about · email me · subscribe
Spurious correlation #5,392 · 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 South Bend, Indiana 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
Download png
, svg

AI explanation

As the smog thickened over South Bend, residents sought indoor activities to avoid the contaminated air, leading to a surge in online interest in the tragic and iconic shipwreck. Perhaps they were looking for a breath of fresh 'sea' air!

Model: dalle-3
Prompt: A photo-realistic image depicting South Bend, Indiana engulfed in thick smog, with silhouettes of people staying indoors in the background. Through the smog, the glow of computer screens displaying Google searches for "Titanic" is visible, with faint reflections of the iconic shipwreck appearing in the screens. 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 South Bend, Indiana 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: Realistic A photo-realistic image Oragami Cute 2D animation Low poly
ChatGPT: A photo-realistic image

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 South Bend, Indiana and Google searches for 'Titanic', in the following situation: As the smog thickened over South Bend, residents sought indoor activities to avoid the contaminated air, leading to a surge in online interest in the tragic and iconic shipwreck. Perhaps they were looking for a breath of fresh 'sea' air!. Keep the description simple.
ChatGPT: In South Bend, Indiana, thick smog hangs in the air, as people stay indoors to avoid the pollution. Meanwhile, computer screens flicker with a surge of Google searches for "Titanic", as residents seek a virtual escape to the iconic shipwreck and its tragic tale.

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 photo-realistic image ] and depicting this scene: In South Bend, Indiana, thick smog hangs in the air, as people stay indoors to avoid the pollution. Meanwhile, computer screens flicker with a surge of Google searches for "Titanic", as residents seek a virtual escape to the iconic shipwreck and its tragic tale. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: A photo-realistic image depicting South Bend, Indiana engulfed in thick smog, with silhouettes of people staying indoors in the background. Through the smog, the glow of computer screens displaying Google searches for "Titanic" is visible, with faint reflections of the iconic shipwreck appearing in the screens.

*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 South Bend, Indiana caused Titanic (Google searches for 'Titanic') to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana

The Journal of Eclectic Environmental Studies

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 South Bend, Indiana 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 0.8447954 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.


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 South Bend, Indiana 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
**[[INTRODUCTION]]**

The intertwining complexities of air pollution and public interest never fail to astound us. As we delved into the labyrinthine world of environmental impact, we stumbled upon a peculiar correlation between the concentration of particulate matter in the air and the Google searches for 'Titanic' in South Bend, Indiana. It was as if the universe decided to play matchmaker, pairing the somber notes of environmental degradation with the haunting echoes of a tragic maritime disaster.

As researchers, we are often accustomed to the logical and rational connections that bind our subjects of study. However, the universe occasionally deems it fit to throw us a curveball, reminding us that even the most improbable pairings can harbor insightful revelations.

The aim of this study was initially rooted in the investigation of the tangible consequences of air pollution on public health. Little did we know that our pursuit of empirical evidence would lead us to uncovering a whimsical dance between air quality and the collective fascination with the ill-fated vessel that met its demise in the frigid waters of the North Atlantic.

In the grand symphony of scientific exploration, it is the unexpected movements and enigmatic harmonies that often captivate our attention. The resonance between the concentration of microscopic particulates and the resounding echoes of an ill-fated vessel provides us with a unique opportunity to delve into the uncharted waters of interdisciplinary inquiry.

Our investigation, though initially perplexing, has unraveled a peculiar association that transcends the traditional bounds of our respective disciplines, infusing our research with a level of intrigue that is as refreshing as a gust of clean, unpolluted air. This study serves as a testament to the inexhaustible potential for serendipity in the multifaceted tapestry of scientific exploration.

As we navigate through the currents of this improbable correlation, we invite our fellow researchers to embark on this curious journey with us. For in the midst of the peculiar, there may lie the seeds of a profound understanding that can only be nurtured by embracing the whimsical and the unexpected.

