about · email me · subscribe
Spurious correlation #4,097 · 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 Milwaukee and the second variable is Google searches for 'Titanic'.  The chart goes from 2008 to 2023, and the two variables track closely in value over that time. Small Image

AI explanation

The air pollution in Milwaukee created a murky atmosphere, leading people to seek out the foggy romance of the Titanic. It's like they say, when the smog rises in Milwaukee, interest in the Titanic sets sail!

Model: dalle-3
Prompt: Generate a comic-book-style illustration of the skyline of Milwaukee enveloped in a murky haze of air pollution, with muted colors that evoke a 1960s aesthetic. Show people indoors, engrossed in their phones, amidst the smog-filled atmosphere. Meanwhile, portray a surge of Google searches for "Titanic" symbolizing the enduring fascination with the epic voyage. Use a dotted halftone pattern to create hazy and atmospheric effects. 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 Milwaukee 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: Art nouveau Whimsical illustration A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Hyper-realistic 3D Pixar Style
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

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 Milwaukee and Google searches for 'Titanic', in the following situation: The air pollution in Milwaukee created a murky atmosphere, leading people to seek out the foggy romance of the Titanic. It's like they say, when the smog rises in Milwaukee, interest in the Titanic sets sail!. Keep the description simple.
ChatGPT: The murky skyline of Milwaukee is shrouded in air pollution, creating a hazy atmosphere. Despite this, people are huddled indoors, their fingers dancing across their phones, as searches for "Titanic" surge on Google. The smog may have clouded the city, but the fascination with the epic voyage of the Titanic remains crystal clear.

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: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: The murky skyline of Milwaukee is shrouded in air pollution, creating a hazy atmosphere. Despite this, people are huddled indoors, their fingers dancing across their phones, as searches for "Titanic" surge on Google. The smog may have clouded the city, but the fascination with the epic voyage of the Titanic remains crystal clear. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a comic-book-style illustration of the skyline of Milwaukee enveloped in a murky haze of air pollution, with muted colors that evoke a 1960s aesthetic. Show people indoors, engrossed in their phones, amidst the smog-filled atmosphere. Meanwhile, portray a surge of Google searches for "Titanic" symbolizing the enduring fascination with the epic voyage. Use a dotted halftone pattern to create hazy and atmospheric effects.

*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 Milwaukee caused Titanic (Google searches for 'Titanic') to increase. Include one good pun.

AI academic paper

(Because p < 0.01)
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

The Journal of Irreverent Interdisciplinary Research

Jan 2024
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 witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Rhyme words in the title.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.9041888 and p < 0.01 for 2008 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]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The ominous specter of air pollution poses a significant challenge to environmental and public health, a burden that plagues cities worldwide. At the same time, the insatiable curiosity of the modern populace drives them to seek answers and trivia on the vast expanse of the internet. Here we present an enigmatic conundrum, one that intertwines these seemingly unrelated realms - the correlation between Milwaukee's air quality and Google searches for the fateful vessel, the 'Titanic'.

The title "Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw" piques the curiosity much like the fateful iceberg did to the Titanic. As the age-old question goes, "What do air pollution and the Titanic have in common?" The answer may surprise you, or at the very least, intrigue you.

The abstract has already tantalized you with a sneak peek at the statistical correlation coefficient of 0.9041888 and a p-value that is less than 0.01. Fear not, statistical novices! We will guide you through this statistical sea of numbers and metrics without causing you to shipwreck on the shores of confusion.

The relationship between air pollution and internet search activity may at first glance seem as perplexing as Leonardo DiCaprio's survival tactics in the movie "Titanic". However, through robust statistical analysis leveraging data from the Environmental Protection Agency and Google Trends, this study has endeavored to unravel this peculiar connection. For the skeptics, we offer reassurance - this exploration is not a mere exercise in whimsy; rather, it reveals profound insights into the societal effects of environmental factors on the public's online behaviors.

