about · email me · subscribe
Spurious correlation #4,038 · 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 Butte, Montana and the second variable is Google searches for 'how to hide a body'.  The chart goes from 2004 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

The foul stench of pollution masked any odor emanating from the hidden body, making it harder to locate. The smog also created a hazy atmosphere, effectively concealing any suspicious activity. As air quality decreased, it was as if the city itself was saying, "Nothing to see here, folks!" And in a bizarre twist, it turns out that the pollutants formed a secret alliance with the would-be body hiders, creating the perfect cover-up campaign. It's a classic case of environmental wrongdoing leading to some seriously murky business, giving a whole new meaning to the phrase 'getting away with murder'.

Model: dalle-3
Prompt: Transform this scene into a haunting black and white charcoal sketch that captures the ominous atmosphere of Butte, Montana. The smokestacks should be towering, emitting billows of toxic fumes that blend into the hazy sky. A sense of dread should permeate the scene as silhouetted figures are depicted typing frantically in the dimly lit glow of their electronic devices, alluding to the sinister online searches. Capture the eerie juxtaposition of industrial pollution and hidden secrets in a stark and chilling composition. 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 Butte, Montana and Google searches for 'how to hide a body'. 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: Symbolism Charcoal Magic realism Futuristic Celtic art
ChatGPT: Charcoal

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 Butte, Montana and Google searches for 'how to hide a body', in the following situation: The increase in air pollution in Butte, Montana led to a rise in Google searches for "how to hide a body" as residents tried to mask the smell of decomposing corpses with the stench of sulfur. They were simply trying to cover up their dirty deeds with dirtier air!. Keep the description simple.
ChatGPT: In Butte, Montana, the air is thick with pollution as smokestacks spew out toxic fumes. The sky is hazy and the stench of sulfur hangs in the air. Meanwhile, residents are seen frantically typing "how to hide a body" into their Google search bars, trying to mask the smell of decomposing corpses with the polluted air.

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: [ Charcoal ] and depicting this scene: In Butte, Montana, the air is thick with pollution as smokestacks spew out toxic fumes. The sky is hazy and the stench of sulfur hangs in the air. Meanwhile, residents are seen frantically typing "how to hide a body" into their Google search bars, trying to mask the smell of decomposing corpses with the polluted air. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Transform this scene into a haunting black and white charcoal sketch that captures the ominous atmosphere of Butte, Montana. The smokestacks should be towering, emitting billows of toxic fumes that blend into the hazy sky. A sense of dread should permeate the scene as silhouetted figures are depicted typing frantically in the dimly lit glow of their electronic devices, alluding to the sinister online searches. Capture the eerie juxtaposition of industrial pollution and hidden secrets in a stark and chilling composition.

*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 Butte, Montana caused how to hide a body (Google searches for 'how to hide a body') to increase.

AI academic paper

(Because p < 0.01)
The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

The Journal of Unusual Correlations

Jan 2024

Reminder: This paper is AI-generated. Not real!
Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.




Model: gpt-3.5-turbo-1106
System prompt: You are a 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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Include a pun in the title.

Your research team used data from Environmental Protection Agency and Google Trends to assess this nagging question. You found a correlation coefficient of 0.5783740 and p < 0.01 for 2004 to 2022.

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 Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

As the saying goes, "In science, there are no jokes, only data." But in the spirit of breaking boundaries and turning over new leaves (and dad joke enthusiasts everywhere), we present our findings on the intriguing connection between air pollution in Butte, Montana, and online searches for 'how to hide a body.' It's a tale as old as time – or at least as old as the internet.

The notion that air pollution could be linked to queries about body concealment may seem like a breath of fresh air to some and a whiff of something suspicious to others. However, much like a well-timed dad joke, our research sheds light on unexpected connections and raises eyebrows, if not a chuckle or two.

Butte, a city known for its historic mining and vibrant community spirit, has also grappled with air quality issues due to its industrial legacy. Our research aims to uncover whether there is a significant relationship between the environmental woes of Butte and the rather macabre online behavior observed in Google search trends. It's like conducting a high-stakes game of Clue, but with statistical analysis instead of Colonel Mustard in the conservatory with the lead pipe.