Stay tuned for the data and analysis that will either blow your mind or leave you feeling like you're walking on eggshells - depending on how much you enjoy puns and statistics!


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 South Bend, Indiana 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intertwining complexities of air pollution and public interest never fail to astound us. As we delved into the labyrinthine world of environmental impact, we stumbled upon a peculiar correlation between the concentration of particulate matter in the air and the Google searches for 'Titanic' in South Bend, Indiana. It was as if the universe decided to play matchmaker, pairing the somber notes of environmental degradation with the haunting echoes of a tragic maritime disaster.
As researchers, we are often accustomed to the logical and rational connections that bind our subjects of study. However, the universe occasionally deems it fit to throw us a curveball, reminding us that even the most improbable pairings can harbor insightful revelations.
The aim of this study was initially rooted in the investigation of the tangible consequences of air pollution on public health. Little did we know that our pursuit of empirical evidence would lead us to uncovering a whimsical dance between air quality and the collective fascination with the ill-fated vessel that met its demise in the frigid waters of the North Atlantic.
In the grand symphony of scientific exploration, it is the unexpected movements and enigmatic harmonies that often captivate our attention. The resonance between the concentration of microscopic particulates and the resounding echoes of an ill-fated vessel provides us with a unique opportunity to delve into the uncharted waters of interdisciplinary inquiry.
Our investigation, though initially perplexing, has unraveled a peculiar association that transcends the traditional bounds of our respective disciplines, infusing our research with a level of intrigue that is as refreshing as a gust of clean, unpolluted air. This study serves as a testament to the inexhaustible potential for serendipity in the multifaceted tapestry of scientific exploration.
As we navigate through the currents of this improbable correlation, we invite our fellow researchers to embark on this curious journey with us. For in the midst of the peculiar, there may lie the seeds of a profound understanding that can only be nurtured by embracing the whimsical and the unexpected.
Stay tuned for the data and analysis that will either blow your mind or leave you feeling like you're walking on eggshells - depending on how much you enjoy puns and statistics!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we embark on our quest to unravel the intriguing connection between air pollution in South Bend, Indiana and Google searches for 'Titanic', we first delve into the existing body of literature on air pollution and its far-reaching impacts. Smith et al. (2015) conducted a comprehensive study on the effects of air pollution on public health, shedding light on the detrimental consequences of inhaling particulate matter and toxic pollutants. Their findings serve as a sobering reminder of the urgent need to address air quality issues, lest we continue to suffer the deleterious effects of environmental degradation.

Moving on to the digital realm, Doe and Jones (2018) explored the fascinating world of Google search trends and the underlying motivations that drive public interest in specific events. Their work provides valuable insights into the intricacies of online behavior, offering a glimpse into the mysterious web of human curiosity and intrigue.

In "Air Pollution and Its Impacts" by Environmental Research Group, the authors delve into the intricate web of factors contributing to air pollution, highlighting the multifaceted nature of this environmental menace. Their comprehensive analysis serves as a foundational text in understanding the complex interplay between pollutants and their effects on local communities.

Now, shifting from the serious to the quirky, we turn our attention to non-fiction books that touch on the themes of environmental impact and maritime disasters. "The Big Necessity: The Unmentionable World of Human Waste and Why It Matters" by Rose George provides a fascinating exploration of how human waste and sanitation intersect with environmental concerns, reminding us that even the most taboo topics can hold significant implications for our surroundings.

On a more literary note, "Life of Pi" by Yann Martel invites readers to embark on a captivating journey at sea, prompting contemplation on the fragility of human existence in the face of nature's formidable forces. While not directly related to our research topic, the themes of survival, resilience, and the enigmatic allure of the ocean bear faint echoes of the maritime tragedy that continues to captivate hearts and minds.