So, fasten your seatbelts, or in this case, securely affix your lifejacket, as we embark on this statistical voyage to unearth the intertwined tale of air pollution and 'Titanic' Google searches. The findings of this study promise to illuminate a path toward a deeper understanding of the subtle nuances that govern human interactions, whether with the environment or the digital realm.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. 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 a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The ominous specter of air pollution poses a significant challenge to environmental and public health, a burden that plagues cities worldwide. At the same time, the insatiable curiosity of the modern populace drives them to seek answers and trivia on the vast expanse of the internet. Here we present an enigmatic conundrum, one that intertwines these seemingly unrelated realms - the correlation between Milwaukee's air quality and Google searches for the fateful vessel, the 'Titanic'.
The title "Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw" piques the curiosity much like the fateful iceberg did to the Titanic. As the age-old question goes, "What do air pollution and the Titanic have in common?" The answer may surprise you, or at the very least, intrigue you.
The abstract has already tantalized you with a sneak peek at the statistical correlation coefficient of 0.9041888 and a p-value that is less than 0.01. Fear not, statistical novices! We will guide you through this statistical sea of numbers and metrics without causing you to shipwreck on the shores of confusion.
The relationship between air pollution and internet search activity may at first glance seem as perplexing as Leonardo DiCaprio's survival tactics in the movie "Titanic". However, through robust statistical analysis leveraging data from the Environmental Protection Agency and Google Trends, this study has endeavored to unravel this peculiar connection. For the skeptics, we offer reassurance - this exploration is not a mere exercise in whimsy; rather, it reveals profound insights into the societal effects of environmental factors on the public's online behaviors.
So, fasten your seatbelts, or in this case, securely affix your lifejacket, as we embark on this statistical voyage to unearth the intertwined tale of air pollution and 'Titanic' Google searches. The findings of this study promise to illuminate a path toward a deeper understanding of the subtle nuances that govern human interactions, whether with the environment or the digital realm.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The connection between air pollution and online search behavior holds a certain intrigue, much like a suspenseful mystery novel. Smith and Doe (2015) were among the first to investigate the impact of environmental factors on internet search trends, laying the groundwork for subsequent explorations in this enigmatic realm. Their study, "Clean Air, Dirty Search: Unraveling the Relationship Between Atmospheric Quality and Online Activity," revealed compelling evidence of a correlation between air quality and the frequency of online searches for historical events. Their findings served as the springboard for further investigations into this uncharted statistical territory.

Building upon this foundation, Jones and Smith (2019) delved into the specifics of air pollution's influence on search behavior, offering insights into the nuances of public engagement with online content. In their publication, "Breathless Searches: A Statistical Analysis of Air Quality and Online Query Patterns," the authors unveiled the intricate interplay between atmospheric conditions and virtual exploration, igniting a spark of curiosity in the academic community.

Leveraging the lessons gleaned from these scholarly contributions, the present authors embarked on a quest to unravel the peculiar relationship between Milwaukee's air pollution levels and Google searches for the legendary ship, the 'Titanic'. As we navigate through the ocean of statistical literature, it is imperative to acknowledge the significance of these foundational studies in paving the way for our current investigation.

In addition to these empirical research efforts, a number of non-fiction books have shed light on the societal implications of air pollution and the public's fascination with historical events. "The Air We Breathe: A Comprehensive Analysis of Atmospheric Quality in Urban Environments" by Smith and Johnson (2018) offers a thorough examination of the far-reaching effects of air pollution, providing a comprehensive backdrop for understanding its potential influence on online behaviors.

Similarly, "Tragedy at Sea: A Historical and Societal Analysis of the Titanic Disaster" by Brown and Williams (2017) delves into the enduring allure of the 'Titanic' saga, uncovering the intricacies of human fascination with this iconic maritime tragedy. While these literary works may not directly address the statistical relationship between air pollution and Google searches, they offer valuable contextual insights that enrich our understanding of the broader phenomena at play.

Turning to the world of fiction, several novels have woven tales of environmental adversity and historical intrigue, capturing the essence of our statistical inquiry in an imaginative narrative. "The Polluted Paradise" by Smith (2019) presents an enthralling story set against the backdrop of a city grappling with environmental challenges, subtly echoing the real-world dynamics of air pollution's impact. In a similar vein, "Echoes of the Deep: A Tale of Mystery and Resilience" by Johnson (2016) intertwines the mysteries of the past with the complexities of present-day environmental crises, portraying a captivating fusion of history and atmospheric influence.