The exploration into this peculiar correlation was no walk in the park – unless, of course, you consider strolling through a park with a nose clip and an air quality monitor in hand a leisurely activity. We diligently gathered and analyzed data from the Environmental Protection Agency, documenting levels of air pollutants in Butte, Montana, over an 18-year period. Meanwhile, we also tapped into Google Trends, a treasure trove of user queries and interests, to unravel the patterns of online searches related to the topic at hand. It's like detective work for the digital age, with less magnifying glasses and more computer screens.

Our initial findings, much like a punchline waiting to land, hinted at a potential relationship between air quality and the uptick in searches related to concealing a body. As we delved deeper into the data, we uncovered a statistically significant correlation coefficient of 0.5783740 with a p-value less than 0.01. It's as close to a smoking gun as statistical analysis can get without crossing into the realm of forensic science.

The implications of our findings, much like a dad's well-worn joke repertoire, straddle the line between amusement and concern. The prospect of a psychological link between environmental conditions and online behavior raises important questions about the intersection of public health, mental well-being, and the eerie allure of internet searches. It's like a dark comedy with a side of statistical analysis, leaving us simultaneously scratching our heads and marveling at the unexpected twists of research inquiry.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a few real TV shows that sound like they might be relevant to the topic that you watched as research.

Here is the title and abstract of the paper:
[[TITLE]]
The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As the saying goes, "In science, there are no jokes, only data." But in the spirit of breaking boundaries and turning over new leaves (and dad joke enthusiasts everywhere), we present our findings on the intriguing connection between air pollution in Butte, Montana, and online searches for 'how to hide a body.' It's a tale as old as time – or at least as old as the internet.
The notion that air pollution could be linked to queries about body concealment may seem like a breath of fresh air to some and a whiff of something suspicious to others. However, much like a well-timed dad joke, our research sheds light on unexpected connections and raises eyebrows, if not a chuckle or two.
Butte, a city known for its historic mining and vibrant community spirit, has also grappled with air quality issues due to its industrial legacy. Our research aims to uncover whether there is a significant relationship between the environmental woes of Butte and the rather macabre online behavior observed in Google search trends. It's like conducting a high-stakes game of Clue, but with statistical analysis instead of Colonel Mustard in the conservatory with the lead pipe.
The exploration into this peculiar correlation was no walk in the park – unless, of course, you consider strolling through a park with a nose clip and an air quality monitor in hand a leisurely activity. We diligently gathered and analyzed data from the Environmental Protection Agency, documenting levels of air pollutants in Butte, Montana, over an 18-year period. Meanwhile, we also tapped into Google Trends, a treasure trove of user queries and interests, to unravel the patterns of online searches related to the topic at hand. It's like detective work for the digital age, with less magnifying glasses and more computer screens.
Our initial findings, much like a punchline waiting to land, hinted at a potential relationship between air quality and the uptick in searches related to concealing a body. As we delved deeper into the data, we uncovered a statistically significant correlation coefficient of 0.5783740 with a p-value less than 0.01. It's as close to a smoking gun as statistical analysis can get without crossing into the realm of forensic science.
The implications of our findings, much like a dad's well-worn joke repertoire, straddle the line between amusement and concern. The prospect of a psychological link between environmental conditions and online behavior raises important questions about the intersection of public health, mental well-being, and the eerie allure of internet searches. It's like a dark comedy with a side of statistical analysis, leaving us simultaneously scratching our heads and marveling at the unexpected twists of research inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The literature on air pollution and its potential impacts on human behavior is extensive and varied. Smith, in their study "Air Quality and Public Health," explores the adverse effects of air pollution on respiratory health and cardiovascular disease, laying the groundwork for understanding the physical toll of poor air quality. Similarly, Doe's research in "The Environmental Burden of Industrial Legacy" unveils the ongoing challenges faced by communities like Butte, Montana, which grapple with the environmental legacies of industrial activities. It's like the buildup to a punchline - setting the stage for the unexpected twist of our research findings.

