about · email me · subscribe
Spurious correlation #4,334 · 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 housekeepers in West Virginia and the second variable is Total comments on SciShow Space YouTube videos.  The chart goes from 2014 to 2022, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

It seems that as the number of housekeepers in West Virginia dwindles, there's a corresponding decrease in the state's clean energy output. This is leading to a spacey situation where the Total comments on SciShow Space YouTube videos are on a downward trajectory. It's a real cosmic coincidence, but it just goes to show that when it comes to sparking discussions about the universe, cleanliness is next to godliness.

Model: dalle-3
Prompt: [ An image that looks like it is a scene from a Pixar movie ] Create a visual representation of the following: In a vibrant and whimsical scene, two animated graphs come to life in a charmingly abstract manner. On the left, a graph gracefully tapers downwards, depicting the decreasing number of housekeepers in West Virginia. On the right, a companion graph mirrors the downward trend, portraying the declining total comments on SciShow Space YouTube videos. The graphs are artistically connected by a meandering path, adorned with enchanting imagery of wind turbines, solar panels, and other diverse clean energy sources. As the path winds from one graph to the other, the images seamlessly morph into captivating space-themed elements, such as planets, stars, and rockets, symbolizing the diminishing cosmic discussions on SciShow Space. The entire scene radiates an aura of nostalgia, hope, and interconnectedness, effectively capturing the poignant impact of the decrease in housekeepers on clean energy and cosmic exploration. 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: The number of housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. 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: An image that looks like it is a scene from a Pixar movie Charcoal Cubism Oragami Concept art
ChatGPT: An image that looks like it is a scene from a Pixar movie

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 The number of housekeepers in West Virginia and Total comments on SciShow Space YouTube videos, in the following situation: It seems that as the number of housekeepers in West Virginia dwindles, there's a corresponding decrease in the state's clean energy output. This is leading to a spacey situation where the Total comments on SciShow Space YouTube videos are on a downward trajectory. It's a real cosmic coincidence, but it just goes to show that when it comes to sparking discussions about the universe, cleanliness is next to godliness.. Keep the description simple.
ChatGPT: In a simple visual scene, we see a graph showing the decreasing number of housekeepers in West Virginia on one side. On the other side, we see a graph depicting the declining total comments on SciShow Space YouTube videos. The two graphs are connected by a winding path, and along this path, we see images of clean energy sources and space-themed comments slowly fading away. The scene symbolizes how the decrease in housekeepers is leading to a decline in clean energy output, ultimately affecting the cosmic discussions on SciShow Space.

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: [ An image that looks like it is a scene from a Pixar movie ] and depicting this scene: In a simple visual scene, we see a graph showing the decreasing number of housekeepers in West Virginia on one side. On the other side, we see a graph depicting the declining total comments on SciShow Space YouTube videos. The two graphs are connected by a winding path, and along this path, we see images of clean energy sources and space-themed comments slowly fading away. The scene symbolizes how the decrease in housekeepers is leading to a decline in clean energy output, ultimately affecting the cosmic discussions on SciShow Space. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ An image that looks like it is a scene from a Pixar movie ] Create a visual representation of the following: In a vibrant and whimsical scene, two animated graphs come to life in a charmingly abstract manner. On the left, a graph gracefully tapers downwards, depicting the decreasing number of housekeepers in West Virginia. On the right, a companion graph mirrors the downward trend, portraying the declining total comments on SciShow Space YouTube videos. The graphs are artistically connected by a meandering path, adorned with enchanting imagery of wind turbines, solar panels, and other diverse clean energy sources. As the path winds from one graph to the other, the images seamlessly morph into captivating space-themed elements, such as planets, stars, and rockets, symbolizing the diminishing cosmic discussions on SciShow Space. The entire scene radiates an aura of nostalgia, hope, and interconnectedness, effectively capturing the poignant impact of the decrease in housekeepers on clean energy and cosmic exploration.

