about · email me · subscribe
Spurious correlation #1,289 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of carpet installers in Kentucky 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

As the number of carpet installers in Kentucky decreased, there were fewer experts in concealing unsightly seams. This led to an increase in DIY body hiding attempts, as people resorted to using carpeting techniques they saw on HGTV. The spate of poorly hidden bodies is reshaping crime scenes into makeshift home improvement projects. Remember, a poorly hidden body is a decor disaster!

Model: dalle-3
Prompt: Generate an image depicting a scene in a small town in Kentucky where a group of friends are huddled around a computer, frantically typing in search terms. The screen displays Google's search bar filled with queries like "DIY concealment ideas" and "best hiding places at home." Meanwhile, across town, a frustrated homeowner stands in a room with unfinished floors and a roll of carpet lying unused in the corner. The image should capture the sense of urgency and the juxtaposition between the friends' online search and the homeowner's physical dilemma, emphasizing the contrast between the two scenarios. Each element should be portrayed with attention to detail, such as the expressions of the friends and the homeowner's exasperation, to convey the intensity and frustration of the situation. 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 situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: As the number of carpet installers in Kentucky decreased, people were forced to get creative with concealing evidence, leading to an uptick in Google searches for alternative ways to hide a body. With fewer carpet installations, the need for new hiding spots skyrocketed, resulting in a surge of morbid internet research.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: A Discovery magazine cover image A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s Cute 2D animation Voxel art Scalar art
ChatGPT: A Discovery magazine cover image

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. As the number of carpet installers in Kentucky decreased, people were forced to get creative with concealing evidence, leading to an uptick in Google searches for alternative ways to hide a body. With fewer carpet installations, the need for new hiding spots skyrocketed, resulting in a surge of morbid internet research.
ChatGPT: In a small town in Kentucky, a group of friends huddled around a computer, furiously typing in search terms. On the screen, Google's search bar filled with queries like "DIY concealment ideas" and "best hiding places at home." Meanwhile, across town, a frustrated homeowner stood in a room with unfinished floors and a roll of carpet lying unused in the corner.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A Discovery magazine cover image ] and depicting this scene: In a small town in Kentucky, a group of friends huddled around a computer, furiously typing in search terms. On the screen, Google's search bar filled with queries like "DIY concealment ideas" and "best hiding places at home." Meanwhile, across town, a frustrated homeowner stood in a room with unfinished floors and a roll of carpet lying unused in the corner. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image depicting a scene in a small town in Kentucky where a group of friends are huddled around a computer, frantically typing in search terms. The screen displays Google's search bar filled with queries like "DIY concealment ideas" and "best hiding places at home." Meanwhile, across town, a frustrated homeowner stands in a room with unfinished floors and a roll of carpet lying unused in the corner. The image should capture the sense of urgency and the juxtaposition between the friends' online search and the homeowner's physical dilemma, emphasizing the contrast between the two scenarios. Each element should be portrayed with attention to detail, such as the expressions of the friends and the homeowner's exasperation, to convey the intensity and frustration of the situation.

*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 a decrease in The number of carpet installers in Kentucky caused how to hide a body (Google searches for 'how to hide a body') to increase.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and How to Hide a Body Google Queries

The Journal of Quirky Carpet Studies

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, just make it sound clever.

Your research team used data from Bureau of Larbor Statistics and Google Trends to assess this nagging question. You found a correlation coefficient of -0.8145243 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The world of research often leads us down unexpected paths, and true to form, our study has taken an intriguing turn as we explore the peculiar relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body." The convergence of these two seemingly disparate elements has unveiled a correlation that defies conventional logic and beckons us to a whimsical dance of inquiry.

At first glance, one might ponder the connection between the soft, plush comfort of freshly laid carpets and the enigmatic quest for knowledge about concealing bodies. Is there an underlying metaphor in the depths of the Kentucky labor market that burrows beneath the fibers of this correlation? As we delve into the labyrinthine tapestry of association, we must not tread lightly, for beneath the surface lies a landscape ripe with quirks and quips that tease the bounds of statistical inquiry.

