about · email me · subscribe
Spurious correlation #5,643 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Air quality in Miami and the second variable is Google searches for 'velociraptor'.  The chart goes from 2004 to 2023, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the air quality in Miami improved, it created the perfect conditions for the growth of lush, prehistoric ferns. Little did anyone know, these ferns happened to be a favorite snack of a roaming pack of hidden velociraptors. So, as Miami's air became cleaner, it unwittingly turned into a dino-utopia, luring the velociraptors out of extinction and into the hearts of internet users everywhere. After all, who wouldn't want to witness a real-life Jurassic Park situation unfolding in the midst of sunny Florida? So, it seems that the key to reviving these ancient predators was simply to let the air be as fresh as a daisy and as dino-mite as can be!

Model: dalle-3
Prompt: Generate a pop art style image of Miami's skyline with vibrant, contrasting colors. Amongst the cityscape, prehistoric ferns flourish, towering over the modern buildings. A pack of velociraptors roam the lush greenery, with their vibrant hues standing out against the backdrop of the city. In the foreground, people are seen on their phones, representing the surge in Google searches for "velociraptor." The atmosphere exudes a sense of wonder and disbelief at the unexpected revival of these ancient creatures in the heart of Miami. 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 quality in Miami and Google searches for 'velociraptor'. 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 A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Cubism Cute cartoon Pop art
ChatGPT: Pop art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Air quality in Miami and Google searches for 'velociraptor', in the following situation: As the air quality in Miami improved, it created the perfect conditions for the growth of lush, prehistoric ferns. Little did anyone know, these ferns happened to be a favorite snack of a roaming pack of hidden velociraptors. So, as Miami's air became cleaner, it unwittingly turned into a dino-utopia, luring the velociraptors out of extinction and into the hearts of internet users everywhere. After all, who wouldn't want to witness a real-life Jurassic Park situation unfolding in the midst of sunny Florida? So, it seems that the key to reviving these ancient predators was simply to let the air be as fresh as a daisy and as dino-mite as can be!. Keep the description simple.
ChatGPT: In Miami, with improved air quality, lush prehistoric ferns thrive, attracting a pack of velociraptors. Meanwhile, across the globe, Google searches for "velociraptor" skyrocket as the creatures make a surprising comeback in the dino-utopia of sunny Florida.

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: [ Pop art ] and depicting this scene: In Miami, with improved air quality, lush prehistoric ferns thrive, attracting a pack of velociraptors. Meanwhile, across the globe, Google searches for "velociraptor" skyrocket as the creatures make a surprising comeback in the dino-utopia of sunny Florida. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a pop art style image of Miami's skyline with vibrant, contrasting colors. Amongst the cityscape, prehistoric ferns flourish, towering over the modern buildings. A pack of velociraptors roam the lush greenery, with their vibrant hues standing out against the backdrop of the city. In the foreground, people are seen on their phones, representing the surge in Google searches for "velociraptor." The atmosphere exudes a sense of wonder and disbelief at the unexpected revival of these ancient creatures in the heart of Miami.

*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 quality in Miami caused velociraptor (Google searches for 'velociraptor') to increase.

AI academic paper

(Because p < 0.01)
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

The Journal of Eclectic Ecological Enigmas

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 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 quality in Miami and Google searches for 'velociraptor'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.8324858 and p < 0.01 for 2004 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.


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 quality in Miami and Google searches for 'velociraptor'. 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The bustling metropolis of Miami conjures images of sunny beaches, vibrant nightlife, and a certain fascination with all things extravagant and outlandish. Yet, amidst the waves of swaying palms and colorful Art Deco architecture, a mysterious connection has emerged, one that has piqued the curiosity of both the astute researcher and the casual observer. It is within this enigmatic arena that we embark on a quest to unravel the perplexing correlation between air quality in Miami and the peculiar penchant for searching 'velociraptor' on the ubiquitous search engine, Google.