On a more lighthearted note, popular television shows such as "Mystery Investigations" and "Curious Queries" have offered glimpses into the public's fascination with historical events and the power of online search engines to satiate their curiosity. The authors confess to frequenting these programs during the research process, drawing inspiration from the intriguing parallels between on-screen investigations and our own statistical exploration.

As we plunge into the depths of the statistical sea, these diverse sources of inspiration and knowledge serve to illuminate the multifaceted dimensions of our inquiry. With this eclectic array of literature and media as our compass, we navigate the turbulent waters of statistical analysis, poised to unravel the captivating intersection of air pollution and 'Titanic' Google searches.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 2008 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]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

[[INTRODUCTION]]
The ominous specter of air pollution poses a significant challenge to environmental and public health, a burden that plagues cities worldwide. At the same time, the insatiable curiosity of the modern populace drives them to seek answers and trivia on the vast expanse of the internet. Here we present an enigmatic conundrum, one that intertwines these seemingly unrelated realms - the correlation between Milwaukee's air quality and Google searches for the fateful vessel, the 'Titanic'.
The title "Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw" piques the curiosity much like the fateful iceberg did to the Titanic. As the age-old question goes, "What do air pollution and the Titanic have in common?" The answer may surprise you, or at the very least, intrigue you.
The abstract has already tantalized you with a sneak peek at the statistical correlation coefficient of 0.9041888 and a p-value that is less than 0.01. Fear not, statistical novices! We will guide you through this statistical sea of numbers and metrics without causing you to shipwreck on the shores of confusion.
The relationship between air pollution and internet search activity may at first glance seem as perplexing as Leonardo DiCaprio's survival tactics in the movie "Titanic". However, through robust statistical analysis leveraging data from the Environmental Protection Agency and Google Trends, this study has endeavored to unravel this peculiar connection. For the skeptics, we offer reassurance - this exploration is not a mere exercise in whimsy; rather, it reveals profound insights into the societal effects of environmental factors on the public's online behaviors.
So, fasten your seatbelts, or in this case, securely affix your lifejacket, as we embark on this statistical voyage to unearth the intertwined tale of air pollution and 'Titanic' Google searches. The findings of this study promise to illuminate a path toward a deeper understanding of the subtle nuances that govern human interactions, whether with the environment or the digital realm.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To delve into the murky depths of the connection between Milwaukee's air pollution and Google searches for the 'Titanic', our research team embarked on a methodological odyssey befitting of these enigmatic phenomena. We harnessed data from the Environmental Protection Agency (EPA) to encapsulate the atmospheric quality of Milwaukee, measuring various pollutants such as particulate matter, carbon monoxide, sulfur dioxide, and nitrogen dioxide. This comprehensive approach allowed us to capture the multi-faceted nature of air pollution, recognizing that pollutants, much like the characters in a shipboard drama, each play their distinct roles in influencing the environment.

Simultaneously, we embraced the methodology of Google Trends, casting our net into the vast ocean of internet search activity to ensnare the keyword 'Titanic'. This digital trawling voyage enabled us to capture the ebbs and flows of public intrigue in the storied vessel, traversing the maelstrom of internet queries to illuminate the patterns of interest over the 2008-2023 timeframe. Through these digital breadcrumbs left by internet users, we sought to map the vicissitudes of 'Titanic' searches, resembling a quest for a fabled treasure amidst the ocean of digital data.

Once we gathered our trove of data, we embarked on a statistical odyssey, navigating through the tempestuous waters of correlation analysis. Our statistical vessel weathered the storm to reveal a substantial correlation coefficient of 0.9041888, reminiscent of a sturdy ship that steers through turbulent seas. We employed the venerable Pearson correlation method to scrutinize the assimilation of air pollution levels and 'Titanic' search volumes, painting a statistical portrait that rivaled the legendary artworks adorning the titular vessel.

To navigate the treacherous waters of statistical significance, we set our sights on the elusive p-value, diligently steering our course toward the shores of confident inference. Our endeavors were not in vain, as we witnessed a p-value of less than 0.01 emerge from the statistical mist, signifying a robust relationship worthy of unearthing. This fateful encounter with the p-value echoes the triumph of discovery, akin to finding a hidden gem amidst the debris of statistical noise.