The data harnessed from the Bureau of Labor Statistics and Google Trends paint a remarkably distinctive picture, revealing a correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. So, what does this negative correlation signify? Does it point to a peculiar aversion to carpeted locales as potential hideaways for ne'er-do-wells? Or could it be indicative of a sudden surge in the cleanliness and upkeep of existing carpets, leaving little room for clandestine activities? These questions, though laden with a hint of facetiousness, lay the groundwork for a deeper excavation into the nuances of this unexpected linkage.

As researchers, we must move beyond the conventional and allow ourselves to be lured by the siren song of whimsy that whispers through the corridors of our findings. Perhaps, within this unusual coupling of seemingly unrelated subjects, there resides a fount of amusement and curiosity that urges us to embrace the unexpected with open arms and buoyant spirits. As we embark on this academic journey, let us be reminded that even in the most serious of pursuits, a sprinkle of lightheartedness can render the most enigmatic of correlations into a delightful intellectual romp.

With this perspective, we set the stage for a robust and laughter-laden exploration of the connective threads that weave through the world of carpet installation and the confounding inquiries of Google searchers. As the curtains rise on this whimsical saga, we endeavor to peel back the layers of statistical intrigue and embrace the peculiar, with an unwavering commitment to unraveling the knots of quirkiness that entwine our scholarly pursuits.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of research often leads us down unexpected paths, and true to form, our study has taken an intriguing turn as we explore the peculiar relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body." The convergence of these two seemingly disparate elements has unveiled a correlation that defies conventional logic and beckons us to a whimsical dance of inquiry.
At first glance, one might ponder the connection between the soft, plush comfort of freshly laid carpets and the enigmatic quest for knowledge about concealing bodies. Is there an underlying metaphor in the depths of the Kentucky labor market that burrows beneath the fibers of this correlation? As we delve into the labyrinthine tapestry of association, we must not tread lightly, for beneath the surface lies a landscape ripe with quirks and quips that tease the bounds of statistical inquiry.
The data harnessed from the Bureau of Labor Statistics and Google Trends paint a remarkably distinctive picture, revealing a correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. So, what does this negative correlation signify? Does it point to a peculiar aversion to carpeted locales as potential hideaways for ne'er-do-wells? Or could it be indicative of a sudden surge in the cleanliness and upkeep of existing carpets, leaving little room for clandestine activities? These questions, though laden with a hint of facetiousness, lay the groundwork for a deeper excavation into the nuances of this unexpected linkage.
As researchers, we must move beyond the conventional and allow ourselves to be lured by the siren song of whimsy that whispers through the corridors of our findings. Perhaps, within this unusual coupling of seemingly unrelated subjects, there resides a fount of amusement and curiosity that urges us to embrace the unexpected with open arms and buoyant spirits. As we embark on this academic journey, let us be reminded that even in the most serious of pursuits, a sprinkle of lightheartedness can render the most enigmatic of correlations into a delightful intellectual romp.
With this perspective, we set the stage for a robust and laughter-laden exploration of the connective threads that weave through the world of carpet installation and the confounding inquiries of Google searchers. As the curtains rise on this whimsical saga, we endeavor to peel back the layers of statistical intrigue and embrace the peculiar, with an unwavering commitment to unraveling the knots of quirkiness that entwine our scholarly pursuits.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The curious correlation between the quantity of carpet installers in Kentucky and the prevalence of Google inquiries concerning "how to hide a body" has ignited a wave of fascination and bemusement within the realm of scholarly investigation. A plethora of previous studies have ventured into the realm of unlikely connections, prompting a blend of the earnest and the absurd. Smith and Doe (2015) delved into the idiosyncrasies of labor trends, paralleling them with unforeseen societal phenomena, unwittingly igniting the spark of curiosity that has now culminated in our present inquiry. Jones et al. (2019) veered precariously close to the borders of statistical absurdity, hinting at potential correlations between occupational cohorts and unsuspecting online quests, laying the foundation for the playful ponderings that we embark upon.

Stepping into the realm of theoretical grounding, "The Art of Deception" by Kevin D. Mitnick and William L. Simon (2002) presents a tangentially connected exploration into the clandestine world of covert activities, providing the perfect backdrop for our whimsical musings. Equally, "The Carpet People" by Terry Pratchett (1971) offers a fictitious journey across a landscape of woven wonder, much akin to the labyrinthine pathways we tread in our quest for correlation curiosities. Furthermore, the episodic intrigue of programs such as "How to Get Away with Murder" and "Dexter" has provided a quirky window into the enigmatic allure of subterfuge and concealment, fostering a spirit of mirthful contemplation within the folds of our scholarly pursuits.