While the notion of linking air quality with online search behavior may initially seem about as plausible as a tropical snowstorm, our foray into this uncharted territory has yielded some unexpected, and frankly, quite astonishing results. This study represents an attempt to bring a measure of empirical rigor to what may, at first glance, appear to be an unlikely marriage of scientific inquiry and popular curiosity. Nevertheless, as we shall see, the human capacity for erratically directed interest knows no bounds, and it may very well be influenced by the invisible tendrils of the gaseous composition that envelops our fair city.

Of course, this investigation is not without its fair share of skepticism and raised eyebrows. The very idea of discerning a connection between the air we breathe and the ancient, fleet-footed predator that once roamed the earth seems, to many, as absurd as claiming correlation between the number of cats in Paris and the rise and fall of the stock market. However, as the saying goes, "correlation does not imply causation," and it is precisely this refrain that underpins our approach to this most fantastical of scientific journeys.

As we present our findings, it is with the hope that the scientific community will approach this rather whimsical association with an open mind and a keen appreciation for the unexpected. Just as the wind can carry with it the smell of salt from the nearby ocean, it may also carry with it the echo of ancient roars and the stories of a time long past. So, with an intrepid spirit and an ample supply of data analysis tools, let us venture forth into the mysterious miasma of Miami and the melodious mania of velociraptor searches, for what lies beyond may prove to be far more than mere statistical fancy.


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 quality in Miami and Google searches for 'velociraptor'. 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 you might move on to cartoons and children's shows that you watched for research.

Here is the title and abstract of the paper:
[[TITLE]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The bustling metropolis of Miami conjures images of sunny beaches, vibrant nightlife, and a certain fascination with all things extravagant and outlandish. Yet, amidst the waves of swaying palms and colorful Art Deco architecture, a mysterious connection has emerged, one that has piqued the curiosity of both the astute researcher and the casual observer. It is within this enigmatic arena that we embark on a quest to unravel the perplexing correlation between air quality in Miami and the peculiar penchant for searching 'velociraptor' on the ubiquitous search engine, Google.
While the notion of linking air quality with online search behavior may initially seem about as plausible as a tropical snowstorm, our foray into this uncharted territory has yielded some unexpected, and frankly, quite astonishing results. This study represents an attempt to bring a measure of empirical rigor to what may, at first glance, appear to be an unlikely marriage of scientific inquiry and popular curiosity. Nevertheless, as we shall see, the human capacity for erratically directed interest knows no bounds, and it may very well be influenced by the invisible tendrils of the gaseous composition that envelops our fair city.
Of course, this investigation is not without its fair share of skepticism and raised eyebrows. The very idea of discerning a connection between the air we breathe and the ancient, fleet-footed predator that once roamed the earth seems, to many, as absurd as claiming correlation between the number of cats in Paris and the rise and fall of the stock market. However, as the saying goes, "correlation does not imply causation," and it is precisely this refrain that underpins our approach to this most fantastical of scientific journeys.
As we present our findings, it is with the hope that the scientific community will approach this rather whimsical association with an open mind and a keen appreciation for the unexpected. Just as the wind can carry with it the smell of salt from the nearby ocean, it may also carry with it the echo of ancient roars and the stories of a time long past. So, with an intrepid spirit and an ample supply of data analysis tools, let us venture forth into the mysterious miasma of Miami and the melodious mania of velociraptor searches, for what lies beyond may prove to be far more than mere statistical fancy.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

As we delve into the astonishing realm of air quality and the peculiar predilection for velociraptors, it is critical to first explore the existing body of literature to provide context and insight into this improbable juxtaposition.

Smith et al. (2017) conducted a comprehensive study on air pollution in urban environments, highlighting the intricate interplay between emissions and atmospheric quality. Their findings elucidated the multifaceted nature of air pollutants and the potential impact on public health and wellbeing.

Building on this foundation, Doe (2019) investigated the evolving landscape of online search behavior and its correlation with environmental factors. The study presented compelling evidence of how external influences could shape internet queries, shedding light on the enigmatic realm of human curiosity and its susceptibility to outside forces.

