about · email me · subscribe
Spurious correlation #5,414 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is How fun Computerphile YouTube video titles are and the second variable is Kerosene used in Mali.  The chart goes from 2013 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As the kerosene usage in Mali rises, it leads to an unexpected surplus of laughter-infused molecules in the atmosphere, which coincidentally boosts the creativity of Computerphile video title creators. It's like the internet is getting a dose of combustible comedy!

Model: dalle-3
Prompt: An image that looks like it is a scene from a Pixar movie where in Mali, people are using kerosene more frequently, leading to a rise in laughter-infused molecules in the atmosphere. Meanwhile, at a Computerphile video title creation studio, the team is surrounded by swirling, colorful laughter-infused molecules, sparking a burst of creativity. The room is filled with laughter as the team comes up with hilariously fun YouTube video titles. The room is bathed in warm, golden light, with the team animatedly interacting with one another in the midst of the colorful, shimmering molecules. 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: How fun Computerphile YouTube video titles are and Kerosene used in Mali. 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: Futuristic Minimalism An image that looks like it is a scene from a Pixar movie Voxel art Cybernetic 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 How fun Computerphile YouTube video titles are and Kerosene used in Mali, in the following situation: As the kerosene usage in Mali rises, it leads to an unexpected surplus of laughter-infused molecules in the atmosphere, which coincidentally boosts the creativity of Computerphile video title creators. It's like the internet is getting a dose of combustible comedy!. Keep the description simple.
ChatGPT: In Mali, people are using kerosene more frequently, leading to a rise in laughter-infused molecules in the atmosphere. Meanwhile, at a Computerphile video title creation studio, the team is surrounded by swirling, colorful laughter-infused molecules, sparking a burst of creativity. The room is filled with laughter as the team comes up with hilariously fun YouTube video titles.

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 Mali, people are using kerosene more frequently, leading to a rise in laughter-infused molecules in the atmosphere. Meanwhile, at a Computerphile video title creation studio, the team is surrounded by swirling, colorful laughter-infused molecules, sparking a burst of creativity. The room is filled with laughter as the team comes up with hilariously fun YouTube video titles. 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 where in Mali, people are using kerosene more frequently, leading to a rise in laughter-infused molecules in the atmosphere. Meanwhile, at a Computerphile video title creation studio, the team is surrounded by swirling, colorful laughter-infused molecules, sparking a burst of creativity. The room is filled with laughter as the team comes up with hilariously fun YouTube video titles. The room is bathed in warm, golden light, with the team animatedly interacting with one another in the midst of the colorful, shimmering molecules.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how an increase in How fun Computerphile YouTube video titles are caused Kerosene used in Mali to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

The Journal of Quirky Science and Unconventional Research

Jan 2024

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




Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

Rhyme words in the title.

Your research team used data from AI analysis of YouTube video titles and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.8296455 and p < 0.01 for 2013 to 2021.

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]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

Oftentimes in the realm of academic research, we find ourselves stumbling upon whimsical correlations that seem too absurd to be true, like the connection between the delightful absurdity of Computerphile video titles and the use of kerosene in Mali. One might ponder, "What do viral videos about computer science have to do with household fuel choices in a West African country?" But as researchers, we are bound by duty to investigate even the most seemingly nonsensical linkages, much like your dad is bound by duty to make puns at every opportunity.

As we delve into this delightfully unexpected correlation, one can't help but recall the wise words of our favorite statistician: "Correlation does not imply causation, but it sure does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.’" So, with a healthy dose of skepticism and a sprinkle of humor, we set out to explore this peculiar relationship between digital amusement and the consumption of kerosene. It's like trying to balance an equation with a pun - unexpected and yet strangely satisfying.

Leaping headfirst into the rabbit hole of statistical analysis, we were met with an eyebrow-raising correlation coefficient of 0.8296455 and a gleamingly significant p-value (p < 0.01), validating the unexpected association between the fun factor of Computerphile video titles and the adoption of kerosene as a household energy source in Mali. It's as if the stats were saying, "Now isn't this a gas?"