As we navigate the realm of scholarly inquiries and fictitious fantasies, we stand at the precipice of enlightenment and entertainment, poised to uncover the jovial undertones that lurk within the seemingly solemn world of statistical association. It is with a light-hearted resolve and a twinkle in our eye that we traverse this labyrinth of academic inquiry, drawing from a spectrum of sources that underscore the joviality woven into the fabric of our research pursuits.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. 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 Bureau of Larbor Statistics 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

[[INTRODUCTION]]
The world of research often leads us down unexpected paths, and true to form, our study has taken an intriguing turn as we explore the peculiar relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body." The convergence of these two seemingly disparate elements has unveiled a correlation that defies conventional logic and beckons us to a whimsical dance of inquiry.
At first glance, one might ponder the connection between the soft, plush comfort of freshly laid carpets and the enigmatic quest for knowledge about concealing bodies. Is there an underlying metaphor in the depths of the Kentucky labor market that burrows beneath the fibers of this correlation? As we delve into the labyrinthine tapestry of association, we must not tread lightly, for beneath the surface lies a landscape ripe with quirks and quips that tease the bounds of statistical inquiry.
The data harnessed from the Bureau of Labor Statistics and Google Trends paint a remarkably distinctive picture, revealing a correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. So, what does this negative correlation signify? Does it point to a peculiar aversion to carpeted locales as potential hideaways for ne'er-do-wells? Or could it be indicative of a sudden surge in the cleanliness and upkeep of existing carpets, leaving little room for clandestine activities? These questions, though laden with a hint of facetiousness, lay the groundwork for a deeper excavation into the nuances of this unexpected linkage.
As researchers, we must move beyond the conventional and allow ourselves to be lured by the siren song of whimsy that whispers through the corridors of our findings. Perhaps, within this unusual coupling of seemingly unrelated subjects, there resides a fount of amusement and curiosity that urges us to embrace the unexpected with open arms and buoyant spirits. As we embark on this academic journey, let us be reminded that even in the most serious of pursuits, a sprinkle of lightheartedness can render the most enigmatic of correlations into a delightful intellectual romp.
With this perspective, we set the stage for a robust and laughter-laden exploration of the connective threads that weave through the world of carpet installation and the confounding inquiries of Google searchers. As the curtains rise on this whimsical saga, we endeavor to peel back the layers of statistical intrigue and embrace the peculiar, with an unwavering commitment to unraveling the knots of quirkiness that entwine our scholarly pursuits.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic relationship between the workforce of carpet installers in the captivating expanse of Kentucky and the inscrutable phenomenon of Google queries regarding body concealment, our research team embarked on a convoluted expedition through the data wilderness. With a blend of pragmatism and whimsy, we utilized data sourced from the hallowed halls of the Bureau of Labor Statistics and the labyrinthine corridors of Google Trends. Our journey through the digital realm spanned the inconceivable years from 2004 to 2022, capturing a tapestry of statistical whispers and enigmatic trends.

The Bureau of Labor Statistics served as our guide through the undulating terrain of employment figures, providing a robust dataset mapping the ebbs and flows of carpet installation labor force in the state of Kentucky. With their revered archives at our disposal, we meticulously charted the rise and fall of laborers in this oft-overlooked niche, seeking the glimmers of correlation that might lead us to the heart of this mysterious linkage.

Simultaneously, our intrepid expedition ventured across Google Trends, navigating through the cacophony of digital footprints left by the seekers of information, weaving a tale of peculiar quests for knowledge about clandestine practices. We diligently harvested data on Google searches for "how to hide a body," capturing the ebb and flow of these perplexing inquiries over the selected temporal expanse.

The call for data triangulation echoed through the archways of our research citadel, driving us to merge these disparate datasets into a harmonious ensemble. Armed with the potent elixir of statistical software, we took our primordial findings and stirred them into a heady brew of correlation analyses. A dance with numbers ensued, bringing to light the significant correlation coefficient of -0.8145243 and p < 0.01 woven into the very fabric of our discoveries.