*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 housekeepers in West Virginia caused Total comments on SciShow Space YouTube videos to decrease. Include one good pun.

AI academic paper

(Because p < 0.01)
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

The International Journal of Domestic Hygiene and Astrophysical Anecdotes

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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns.

Make the title an alliteration.

Your research team used data from Bureau of Larbor Statistics and YouTube to assess this nagging question. You found a correlation coefficient of 0.9633028 and p < 0.01 for 2014 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]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Here is the title and abstract of the paper:
[[TITLE]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

"Cleanliness is next to godliness," or so the saying goes. But who would have thought that the number of housekeepers in West Virginia could also be next to an abundance of comments on SciShow Space YouTube videos? In this unprecedented study, we explore the unexpected correlation between the seemingly mundane occupation of housekeeping and the virtual chatter unfolding in the comment sections of popular science videos.

The notion of connecting the act of mopping and vacuuming with the discussions of astrophysics and space exploration may seem as far-fetched as finding a vacuum cleaner on the moon. However, our findings unravel a correlation so strong, even a stubborn stain would be impressed. We delve into the uncharted territory where the domestic and the digital intersect, scrubbing away the dirt of misconceptions and exposing the gleaming linoleum of statistical significance.

As we embark on this unique investigation, it is essential to recognize that correlation does not imply causation; however, it certainly does raise some eyebrows, much like discovering a stray sock stuffed behind the sofa. With a correlation coefficient of 0.9633028 (p < 0.01) for the years 2014 to 2022, we are faced with a relationship so striking, it makes the bond between electrons and protons seem positively lukewarm in comparison.

Through this study, we aim to dust off the presumptions that only cutting-edge, futuristic topics trigger online engagement, and to illuminate the curious ways in which seemingly mundane variables can unexpectedly influence virtual interactions. Now, without further ado, let's roll up our sleeves, don our research gloves, and embark on a journey to uncover the surprising correlations between housekeeping and high-engagement YouTube discussions.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
"Cleanliness is next to godliness," or so the saying goes. But who would have thought that the number of housekeepers in West Virginia could also be next to an abundance of comments on SciShow Space YouTube videos? In this unprecedented study, we explore the unexpected correlation between the seemingly mundane occupation of housekeeping and the virtual chatter unfolding in the comment sections of popular science videos.
The notion of connecting the act of mopping and vacuuming with the discussions of astrophysics and space exploration may seem as far-fetched as finding a vacuum cleaner on the moon. However, our findings unravel a correlation so strong, even a stubborn stain would be impressed. We delve into the uncharted territory where the domestic and the digital intersect, scrubbing away the dirt of misconceptions and exposing the gleaming linoleum of statistical significance.
As we embark on this unique investigation, it is essential to recognize that correlation does not imply causation; however, it certainly does raise some eyebrows, much like discovering a stray sock stuffed behind the sofa. With a correlation coefficient of 0.9633028 (p < 0.01) for the years 2014 to 2022, we are faced with a relationship so striking, it makes the bond between electrons and protons seem positively lukewarm in comparison.
Through this study, we aim to dust off the presumptions that only cutting-edge, futuristic topics trigger online engagement, and to illuminate the curious ways in which seemingly mundane variables can unexpectedly influence virtual interactions. Now, without further ado, let's roll up our sleeves, don our research gloves, and embark on a journey to uncover the surprising correlations between housekeeping and high-engagement YouTube discussions.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.," the authors find an intricate correlation between occupational demographics and online engagement, shedding light on the unexpected relationships that can emerge from the clutter of statistical data. Similarly, "Doe and Jones" offer insights into the subtle interplay between state-specific employment trends and virtual interactive behaviors, paving the way for our exploration of the seemingly preposterous links between housekeepers in West Virginia and the fervent discussions swirling around SciShow Space YouTube videos.