Jones (2020) delved into the realm of prehistoric fascinations, examining the enduring allure of dinosaurs in popular culture and the enduring legacy of these ancient creatures. The study provided valuable insights into the persistent interest in velociraptors and their cultural significance, laying the groundwork for the subsequent exploration of their connection to contemporary environmental phenomena.

Transitioning from the empirical studies, it is prudent to consider the contributions of non-fiction literature that may inform our understanding of this seemingly improbable association. Works such as "The Sixth Extinction: An Unnatural History" by Elizabeth Kolbert and "The Song of the Dodo: Island Biogeography in an Age of Extinctions" by David Quammen offer profound insights into the world of environmental changes and the lingering echoes of ancient species.

Furthermore, the realm of fiction provides a fertile ground for exploring the fantastical allure of prehistoric creatures and the whimsical imaginings of their resurgence. Michael Crichton's "Jurassic Park" and its subsequent sequels have captivated audiences with their thrilling portrayal of resurrected dinosaurs, fostering a popular fascination with these ancient beasts that extends beyond the confines of scientific discourse.

Additionally, the influence of children's entertainment cannot be overlooked, with animated series such as "Dino Dana" and "Dinosaur Train" captivating young audiences with their endearing portrayals of prehistoric creatures. These innocent forays into the world of dinosaurs may serve as a testament to the enduring appeal of velociraptors across diverse age groups and cultural contexts.

With this eclectic array of literature serving as our backdrop, we embark on a journey to unravel the intriguing connection between Miami's atmospheric composition and the inquisitive queries for velociraptors, brimming with anticipation for the unexpected revelations that await us.


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 quality in Miami and Google searches for 'velociraptor'. 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 2004 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

[[INTRODUCTION]]
The bustling metropolis of Miami conjures images of sunny beaches, vibrant nightlife, and a certain fascination with all things extravagant and outlandish. Yet, amidst the waves of swaying palms and colorful Art Deco architecture, a mysterious connection has emerged, one that has piqued the curiosity of both the astute researcher and the casual observer. It is within this enigmatic arena that we embark on a quest to unravel the perplexing correlation between air quality in Miami and the peculiar penchant for searching 'velociraptor' on the ubiquitous search engine, Google.
While the notion of linking air quality with online search behavior may initially seem about as plausible as a tropical snowstorm, our foray into this uncharted territory has yielded some unexpected, and frankly, quite astonishing results. This study represents an attempt to bring a measure of empirical rigor to what may, at first glance, appear to be an unlikely marriage of scientific inquiry and popular curiosity. Nevertheless, as we shall see, the human capacity for erratically directed interest knows no bounds, and it may very well be influenced by the invisible tendrils of the gaseous composition that envelops our fair city.
Of course, this investigation is not without its fair share of skepticism and raised eyebrows. The very idea of discerning a connection between the air we breathe and the ancient, fleet-footed predator that once roamed the earth seems, to many, as absurd as claiming correlation between the number of cats in Paris and the rise and fall of the stock market. However, as the saying goes, "correlation does not imply causation," and it is precisely this refrain that underpins our approach to this most fantastical of scientific journeys.
As we present our findings, it is with the hope that the scientific community will approach this rather whimsical association with an open mind and a keen appreciation for the unexpected. Just as the wind can carry with it the smell of salt from the nearby ocean, it may also carry with it the echo of ancient roars and the stories of a time long past. So, with an intrepid spirit and an ample supply of data analysis tools, let us venture forth into the mysterious miasma of Miami and the melodious mania of velociraptor searches, for what lies beyond may prove to be far more than mere statistical fancy.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To embark on our whimsically wistful quest for the connection between Miami's atmospheric odyssey and the fervent search for the illustrious velociraptor, we methodically gathered data from the Environmental Protection Agency (EPA) and Google Trends. The EPA, with its vast repository of air quality metrics, provided a robust foundation for our atmospheric analyses. Meanwhile, Google Trends, an unparalleled fount of digital curiosity, supplied us with the frequency of searches for the enigmatic reptilian creature of yore.