With a mischievous twinkle in our eyes, we undertook sensitivity analyses and outlier examinations, mindful of the capricious nature of statistical relationships. For through this arcane pursuit of linkages between linear and non-linear associations, we intended to unearth the gems of insight hidden within the folds of the correlation matrix.

The empirical terrain of this study came alive with the peculiar machinations of our research methodologies, offering a whimsical juxtaposition of measured inquiry and mirthful revelry. In the tangled webs of obscure correlations, we sought not only the solemn visage of scholarly rigor but also the glimmering mirth that can illuminate even the most shadowed of statistical landscapes.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. 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 Bureau of Larbor Statistics and Google Trends .

For the time period 2004 to 2022, you found a correlation -0.8145243, r-squared of 0.6634499, 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The world of research often leads us down unexpected paths, and true to form, our study has taken an intriguing turn as we explore the peculiar relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body." The convergence of these two seemingly disparate elements has unveiled a correlation that defies conventional logic and beckons us to a whimsical dance of inquiry.
At first glance, one might ponder the connection between the soft, plush comfort of freshly laid carpets and the enigmatic quest for knowledge about concealing bodies. Is there an underlying metaphor in the depths of the Kentucky labor market that burrows beneath the fibers of this correlation? As we delve into the labyrinthine tapestry of association, we must not tread lightly, for beneath the surface lies a landscape ripe with quirks and quips that tease the bounds of statistical inquiry.
The data harnessed from the Bureau of Labor Statistics and Google Trends paint a remarkably distinctive picture, revealing a correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. So, what does this negative correlation signify? Does it point to a peculiar aversion to carpeted locales as potential hideaways for ne'er-do-wells? Or could it be indicative of a sudden surge in the cleanliness and upkeep of existing carpets, leaving little room for clandestine activities? These questions, though laden with a hint of facetiousness, lay the groundwork for a deeper excavation into the nuances of this unexpected linkage.
As researchers, we must move beyond the conventional and allow ourselves to be lured by the siren song of whimsy that whispers through the corridors of our findings. Perhaps, within this unusual coupling of seemingly unrelated subjects, there resides a fount of amusement and curiosity that urges us to embrace the unexpected with open arms and buoyant spirits. As we embark on this academic journey, let us be reminded that even in the most serious of pursuits, a sprinkle of lightheartedness can render the most enigmatic of correlations into a delightful intellectual romp.
With this perspective, we set the stage for a robust and laughter-laden exploration of the connective threads that weave through the world of carpet installation and the confounding inquiries of Google searchers. As the curtains rise on this whimsical saga, we endeavor to peel back the layers of statistical intrigue and embrace the peculiar, with an unwavering commitment to unraveling the knots of quirkiness that entwine our scholarly pursuits.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

Our foray into the unexpected wonderland of statistical correlations has yielded compelling results that are bound to raise eyebrows and elicit a chuckle or two. Behold, a correlation coefficient of -0.8145243 and an r-squared value of 0.6634499, accompanied by a p-value of less than 0.01, all pointing to a significant and robust relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body" from 2004 to 2022.

Upon gazing at Fig. 1, the scatterplot showcasing the undeniable negative correlation between these two seemingly incongruous variables, one cannot help but marvel at the whimsical dance of data that unfolds before our eyes. With each data point, a tale unfolds—perhaps a freshly laid Persian carpet or a meticulously hidden search history, embroiled in a comical tango of association.

The negative correlation indicates a curious trend: as the ranks of carpet installers swelled, the quest for knowledge regarding body concealment experienced a proportional downturn. Does this suggest a newfound emphasis on the integrity of flooring, leaving little space for clandestine activity? Or does it hint at a possible preference for more open, uncarpeted spaces among certain online enquirers? These are but a few of the amusing reflections this correlation conjures, inviting us on a merry carousel of contemplation and levity in the realm of data analysis.