Our research seeks to not only illuminate this surprising connection but also to prompt a shift in perspective, challenging the conventional boundaries of what influences consumer behavior. After all, who would have thought that a cleverly titled video on algorithms could influence the way people light their homes? It's like finding a hidden message in a string of ASCII art – cryptic, yet undeniably intriguing.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Oftentimes in the realm of academic research, we find ourselves stumbling upon whimsical correlations that seem too absurd to be true, like the connection between the delightful absurdity of Computerphile video titles and the use of kerosene in Mali. One might ponder, "What do viral videos about computer science have to do with household fuel choices in a West African country?" But as researchers, we are bound by duty to investigate even the most seemingly nonsensical linkages, much like your dad is bound by duty to make puns at every opportunity.
As we delve into this delightfully unexpected correlation, one can't help but recall the wise words of our favorite statistician: "Correlation does not imply causation, but it sure does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.’" So, with a healthy dose of skepticism and a sprinkle of humor, we set out to explore this peculiar relationship between digital amusement and the consumption of kerosene. It's like trying to balance an equation with a pun - unexpected and yet strangely satisfying.
Leaping headfirst into the rabbit hole of statistical analysis, we were met with an eyebrow-raising correlation coefficient of 0.8296455 and a gleamingly significant p-value (p < 0.01), validating the unexpected association between the fun factor of Computerphile video titles and the adoption of kerosene as a household energy source in Mali. It's as if the stats were saying, "Now isn't this a gas?"
Our research seeks to not only illuminate this surprising connection but also to prompt a shift in perspective, challenging the conventional boundaries of what influences consumer behavior. After all, who would have thought that a cleverly titled video on algorithms could influence the way people light their homes? It's like finding a hidden message in a string of ASCII art – cryptic, yet undeniably intriguing.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In "Smith et al.'s Study on Digital Content and Consumer Choices," the authors find that the influence of digital content on consumer behavior is a multifaceted and complex phenomenon, with potential impacts reaching far beyond traditional marketing strategies. It's like trying to solve a Rubik's Cube blindfolded - perplexing, yet strangely exhilarating. One might compare the unexpected influence of digital content to finding a surprise ingredient in a recipe - it adds an unexpected flavor to the mix.

Doe and Jones, in "The Unlikely Impact of Online Entertainment on Household Habits," further explore the nuanced relationship between digital amusement and everyday choices, suggesting that the influence of online entertainment may extend to domains not conventionally associated with leisure activities. It's as if the internet were sprinkling some spice into the stew of mundane life - utterly surprising, yet undeniably flavorful.

As we delve deeper into this whimsical exploration, we cannot overlook the potential intersection of kerosene usage and digital influence. Just as a good dad joke can lighten the mood in any situation, our research aims to bring lightheartedness to the seemingly serious realm of household energy consumption. After all, who wouldn't appreciate a good laugh while pondering the implications of digital amusement on energy dynamics?

Moving beyond the realm of academic literature, books such as "The Kerosene Chronicles" and "The Algorithmic Amusement" offer an intriguing blend of fiction and non-fiction narratives that may provide insights into the interconnectedness of kerosene usage and digital entertainment. It's like a choose-your-own-adventure book, where every turn leads to an unexpected discovery - an adventure in statistical analysis and absurd correlations.

Furthermore, we stumbled upon some social media posts discussing the unforeseen impacts of digital content on daily life choices. One post humorously speculated, "Are Computerphile video titles secretly the spark that lights the kerosene lantern in Mali? Maybe one day we'll find out they've been the fuel for enlightenment all along!" This tongue-in-cheek perspective encapsulates the whimsy of our inquiry, reminding us that statistical analysis need not be devoid of humor and creativity.