And now, for a more cinematic perspective, we draw inspiration from the silver screen with films that vaguely touch on the themes at hand. "The Fog" and "Titanic" - two seemingly unrelated movies, yet both offering glimpses into the eerie beauty and perilous nature of waterways. While one is a classic horror film and the other a sweeping romantic epic, the juxtaposition of their titles alone beckons us to explore the enigmatic allure of environmental phenomena and their impact on human culture.

So, dear reader, as we venture into the realm of whimsical connections and improbable correlations, let us not forget to embrace the unexpected with open arms, for it is often amidst the unconventional that we unearth the most extraordinary insights. As we navigate through the murky waters of literature and popular culture, we do so with a sense of curiosity and a dash of humor, for in the world of academia, a little levity can go a long way in enlivening the scholarly pursuit of knowledge.


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 South Bend, Indiana 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 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

[[INTRODUCTION]]
The intertwining complexities of air pollution and public interest never fail to astound us. As we delved into the labyrinthine world of environmental impact, we stumbled upon a peculiar correlation between the concentration of particulate matter in the air and the Google searches for 'Titanic' in South Bend, Indiana. It was as if the universe decided to play matchmaker, pairing the somber notes of environmental degradation with the haunting echoes of a tragic maritime disaster.
As researchers, we are often accustomed to the logical and rational connections that bind our subjects of study. However, the universe occasionally deems it fit to throw us a curveball, reminding us that even the most improbable pairings can harbor insightful revelations.
The aim of this study was initially rooted in the investigation of the tangible consequences of air pollution on public health. Little did we know that our pursuit of empirical evidence would lead us to uncovering a whimsical dance between air quality and the collective fascination with the ill-fated vessel that met its demise in the frigid waters of the North Atlantic.
In the grand symphony of scientific exploration, it is the unexpected movements and enigmatic harmonies that often captivate our attention. The resonance between the concentration of microscopic particulates and the resounding echoes of an ill-fated vessel provides us with a unique opportunity to delve into the uncharted waters of interdisciplinary inquiry.
Our investigation, though initially perplexing, has unraveled a peculiar association that transcends the traditional bounds of our respective disciplines, infusing our research with a level of intrigue that is as refreshing as a gust of clean, unpolluted air. This study serves as a testament to the inexhaustible potential for serendipity in the multifaceted tapestry of scientific exploration.
As we navigate through the currents of this improbable correlation, we invite our fellow researchers to embark on this curious journey with us. For in the midst of the peculiar, there may lie the seeds of a profound understanding that can only be nurtured by embracing the whimsical and the unexpected.
Stay tuned for the data and analysis that will either blow your mind or leave you feeling like you're walking on eggshells - depending on how much you enjoy puns and statistics!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic connection between air pollution and Google searches for 'Titanic' in South Bend, Indiana, we embarked on a methodological odyssey that combined rigorous statistical analysis with a touch of whimsy. The data collection process was akin to casting a net into the vast ocean of information, where the catch of the day included air quality measurements and digital search trends.

Firstly, we obtained air quality data from the Environmental Protection Agency, utilizing measurements of particulate matter (PM10 and PM2.5) concentrations in South Bend, Indiana from 2008 to 2023. These microscopic particles, suspended in the air like flecks of cosmic dust, provided the quantitative foundation for our exploration of atmospheric conditions.

Simultaneously, we tapped into the digital pulse of the internet by harnessing the power of Google Trends. Through this digital oracle, we accessed search volume data for the term 'Titanic' within the geographic confines of South Bend, Indiana. The ebbs and flows of public intrigue in this maritime tragedy were captured in the digital footprints left behind by curious netizens, enabling us to measure the temporal variability of this cultural phenomenon.

Upon collecting these disparate strands of data, we engaged in a delicate ballet of statistical analysis. Like seasoned conductors orchestrating a symphony, we meticulously curated our dataset and conducted a Pearson correlation analysis to unveil the relationship between air pollution and 'Titanic' searches. The correlation coefficient and its associated p-value shimmered like constellations in the statistical firmament, guiding our interpretation of the interconnectedness between these distinct yet intriguing variables.