The period under investigation spanned from 2004 to 2023, encompassing a tumultuous tapestry of environmental ebbs and flows and the ever-evolving fabric of online interests. Our data collection process entailed meticulous scrutiny of air quality indices, particularly focusing on parameters such as ozone levels, particulate matter, and carbon monoxide concentrations. We then harmonized this atmospheric symphony with the resonant crescendos of 'velociraptor' searches on Google, ensuring that our timeframe encapsulated the full spectrum of meteorological tumult and digital intrigue.

To render our analysis as comprehensive as a brachiosaurus's reach, we meticulously accounted for potential confounding variables such as weather patterns, seasonal fluctuations, and major socio-political events that might inadvertently influence both air quality and public search behavior. Our intention was not to trample heedlessly like a stampeding herd of triceratops over the subtleties of data interpretation, but rather to carve a path that navigates the convoluted underbrush of observational study with due diligence and methodological finesse.

In a nod to the spirit of scientific inquiry and the inherent unpredictability of human curiosity, we approached our statistical methodology with an appreciation for the nuanced dance of probability and hypothesis testing. Employing a robust array of regression analyses, we sought to elucidate the strength and direction of the relationship between Miami's atmospheric canvas and the virtual discovery of the elusive velociraptor.

Our quest for academic inquiry was joined by our relentless march through the halls of statistical significance, where we employed a two-tailed hypothesis test to assess the strength of association between air quality and 'velociraptor' searches. To further underscore the vigor of our findings, we integrated a comprehensive sensitivity analysis to test the robustness of our conclusions across various sub-samples and time periods, akin to scouring the fossil record for corroborative evidence in the annals of natural history.

Finally, mindful of the alluring siren song of spurious correlations, we conducted a meticulous examination of our results to discern the potential presence of confounding factors and to forestall the accidental embrace of statistical fossils that might beguile us with their deceptive allure.

In summary, our methodology represents a harmonious marriage of meteorological scrutiny and digital dalliance, as we sought to untangle the delightful conundrum of air quality and velociraptor searches with meticulous attention and a splash of statistical finesse.


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 quality in Miami and Google searches for 'velociraptor'. 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 2004 to 2023, you found a correlation 0.8324858, r-squared of 0.6930327, 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The bustling metropolis of Miami conjures images of sunny beaches, vibrant nightlife, and a certain fascination with all things extravagant and outlandish. Yet, amidst the waves of swaying palms and colorful Art Deco architecture, a mysterious connection has emerged, one that has piqued the curiosity of both the astute researcher and the casual observer. It is within this enigmatic arena that we embark on a quest to unravel the perplexing correlation between air quality in Miami and the peculiar penchant for searching 'velociraptor' on the ubiquitous search engine, Google.
While the notion of linking air quality with online search behavior may initially seem about as plausible as a tropical snowstorm, our foray into this uncharted territory has yielded some unexpected, and frankly, quite astonishing results. This study represents an attempt to bring a measure of empirical rigor to what may, at first glance, appear to be an unlikely marriage of scientific inquiry and popular curiosity. Nevertheless, as we shall see, the human capacity for erratically directed interest knows no bounds, and it may very well be influenced by the invisible tendrils of the gaseous composition that envelops our fair city.
Of course, this investigation is not without its fair share of skepticism and raised eyebrows. The very idea of discerning a connection between the air we breathe and the ancient, fleet-footed predator that once roamed the earth seems, to many, as absurd as claiming correlation between the number of cats in Paris and the rise and fall of the stock market. However, as the saying goes, "correlation does not imply causation," and it is precisely this refrain that underpins our approach to this most fantastical of scientific journeys.
As we present our findings, it is with the hope that the scientific community will approach this rather whimsical association with an open mind and a keen appreciation for the unexpected. Just as the wind can carry with it the smell of salt from the nearby ocean, it may also carry with it the echo of ancient roars and the stories of a time long past. So, with an intrepid spirit and an ample supply of data analysis tools, let us venture forth into the mysterious miasma of Miami and the melodious mania of velociraptor searches, for what lies beyond may prove to be far more than mere statistical fancy.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between Miami's air quality and Google searches for 'velociraptor' revealed a notably strong correlation, with a Pearson correlation coefficient of 0.8324858. This indicates a substantial positive linear association between the two variables. Additionally, the coefficient of determination (r-squared) of 0.6930327 suggests that approximately 69.3% of the variability in velociraptor searches can be explained by changes in air quality. The p-value of less than 0.01 provides strong evidence against the null hypothesis of no correlation. These results substantiate the presence of a significant relationship between the air quality in Miami and the public's interest in the swift prehistoric predator.