In essence, the literature and musings surrounding this unorthodox correlation not only widen the scope of our inquiry but also infuse a sense of levity into our exploration. Just as a well-timed dad joke can turn a mundane conversation into a memorable one, our research aims to infuse mirth into the statistical investigation of unexpected connections.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from AI analysis of YouTube video titles and Energy Information Administration . You used data from 2013 to 2021

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]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

[[INTRODUCTION]]
Oftentimes in the realm of academic research, we find ourselves stumbling upon whimsical correlations that seem too absurd to be true, like the connection between the delightful absurdity of Computerphile video titles and the use of kerosene in Mali. One might ponder, "What do viral videos about computer science have to do with household fuel choices in a West African country?" But as researchers, we are bound by duty to investigate even the most seemingly nonsensical linkages, much like your dad is bound by duty to make puns at every opportunity.
As we delve into this delightfully unexpected correlation, one can't help but recall the wise words of our favorite statistician: "Correlation does not imply causation, but it sure does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.’" So, with a healthy dose of skepticism and a sprinkle of humor, we set out to explore this peculiar relationship between digital amusement and the consumption of kerosene. It's like trying to balance an equation with a pun - unexpected and yet strangely satisfying.
Leaping headfirst into the rabbit hole of statistical analysis, we were met with an eyebrow-raising correlation coefficient of 0.8296455 and a gleamingly significant p-value (p < 0.01), validating the unexpected association between the fun factor of Computerphile video titles and the adoption of kerosene as a household energy source in Mali. It's as if the stats were saying, "Now isn't this a gas?"
Our research seeks to not only illuminate this surprising connection but also to prompt a shift in perspective, challenging the conventional boundaries of what influences consumer behavior. After all, who would have thought that a cleverly titled video on algorithms could influence the way people light their homes? It's like finding a hidden message in a string of ASCII art – cryptic, yet undeniably intriguing.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic link between the delightful absurdity of Computerphile video titles and the consumption of kerosene in Mali, we employed a methodological approach that was as whimsical as it was rigorous. Our data collection process was akin to piecing together a puzzle with a mischievous twist, where each data point was a potential punchline waiting to be uncovered.

Firstly, we harnessed the power of artificial intelligence (AI) to analyze the lexical merriment encapsulated within the titles of Computerphile YouTube videos. Our algorithmic detectives were on the prowl for puns, wordplay, and general witticisms that could tickle even the most stoic of statisticians. It was a bit like training a neural network to appreciate dad jokes – a labor of love and a testament to our commitment to finding humor in the unlikeliest of places.

Simultaneously, we delved into the world of energy dynamics, drawing upon data from the Energy Information Administration to track kerosene consumption in Mali from 2013 to 2021. It was as if we were on a quest to uncover the arcane secrets of household fuel preferences, armed with spreadsheets and a sense of humor sharp enough to cut through the statistical noise.

Our statistical analysis was a delightful fusion of complexity and levity, not unlike a statistical equation with a hidden punchline. We employed robust correlation and regression analyses to unravel the relationship between the mirthful allure of Computerphile video titles and the utilization of kerosene in Mali. Our calculations had a certain comedic timing, as if the numbers themselves were teasing us with their unexpected affinity for laughter.

Additionally, we conducted rigorous sensitivity analyses to ensure that our findings were resilient to variations and disruptions, much like a seasoned comedian weathering unexpected hecklers in the audience. Our methods were not just statistically sound; they were also designed to withstand the capricious whims of data, ensuring that our conclusions were as sturdy as a well-crafted setup to a pun-filled punchline.

In essence, our methodology was a testament to the whimsical yet diligent nature of scientific inquiry, where laughter and statistical significance converged to shed light on an improbable yet substantial relationship. It was research with a twinkle in its eye and a punchline waiting to be discovered.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from AI analysis of YouTube video titles and Energy Information Administration .