In summary, our methodology blends the rigors of environmental data collection with the intangible waves of internet search trends, culminating in a statistical exploration that mirrors the intertwined nature of environmental and digital spheres. Our methodological compass steers true north, guiding us toward a deeper understanding of the serendipitous connection between Milwaukee's air pollution and the indomitable allure of 'Titanic' in the virtual realm.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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 2008 to 2023, you found a correlation 0.9041888, r-squared of 0.8175573, 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]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The ominous specter of air pollution poses a significant challenge to environmental and public health, a burden that plagues cities worldwide. At the same time, the insatiable curiosity of the modern populace drives them to seek answers and trivia on the vast expanse of the internet. Here we present an enigmatic conundrum, one that intertwines these seemingly unrelated realms - the correlation between Milwaukee's air quality and Google searches for the fateful vessel, the 'Titanic'.
The title "Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw" piques the curiosity much like the fateful iceberg did to the Titanic. As the age-old question goes, "What do air pollution and the Titanic have in common?" The answer may surprise you, or at the very least, intrigue you.
The abstract has already tantalized you with a sneak peek at the statistical correlation coefficient of 0.9041888 and a p-value that is less than 0.01. Fear not, statistical novices! We will guide you through this statistical sea of numbers and metrics without causing you to shipwreck on the shores of confusion.
The relationship between air pollution and internet search activity may at first glance seem as perplexing as Leonardo DiCaprio's survival tactics in the movie "Titanic". However, through robust statistical analysis leveraging data from the Environmental Protection Agency and Google Trends, this study has endeavored to unravel this peculiar connection. For the skeptics, we offer reassurance - this exploration is not a mere exercise in whimsy; rather, it reveals profound insights into the societal effects of environmental factors on the public's online behaviors.
So, fasten your seatbelts, or in this case, securely affix your lifejacket, as we embark on this statistical voyage to unearth the intertwined tale of air pollution and 'Titanic' Google searches. The findings of this study promise to illuminate a path toward a deeper understanding of the subtle nuances that govern human interactions, whether with the environment or the digital realm.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

We uncovered a substantial correlation between the levels of air pollution in Milwaukee and the frequency of Google searches for the term 'Titanic' over the period from 2008 to 2023. The correlation coefficient of 0.9041888 signifies a remarkably strong linear relationship between these seemingly disparate variables. While we wield our statistical compass and sextant, we observed an r-squared value of 0.8175573, indicating that approximately 81.76% of the variation in 'Titanic' search activity can be explained by changes in air pollution levels. We also calculated a p-value of less than 0.01, which further reinforces the robustness of the discovered link.

The aptly named Figure 1, which we have chosen not to place on a pedestal (because it might develop a fear of heights), depicts a scatterplot showcasing the compelling correlation between air pollution and 'Titanic' search volumes. This visual representation paints a portrait so vivid that even the most seasoned sailor would find it hard to resist a second glance.

In summary, the results of this investigation illustrate a significant association between air pollution in Milwaukee and the public's interest in the oceanic tragedy of the 'Titanic'. This intriguing finding raises a veritable tidal wave of questions about the intricate interplay between environmental factors and online search behavior and beckons for further exploration into the depths of this unexpected connection.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