Further reinforcing the relevance of seemingly mundane occupations in the digital milieu, "The Power of Cleaning: How Tidying Up Transforms Lives" by Kondo presents a compelling argument about the transformative power of household chores, perhaps hinting at a deeper connection to the virtual universe. Additionally, "The Cosmic Cleanse: Decluttering Your Space for Stellar Enlightenment" by Stardust delves into the cosmic implications of tidiness, providing an unexpectedly celestial perspective on the domestic duties that may foreshadow the connection with online engagement.

Venturing into the realm of fiction, the epic tale "The Vacuum Chronicles: A Saga of Space Dust and Hyperspace Housekeeping" by Nebula captures the imagination with its improbable narrative, hinting at a cosmic ballet of household cleaning influencing the far reaches of the galaxy. In a similar vein, "The Cleaning Comet: A Sci-Fi Adventure of Maid Robots and Interstellar Tidying" by Sparkle weaves a whimsical yarn that toys with the notion of household chores shaping the destiny of intergalactic communities, mirroring the surprising correlations we have uncovered.

Beyond the traditional confines of academic literature, our investigation reaches further into the unexplored territories of unconventional data sources. In a bold departure from convention, we scoured the cryptic codes of CVS receipts, seeking hidden messages and subtle clues that could shine a light on the unexpected nexus between housekeepers in West Virginia and the reverberating echo within the virtual halls of scientific discourse. While this unorthodox approach may raise some eyebrows, it underscores our commitment to peeling back the layers of absurdity in pursuit of groundbreaking revelations.

As we navigate through the labyrinthine corridors of literature, the unexpected correlations between the mundane and the virtual shimmer like a freshly polished marble floor, challenging our preconceived notions and inviting us to embrace the whimsy that may lie beneath the surface of seemingly ordinary phenomena.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and YouTube . You used data from 2014 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]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

[[INTRODUCTION]]
"Cleanliness is next to godliness," or so the saying goes. But who would have thought that the number of housekeepers in West Virginia could also be next to an abundance of comments on SciShow Space YouTube videos? In this unprecedented study, we explore the unexpected correlation between the seemingly mundane occupation of housekeeping and the virtual chatter unfolding in the comment sections of popular science videos.
The notion of connecting the act of mopping and vacuuming with the discussions of astrophysics and space exploration may seem as far-fetched as finding a vacuum cleaner on the moon. However, our findings unravel a correlation so strong, even a stubborn stain would be impressed. We delve into the uncharted territory where the domestic and the digital intersect, scrubbing away the dirt of misconceptions and exposing the gleaming linoleum of statistical significance.
As we embark on this unique investigation, it is essential to recognize that correlation does not imply causation; however, it certainly does raise some eyebrows, much like discovering a stray sock stuffed behind the sofa. With a correlation coefficient of 0.9633028 (p < 0.01) for the years 2014 to 2022, we are faced with a relationship so striking, it makes the bond between electrons and protons seem positively lukewarm in comparison.
Through this study, we aim to dust off the presumptions that only cutting-edge, futuristic topics trigger online engagement, and to illuminate the curious ways in which seemingly mundane variables can unexpectedly influence virtual interactions. Now, without further ado, let's roll up our sleeves, don our research gloves, and embark on a journey to uncover the surprising correlations between housekeeping and high-engagement YouTube discussions.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To conduct our groundbreaking investigation into the relationship between the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos, our research team embarked on a quest for data that would clean up any lingering doubts about the validity of our findings. We meticulously gathered information from a variety of sources, meticulously sifting through the digital detritus to ensure our results were as squeaky-clean as possible.

First, we turned to the Bureau of Labor Statistics to obtain comprehensive data on the number of employed housekeepers in West Virginia from 2014 to 2022. We meticulously scrubbed through the BLS database, ensuring that no statistical crumbs were left unturned in our pursuit of this crucial variable. After this painstaking process, we emerged with a sparkling dataset that provided a robust foundation for our investigation into the domestic side of our correlation.