But as we wade deeper into the literature, we cannot help but be drawn to the unexpected correlations that sometimes emerge in the unlikeliest of places. Jones, in "Strange Patterns in Online Behavior," touches upon the intriguing realm of digital footprints and reveals the curious ways in which online searches can reflect societal concerns and underlying psychological currents. It's like finding a hidden punchline in a serious conversation - a twist that catches you off guard.

Now, branching out from the traditional academic sources, we turn our attention to non-fiction books that shed light on the darker side of human nature and the art of concealment. "The Gift of Fear" by Gavin de Becker skillfully delves into the realm of intuition, fear, and survival instincts, offering valuable insights into the psychology of threat assessment and danger. It's like a guidebook for navigating the treacherous terrain of research inquiries, albeit with a much-needed dose of seriousness.

In a more fictional realm, works like Agatha Christie's "Murder on the Orient Express" and Gillian Flynn's "Gone Girl" transport readers into the realm of intricate plots and concealed truths, demonstrating the captivating allure of mysteries and the art of hiding secrets. It's like taking a detour into the world of fiction to inform our understanding of the unexpected twists and turns in real-world data analysis.

Diving into the world of popular culture, TV shows such as "Dexter" and "Breaking Bad" offer intriguing forays into the shadowy realms of crime and concealment, providing a cultural backdrop against which to consider the macabre nature of internet searches. It's like conducting field research in the realm of television drama, where the unexpected plot twists mirror our research findings in their ability to captivate and confound.

Stay tuned for more puns and twists in the subsequent sections of this research paper, where we delve further into the eerie correlation between air pollution in Butte, Montana, and online searches for 'how to hide a body.' As we unravel the layers of this enigmatic connection, we hope to shed light on the unexpected intersections of environmental conditions and digital behavior, offering a fresh perspective that is as refreshing as a dad joke at a scientific conference.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Environmental Protection Agency and Google Trends . You used data from 2004 to 2022

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 Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

[[INTRODUCTION]]
As the saying goes, "In science, there are no jokes, only data." But in the spirit of breaking boundaries and turning over new leaves (and dad joke enthusiasts everywhere), we present our findings on the intriguing connection between air pollution in Butte, Montana, and online searches for 'how to hide a body.' It's a tale as old as time – or at least as old as the internet.
The notion that air pollution could be linked to queries about body concealment may seem like a breath of fresh air to some and a whiff of something suspicious to others. However, much like a well-timed dad joke, our research sheds light on unexpected connections and raises eyebrows, if not a chuckle or two.
Butte, a city known for its historic mining and vibrant community spirit, has also grappled with air quality issues due to its industrial legacy. Our research aims to uncover whether there is a significant relationship between the environmental woes of Butte and the rather macabre online behavior observed in Google search trends. It's like conducting a high-stakes game of Clue, but with statistical analysis instead of Colonel Mustard in the conservatory with the lead pipe.
The exploration into this peculiar correlation was no walk in the park – unless, of course, you consider strolling through a park with a nose clip and an air quality monitor in hand a leisurely activity. We diligently gathered and analyzed data from the Environmental Protection Agency, documenting levels of air pollutants in Butte, Montana, over an 18-year period. Meanwhile, we also tapped into Google Trends, a treasure trove of user queries and interests, to unravel the patterns of online searches related to the topic at hand. It's like detective work for the digital age, with less magnifying glasses and more computer screens.
Our initial findings, much like a punchline waiting to land, hinted at a potential relationship between air quality and the uptick in searches related to concealing a body. As we delved deeper into the data, we uncovered a statistically significant correlation coefficient of 0.5783740 with a p-value less than 0.01. It's as close to a smoking gun as statistical analysis can get without crossing into the realm of forensic science.
The implications of our findings, much like a dad's well-worn joke repertoire, straddle the line between amusement and concern. The prospect of a psychological link between environmental conditions and online behavior raises important questions about the intersection of public health, mental well-being, and the eerie allure of internet searches. It's like a dark comedy with a side of statistical analysis, leaving us simultaneously scratching our heads and marveling at the unexpected twists of research inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To uncover the enigmatic link between air pollution in Butte, Montana, and the Google searches for 'how to hide a body,' our research team implemented a plethora of methodological maneuvers that would make even the most intrepid statistician raise an eyebrow – or perhaps both.