For the time period 2013 to 2021, you found a correlation 0.8296455, r-squared of 0.6883117, 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]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Oftentimes in the realm of academic research, we find ourselves stumbling upon whimsical correlations that seem too absurd to be true, like the connection between the delightful absurdity of Computerphile video titles and the use of kerosene in Mali. One might ponder, "What do viral videos about computer science have to do with household fuel choices in a West African country?" But as researchers, we are bound by duty to investigate even the most seemingly nonsensical linkages, much like your dad is bound by duty to make puns at every opportunity.
As we delve into this delightfully unexpected correlation, one can't help but recall the wise words of our favorite statistician: "Correlation does not imply causation, but it sure does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.’" So, with a healthy dose of skepticism and a sprinkle of humor, we set out to explore this peculiar relationship between digital amusement and the consumption of kerosene. It's like trying to balance an equation with a pun - unexpected and yet strangely satisfying.
Leaping headfirst into the rabbit hole of statistical analysis, we were met with an eyebrow-raising correlation coefficient of 0.8296455 and a gleamingly significant p-value (p < 0.01), validating the unexpected association between the fun factor of Computerphile video titles and the adoption of kerosene as a household energy source in Mali. It's as if the stats were saying, "Now isn't this a gas?"
Our research seeks to not only illuminate this surprising connection but also to prompt a shift in perspective, challenging the conventional boundaries of what influences consumer behavior. After all, who would have thought that a cleverly titled video on algorithms could influence the way people light their homes? It's like finding a hidden message in a string of ASCII art – cryptic, yet undeniably intriguing.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of data collected from 2013 to 2021 revealed a remarkably strong correlation between the whimsicality of Computerphile video titles and kerosene consumption in Mali (r = 0.8296455, r-squared = 0.6883117, p < 0.01). It appears that the puns and witty wordplay in the video titles were not the only things lighting up the screen – they were also igniting a spark in the energy choices of households in Mali.

Fig. 1 showcases the scatterplot depicting this unexpected relationship between the fun factor of Computerphile video titles and kerosene usage. It's as if the statistical analysis itself couldn't resist making a visual pun, portraying the correlation in a way that is sure to draw a chuckle from even the most stoic researcher.

In scrutinizing this peculiar linkage, we unearthed a connection that is undeniably puzzling but remarkable in its statistical robustness. It’s like finding the punchline to a statistical joke buried within the data – unexpected, yet undeniably satisfying.

The findings not only present a fascinating conundrum but also suggest an unconventional insight into the potential influence of digital content on everyday choices. It's akin to stumbling upon a hidden algorithm in a string of data – surprising, yet thought-provoking.

Moreover, the correlation coefficient of 0.8296455 indicates a strong positive association between the delightful absurdity of Computerphile video titles and the use of kerosene, inviting one to wonder if the anxiously anticipated punchline was, in fact, the statistical correlation all along.

This unexpected coupling raises new questions and offers a playful twist to our understanding of consumer behavior. It’s as if statistics pulled off the ultimate dad joke, leaving us pondering the punchline long after the laughter has subsided.

In summary, the results of our study unveil a captivating correlation between the amusement derived from Computerphile video titles and the consumption of kerosene in Mali, sparking both curiosity and a shared chuckle among scholars. The statistical analysis not only illuminated this unexpected relationship but also kindled a flame of light-hearted inquiry, reminding us that in the world of research, even the most unexpected correlations can elicit a hearty laugh.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

[[LITERATURE REVIEW]]
In "Smith et al.'s Study on Digital Content and Consumer Choices," the authors find that the influence of digital content on consumer behavior is a multifaceted and complex phenomenon, with potential impacts reaching far beyond traditional marketing strategies. It's like trying to solve a Rubik's Cube blindfolded - perplexing, yet strangely exhilarating. One might compare the unexpected influence of digital content to finding a surprise ingredient in a recipe - it adds an unexpected flavor to the mix.
Doe and Jones, in "The Unlikely Impact of Online Entertainment on Household Habits," further explore the nuanced relationship between digital amusement and everyday choices, suggesting that the influence of online entertainment may extend to domains not conventionally associated with leisure activities. It's as if the internet were sprinkling some spice into the stew of mundane life - utterly surprising, yet undeniably flavorful.
As we delve deeper into this whimsical exploration, we cannot overlook the potential intersection of kerosene usage and digital influence. Just as a good dad joke can lighten the mood in any situation, our research aims to bring lightheartedness to the seemingly serious realm of household energy consumption. After all, who wouldn't appreciate a good laugh while pondering the implications of digital amusement on energy dynamics?
Moving beyond the realm of academic literature, books such as "The Kerosene Chronicles" and "The Algorithmic Amusement" offer an intriguing blend of fiction and non-fiction narratives that may provide insights into the interconnectedness of kerosene usage and digital entertainment. It's like a choose-your-own-adventure book, where every turn leads to an unexpected discovery - an adventure in statistical analysis and absurd correlations.
Furthermore, we stumbled upon some social media posts discussing the unforeseen impacts of digital content on daily life choices. One post humorously speculated, "Are Computerphile video titles secretly the spark that lights the kerosene lantern in Mali? Maybe one day we'll find out they've been the fuel for enlightenment all along!" This tongue-in-cheek perspective encapsulates the whimsy of our inquiry, reminding us that statistical analysis need not be devoid of humor and creativity.
In essence, the literature and musings surrounding this unorthodox correlation not only widen the scope of our inquiry but also infuse a sense of levity into our exploration. Just as a well-timed dad joke can turn a mundane conversation into a memorable one, our research aims to infuse mirth into the statistical investigation of unexpected connections.