Further supporting the robustness of the observed association, Fig. 1 displays a scatterplot depicting the striking correlation between air quality and the frequency of Google searches for 'velociraptor'. The tightly clustered data points form a discernible upward trend, affirming the coherence between the variables and reinforcing the statistical findings.

The compelling correlation coefficient and associated statistics serve as a notable testament to the unexpected convergence of environmental factors and online search behavior. This discovery shines a whimsical light on the intricate interplay between atmospheric conditions and public fascination with ancient creatures, reminding researchers to remain open to the endless possibilities that emerge from the fusion of distinct realms of inquiry.


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 quality in Miami and Google searches for 'velociraptor'. 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

[[LITERATURE REVIEW]]
As we delve into the astonishing realm of air quality and the peculiar predilection for velociraptors, it is critical to first explore the existing body of literature to provide context and insight into this improbable juxtaposition.
Smith et al. (2017) conducted a comprehensive study on air pollution in urban environments, highlighting the intricate interplay between emissions and atmospheric quality. Their findings elucidated the multifaceted nature of air pollutants and the potential impact on public health and wellbeing.
Building on this foundation, Doe (2019) investigated the evolving landscape of online search behavior and its correlation with environmental factors. The study presented compelling evidence of how external influences could shape internet queries, shedding light on the enigmatic realm of human curiosity and its susceptibility to outside forces.
Jones (2020) delved into the realm of prehistoric fascinations, examining the enduring allure of dinosaurs in popular culture and the enduring legacy of these ancient creatures. The study provided valuable insights into the persistent interest in velociraptors and their cultural significance, laying the groundwork for the subsequent exploration of their connection to contemporary environmental phenomena.
Transitioning from the empirical studies, it is prudent to consider the contributions of non-fiction literature that may inform our understanding of this seemingly improbable association. Works such as "The Sixth Extinction: An Unnatural History" by Elizabeth Kolbert and "The Song of the Dodo: Island Biogeography in an Age of Extinctions" by David Quammen offer profound insights into the world of environmental changes and the lingering echoes of ancient species.
Furthermore, the realm of fiction provides a fertile ground for exploring the fantastical allure of prehistoric creatures and the whimsical imaginings of their resurgence. Michael Crichton's "Jurassic Park" and its subsequent sequels have captivated audiences with their thrilling portrayal of resurrected dinosaurs, fostering a popular fascination with these ancient beasts that extends beyond the confines of scientific discourse.
Additionally, the influence of children's entertainment cannot be overlooked, with animated series such as "Dino Dana" and "Dinosaur Train" captivating young audiences with their endearing portrayals of prehistoric creatures. These innocent forays into the world of dinosaurs may serve as a testament to the enduring appeal of velociraptors across diverse age groups and cultural contexts.
With this eclectic array of literature serving as our backdrop, we embark on a journey to unravel the intriguing connection between Miami's atmospheric composition and the inquisitive queries for velociraptors, brimming with anticipation for the unexpected revelations that await us.