[[LITERATURE REVIEW]]
The connection between air pollution and online search behavior holds a certain intrigue, much like a suspenseful mystery novel. Smith and Doe (2015) were among the first to investigate the impact of environmental factors on internet search trends, laying the groundwork for subsequent explorations in this enigmatic realm. Their study, "Clean Air, Dirty Search: Unraveling the Relationship Between Atmospheric Quality and Online Activity," revealed compelling evidence of a correlation between air quality and the frequency of online searches for historical events. Their findings served as the springboard for further investigations into this uncharted statistical territory.
Building upon this foundation, Jones and Smith (2019) delved into the specifics of air pollution's influence on search behavior, offering insights into the nuances of public engagement with online content. In their publication, "Breathless Searches: A Statistical Analysis of Air Quality and Online Query Patterns," the authors unveiled the intricate interplay between atmospheric conditions and virtual exploration, igniting a spark of curiosity in the academic community.
Leveraging the lessons gleaned from these scholarly contributions, the present authors embarked on a quest to unravel the peculiar relationship between Milwaukee's air pollution levels and Google searches for the legendary ship, the 'Titanic'. As we navigate through the ocean of statistical literature, it is imperative to acknowledge the significance of these foundational studies in paving the way for our current investigation.
In addition to these empirical research efforts, a number of non-fiction books have shed light on the societal implications of air pollution and the public's fascination with historical events. "The Air We Breathe: A Comprehensive Analysis of Atmospheric Quality in Urban Environments" by Smith and Johnson (2018) offers a thorough examination of the far-reaching effects of air pollution, providing a comprehensive backdrop for understanding its potential influence on online behaviors.
Similarly, "Tragedy at Sea: A Historical and Societal Analysis of the Titanic Disaster" by Brown and Williams (2017) delves into the enduring allure of the 'Titanic' saga, uncovering the intricacies of human fascination with this iconic maritime tragedy. While these literary works may not directly address the statistical relationship between air pollution and Google searches, they offer valuable contextual insights that enrich our understanding of the broader phenomena at play.
Turning to the world of fiction, several novels have woven tales of environmental adversity and historical intrigue, capturing the essence of our statistical inquiry in an imaginative narrative. "The Polluted Paradise" by Smith (2019) presents an enthralling story set against the backdrop of a city grappling with environmental challenges, subtly echoing the real-world dynamics of air pollution's impact. In a similar vein, "Echoes of the Deep: A Tale of Mystery and Resilience" by Johnson (2016) intertwines the mysteries of the past with the complexities of present-day environmental crises, portraying a captivating fusion of history and atmospheric influence.
On a more lighthearted note, popular television shows such as "Mystery Investigations" and "Curious Queries" have offered glimpses into the public's fascination with historical events and the power of online search engines to satiate their curiosity. The authors confess to frequenting these programs during the research process, drawing inspiration from the intriguing parallels between on-screen investigations and our own statistical exploration.
As we plunge into the depths of the statistical sea, these diverse sources of inspiration and knowledge serve to illuminate the multifaceted dimensions of our inquiry. With this eclectic array of literature and media as our compass, we navigate the turbulent waters of statistical analysis, poised to unravel the captivating intersection of air pollution and 'Titanic' Google searches.

[[RESULTS]]
We uncovered a substantial correlation between the levels of air pollution in Milwaukee and the frequency of Google searches for the term 'Titanic' over the period from 2008 to 2023. The correlation coefficient of 0.9041888 signifies a remarkably strong linear relationship between these seemingly disparate variables. While we wield our statistical compass and sextant, we observed an r-squared value of 0.8175573, indicating that approximately 81.76% of the variation in 'Titanic' search activity can be explained by changes in air pollution levels. We also calculated a p-value of less than 0.01, which further reinforces the robustness of the discovered link.
The aptly named Figure 1, which we have chosen not to place on a pedestal (because it might develop a fear of heights), depicts a scatterplot showcasing the compelling correlation between air pollution and 'Titanic' search volumes. This visual representation paints a portrait so vivid that even the most seasoned sailor would find it hard to resist a second glance.
In summary, the results of this investigation illustrate a significant association between air pollution in Milwaukee and the public's interest in the oceanic tragedy of the 'Titanic'. This intriguing finding raises a veritable tidal wave of questions about the intricate interplay between environmental factors and online search behavior and beckons for further exploration into the depths of this unexpected connection.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our investigation underscore the compelling relationship between air pollution in Milwaukee and Google search activity for the term 'Titanic'. Our findings provide empirical support for the curious speculations put forth by Smith and Doe's (2015) seminal work on the influence of atmospheric quality on internet search trends. It seems our statistical expedition has navigated the murky waters of environmental impact on virtual voyages of knowledge, arriving at a convergence with the pioneering research that set sail in this enigmatic domain.

While the notion of air pollution setting the stage for increased interest in a historic maritime disaster may initially appear as far-fetched as a tall tale spun by a salty sea captain, our results reveal a solid statistical anchor to this proposition. Jones and Smith's (2019) exploration of air pollution's influence on search behavior now finds reaffirmation in our own study, as the waves of correlation between atmospheric conditions and online query patterns wash ashore in our findings. Their insightful revelations, akin to treasures gleaming under the moonlit statistical sea, have guided our own expedition toward a richer understanding of this enthralling relationship.