First, we meticulously gathered air quality data from the Environmental Protection Agency, sifting through years of records like avid treasure hunters in search of the elusive correlation. Much like prospectors panning for gold during Butte's mining heyday, we sieved through particulate matter (PM10 and PM2.5), sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), and ozone (O3) concentrations. It was a data-digging expedition akin to unearthing buried treasure – only the "treasure" in this case was a statistically significant association.

Next, we ventured into the unpredictable terrain of Google Trends, analyzing search query data with the precision of a detective solving a perplexing case. We wrangled with search volumes for key terms related to concealment techniques, all while keeping a watchful eye out for any statistical anomalies that could throw a proverbial wrench into our investigation. After all, in the world of internet searches, one must be prepared for the unexpected – much like a seasoned comedian anticipating a heckler in the audience.

To ensure the robustness of our findings, we employed a daring array of statistical analyses, including correlation coefficients and regression models. These analytical tools allowed us to uncover underlying patterns and relationships, much like a sleuth unraveling a complex mystery – albeit one that involved data sets and computer screens instead of magnifying glasses and shadowy alleyways. We also cross-validated our findings using time-series analyses, traversing the dynamic landscape of temporal trends with the agility of a tightrope walker – albeit a metaphorical one, with data points serving as our balancing pole.

The data from 2004 to 2022 formed the crux of our investigation, capturing the evolution of both air quality in Butte and the virtual intrigue surrounding body concealment. With each year meticulously examined, we aimed to construct a comprehensive narrative, akin to weaving together the threads of a compelling tale – albeit one with statistical significance tests and confidence intervals in place of plot twists and character arcs.

With our methodological approach charted and our data scrutinized through a curious lens, we ventured forth into the uncharted territory of uncovering the intersection between environmental conditions and online behavior. Our journey, much like a puzzling riddle, promised unexpected twists and turns, keeping us both bewildered and captivated by the enigmatic relationship between air quality and peculiar Google searches.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

For the time period 2004 to 2022, you found a correlation 0.5783740, r-squared of 0.3345165, 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 Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
As the saying goes, "In science, there are no jokes, only data." But in the spirit of breaking boundaries and turning over new leaves (and dad joke enthusiasts everywhere), we present our findings on the intriguing connection between air pollution in Butte, Montana, and online searches for 'how to hide a body.' It's a tale as old as time – or at least as old as the internet.
The notion that air pollution could be linked to queries about body concealment may seem like a breath of fresh air to some and a whiff of something suspicious to others. However, much like a well-timed dad joke, our research sheds light on unexpected connections and raises eyebrows, if not a chuckle or two.
Butte, a city known for its historic mining and vibrant community spirit, has also grappled with air quality issues due to its industrial legacy. Our research aims to uncover whether there is a significant relationship between the environmental woes of Butte and the rather macabre online behavior observed in Google search trends. It's like conducting a high-stakes game of Clue, but with statistical analysis instead of Colonel Mustard in the conservatory with the lead pipe.
The exploration into this peculiar correlation was no walk in the park – unless, of course, you consider strolling through a park with a nose clip and an air quality monitor in hand a leisurely activity. We diligently gathered and analyzed data from the Environmental Protection Agency, documenting levels of air pollutants in Butte, Montana, over an 18-year period. Meanwhile, we also tapped into Google Trends, a treasure trove of user queries and interests, to unravel the patterns of online searches related to the topic at hand. It's like detective work for the digital age, with less magnifying glasses and more computer screens.
Our initial findings, much like a punchline waiting to land, hinted at a potential relationship between air quality and the uptick in searches related to concealing a body. As we delved deeper into the data, we uncovered a statistically significant correlation coefficient of 0.5783740 with a p-value less than 0.01. It's as close to a smoking gun as statistical analysis can get without crossing into the realm of forensic science.
The implications of our findings, much like a dad's well-worn joke repertoire, straddle the line between amusement and concern. The prospect of a psychological link between environmental conditions and online behavior raises important questions about the intersection of public health, mental well-being, and the eerie allure of internet searches. It's like a dark comedy with a side of statistical analysis, leaving us simultaneously scratching our heads and marveling at the unexpected twists of research inquiry.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our analysis revealed a statistically significant correlation between air pollution in Butte, Montana and Google searches for 'how to hide a body' over the period from 2004 to 2022. The correlation coefficient of 0.5783740 suggests a moderate positive relationship, which is as clear as a crisp Montana sky on a pollution-free day - or should I say, "dad-bod clear"?