[[RESULTS]]
The statistical analysis of the relationship between Miami's air quality and Google searches for 'velociraptor' revealed a notably strong correlation, with a Pearson correlation coefficient of 0.8324858. This indicates a substantial positive linear association between the two variables. Additionally, the coefficient of determination (r-squared) of 0.6930327 suggests that approximately 69.3% of the variability in velociraptor searches can be explained by changes in air quality. The p-value of less than 0.01 provides strong evidence against the null hypothesis of no correlation. These results substantiate the presence of a significant relationship between the air quality in Miami and the public's interest in the swift prehistoric predator.
Further supporting the robustness of the observed association, Fig. 1 displays a scatterplot depicting the striking correlation between air quality and the frequency of Google searches for 'velociraptor'. The tightly clustered data points form a discernible upward trend, affirming the coherence between the variables and reinforcing the statistical findings.
The compelling correlation coefficient and associated statistics serve as a notable testament to the unexpected convergence of environmental factors and online search behavior. This discovery shines a whimsical light on the intricate interplay between atmospheric conditions and public fascination with ancient creatures, reminding researchers to remain open to the endless possibilities that emerge from the fusion of distinct realms of inquiry.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our investigation have unraveled a captivating correlation between air quality in Miami and the frequency of Google searches for 'velociraptor', lending credence to the seemingly whimsical juxtaposition of atmospheric conditions and prehistoric curiosity. Our findings echo and extend the prior research in several remarkable ways.

First and foremost, the study by Smith et al. (2017) emphasized the pervasive impact of air pollutants on urban environments, underlying the significance of our exploration into the intersection of air quality and public interest in velociraptors. While Smith et al. focused on the implications for public health, our findings add a fanciful twist by illuminating the unanticipated reverberations of atmospheric composition on online search behavior, offering a playful spin on the resonating effects of air quality.

Similarly, the work of Doe (2019) elucidated the susceptibility of online search patterns to external influences, setting the stage for our investigation into the alluring pull of ancient reptilian wonders amid the invisible currents of air pollution. The synchronicity revealed in our study underscores the nuanced interplay between environmental factors and human curiosity, steering the conversation from the tangible impacts of pollution to the intangible yet tangible allure of prehistoric creatures.

Furthermore, the literary groundwork laid by Jones (2020) and the cultural musings of non-fiction and fiction authors nudge us to consider the significance of the enduring fascination with velociraptors in the context of contemporary environmental influences. As our statistical analysis unearthed a robust correlation, it humbly bows to the enduring allure of these prehistoric predators, weaving a whimsical narrative that extends beyond the realms of empirical data to the fantastical reaches of popular culture.

Provocatively, our findings beckon researchers to embrace the unforeseen connections that transcend disciplinary boundaries, inviting a dance between the empirical rigor of statistics and the playful capers of internet inquiry. This delightful dalliance between air quality and ancient curiosities adds a gossamer thread to the tapestry of interdisciplinary exploration, prompting scholars to venture into the unexpected and relish the serendipitous discoveries that abound in the research landscape.

In essence, our analysis elegantly reinforces the adage that truth is often stranger than fiction, as the ethereal tendrils of air quality intertwine with the enduring echoes of a long-lost world, compelling internet users to embark on virtual expeditions in search of the swift predator of ancient renown. As we venture deeper into the enthralling confluence of atmospheric dynamics and public piquancy, our study serves as a lighthearted reminder to remain attuned to the whimsy that infuses the most unexpected domains of inquiry.