As we reflect on the seemingly incongruous connection between air pollution and 'Titanic' searches, the words of Brown and Williams (2017), in their captivating analysis of the enduring allure of the maritime tragedy, echo with newfound relevance. Like a compass pointing steadfastly toward uncharted statistical territories, their exploration of the societal fascination with the 'Titanic' saga foreshadowed the unexpected convergence of air pollution and online inquisition that we have unveiled.

In this era of data-driven exploration, our findings serve as yet another drop in the statistical ocean, adding depth to the growing body of knowledge surrounding the influence of environmental factors on online engagement. The age-old adage of "digging for gold" in data has taken on a new twist – we seem to have stumbled upon a statistical treasure trove at the intersection of Milwaukee's air pollution and public interest in the 'Titanic' saga.

Our research uncovers a rich seam of statistical significance, inviting fellow scholars to embark on their own voyages of inquiry into the enigmatic realm of environmental influence on virtual exploration. The allure of the 'Titanic' and the ever-present haze of air pollution have cast a compelling net, drawing us into a churning maelstrom of statistical curiosity and revealing a seamless intertwining of seemingly disparate phenomena. As we eagerly anticipate the waves of subsequent research to ripple forth from this discovery, our own scholarly ship sets a course toward untold statistical horizons, ready to unravel the mysteries that lie beyond the surface of this unexpected statistical seasaw.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.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 Milwaukee and Google searches for 'Titanic'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw

[[ABSTRACT]]
This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

[[INTRDUCTION]]
The ominous specter of air pollution poses a significant challenge to environmental and public health, a burden that plagues cities worldwide. At the same time, the insatiable curiosity of the modern populace drives them to seek answers and trivia on the vast expanse of the internet. Here we present an enigmatic conundrum, one that intertwines these seemingly unrelated realms - the correlation between Milwaukee's air quality and Google searches for the fateful vessel, the 'Titanic'.
The title "Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw" piques the curiosity much like the fateful iceberg did to the Titanic. As the age-old question goes, "What do air pollution and the Titanic have in common?" The answer may surprise you, or at the very least, intrigue you.
The abstract has already tantalized you with a sneak peek at the statistical correlation coefficient of 0.9041888 and a p-value that is less than 0.01. Fear not, statistical novices! We will guide you through this statistical sea of numbers and metrics without causing you to shipwreck on the shores of confusion.
The relationship between air pollution and internet search activity may at first glance seem as perplexing as Leonardo DiCaprio's survival tactics in the movie "Titanic". However, through robust statistical analysis leveraging data from the Environmental Protection Agency and Google Trends, this study has endeavored to unravel this peculiar connection. For the skeptics, we offer reassurance - this exploration is not a mere exercise in whimsy; rather, it reveals profound insights into the societal effects of environmental factors on the public's online behaviors.
So, fasten your seatbelts, or in this case, securely affix your lifejacket, as we embark on this statistical voyage to unearth the intertwined tale of air pollution and 'Titanic' Google searches. The findings of this study promise to illuminate a path toward a deeper understanding of the subtle nuances that govern human interactions, whether with the environment or the digital realm.

[[RESULTS]]
We uncovered a substantial correlation between the levels of air pollution in Milwaukee and the frequency of Google searches for the term 'Titanic' over the period from 2008 to 2023. The correlation coefficient of 0.9041888 signifies a remarkably strong linear relationship between these seemingly disparate variables. While we wield our statistical compass and sextant, we observed an r-squared value of 0.8175573, indicating that approximately 81.76% of the variation in 'Titanic' search activity can be explained by changes in air pollution levels. We also calculated a p-value of less than 0.01, which further reinforces the robustness of the discovered link.
The aptly named Figure 1, which we have chosen not to place on a pedestal (because it might develop a fear of heights), depicts a scatterplot showcasing the compelling correlation between air pollution and 'Titanic' search volumes. This visual representation paints a portrait so vivid that even the most seasoned sailor would find it hard to resist a second glance.
In summary, the results of this investigation illustrate a significant association between air pollution in Milwaukee and the public's interest in the oceanic tragedy of the 'Titanic'. This intriguing finding raises a veritable tidal wave of questions about the intricate interplay between environmental factors and online search behavior and beckons for further exploration into the depths of this unexpected connection.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has voyaged into uncharted statistical waters to unravel the enigmatic link between Milwaukee's air pollution and Google searches for the 'Titanic'. The substantial correlation coefficient of 0.9041888, akin to the Titanic's iceberg encounter, highlights the unexpected bond between atmospheric quality and public online engagements. The robust statistical findings, much like a lifeboat in a statistical storm, buoy our claim of a significant association between these seemingly incongruous variables.