Moreover, we performed a time series analysis to discern temporal patterns and trends in both air pollution levels and search volumes for 'Titanic', allowing us to peer into the dynamic interplay of atmospheric conditions and public curiosity. By charting these temporal trajectories, we sought to illuminate the underlying rhythms that govern the synchrony of environmental fluctuations and cultural interests.

With a quasi-experimental design underpinning our methodological framework, we controlled for potential confounding variables such as weather patterns and local events to ensure the robustness of our findings. While the whims of fate may color our exploratory journey, we remained steadfast in our commitment to methodological rigor and statistical integrity.

In sum, our methodological approach resembled a delightful blend of Sherlock Holmes' deductive prowess and Alice's whimsical adventures in Wonderland. This fusion of analytical precision and playful curiosity allowed us to untangle the curious rapport between air pollution and public fascination with a fateful vessel lost in the mists of time. As we march forward to unveil the intriguing findings that await, we invite our fellow researchers to join us in this fusion of empirical rigor and serendipitous discovery.


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 South Bend, Indiana 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 2008 to 2023, you found a correlation 0.8447954, r-squared of 0.7136793, 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intertwining complexities of air pollution and public interest never fail to astound us. As we delved into the labyrinthine world of environmental impact, we stumbled upon a peculiar correlation between the concentration of particulate matter in the air and the Google searches for 'Titanic' in South Bend, Indiana. It was as if the universe decided to play matchmaker, pairing the somber notes of environmental degradation with the haunting echoes of a tragic maritime disaster.
As researchers, we are often accustomed to the logical and rational connections that bind our subjects of study. However, the universe occasionally deems it fit to throw us a curveball, reminding us that even the most improbable pairings can harbor insightful revelations.
The aim of this study was initially rooted in the investigation of the tangible consequences of air pollution on public health. Little did we know that our pursuit of empirical evidence would lead us to uncovering a whimsical dance between air quality and the collective fascination with the ill-fated vessel that met its demise in the frigid waters of the North Atlantic.
In the grand symphony of scientific exploration, it is the unexpected movements and enigmatic harmonies that often captivate our attention. The resonance between the concentration of microscopic particulates and the resounding echoes of an ill-fated vessel provides us with a unique opportunity to delve into the uncharted waters of interdisciplinary inquiry.
Our investigation, though initially perplexing, has unraveled a peculiar association that transcends the traditional bounds of our respective disciplines, infusing our research with a level of intrigue that is as refreshing as a gust of clean, unpolluted air. This study serves as a testament to the inexhaustible potential for serendipity in the multifaceted tapestry of scientific exploration.
As we navigate through the currents of this improbable correlation, we invite our fellow researchers to embark on this curious journey with us. For in the midst of the peculiar, there may lie the seeds of a profound understanding that can only be nurtured by embracing the whimsical and the unexpected.
Stay tuned for the data and analysis that will either blow your mind or leave you feeling like you're walking on eggshells - depending on how much you enjoy puns and statistics!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis unveiled a surprising correlation between air pollution levels and Google searches for 'Titanic' in South Bend, Indiana during the period from 2008 to 2023. The correlation coefficient of 0.8447954 indicated a robust relationship between these seemingly unrelated variables, leaving us in awe of the mysterious ways in which the universe weaves its narrative.

Furthermore, the r-squared value of 0.7136793 suggested that approximately 71.4% of the variation in Google searches for 'Titanic' could be explained by fluctuations in air pollution levels. It's as if the air quality was whispering tragic tales of a sunken ship to the citizens of South Bend, compelling them to seek solace in the vast ocean of information available at their fingertips.

With a p-value of less than 0.01, our findings reinforced the statistical significance of this unexpected association, urging us to dive deeper into the enigmatic depths of this peculiar correlation. We were left feeling as though we had stumbled upon a hidden treasure chest of interconnectedness, where the winds of curiosity showed no sign of abating.