The scatterplot (Fig. 1) visually supports our findings, depicting a notable upward trend as air pollution levels increase and the frequency of sinister searches rises. It's as if the data points are playing a game of hide-and-seek, but alas, statistical analysis always finds them!

The r-squared value of 0.3345165 indicates that approximately 33.45% of the variation in Google searches for 'how to hide a body' can be explained by changes in air pollution levels in Butte. This degree of association is nothing to sneeze at, especially when considering the potential implications for public health and online behavior. It's like connecting the dots between an air pollution monitor and a web browser – talk about an unexpected link!

The significance level of p < 0.01 further strengthens the case for a meaningful relationship between the two variables. With a p-value that low, we can confidently say that this is not just a fluke, unlike that time Uncle Joe tried to pass off his "original" knock-knock joke at Thanksgiving.

Overall, our results provide compelling evidence of a correlation between air quality in Butte, Montana and online searches for 'how to hide a body.' While the implications of this connection may be both intriguing and, dare I say, a tad morbid, they underscore the multifaceted nature of research inquiry and the unexpected relationships that can emerge from the analysis of diverse datasets. It's like finding a hidden gem in a statistical mine – only this gem is more darkly intriguing than sparkly.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

[[LITERATURE REVIEW]]
The literature on air pollution and its potential impacts on human behavior is extensive and varied. Smith, in their study "Air Quality and Public Health," explores the adverse effects of air pollution on respiratory health and cardiovascular disease, laying the groundwork for understanding the physical toll of poor air quality. Similarly, Doe's research in "The Environmental Burden of Industrial Legacy" unveils the ongoing challenges faced by communities like Butte, Montana, which grapple with the environmental legacies of industrial activities. It's like the buildup to a punchline - setting the stage for the unexpected twist of our research findings.
But as we wade deeper into the literature, we cannot help but be drawn to the unexpected correlations that sometimes emerge in the unlikeliest of places. Jones, in "Strange Patterns in Online Behavior," touches upon the intriguing realm of digital footprints and reveals the curious ways in which online searches can reflect societal concerns and underlying psychological currents. It's like finding a hidden punchline in a serious conversation - a twist that catches you off guard.
Now, branching out from the traditional academic sources, we turn our attention to non-fiction books that shed light on the darker side of human nature and the art of concealment. "The Gift of Fear" by Gavin de Becker skillfully delves into the realm of intuition, fear, and survival instincts, offering valuable insights into the psychology of threat assessment and danger. It's like a guidebook for navigating the treacherous terrain of research inquiries, albeit with a much-needed dose of seriousness.
In a more fictional realm, works like Agatha Christie's "Murder on the Orient Express" and Gillian Flynn's "Gone Girl" transport readers into the realm of intricate plots and concealed truths, demonstrating the captivating allure of mysteries and the art of hiding secrets. It's like taking a detour into the world of fiction to inform our understanding of the unexpected twists and turns in real-world data analysis.
Diving into the world of popular culture, TV shows such as "Dexter" and "Breaking Bad" offer intriguing forays into the shadowy realms of crime and concealment, providing a cultural backdrop against which to consider the macabre nature of internet searches. It's like conducting field research in the realm of television drama, where the unexpected plot twists mirror our research findings in their ability to captivate and confound.
Stay tuned for more puns and twists in the subsequent sections of this research paper, where we delve further into the eerie correlation between air pollution in Butte, Montana, and online searches for 'how to hide a body.' As we unravel the layers of this enigmatic connection, we hope to shed light on the unexpected intersections of environmental conditions and digital behavior, offering a fresh perspective that is as refreshing as a dad joke at a scientific conference.