The unexpected link between the unfurling of carpets and the curiosity about the act of concealment is rife with subtle nuances and unmistakable humor. It prompts a bemused examination of the peculiar threads that weave through the fabric of our scholarly pursuits, shrouding even the most solemn statistics in a cloak of wit and fanciful speculation.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

[[LITERATURE REVIEW]]
The curious correlation between the quantity of carpet installers in Kentucky and the prevalence of Google inquiries concerning "how to hide a body" has ignited a wave of fascination and bemusement within the realm of scholarly investigation. A plethora of previous studies have ventured into the realm of unlikely connections, prompting a blend of the earnest and the absurd. Smith and Doe (2015) delved into the idiosyncrasies of labor trends, paralleling them with unforeseen societal phenomena, unwittingly igniting the spark of curiosity that has now culminated in our present inquiry. Jones et al. (2019) veered precariously close to the borders of statistical absurdity, hinting at potential correlations between occupational cohorts and unsuspecting online quests, laying the foundation for the playful ponderings that we embark upon.
Stepping into the realm of theoretical grounding, "The Art of Deception" by Kevin D. Mitnick and William L. Simon (2002) presents a tangentially connected exploration into the clandestine world of covert activities, providing the perfect backdrop for our whimsical musings. Equally, "The Carpet People" by Terry Pratchett (1971) offers a fictitious journey across a landscape of woven wonder, much akin to the labyrinthine pathways we tread in our quest for correlation curiosities. Furthermore, the episodic intrigue of programs such as "How to Get Away with Murder" and "Dexter" has provided a quirky window into the enigmatic allure of subterfuge and concealment, fostering a spirit of mirthful contemplation within the folds of our scholarly pursuits.
As we navigate the realm of scholarly inquiries and fictitious fantasies, we stand at the precipice of enlightenment and entertainment, poised to uncover the jovial undertones that lurk within the seemingly solemn world of statistical association. It is with a light-hearted resolve and a twinkle in our eye that we traverse this labyrinth of academic inquiry, drawing from a spectrum of sources that underscore the joviality woven into the fabric of our research pursuits.

[[RESULTS]]
Our foray into the unexpected wonderland of statistical correlations has yielded compelling results that are bound to raise eyebrows and elicit a chuckle or two. Behold, a correlation coefficient of -0.8145243 and an r-squared value of 0.6634499, accompanied by a p-value of less than 0.01, all pointing to a significant and robust relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body" from 2004 to 2022.
Upon gazing at Fig. 1, the scatterplot showcasing the undeniable negative correlation between these two seemingly incongruous variables, one cannot help but marvel at the whimsical dance of data that unfolds before our eyes. With each data point, a tale unfolds—perhaps a freshly laid Persian carpet or a meticulously hidden search history, embroiled in a comical tango of association.
The negative correlation indicates a curious trend: as the ranks of carpet installers swelled, the quest for knowledge regarding body concealment experienced a proportional downturn. Does this suggest a newfound emphasis on the integrity of flooring, leaving little space for clandestine activity? Or does it hint at a possible preference for more open, uncarpeted spaces among certain online enquirers? These are but a few of the amusing reflections this correlation conjures, inviting us on a merry carousel of contemplation and levity in the realm of data analysis.
The unexpected link between the unfurling of carpets and the curiosity about the act of concealment is rife with subtle nuances and unmistakable humor. It prompts a bemused examination of the peculiar threads that weave through the fabric of our scholarly pursuits, shrouding even the most solemn statistics in a cloak of wit and fanciful speculation.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The revelation of a robust negative correlation between the number of carpet installers in Kentucky and Google searches for "how to hide a body" adds a whimsical twist to the tapestry of statistical inquiry. Our findings stand as a testament to the unlikely interplay between seemingly unrelated variables, inviting contemplation and laughter in equal measure. It seems that as the carpeting clamor increased, a decline in surreptitious searches ensued, leaving us to ponder the curious machinations of human behavior in the digital age.

Drawing from the literature review, the zany musings of previous researchers have found an unexpected resonance in our current investigation. Smith and Doe’s exploration of labor trends unwittingly stoked the embers of curiosity, which we have now fanned into a merry blaze of statistical revelry. Jones et al.'s daring dance along the precipice of statistical absurdity now seems to have landed on the solid ground of our substantial correlation. It becomes clear that our findings have provided empirical support for the flirtations with statistical whimsy that have characterized prior research endeavors.

As we reflect on the serendipitous parallels between our work and the tangentially connected realms of subterfuge and whimsy, it becomes apparent that our study has borne unexpected fruit. The literary jaunt through "The Carpet People" by Terry Pratchett serves as a metaphorical jaunt through the yarns of our statistical regression, revealing hidden patterns in the seemingly mundane. Just as Mitnick and Simon’s exploration illuminated the clandestine arts, our work uncovers the cryptic patterns woven into the digital fabric of online inquiry.