While this investigation has shed light on the captivating relationship between air pollution and 'Titanic' search activity, it has also evoked a cascade of unanticipated puns and jests, just like Jack's sketching escapades aboard the ill-fated vessel. The statistical compass and sextant, though not as glamorous as Rose's Heart of the Ocean necklace, have guided us through this unusual correlation, lighting the way for further research endeavors.

However, while our findings may titillate the statistical senses, like the suspense of the blockbuster movie, it is crucial to acknowledge the limitations of this study. Our analysis, much like the mythical depths of the ocean, cannot capture the entirety of the complex interplay between environmental factors and online behaviors. Future research may delve deeper into the nuances of this correlation, but for now, we have unearthed the hidden treasure of a statistically significant connection between Milwaukee's air pollution and the 'Titanic' on Google. Thus, we assert, like a confident captain steering his vessel, that no further research is needed in this area - we have reached the pinnacle of statistical serendipity.


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 Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Irreverent Interdisciplinary 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 Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Environmental Data 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 Milwaukee Air Pollution's Influence on 'Titanic' Google Searches: A Statistical Seasaw with an abstract of This paper investigates the relationship between air pollution levels in Milwaukee and Google search activity for the term 'Titanic'. Leveraging data from the Environmental Protection Agency and Google Trends, our research team examined the potential impact of air pollution on internet search behavior. Utilizing statistical analysis, we calculated a substantial correlation coefficient of 0.9041888 and observed a significant p-value of less than 0.01 for the period from 2008 to 2023. The findings shed light on the intriguing connection between atmospheric quality and the public's online engagements, revealing an unexpected parallel between pollution levels and the iconic maritime disaster. This study prompts a reevaluation of the societal effects of environmental factors and showcases the wealth of information that can be gleaned from seemingly unrelated data sources.

ChatGPT:

Milwaukee air pollution, Google search activity, Titanic, environmental protection agency data, Google Trends, statistical analysis, correlation coefficient, atmospheric quality, online engagement, public behavior, pollution levels, maritime disaster, societal effects, environmental factors

*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 Milwaukee
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Milwaukee-Waukesha-West Allis, WI
Source: Environmental Protection Agency
See what else correlates with Air pollution in Milwaukee

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 = 0.9041888 (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 = 0.8175573 (Coefficient of determination)
This means 81.8% 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 Milwaukee) over the 16 years from 2008 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-6. 0.0000015376926290819142000000
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 0.00015% of random cases. Said differently, if you correlated 650,325 random variables You don't actually need 650 thousand variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 15 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 15 because we have two variables measured over a period of 16 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.

[ 0.74, 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.
2008200920102011201220132014201520162017201820192020202120222023
Air pollution in Milwaukee (Bad air quality days)0.2732240.2739730.2739730.2739732.459020000.27322400.54794500.27322400.2739731.64835
Google searches for 'Titanic' (Rel. search volume)12.513.514.083314.66672414.2512.666712.166712.7512.511.916711.25119.916679.9166719.6667




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([0.273224,0.273973,0.273973,0.273973,2.45902,0,0,0,0.273224,0,0.547945,0,0.273224,0,0.273973,1.64835,])
array_2 = np.array([12.5,13.5,14.0833,14.6667,24,14.25,12.6667,12.1667,12.75,12.5,11.9167,11.25,11,9.91667,9.91667,19.6667,])
array_1_name = "Air pollution in Milwaukee"
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?

Big thanks for reviewing!


Correlation ID: 4097 · Black Variable ID: 20899 · Red Variable ID: 1419
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0