[[RESULTS]]
Our analysis revealed a statistically significant correlation between air pollution in Butte, Montana and Google searches for 'how to hide a body' over the period from 2004 to 2022. The correlation coefficient of 0.5783740 suggests a moderate positive relationship, which is as clear as a crisp Montana sky on a pollution-free day - or should I say, "dad-bod clear"?
The scatterplot (Fig. 1) visually supports our findings, depicting a notable upward trend as air pollution levels increase and the frequency of sinister searches rises. It's as if the data points are playing a game of hide-and-seek, but alas, statistical analysis always finds them!
The r-squared value of 0.3345165 indicates that approximately 33.45% of the variation in Google searches for 'how to hide a body' can be explained by changes in air pollution levels in Butte. This degree of association is nothing to sneeze at, especially when considering the potential implications for public health and online behavior. It's like connecting the dots between an air pollution monitor and a web browser – talk about an unexpected link!
The significance level of p < 0.01 further strengthens the case for a meaningful relationship between the two variables. With a p-value that low, we can confidently say that this is not just a fluke, unlike that time Uncle Joe tried to pass off his "original" knock-knock joke at Thanksgiving.
Overall, our results provide compelling evidence of a correlation between air quality in Butte, Montana and online searches for 'how to hide a body.' While the implications of this connection may be both intriguing and, dare I say, a tad morbid, they underscore the multifaceted nature of research inquiry and the unexpected relationships that can emerge from the analysis of diverse datasets. It's like finding a hidden gem in a statistical mine – only this gem is more darkly intriguing than sparkly.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings not only align with prior research on the impact of air pollution but also highlight the surprising link between environmental factors and online behavior, much like finding a punchline in a scientific journal article. The statistically significant correlation we observed between air pollution in Butte, Montana and Google searches for 'how to hide a body' reinforces the importance of considering the potential psychological repercussions of living in areas with poor air quality and the manifestation of these concerns through online activity. It's like watching a correlation coefficient deliver a punchline - unexpected but undeniably present.

In line with Smith's exploration of the adverse effects of air pollution, our findings suggest that the influence of environmental conditions extends beyond physiological health to potentially impact individuals' cognitive and behavioral responses. It's like the setup to a scientific joke – the punchline being the unexpected connection to online searches for nefarious activities.

Furthermore, the correlation coefficient of 0.5783740 and the r-squared value indicate a moderately strong relationship between air pollution and online searches, emphasizing the substantial influence of air quality on internet behavior. It's like discovering a correlation coefficient at a comedy club – unexpected, but undeniably there.

Our results contribute to the growing body of literature, shedding light on the intersection of environmental quality and digital behavior, much like a spotlight on a comedic stage. While the implications may be, dare I say, grim, they underscore the complex interplay between environmental conditions and human responses, offering a fresh perspective that is as thought-provoking as a dad joke at a scientific conference.

In a twist that would make Agatha Christie proud, our research highlights the surprising ways in which seemingly unrelated variables can interweave, illustrating the multifaceted nature of data analysis and the unexpected connections that may emerge. It's as captivating as a narrative twist in a mystery novel – only this mystery involves statistical relationships and internet searches for clandestine activities.

This study not only adds a darkly humorous twist to the discourse on air pollution but also underscores the need to explore the intricate web of factors that shape human behavior and decision-making. It's like turning a serious discussion into a lighthearted moment - unexpected, but undeniably engaging.

As we continue to unpack the enigmatic relationship between air quality and online searches, our findings beckon further investigation into the psychological and societal implications of environmental conditions on internet behavior. It's like a research inquiry with an unexpected punchline – a revelation that leaves us both curious and contemplative.


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 Butte, Montana and Google searches for 'how to hide a body'. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'

[[ABSTRACT]]
The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.

Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).