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 quality in Miami and Google searches for 'velociraptor'. 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]]
Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches

[[ABSTRACT]]
In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

[[INTRDUCTION]]
The bustling metropolis of Miami conjures images of sunny beaches, vibrant nightlife, and a certain fascination with all things extravagant and outlandish. Yet, amidst the waves of swaying palms and colorful Art Deco architecture, a mysterious connection has emerged, one that has piqued the curiosity of both the astute researcher and the casual observer. It is within this enigmatic arena that we embark on a quest to unravel the perplexing correlation between air quality in Miami and the peculiar penchant for searching 'velociraptor' on the ubiquitous search engine, Google.
While the notion of linking air quality with online search behavior may initially seem about as plausible as a tropical snowstorm, our foray into this uncharted territory has yielded some unexpected, and frankly, quite astonishing results. This study represents an attempt to bring a measure of empirical rigor to what may, at first glance, appear to be an unlikely marriage of scientific inquiry and popular curiosity. Nevertheless, as we shall see, the human capacity for erratically directed interest knows no bounds, and it may very well be influenced by the invisible tendrils of the gaseous composition that envelops our fair city.
Of course, this investigation is not without its fair share of skepticism and raised eyebrows. The very idea of discerning a connection between the air we breathe and the ancient, fleet-footed predator that once roamed the earth seems, to many, as absurd as claiming correlation between the number of cats in Paris and the rise and fall of the stock market. However, as the saying goes, "correlation does not imply causation," and it is precisely this refrain that underpins our approach to this most fantastical of scientific journeys.
As we present our findings, it is with the hope that the scientific community will approach this rather whimsical association with an open mind and a keen appreciation for the unexpected. Just as the wind can carry with it the smell of salt from the nearby ocean, it may also carry with it the echo of ancient roars and the stories of a time long past. So, with an intrepid spirit and an ample supply of data analysis tools, let us venture forth into the mysterious miasma of Miami and the melodious mania of velociraptor searches, for what lies beyond may prove to be far more than mere statistical fancy.

[[RESULTS]]
The statistical analysis of the relationship between Miami's air quality and Google searches for 'velociraptor' revealed a notably strong correlation, with a Pearson correlation coefficient of 0.8324858. This indicates a substantial positive linear association between the two variables. Additionally, the coefficient of determination (r-squared) of 0.6930327 suggests that approximately 69.3% of the variability in velociraptor searches can be explained by changes in air quality. The p-value of less than 0.01 provides strong evidence against the null hypothesis of no correlation. These results substantiate the presence of a significant relationship between the air quality in Miami and the public's interest in the swift prehistoric predator.
Further supporting the robustness of the observed association, Fig. 1 displays a scatterplot depicting the striking correlation between air quality and the frequency of Google searches for 'velociraptor'. The tightly clustered data points form a discernible upward trend, affirming the coherence between the variables and reinforcing the statistical findings.
The compelling correlation coefficient and associated statistics serve as a notable testament to the unexpected convergence of environmental factors and online search behavior. This discovery shines a whimsical light on the intricate interplay between atmospheric conditions and public fascination with ancient creatures, reminding researchers to remain open to the endless possibilities that emerge from the fusion of distinct realms of inquiry.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In summary, our investigation into the surprising correlation between air quality in Miami and Google searches for 'velociraptor' has yielded results that are as intriguing as a fossilized puzzle waiting to be unearthed. Our findings point to a remarkably robust relationship, with the statistical analyses revealing a substantial positive linear association between these seemingly disparate phenomena. It appears that the gaseous symphony of Miami's air and the digital quest for prehistoric predators dance in harmonious step, much like the synchronized movements of a herd of Velociraptors.

While our study cannot elucidate the exact mechanisms driving this correlation, the prominent link we have uncovered serves as a captivating muse for future inquiries. It is a fervent hope that our research will inspire further exploration into the enigmatic interplay of environmental influences and online interests, reminding scholars that the scientific landscape is teeming with unexpected connections, much like the lively streets of Miami on a balmy evening.

The peculiar union of ecological nuances and online inquiries, while initially reminiscent of an amusing anecdote, has emerged as a tale worth testament in the annals of scientific inquiry. Our findings beckon for a continued expedition into the whimsical world of web searches and atmospheric peculiarities, encouraging researchers to keep their telescopic lenses trained on the horizon of uncharted research territory.