Figure 1 presents a scatterplot depicting the striking relationship between air pollution levels and Google searches for 'Titanic'. The data points form a clear pattern, resembling the constellations in the night sky, albeit with a touch of melancholic undertones. Much like a steam-powered locomotive hurtling through the fog, this correlation chugged along with unwavering determination, leaving us both intrigued and amused by the whimsy of statistical analysis.

In essence, our findings shed light on a curious intersection between environmental conditions and public interest, reminding us that even the most unexpected connections can lead to profound insights. As we reconcile with the inexplicable allure of this correlation, we invite our peers to join us in exploring the uncharted waters of interdisciplinary research, where the unexpected may hold the keys to knowledge and the occasional chuckle.


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 South Bend, Indiana 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

[[LITERATURE REVIEW]]
As we embark on our quest to unravel the intriguing connection between air pollution in South Bend, Indiana and Google searches for 'Titanic', we first delve into the existing body of literature on air pollution and its far-reaching impacts. Smith et al. (2015) conducted a comprehensive study on the effects of air pollution on public health, shedding light on the detrimental consequences of inhaling particulate matter and toxic pollutants. Their findings serve as a sobering reminder of the urgent need to address air quality issues, lest we continue to suffer the deleterious effects of environmental degradation.
Moving on to the digital realm, Doe and Jones (2018) explored the fascinating world of Google search trends and the underlying motivations that drive public interest in specific events. Their work provides valuable insights into the intricacies of online behavior, offering a glimpse into the mysterious web of human curiosity and intrigue.
In "Air Pollution and Its Impacts" by Environmental Research Group, the authors delve into the intricate web of factors contributing to air pollution, highlighting the multifaceted nature of this environmental menace. Their comprehensive analysis serves as a foundational text in understanding the complex interplay between pollutants and their effects on local communities.
Now, shifting from the serious to the quirky, we turn our attention to non-fiction books that touch on the themes of environmental impact and maritime disasters. "The Big Necessity: The Unmentionable World of Human Waste and Why It Matters" by Rose George provides a fascinating exploration of how human waste and sanitation intersect with environmental concerns, reminding us that even the most taboo topics can hold significant implications for our surroundings.
On a more literary note, "Life of Pi" by Yann Martel invites readers to embark on a captivating journey at sea, prompting contemplation on the fragility of human existence in the face of nature's formidable forces. While not directly related to our research topic, the themes of survival, resilience, and the enigmatic allure of the ocean bear faint echoes of the maritime tragedy that continues to captivate hearts and minds.
And now, for a more cinematic perspective, we draw inspiration from the silver screen with films that vaguely touch on the themes at hand. "The Fog" and "Titanic" - two seemingly unrelated movies, yet both offering glimpses into the eerie beauty and perilous nature of waterways. While one is a classic horror film and the other a sweeping romantic epic, the juxtaposition of their titles alone beckons us to explore the enigmatic allure of environmental phenomena and their impact on human culture.
So, dear reader, as we venture into the realm of whimsical connections and improbable correlations, let us not forget to embrace the unexpected with open arms, for it is often amidst the unconventional that we unearth the most extraordinary insights. As we navigate through the murky waters of literature and popular culture, we do so with a sense of curiosity and a dash of humor, for in the world of academia, a little levity can go a long way in enlivening the scholarly pursuit of knowledge.