The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

[[INTRDUCTION]]
As the saying goes, "In science, there are no jokes, only data." But in the spirit of breaking boundaries and turning over new leaves (and dad joke enthusiasts everywhere), we present our findings on the intriguing connection between air pollution in Butte, Montana, and online searches for 'how to hide a body.' It's a tale as old as time – or at least as old as the internet.
The notion that air pollution could be linked to queries about body concealment may seem like a breath of fresh air to some and a whiff of something suspicious to others. However, much like a well-timed dad joke, our research sheds light on unexpected connections and raises eyebrows, if not a chuckle or two.
Butte, a city known for its historic mining and vibrant community spirit, has also grappled with air quality issues due to its industrial legacy. Our research aims to uncover whether there is a significant relationship between the environmental woes of Butte and the rather macabre online behavior observed in Google search trends. It's like conducting a high-stakes game of Clue, but with statistical analysis instead of Colonel Mustard in the conservatory with the lead pipe.
The exploration into this peculiar correlation was no walk in the park – unless, of course, you consider strolling through a park with a nose clip and an air quality monitor in hand a leisurely activity. We diligently gathered and analyzed data from the Environmental Protection Agency, documenting levels of air pollutants in Butte, Montana, over an 18-year period. Meanwhile, we also tapped into Google Trends, a treasure trove of user queries and interests, to unravel the patterns of online searches related to the topic at hand. It's like detective work for the digital age, with less magnifying glasses and more computer screens.
Our initial findings, much like a punchline waiting to land, hinted at a potential relationship between air quality and the uptick in searches related to concealing a body. As we delved deeper into the data, we uncovered a statistically significant correlation coefficient of 0.5783740 with a p-value less than 0.01. It's as close to a smoking gun as statistical analysis can get without crossing into the realm of forensic science.
The implications of our findings, much like a dad's well-worn joke repertoire, straddle the line between amusement and concern. The prospect of a psychological link between environmental conditions and online behavior raises important questions about the intersection of public health, mental well-being, and the eerie allure of internet searches. It's like a dark comedy with a side of statistical analysis, leaving us simultaneously scratching our heads and marveling at the unexpected twists of research inquiry.

[[RESULTS]]
Our analysis revealed a statistically significant correlation between air pollution in Butte, Montana and Google searches for 'how to hide a body' over the period from 2004 to 2022. The correlation coefficient of 0.5783740 suggests a moderate positive relationship, which is as clear as a crisp Montana sky on a pollution-free day - or should I say, "dad-bod clear"?
The scatterplot (Fig. 1) visually supports our findings, depicting a notable upward trend as air pollution levels increase and the frequency of sinister searches rises. It's as if the data points are playing a game of hide-and-seek, but alas, statistical analysis always finds them!
The r-squared value of 0.3345165 indicates that approximately 33.45% of the variation in Google searches for 'how to hide a body' can be explained by changes in air pollution levels in Butte. This degree of association is nothing to sneeze at, especially when considering the potential implications for public health and online behavior. It's like connecting the dots between an air pollution monitor and a web browser – talk about an unexpected link!
The significance level of p < 0.01 further strengthens the case for a meaningful relationship between the two variables. With a p-value that low, we can confidently say that this is not just a fluke, unlike that time Uncle Joe tried to pass off his "original" knock-knock joke at Thanksgiving.
Overall, our results provide compelling evidence of a correlation between air quality in Butte, Montana and online searches for 'how to hide a body.' While the implications of this connection may be both intriguing and, dare I say, a tad morbid, they underscore the multifaceted nature of research inquiry and the unexpected relationships that can emerge from the analysis of diverse datasets. It's like finding a hidden gem in a statistical mine – only this gem is more darkly intriguing than sparkly.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

Drawing conclusions from our research is like solving a riddle wrapped in a mystery inside an enigma – with a healthy dose of statistical analysis. Our findings reveal a correlation between air pollution in Butte, Montana and Google searches for 'how to hide a body' that is as clear as day, though hopefully not as eerily clear as a moonlit night in a horror movie.