The chatter of hidden jokes and puns we have interspersed throughout our academic tapestry infuses the rugged contours of our results with a playful spirit. These lighthearted asides add color to the otherwise somber dance of statistical inference, allowing us to revel in the mirthful undercurrents that bubble beneath the surface of our scholarly enterprise.

In traversing the labyrinth of our findings, we have not only uncovered a compelling correlation but also unveiled the mirthful enticements that beckon from the periphery of our academic pursuits. Our work stands as a testament to the unpredictable jaunt that is statistical investigation, reminding us of the joviality that often lies concealed within the serious pursuit of knowledge.


Model: gpt-3.5-turbo-1106
System prompt: You are a researcher writing an academic paper.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 The number of carpet installers in Kentucky and Google searches for 'how to hide a body'. 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]]
Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and "How to Hide a Body" Google Queries

[[ABSTRACT]]
This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

[[INTRDUCTION]]
The world of research often leads us down unexpected paths, and true to form, our study has taken an intriguing turn as we explore the peculiar relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body." The convergence of these two seemingly disparate elements has unveiled a correlation that defies conventional logic and beckons us to a whimsical dance of inquiry.
At first glance, one might ponder the connection between the soft, plush comfort of freshly laid carpets and the enigmatic quest for knowledge about concealing bodies. Is there an underlying metaphor in the depths of the Kentucky labor market that burrows beneath the fibers of this correlation? As we delve into the labyrinthine tapestry of association, we must not tread lightly, for beneath the surface lies a landscape ripe with quirks and quips that tease the bounds of statistical inquiry.
The data harnessed from the Bureau of Labor Statistics and Google Trends paint a remarkably distinctive picture, revealing a correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. So, what does this negative correlation signify? Does it point to a peculiar aversion to carpeted locales as potential hideaways for ne'er-do-wells? Or could it be indicative of a sudden surge in the cleanliness and upkeep of existing carpets, leaving little room for clandestine activities? These questions, though laden with a hint of facetiousness, lay the groundwork for a deeper excavation into the nuances of this unexpected linkage.
As researchers, we must move beyond the conventional and allow ourselves to be lured by the siren song of whimsy that whispers through the corridors of our findings. Perhaps, within this unusual coupling of seemingly unrelated subjects, there resides a fount of amusement and curiosity that urges us to embrace the unexpected with open arms and buoyant spirits. As we embark on this academic journey, let us be reminded that even in the most serious of pursuits, a sprinkle of lightheartedness can render the most enigmatic of correlations into a delightful intellectual romp.
With this perspective, we set the stage for a robust and laughter-laden exploration of the connective threads that weave through the world of carpet installation and the confounding inquiries of Google searchers. As the curtains rise on this whimsical saga, we endeavor to peel back the layers of statistical intrigue and embrace the peculiar, with an unwavering commitment to unraveling the knots of quirkiness that entwine our scholarly pursuits.

[[RESULTS]]
Our foray into the unexpected wonderland of statistical correlations has yielded compelling results that are bound to raise eyebrows and elicit a chuckle or two. Behold, a correlation coefficient of -0.8145243 and an r-squared value of 0.6634499, accompanied by a p-value of less than 0.01, all pointing to a significant and robust relationship between the number of carpet installers in Kentucky and the Google searches for "how to hide a body" from 2004 to 2022.
Upon gazing at Fig. 1, the scatterplot showcasing the undeniable negative correlation between these two seemingly incongruous variables, one cannot help but marvel at the whimsical dance of data that unfolds before our eyes. With each data point, a tale unfolds—perhaps a freshly laid Persian carpet or a meticulously hidden search history, embroiled in a comical tango of association.
The negative correlation indicates a curious trend: as the ranks of carpet installers swelled, the quest for knowledge regarding body concealment experienced a proportional downturn. Does this suggest a newfound emphasis on the integrity of flooring, leaving little space for clandestine activity? Or does it hint at a possible preference for more open, uncarpeted spaces among certain online enquirers? These are but a few of the amusing reflections this correlation conjures, inviting us on a merry carousel of contemplation and levity in the realm of data analysis.
The unexpected link between the unfurling of carpets and the curiosity about the act of concealment is rife with subtle nuances and unmistakable humor. It prompts a bemused examination of the peculiar threads that weave through the fabric of our scholarly pursuits, shrouding even the most solemn statistics in a cloak of wit and fanciful speculation.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our pursuit of the unexpected correlation between the number of carpet installers in Kentucky and Google searches for "how to hide a body" has led us through a whimsical maze of statistical musings. The robust negative correlation coefficient and significant p-value unearthed from our analysis present an incongruous liaison between the practical world of carpet fitting and the enigmatic curiosity of online searches. The comical tango of association revealed by our findings invites us to ponder the quirky nuances of this unlikely pairing, provoking a merry carousel of contemplation and levity in the realm of data analysis.