Next, we set our sights on the expansive realm of YouTube, diving deep into the comment sections of SciShow Space videos to tally the total engagement in the form of comments. This involved a significant amount of digital dusting, as we combed through countless comments to ensure accuracy and completeness in our data collection. Much like diligent housekeepers tending to every nook and cranny, we left no comment uncounted in our mission to illuminate the intriguing relationship between domestic occupations and digital discourse.

After meticulously gathering the requisite data, we deployed our array of statistical tools to analyze the correlations between these seemingly disparate variables. Donning our metaphorical lab coats, we engaged in a rigorous process of data cleaning, statistical modeling, and correlation analysis to ensure that our findings were upheld to the highest standards of scholarly cleanliness. Through this meticulous process, we uncovered a correlation coefficient so striking that it could mop the floor with the conventional wisdom about the relationship between mundane occupations and online engagement.

In addition to our quantitative analysis, we delved into qualitative factors that may contribute to the unexpected correlation between housekeeping and YouTube engagement. This involved engaging in lively discussions and conjectures among our research team, as we explored potential explanations for this seemingly improbable connection. While some may view our qualitative analysis as akin to searching for lost socks under the bed, we approached this aspect of the research with the same level of dedication and scrutiny as the rest of our methodology.

Through this multifaceted approach, we endeavored to achieve a level of rigour and thoroughness befitting such an unexpected and captivating research question. Our methodology stands as a testament to the stringent standards of academic investigation, even when the subject matter may initially appear as unlikely as finding a vacuum cleaner on the lunar surface.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and YouTube .

For the time period 2014 to 2022, you found a correlation 0.9633028, r-squared of 0.9279523, 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]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
"Cleanliness is next to godliness," or so the saying goes. But who would have thought that the number of housekeepers in West Virginia could also be next to an abundance of comments on SciShow Space YouTube videos? In this unprecedented study, we explore the unexpected correlation between the seemingly mundane occupation of housekeeping and the virtual chatter unfolding in the comment sections of popular science videos.
The notion of connecting the act of mopping and vacuuming with the discussions of astrophysics and space exploration may seem as far-fetched as finding a vacuum cleaner on the moon. However, our findings unravel a correlation so strong, even a stubborn stain would be impressed. We delve into the uncharted territory where the domestic and the digital intersect, scrubbing away the dirt of misconceptions and exposing the gleaming linoleum of statistical significance.
As we embark on this unique investigation, it is essential to recognize that correlation does not imply causation; however, it certainly does raise some eyebrows, much like discovering a stray sock stuffed behind the sofa. With a correlation coefficient of 0.9633028 (p < 0.01) for the years 2014 to 2022, we are faced with a relationship so striking, it makes the bond between electrons and protons seem positively lukewarm in comparison.
Through this study, we aim to dust off the presumptions that only cutting-edge, futuristic topics trigger online engagement, and to illuminate the curious ways in which seemingly mundane variables can unexpectedly influence virtual interactions. Now, without further ado, let's roll up our sleeves, don our research gloves, and embark on a journey to uncover the surprising correlations between housekeeping and high-engagement YouTube discussions.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The correlation analysis between the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos revealed a remarkably robust relationship, defying expectations like a vacuum cleaner able to recite the periodic table.

The correlation coefficient of 0.9633028 and an r-squared value of 0.9279523 signify a connection so strong that it could practically sweep you off your feet. With a p-value of less than 0.01, this correlation isn't just a speck of dust in the wind; it's a statistical hurricane wreaking havoc on our assumptions.

Upon visual inspection, the scatterplot (Fig. 1) depicts a trend so clear, it's as if the dust bunnies have finally organized themselves into a coherent pattern. The upward trajectory of the data points suggests that as the number of housekeepers in West Virginia rises, so does the level of engagement in the comment section of SciShow Space YouTube videos, leaving us to wonder if the secret to captivating online discussions involves a well-polished household.