The statistically significant relationship we've uncovered, much like a dad's favorite punchline, is both surprising and thought-provoking. It raises questions about how environmental factors can influence online behavior, prompting us to consider the psychological impact of residing in areas with poor air quality. It's like a "whodunit" where the culprit is a sneaky pollutant hiding in plain sight.

With a correlation coefficient of 0.5783740 and a p-value less than 0.01, our results point to a meaningful association between air quality in Butte and the frequency of macabre Google searches. It's like a statistical "gotcha!" moment that leaves no room for doubt – except, perhaps, when Uncle Joe tries to claim credit for the results at the next family gathering.

In conclusion, the findings of our research urge further exploration of the complex interplay between environmental conditions and online behavior. However, we are confident that no more research is needed in the specific arena of air pollution and eerie online searches. We can all breathe a sigh of relief and move on to less spooky statistical endeavors. After all, some mysteries are best left buried, much like that old dad joke that just won't stay forgotten.


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 Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Unusual Correlations


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body'. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Environmental Research Applications


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 Polluted Plot: A Correlation Between Air Quality in Butte, Montana and Online Searches for 'How to Hide a Body' with an abstract of The eerie correlation between air pollution in Butte, Montana, and the Google searches for 'how to hide a body' has left us gasping for fresh air. Our research team, despite facing some raised eyebrows, bravely explored this connection using data from the Environmental Protection Agency and Google Trends.
Our findings, much like a bad pun, were eye-opening. Analyzing the data from 2004 to 2022, we uncovered a correlation coefficient of 0.5783740 and p < 0.01. The statistically significant link between air quality in Butte and searches related to body concealment on Google has left us scratching our heads (and hopefully not reaching for shovels).
The implications of this correlation, much like a dad joke, are both amusing and concerning. It raises questions about the potential psychological impacts of living in areas with poor air quality, as well as the dark humor of internet searches in response to environmental conditions. Our research delves into these serious and, dare I say, grave matters with a lighthearted tone, much like a dad telling his favorite joke at a family gathering.

ChatGPT:

air quality, Butte Montana, pollution, correlation, Google searches, how to hide a body, environmental impacts, psychological effects, dark humor, internet searches, environmental conditions

*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 Butte, Montana
Detailed data title: Percentage of days 'unhealthy' or worse air quality in Butte-Silver Bow, MT
Source: Environmental Protection Agency
See what else correlates with Air pollution in Butte, Montana

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

See what else correlates with Google searches for 'how to hide a body'

Correlation r = 0.5783740 (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 = 0.3345165 (Coefficient of determination)
This means 33.5% of the change in the one variable (i.e., Google searches for 'how to hide a body') is predictable based on the change in the other (i.e., Air pollution in Butte, Montana) over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0095. 0.0094834191299965500000000000
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 0.58 in 0.95% of random cases. Said differently, if you correlated 105 random variables Which I absolutely did.
with the same 18 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 18 because we have two variables measured over a period of 19 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.

[ 0.17, 0.82 ] 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.
2004200520062007200820092010201120122013201420152016201720182019202020212022
Air pollution in Butte, Montana (Bad air quality days)0000.27777800001.377410.27397301.6438401.12994000.8196721.643840.547945
Google searches for 'how to hide a body' (Rel. search volume)9.56.333336.583338.2515.7515.583316.2530.166751.416754.08338370.583343.666738.7536.416741.333356.583375.2572.25




Why this works

  1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.




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([0,0,0,0.277778,0,0,0,0,1.37741,0.273973,0,1.64384,0,1.12994,0,0,0.819672,1.64384,0.547945,])
array_2 = np.array([9.5,6.33333,6.58333,8.25,15.75,15.5833,16.25,30.1667,51.4167,54.0833,83,70.5833,43.6667,38.75,36.4167,41.3333,56.5833,75.25,72.25,])
array_1_name = "Air pollution in Butte, Montana"
array_2_name = "Google searches for 'how to hide a body'"

# 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?

Hats off to you for rating!


Correlation ID: 4038 · Black Variable ID: 20399 · Red Variable ID: 1513
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0