As we bid adieu to this amusing escapade, it is worth noting that while our study sheds light on the unexpected relationship, it leaves a myriad of questions unexplored. What other peculiar connections lie buried within the convoluted pathways of statistical data? Are there more unsuspecting correlations waiting to be unraveled, lending a touch of levity and intrigue to the seemingly mundane? The whimsical tapestry of statistical inquiry never fails to surprise, offering a treasure trove of unexpected unions waiting to be unearthed.

Alas, for now, we must bid adieu to the curious coupling of carpet installers and clandestine inquiries, for our findings, though laced with amusement, spearhead a compelling adieu to any further research in this unconventional confluence. Let us part with a chuckle and a nod, knowing that even in the most rigorous of academic pursuits, a dash of whimsy can transform the most enigmatic of discoveries into a delightful intellectual romp.


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 Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and How to Hide a Body Google Queries. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Carpet Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and How to Hide a Body Google Queries. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Carpetology and Cryptic Inquiries


Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Rug-ratios and Mysterious Searches: Exploring the Relationship Between Carpet Installers in Kentucky and How to Hide a Body Google Queries with an abstract of This study delves into the connection between the labor force of carpet installers in the beautiful state of Kentucky and the peculiar choice of Google searches for "how to hide a body." Leveraging data from the Bureau of Labor Statistics and Google Trends, an unexpected correlation has been found. Our research reveals a significant correlation coefficient of -0.8145243 and p < 0.01 from 2004 to 2022. The noteworthy negative correlation suggests that as the number of carpet installers increases, there is a decrease in searches for the rather dubious topic related to body concealment. These findings raise more questions than answers and propel us into a maze of perplexing musings. Whispers of innuendo and carpeted complications flow through these unexpected results, inviting a spectacle of curiosity and intrigue in the seemingly mundane world of carpet fitting. This study sets the stage for laughter, a merry trot through the field of data, and a toe-dip into the perplexing realm of online inquiries – all with the hope of uncovering humor in the statistical tapestry of life.

ChatGPT:

Kentucky, carpet installers, Google searches, how to hide a body, correlation, Bureau of Labor Statistics, Google Trends, correlation coefficient, data analysis

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

The number of carpet installers in Kentucky
Detailed data title: BLS estimate of carpet installers in Kentucky
Source: Bureau of Larbor Statistics
See what else correlates with The number of carpet installers in Kentucky

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 = -0.8145243 (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 = 0.6634499 (Coefficient of determination)
This means 66.3% 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., The number of carpet installers in Kentucky) over the 19 years from 2004 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.2E-5. 0.0000217960388761713000000000
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 -0.81 in 0.0022% of random cases. Said differently, if you correlated 45,880 random variables You don't actually need 45 thousand variables to find a correlation like this one. You can also correlate variables that are not independent. I do this a lot.

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 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.

[ -0.93, -0.57 ] 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
The number of carpet installers in Kentucky (Carpet Installers)300320290260260300240260160140140150250170210170280160160
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.
  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.
  5. Inverted Y-axis: I inverted the Y-axis on the chart above so that the lines would move together. This is visually pleasing, but not at all intuitive. Below is a line graph that does not invert the Y-axis.




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([300,320,290,260,260,300,240,260,160,140,140,150,250,170,210,170,280,160,160,])
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 = "The number of carpet installers in Kentucky"
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?

Your rating skills are top-notch!


Correlation ID: 1289 · Black Variable ID: 8528 · Red Variable ID: 1513
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0