In keeping with the spirit of scientific inquiry, it's important to recognize that correlation does not imply causation. Nonetheless, our findings raise intriguing questions about the unexplored dynamics of online engagement and the unassuming influences that may play a role in shaping virtual interactions.

In essence, our results not only sweep away the cobwebs of conventional thinking but also highlight the unforeseen ways in which the most commonplace variables can wield surprising influence in the digital domain. This study serves as a bold reminder that in the realm of data analysis, even the most pedestrian factors can harbor unexpected and intriguing connections, much like finding a hidden treasure trove of discourse between the bottles of cleaning supplies.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

[[LITERATURE REVIEW]]
In "Smith et al.," the authors find an intricate correlation between occupational demographics and online engagement, shedding light on the unexpected relationships that can emerge from the clutter of statistical data. Similarly, "Doe and Jones" offer insights into the subtle interplay between state-specific employment trends and virtual interactive behaviors, paving the way for our exploration of the seemingly preposterous links between housekeepers in West Virginia and the fervent discussions swirling around SciShow Space YouTube videos.
Further reinforcing the relevance of seemingly mundane occupations in the digital milieu, "The Power of Cleaning: How Tidying Up Transforms Lives" by Kondo presents a compelling argument about the transformative power of household chores, perhaps hinting at a deeper connection to the virtual universe. Additionally, "The Cosmic Cleanse: Decluttering Your Space for Stellar Enlightenment" by Stardust delves into the cosmic implications of tidiness, providing an unexpectedly celestial perspective on the domestic duties that may foreshadow the connection with online engagement.
Venturing into the realm of fiction, the epic tale "The Vacuum Chronicles: A Saga of Space Dust and Hyperspace Housekeeping" by Nebula captures the imagination with its improbable narrative, hinting at a cosmic ballet of household cleaning influencing the far reaches of the galaxy. In a similar vein, "The Cleaning Comet: A Sci-Fi Adventure of Maid Robots and Interstellar Tidying" by Sparkle weaves a whimsical yarn that toys with the notion of household chores shaping the destiny of intergalactic communities, mirroring the surprising correlations we have uncovered.
Beyond the traditional confines of academic literature, our investigation reaches further into the unexplored territories of unconventional data sources. In a bold departure from convention, we scoured the cryptic codes of CVS receipts, seeking hidden messages and subtle clues that could shine a light on the unexpected nexus between housekeepers in West Virginia and the reverberating echo within the virtual halls of scientific discourse. While this unorthodox approach may raise some eyebrows, it underscores our commitment to peeling back the layers of absurdity in pursuit of groundbreaking revelations.
As we navigate through the labyrinthine corridors of literature, the unexpected correlations between the mundane and the virtual shimmer like a freshly polished marble floor, challenging our preconceived notions and inviting us to embrace the whimsy that may lie beneath the surface of seemingly ordinary phenomena.

[[RESULTS]]
The correlation analysis between the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos revealed a remarkably robust relationship, defying expectations like a vacuum cleaner able to recite the periodic table.
The correlation coefficient of 0.9633028 and an r-squared value of 0.9279523 signify a connection so strong that it could practically sweep you off your feet. With a p-value of less than 0.01, this correlation isn't just a speck of dust in the wind; it's a statistical hurricane wreaking havoc on our assumptions.
Upon visual inspection, the scatterplot (Fig. 1) depicts a trend so clear, it's as if the dust bunnies have finally organized themselves into a coherent pattern. The upward trajectory of the data points suggests that as the number of housekeepers in West Virginia rises, so does the level of engagement in the comment section of SciShow Space YouTube videos, leaving us to wonder if the secret to captivating online discussions involves a well-polished household.
In keeping with the spirit of scientific inquiry, it's important to recognize that correlation does not imply causation. Nonetheless, our findings raise intriguing questions about the unexplored dynamics of online engagement and the unassuming influences that may play a role in shaping virtual interactions.
In essence, our results not only sweep away the cobwebs of conventional thinking but also highlight the unforeseen ways in which the most commonplace variables can wield surprising influence in the digital domain. This study serves as a bold reminder that in the realm of data analysis, even the most pedestrian factors can harbor unexpected and intriguing connections, much like finding a hidden treasure trove of discourse between the bottles of cleaning supplies.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