It is with great certainty, and a touch of lighthearted wonder, that we declare the conclusion of our investigation into the enigmatic connection between Miami's atmospheric profile and the resounding curiosity for 'velociraptor' on the digital domain. As the sun sets over the horizon of this peculiar study, we can confidently assert that the relationship between these variables has been brought to light with scholarly finesse, leaving no stone unturned in our pursuit of understanding this inexplicable correlation.

In light of these entertaining and thought-provoking findings, we can confidently assert that no further research is needed at this time to explore the connection between air quality in Miami and the peculiar fascination with the swift prehistoric predator. It seems that, for now, the wistful whispers of the past and the invisible tendrils of air quality shall continue to entwine in the whimsical realm of statistical fancy.


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 Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eclectic Ecological Enigmas


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 Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Prehistoric Ecology and Environmental Research (CPEER)


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 Miami's Mysterious Miasma and the Melodious Mania: The Link between Air Quality and Velociraptor Searches with an abstract of In this study, we delve into the whimsical world of web searches and atmospheric intricacies to uncover a surprising association between air quality in Miami and the frequency of Google searches for 'velociraptor'. Employing data from the Environmental Protection Agency and Google Trends, our research team meticulously analyzed a span of two eventful decades, from 2004 to 2023. Surprisingly, we found a remarkably robust correlation coefficient of 0.8324858 and a p-value of less than 0.01, indicating a significant relationship. While causation cannot be attributed from this observational study, the link between the gaseous expulsions of Miami and public curiosity about the swift prehistoric predator is, indeed, titillating. Our findings merit further investigation into the peculiar interplay between air quality and ancient reptilian interests and serve as a reminder to always keep an eye out for unexpected connections, even amidst the most unconventional realms of research.

ChatGPT:

Miami, Miasma, air quality, Velociraptor searches, atmospheric intricacies, Environmental Protection Agency, Google Trends, correlation coefficient, observational study, prehistoric predator, ancient reptilian interests

*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 quality in Miami
Detailed data title: Percentage of days with good or moderate air quality in Miami-Fort Lauderdale-West Palm Beach, FL
Source: Environmental Protection Agency
See what else correlates with Air quality in Miami

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

See what else correlates with Google searches for 'velociraptor'

Correlation r = 0.8324858 (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 = 0.6930327 (Coefficient of determination)
This means 69.3% of the change in the one variable (i.e., Google searches for 'velociraptor') is predictable based on the change in the other (i.e., Air quality in Miami) over the 20 years from 2004 through 2023.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.3E-6. 0.0000052789331965955140000000
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 0.83 in 0.00053% of random cases. Said differently, if you correlated 189,432 random variables You don't actually need 189 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 19 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.62, 0.93 ] 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.
20042005200620072008200920102011201220132014201520162017201820192020202120222023
Air quality in Miami (Good air quality)97.54197.534296.712396.438497.814299.178198.630197.534298.907198.630198.630199.72698.347197.765498.904199.450599.453699.178199.452198.9011
Google searches for 'velociraptor' (Rel. search volume)15.166712.416711.083310.333322.333324.166724.333328.833339.833325.521.833338.666722.7519.7530.416727.416734.166731.7531.7526.4444




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([97.541,97.5342,96.7123,96.4384,97.8142,99.1781,98.6301,97.5342,98.9071,98.6301,98.6301,99.726,98.3471,97.7654,98.9041,99.4505,99.4536,99.1781,99.4521,98.9011,])
array_2 = np.array([15.1667,12.4167,11.0833,10.3333,22.3333,24.1667,24.3333,28.8333,39.8333,25.5,21.8333,38.6667,22.75,19.75,30.4167,27.4167,34.1667,31.75,31.75,26.4444,])
array_1_name = "Air quality in Miami"
array_2_name = "Google searches for 'velociraptor'"

# 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?

Your rating skills are legendary!


Correlation ID: 5643 · Black Variable ID: 20898 · Red Variable ID: 1516
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0