the Environmental Protection Agency and the voluminous records of Google search queries through the aptly named Google Trends, we embarked on an academic journey rife with statistical analyses, perplexing correlations, and a deep-seated appreciation for the idiosyncrasies of human behavior. The fruits of our labor revealed a robust correlation coefficient of 0.8957514, which beckoned us to peer through the haze of air pollution and discern patterns in the digital footprints left by those in pursuit of cinematic nostalgia.
As we unravel the nuances of this unusual connection, it is our fervent belief that our findings will not only expand the boundaries of interdisciplinary inquiry but also elicit a chuckle or two from readers who are willing to indulge in this lighthearted exploration. So, buckle up and prepare to navigate the curious realms of air pollution and cinematic wistfulness, where the mist of scholarly rigor converges with the buoyancy of good-natured banter. Let the journey begin.

[[RESULTS]]
The statistical analyses conducted in this study revealed a remarkably strong correlation between air pollution levels and Google searches for 'Titanic' in Wichita, Kansas. The correlation coefficient of 0.8957514 signifies a robust relationship between these seemingly incongruous variables. This correlation indicates that as air pollution levels in Wichita increased, so did the frequency of searches for information related to the iconic film 'Titanic' on Google.
The coefficient of determination, with a value of 0.8023706, suggests that approximately 80.24% of the variation in 'Titanic' searches can be explained by changes in air pollution levels. This finding underscores the substantial influence of air pollution on the public's interest in the cinematic masterpiece.
Importantly, the p-value of less than 0.01 points to the statistical significance of this relationship. This indicates that the observed correlation is highly unlikely to have occurred by random chance, further substantiating the validity of the association.
The scatterplot in Figure 1 visually depicts the strong positive correlation between air pollution levels and Google searches for 'Titanic' in Wichita. Each data point on the plot represents the pairing of air pollution levels and the corresponding volume of 'Titanic' searches, displaying a clear trend of increased searches coinciding with higher levels of air pollution.
These results underscore the unexpected but compelling relationship between environmental quality and popular culture, prompting consideration of the potential impact of air pollution on individual behavior and interests. The implications of these findings extend beyond the realms of environmental science and information technology, offering a whimsical window into the subtle ways in which external factors influence societal preferences and activities.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has illuminated a quirky and thought-provoking connection between air pollution and the collective fascination with the immortal tale of the Titanic in Wichita, Kansas. As we navigated through the mist of environmental data and the digital footprints of movie enthusiasts, we unveiled a robust correlation, akin to a grand ship majestically emerging from the fog. It seems that as the air in Wichita gets more polluted, the city's denizens turn to the digital waves in search of tidbits about the iconic vessel, creating a perplexing pas de deux between atmospheric woes and cinematic nostalgia.

While some might view this correlation as simply a "smoggy mirage," our statistical analyses, with a correlation coefficient of 0.8957514 and a p-value less than 0.01, firmly attest to the reality of this connection. It's as if the air pollution whispered to the citizens, "I'm the king of the world" before they hastened to their keyboards in search of their own Leonardo DiCaprio fix.

The implications of this unexpected relationship extend beyond the realms of environmental science and information technology. Our findings beguile us to ponder the whimsical ways in which pollution may sway our leisurely pursuits, perhaps prompting a reimagining of the phrase "smelling like a rose" to "smelling like a sooty search for cinematic delight."

As we bid adieu to this peculiar yet fascinating chapter of our research, we acknowledge that the intersection of air pollution and cultural curiosity is a beguiling rabbit hole worthy of further exploration, though the jest of a Titanic-shaped jack-in-the-box emerging from the fog may just be too tantalizing to resist. Nonetheless, in the spirit of academic injunction and comedic frivolity, we assert that, in the words of Jack Dawson, "No more research needed, that's the spot where I wish to leave my hat."

So, dear readers, let us embrace this lighthearted dalliance into the realms of air pollution and movie enthrallment, and remember that even in the midst of scientific inquiry, there's always room for a playful aside or two. As we bid farewell to this curious foray, let our scholarly musings serve as a reminder: in the labyrinth of research, a touch of whimsy can be the lifeboat that ensures our academic voyage remains buoyant.

In the grand tradition of academia and in the spirit of light-hearted revelry, we quip, but declare earnestly, that for now, the curtain has closed on this oddball act of research.


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 Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Ecological Entertainment Research


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 Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Curious Environmental Inquiries


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 Air-pollution While Googling 'Titanic': A Connection Between Environmental Quality and Movie Curiosity with an abstract of The curious case of air pollution and Google searches for 'Titanic' in Wichita has been examined in this research study. While most academics might steer clear of connecting environmental quality with movie interests, our team boldly delved into this intriguing relationship. Leveraging data from the Environmental Protection Agency and Google Trends, we uncovered a strong correlation between air pollution levels and searches for the iconic film. The correlation coefficient of 0.8957514 and the statistically significant p-value of less than 0.01 indicate a robust association between the two variables. We dive into the implications of this unexpected connection, including potential effects on mental state, entertainment choices influenced by environmental factors, and the possibility of air pollution reshaping public interests. Our findings not only shed light on the unusual relationship between air quality and popular culture, but also provoke a lighthearted and whimsical exploration of the hidden influences of pollution.

ChatGPT:

Air pollution, Google searches, Titanic, environmental quality, movie curiosity, Wichita, correlation coefficient, EPA data, Google Trends, mental state, entertainment choices, air quality effects, popular culture, public interests, pollution influences.

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

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

See what else correlates with Google searches for 'titanic'

Correlation r = 0.8957514 (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 = 0.8023706 (Coefficient of determination)
This means 80.2% of the change in the one variable (i.e., Google searches for 'titanic') is predictable based on the change in the other (i.e., Air pollution in Wichita) over the 13 years from 2004 through 2016.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.5E-5. 0.0000345509855744775250000000
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 0.9 in 0.0035% of random cases. Said differently, if you correlated 28,943 random variables You don't actually need 28 thousand variables to find a correlation like this one. 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.

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 12 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 12 because we have two variables measured over a period of 13 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.

[ 0.68, 0.97 ] 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.
2004200520062007200820092010201120122013201420152016
Air pollution in Wichita (Bad air quality days)000.273973000.273973001.09290000.273224
Google searches for 'titanic' (Rel. search volume)12.666713.083313.416712.916712.583313.51414.666723.666713.916712.833312.2512.5833




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([0,0,0.273973,0,0,0.273973,0,0,1.0929,0,0,0,0.273224,])
array_2 = np.array([12.6667,13.0833,13.4167,12.9167,12.5833,13.5,14,14.6667,23.6667,13.9167,12.8333,12.25,12.5833,])
array_1_name = "Air pollution in Wichita"
array_2_name = "Google searches for 'titanic'"

# 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?

Bravo! Your evaluation rocks!


Correlation ID: 1937 · Black Variable ID: 21444 · Red Variable ID: 1529
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0