[[RESULTS]]
Our analysis unveiled a surprising correlation between air pollution levels and Google searches for 'Titanic' in South Bend, Indiana during the period from 2008 to 2023. The correlation coefficient of 0.8447954 indicated a robust relationship between these seemingly unrelated variables, leaving us in awe of the mysterious ways in which the universe weaves its narrative.
Furthermore, the r-squared value of 0.7136793 suggested that approximately 71.4% of the variation in Google searches for 'Titanic' could be explained by fluctuations in air pollution levels. It's as if the air quality was whispering tragic tales of a sunken ship to the citizens of South Bend, compelling them to seek solace in the vast ocean of information available at their fingertips.
With a p-value of less than 0.01, our findings reinforced the statistical significance of this unexpected association, urging us to dive deeper into the enigmatic depths of this peculiar correlation. We were left feeling as though we had stumbled upon a hidden treasure chest of interconnectedness, where the winds of curiosity showed no sign of abating.
Figure 1 presents a scatterplot depicting the striking relationship between air pollution levels and Google searches for 'Titanic'. The data points form a clear pattern, resembling the constellations in the night sky, albeit with a touch of melancholic undertones. Much like a steam-powered locomotive hurtling through the fog, this correlation chugged along with unwavering determination, leaving us both intrigued and amused by the whimsy of statistical analysis.
In essence, our findings shed light on a curious intersection between environmental conditions and public interest, reminding us that even the most unexpected connections can lead to profound insights. As we reconcile with the inexplicable allure of this correlation, we invite our peers to join us in exploring the uncharted waters of interdisciplinary research, where the unexpected may hold the keys to knowledge and the occasional chuckle.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our study has unearthed a remarkable association between air pollution levels and Google searches for 'Titanic' in South Bend, Indiana, revealing a correlation that lingers in the air like a haunting melody. The robust correlation coefficient of 0.8447954 left us pondering the whimsical ways in which environmental conditions and digital behavior intersect, prompting us to embrace the unexpected with open arms and raise an eyebrow at the quirkier aspects of our scholarly pursuits.

Our findings stand in solidarity with the existing literature on air pollution and its multifaceted impacts, particularly the work of Smith et al. (2015) who highlighted the deleterious effects of inhaling particulate matter. In a curious twist, it seems that while South Bend residents are contending with airborne particles, their digital musings drift off to the depths of the ocean, steered by the allure of the tragic maritime fate of the Titanic. The r-squared value of 0.7136793 further emphasized the substantial influence of air pollution on Google searches for 'Titanic', as if each spike in particulate matter levels whispered tales of a sunken ship to the curious denizens of the city.

Paying homage to the non-fiction literature that touched on themes of environmental impact and maritime disasters, our results offer a tongue-in-cheek nod to the parallels between human waste and the ephemerality of digital curiosity. Much like the inescapable aroma of a famously pungent situation, the link between air pollution and 'Titanic' searches lingers in the ether, inviting us to contemplate the unexpected intersections that perpetually float beneath the surface of our scholarly inquiries.

Our statistical analysis, with a p-value of less than 0.01, fortified the remarkable significance of this correlation, reinforcing the notion that even the most unexpected connections can lead to profound insights. The scatterplot, resembling constellations in the night sky, wields its own unique charm, drawing attention to the enigmatic dance between environmental conditions and the digital quest for knowledge. As we navigate the eccentric currents of this discovery, we encourage our esteemed colleagues to ride the waves of curiosity and whimsy, for in the world of academia, a little levity can go a long way in enlivening the scholarly pursuit of knowledge.

So, dear reader, as we float atop this sea of correlation and causation, may we approach our academic endeavors with a sense of wonder and a mischievous glint in our eyes, for it is amidst the unlikely that we often glimpse the most extraordinary insights.


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 South Bend, Indiana 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]]
"The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana"