Our findings lend credence to the notion that the housekeeping industry in West Virginia may hold more influence over digital discourse than previously suspected. While on the surface this correlation may appear as baffling as finding a mop in a spaceship, our results align with prior research in unexpected ways. The work of Smith et al. and Doe and Jones, which highlighted the intricate links between occupational demographics and online engagement, provided a theoretical foundation that our study seemingly effortlessly swept into. Not to mention the compelling narratives of "The Vacuum Chronicles" and "The Cleaning Comet," which, despite being fictional, nudged our collective broomstick to acknowledge the cosmic implications of household chores. It seems that the seemingly mundane world of cleaning has been quietly whispering cosmic secrets all along.

Our correlation coefficient of 0.9633028 practically shouts for attention, akin to a high-powered vacuum cleaner announcing its presence. With a p-value of less than 0.01, it's as if the statistical gods themselves are nodding in agreement to this unlikely connection. It's evident that as the number of housekeepers in West Virginia grows, so does the chatter in the virtual orbits of SciShow Space YouTube videos. This phenomenon, while confounding at first sight, can no longer be brushed aside.

The implications of our research delve into uncharted territories, shaking the very foundations of the conventional wisdom faster than a whirling dervish with a feather duster. We're prompted to reconsider the influence of seemingly mundane variables on virtual engagements, much like discovering untold adventures within the storage closet. While caution must be exercised in leaping to causal conclusions, our findings promulgate a refreshing perspective on the multifaceted dynamics of human behavior and the peculiar intersections that can emerge within the digital landscape.

Indeed, our study urges us to entertain the notion that behind every mundane occurrence, there may lurk an unexpected correlation – a revelation as illuminating as finding a diamond ring among the debris of scrubbing pads. This research serves as a reminder that the interplay of domestic duties and virtual worlds is as captivating as an enigma wrapped in a feather duster, and as beguiling as discovering a treasure map on the back of a cleaning product label.

In sum, our results not only redefine the boundaries of seemingly unrelated variables, but also encourage a reevaluation of the potential influences lurking within our daily routines – a testament to the sublime beauty that can be uncovered in the most unassuming corners of statistical analysis. As the dust settles on this research, we invite the scientific community to embrace the unexpected, marvel at the improbable, and find inspiration in the most unlikeliest of places – because, as we've learned, sometimes the most surprising connections are swept right under our noses.


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 housekeepers in West Virginia and Total comments on SciShow Space YouTube videos. Make lots of jokes, goofy observations, and puns. Stay serious and dry most of the time, but then occasionally let your wit shine through.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space

[[ABSTRACT]]
In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

[[INTRDUCTION]]
"Cleanliness is next to godliness," or so the saying goes. But who would have thought that the number of housekeepers in West Virginia could also be next to an abundance of comments on SciShow Space YouTube videos? In this unprecedented study, we explore the unexpected correlation between the seemingly mundane occupation of housekeeping and the virtual chatter unfolding in the comment sections of popular science videos.
The notion of connecting the act of mopping and vacuuming with the discussions of astrophysics and space exploration may seem as far-fetched as finding a vacuum cleaner on the moon. However, our findings unravel a correlation so strong, even a stubborn stain would be impressed. We delve into the uncharted territory where the domestic and the digital intersect, scrubbing away the dirt of misconceptions and exposing the gleaming linoleum of statistical significance.
As we embark on this unique investigation, it is essential to recognize that correlation does not imply causation; however, it certainly does raise some eyebrows, much like discovering a stray sock stuffed behind the sofa. With a correlation coefficient of 0.9633028 (p < 0.01) for the years 2014 to 2022, we are faced with a relationship so striking, it makes the bond between electrons and protons seem positively lukewarm in comparison.
Through this study, we aim to dust off the presumptions that only cutting-edge, futuristic topics trigger online engagement, and to illuminate the curious ways in which seemingly mundane variables can unexpectedly influence virtual interactions. Now, without further ado, let's roll up our sleeves, don our research gloves, and embark on a journey to uncover the surprising correlations between housekeeping and high-engagement YouTube discussions.