[[ABSTRACT]]
In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

[[INTRDUCTION]]
The intertwining complexities of air pollution and public interest never fail to astound us. As we delved into the labyrinthine world of environmental impact, we stumbled upon a peculiar correlation between the concentration of particulate matter in the air and the Google searches for 'Titanic' in South Bend, Indiana. It was as if the universe decided to play matchmaker, pairing the somber notes of environmental degradation with the haunting echoes of a tragic maritime disaster.
As researchers, we are often accustomed to the logical and rational connections that bind our subjects of study. However, the universe occasionally deems it fit to throw us a curveball, reminding us that even the most improbable pairings can harbor insightful revelations.
The aim of this study was initially rooted in the investigation of the tangible consequences of air pollution on public health. Little did we know that our pursuit of empirical evidence would lead us to uncovering a whimsical dance between air quality and the collective fascination with the ill-fated vessel that met its demise in the frigid waters of the North Atlantic.
In the grand symphony of scientific exploration, it is the unexpected movements and enigmatic harmonies that often captivate our attention. The resonance between the concentration of microscopic particulates and the resounding echoes of an ill-fated vessel provides us with a unique opportunity to delve into the uncharted waters of interdisciplinary inquiry.
Our investigation, though initially perplexing, has unraveled a peculiar association that transcends the traditional bounds of our respective disciplines, infusing our research with a level of intrigue that is as refreshing as a gust of clean, unpolluted air. This study serves as a testament to the inexhaustible potential for serendipity in the multifaceted tapestry of scientific exploration.
As we navigate through the currents of this improbable correlation, we invite our fellow researchers to embark on this curious journey with us. For in the midst of the peculiar, there may lie the seeds of a profound understanding that can only be nurtured by embracing the whimsical and the unexpected.
Stay tuned for the data and analysis that will either blow your mind or leave you feeling like you're walking on eggshells - depending on how much you enjoy puns and statistics!

[[RESULTS]]
Our analysis unveiled a surprising correlation between air pollution levels and Google searches for 'Titanic' in South Bend, Indiana during the period from 2008 to 2023. The correlation coefficient of 0.8447954 indicated a robust relationship between these seemingly unrelated variables, leaving us in awe of the mysterious ways in which the universe weaves its narrative.
Furthermore, the r-squared value of 0.7136793 suggested that approximately 71.4% of the variation in Google searches for 'Titanic' could be explained by fluctuations in air pollution levels. It's as if the air quality was whispering tragic tales of a sunken ship to the citizens of South Bend, compelling them to seek solace in the vast ocean of information available at their fingertips.
With a p-value of less than 0.01, our findings reinforced the statistical significance of this unexpected association, urging us to dive deeper into the enigmatic depths of this peculiar correlation. We were left feeling as though we had stumbled upon a hidden treasure chest of interconnectedness, where the winds of curiosity showed no sign of abating.
Figure 1 presents a scatterplot depicting the striking relationship between air pollution levels and Google searches for 'Titanic'. The data points form a clear pattern, resembling the constellations in the night sky, albeit with a touch of melancholic undertones. Much like a steam-powered locomotive hurtling through the fog, this correlation chugged along with unwavering determination, leaving us both intrigued and amused by the whimsy of statistical analysis.
In essence, our findings shed light on a curious intersection between environmental conditions and public interest, reminding us that even the most unexpected connections can lead to profound insights. As we reconcile with the inexplicable allure of this correlation, we invite our peers to join us in exploring the uncharted waters of interdisciplinary research, where the unexpected may hold the keys to knowledge and the occasional chuckle.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our study has unearthed a fascinating correlation between air pollution levels and Google searches for 'Titanic' in South Bend, Indiana. The robust relationship, as indicated by the correlation coefficient and r-squared value, stands as a testament to the whimsical nature of scientific inquiry. It's as if the air pollution in South Bend whispered tragic tales of the Titanic to the local populace, leading them to embark on an unexpected digital voyage into the depths of maritime history.

The statistical significance of this association, coupled with the captivating scatterplot, paints a picture of interconnectedness that transcends conventional boundaries. It's like finding a rare Pokémon in the tall grass of empirical data – unexpected, exhilarating, and deserving of further exploration.

While some may view our findings with a raised eyebrow or a quizzical shrug, we believe that they offer a breath of fresh air in the realm of interdisciplinary research. Our hope is that this study serves as a lighthouse guiding future researchers through the murky waters of unforeseen connections, where serendipity and statistical significance converge to illuminate the path forward.

We call to our fellow researchers to embrace the serendipitous and the enigmatic, for in the dance between air pollution and Titanic searches, we find not just correlation, but a reason to marvel at the unpredictable dance of data and human curiosity. And just like Rose and Jack from the Titanic, let our study be a reminder that even the most unexpected pairings can lead to profound insights – and maybe the occasional tear or two.

Finally, in the spirit of Leonardo DiCaprio's character in Titanic, we assert that no further research is needed in this area. For our findings stand as a delightful oddity, a testament to the delightful unpredictability of the world we seek to unravel.


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 The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Environmental Studies


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 The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Environmental Quirkology and Research (CEQR)


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 The Air Pollution Paradox: A Titanic Connection in South Bend, Indiana with an abstract of In the midst of investigating the impact of air pollution on public health in South Bend, Indiana, our research team stumbled upon an unexpected connection between the concentration of particulate matter in the air and Google searches for 'Titanic'. While we initially questioned the correlation, our study revealed a surprisingly strong link between these seemingly disparate phenomena. Leveraging data from the Environmental Protection Agency to measure air pollution levels and Google Trends to track search volume, we found a correlation coefficient of 0.8447954 and p < 0.01 during the period from 2008 to 2023. Our findings suggest a curious association between air quality and public interest in the tragic maritime disaster. The implications of this peculiar correlation extend beyond the realms of environmental science and digital behavior analysis, bringing a breath of fresh air to the world of interdisciplinary research. This study illuminates the need for further exploration into the whimsical connections that lie beneath the surface of seemingly unrelated phenomena.

ChatGPT:

Air pollution, public health, South Bend, Indiana, particulate matter, correlation, Google searches, Titanic, Environmental Protection Agency, Google Trends, correlation coefficient, interdisciplinary research, digital behavior analysis

*There is a bunch of Python happening behind the scenes to turn this prompt sequence into a PDF.



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

Air pollution in South Bend, Indiana
Detailed data title: Percentage of days 'unhealthy' or worse air quality in South Bend-Mishawaka, IN-MI
Source: Environmental Protection Agency
See what else correlates with Air pollution in South Bend, Indiana

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 = 0.8447954 (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 = 0.7136793 (Coefficient of determination)
This means 71.4% 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 South Bend, Indiana) over the 16 years from 2008 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.8E-5. 0.0000381940566039730150000000
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 0.84 in 0.0038% of random cases. Said differently, if you correlated 26,182 random variables You don't actually need 26 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 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.

[ 0.6, 0.94 ] 95% correlation confidence interval (using the Fisher z-transformation)
The confidence interval is an estimate the range of the value of the correlation coefficient, using the correlation itself as an input. The values are meant to be the low and high end of the correlation coefficient with 95% confidence.

This one is a bit more complciated than the other calculations, but I include it because many people have been pushing for confidence intervals instead of p-value calculations (for example: NEJM. However, if you are dredging data, you can reliably find yourself in the 5%. That's my goal!


All values for the years included above: If I were being very sneaky, I could trim years from the beginning or end of the datasets to increase the correlation on some pairs of variables. I don't do that because there are already plenty of correlations in my database without monkeying with the years.

Still, sometimes one of the variables has more years of data available than the other. This page only shows the overlapping years. To see all the years, click on "See what else correlates with..." link above.
2008200920102011201220132014201520162017201820192020202120222023
Air pollution in South Bend, Indiana (Bad air quality days)0000.2754820.8196720.2770080000000.273224001.10294
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 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 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([0,0,0,0.275482,0.819672,0.277008,0,0,0,0,0,0,0.273224,0,0,1.10294,])
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 South Bend, Indiana"
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?

Thanks for shining a light on this correlation!


Correlation ID: 5392 · Black Variable ID: 21279 · Red Variable ID: 1419
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0