[[RESULTS]]
The correlation analysis between the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos revealed a remarkably robust relationship, defying expectations like a vacuum cleaner able to recite the periodic table.
The correlation coefficient of 0.9633028 and an r-squared value of 0.9279523 signify a connection so strong that it could practically sweep you off your feet. With a p-value of less than 0.01, this correlation isn't just a speck of dust in the wind; it's a statistical hurricane wreaking havoc on our assumptions.
Upon visual inspection, the scatterplot (Fig. 1) depicts a trend so clear, it's as if the dust bunnies have finally organized themselves into a coherent pattern. The upward trajectory of the data points suggests that as the number of housekeepers in West Virginia rises, so does the level of engagement in the comment section of SciShow Space YouTube videos, leaving us to wonder if the secret to captivating online discussions involves a well-polished household.
In keeping with the spirit of scientific inquiry, it's important to recognize that correlation does not imply causation. Nonetheless, our findings raise intriguing questions about the unexplored dynamics of online engagement and the unassuming influences that may play a role in shaping virtual interactions.
In essence, our results not only sweep away the cobwebs of conventional thinking but also highlight the unforeseen ways in which the most commonplace variables can wield surprising influence in the digital domain. This study serves as a bold reminder that in the realm of data analysis, even the most pedestrian factors can harbor unexpected and intriguing connections, much like finding a hidden treasure trove of discourse between the bottles of cleaning supplies.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated an unexpected yet palpable correlation between the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos, challenging the notion that virtual discourse is solely driven by the allure of cosmological curiosities. Just as a well-organized pantry can bring joy, it appears that a well-kept household may also prime the conversations in the digital cosmos. Our findings not only dust off preconceived notions about the factors influencing online engagement but also underscore the need to sweep away the boundaries between the commonplace and the extraordinary in the realm of statistical analysis.

While some may dismiss our findings as akin to finding a misplaced feather duster in a telescope, our research holds a mirror to the unexplored interplay between the everyday and the digital. It is evident that, much like the hidden treasures beneath sofa cushions, unassuming variables can stir up a whirlwind of interaction on the virtual stage.

As we bring this study to a close, it is clear that no more research is needed on this eccentric correlation. After all, it's not every day that one uncovers a relationship so surprisingly robust, it could rival the stickiness of a lint roller. With that said, we bid adieu to this topic, leaving behind a polished discussion that sheds light on the remarkable connections that can emerge from the most unexpected corners.


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 Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space. Respond only with the name of a fictional academic journal.

ChatGPT:

The International Journal of Domestic Hygiene and Astrophysical Anecdotes


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 Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space. Respond only with the name of a fictional organization.

ChatGPT:

Society for the Study of Cleanliness and Space Exploration


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 Cleaning Counts: Correlating the Counts of Housekeepers in West Virginia with Comments on SciShow Space with an abstract of In this paper, we present an unexpected and seemingly ludicrous correlation between two seemingly unrelated factors: the number of housekeepers in West Virginia and the total comments on SciShow Space YouTube videos. Our research aims to clean up misconceptions about the interplay between mundane occupations and online engagement. By leveraging data from the Bureau of Labor Statistics and YouTube, we have unearthed a startling correlation coefficient of 0.9633028 (with p < 0.01) for the years 2014 to 2022. This whopping correlation suggests that as the number of housekeepers in West Virginia increases, so does the total engagement in the comment section of SciShow Space YouTube videos. To scrub away any doubts about the significance of this finding, we provide a thorough analysis of the potential factors contributing to this improbable linkage. Our investigation not only brushes away the conventional wisdom that mundane occupations and online engagement are mutually exclusive, but also offers a refreshing perspective on the nuanced dynamics of human behavior. While some may view our findings as a mere surface-level revelation, our research demonstrates that even the most mundane variables can dust off surprising relationships in the realm of data analysis.

ChatGPT:

housekeepers, West Virginia, SciShow Space, YouTube, comments, correlation, Bureau of Labor Statistics, online engagement, data analysis, human behavior, relationship, data correlation, YouTube engagement

*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 housekeepers in West Virginia
Detailed data title: BLS estimate of maids and housekeeping cleaners in West Virginia
Source: Bureau of Larbor Statistics
See what else correlates with The number of housekeepers in West Virginia

Total comments on SciShow Space YouTube videos
Detailed data title: Total comments on SciShow Space YouTube videos.
Source: YouTube
See what else correlates with Total comments on SciShow Space YouTube videos

Correlation r = 0.9633028 (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 = 0.9279523 (Coefficient of determination)
This means 92.8% of the change in the one variable (i.e., Total comments on SciShow Space YouTube videos) is predictable based on the change in the other (i.e., The number of housekeepers in West Virginia) over the 9 years from 2014 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 3.007E-5. 0.0000300715105799054230000000
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 0.96 in 0.003007% of random cases. Said differently, if you correlated 33,254 random variables You don't actually need 33 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 8 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 8 because we have two variables measured over a period of 9 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.

[ 0.83, 0.99 ] 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.
201420152016201720182019202020212022
The number of housekeepers in West Virginia (Laborers)616059906470579057405960514050404550
Total comments on SciShow Space YouTube videos (Total comments)564225672977831520775006349627344273563021308




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. Very low n: There are not many data points included in this analysis. Even if the p-value is high, we should be suspicious of using so few datapoints in a correlation.
  5. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

You can calculate the values on this page on your own! Try running the Python code to see the calculation results. Step 1: Download and install Python on your computer.

Step 2: Open a plaintext editor like Notepad and paste the code below into it.

Step 3: Save the file as "calculate_correlation.py" in a place you will remember, like your desktop. Copy the file location to your clipboard. On Windows, you can right-click the file and click "Properties," and then copy what comes after "Location:" As an example, on my computer the location is "C:\Users\tyler\Desktop"

Step 4: Open a command line window. For example, by pressing start and typing "cmd" and them pressing enter.

Step 5: Install the required modules by typing "pip install numpy", then pressing enter, then typing "pip install scipy", then pressing enter.

Step 6: Navigate to the location where you saved the Python file by using the "cd" command. For example, I would type "cd C:\Users\tyler\Desktop" and push enter.

Step 7: Run the Python script by typing "python calculate_correlation.py"

If you run into any issues, I suggest asking ChatGPT to walk you through installing Python and running the code below on your system. Try this question:

"Walk me through installing Python on my computer to run a script that uses scipy and numpy. Go step-by-step and ask me to confirm before moving on. Start by asking me questions about my operating system so that you know how to proceed. Assume I want the simplest installation with the latest version of Python and that I do not currently have any of the necessary elements installed. Remember to only give me one step per response and confirm I have done it before proceeding."


# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([6160,5990,6470,5790,5740,5960,5140,5040,4550,])
array_2 = np.array([56422,56729,77831,52077,50063,49627,34427,35630,21308,])
array_1_name = "The number of housekeepers in West Virginia"
array_2_name = "Total comments on SciShow Space YouTube videos"

# 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 is stellar!


Correlation ID: 4334 · Black Variable ID: 16021 · Red Variable ID: 25678
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0