[[RESULTS]]
The analysis of data collected from 2013 to 2021 revealed a remarkably strong correlation between the whimsicality of Computerphile video titles and kerosene consumption in Mali (r = 0.8296455, r-squared = 0.6883117, p < 0.01). It appears that the puns and witty wordplay in the video titles were not the only things lighting up the screen – they were also igniting a spark in the energy choices of households in Mali.
Fig. 1 showcases the scatterplot depicting this unexpected relationship between the fun factor of Computerphile video titles and kerosene usage. It's as if the statistical analysis itself couldn't resist making a visual pun, portraying the correlation in a way that is sure to draw a chuckle from even the most stoic researcher.
In scrutinizing this peculiar linkage, we unearthed a connection that is undeniably puzzling but remarkable in its statistical robustness. It’s like finding the punchline to a statistical joke buried within the data – unexpected, yet undeniably satisfying.
The findings not only present a fascinating conundrum but also suggest an unconventional insight into the potential influence of digital content on everyday choices. It's akin to stumbling upon a hidden algorithm in a string of data – surprising, yet thought-provoking.
Moreover, the correlation coefficient of 0.8296455 indicates a strong positive association between the delightful absurdity of Computerphile video titles and the use of kerosene, inviting one to wonder if the anxiously anticipated punchline was, in fact, the statistical correlation all along.
This unexpected coupling raises new questions and offers a playful twist to our understanding of consumer behavior. It’s as if statistics pulled off the ultimate dad joke, leaving us pondering the punchline long after the laughter has subsided.
In summary, the results of our study unveil a captivating correlation between the amusement derived from Computerphile video titles and the consumption of kerosene in Mali, sparking both curiosity and a shared chuckle among scholars. The statistical analysis not only illuminated this unexpected relationship but also kindled a flame of light-hearted inquiry, reminding us that in the world of research, even the most unexpected correlations can elicit a hearty laugh.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The findings from our study have ignited a lively discussion on the unexpected yet remarkably robust relationship between the whimsicality of Computerphile video titles and kerosene consumption in Mali. It seems that the puns and clever wordplays in the video titles were not just sparking amusement but also kindling a spark in the energy choices of households in Mali. It's like the statistical analysis stumbled upon a hidden punchline within the data, a delightful surprise akin to finding a dad joke hidden in a serious conversation.

Our results align with prior research, echoing the observations of Smith et al. and Doe and Jones on the potential influence of digital entertainment on consumer choices. Much like solving a Rubik's Cube blindfolded, the tangled association between digital content and household habits may be perplexing, but it undoubtedly carries an exhilarating twist. The unexpectedly strong correlation coefficient of 0.8296455 and a significant p-value (p < 0.01) not only substantiate the findings reported in the existing literature but also serve as a poignant reminder that statistical analyses, much like a well-timed dad joke, can add unexpected flavor to scholarly inquiries.

The scatterplot depicting the correlation is a visual pun unto itself – providing a chuckle and a stark reminder that even in the realm of empirical research, there is room for wit and humor. It's as if the statistical analysis couldn't resist making a visual pun, portraying the correlation in a way that is sure to draw a chuckle from even the most stoic researcher, much like a clever quip at a prestigious scientific conference.

Our investigation has shed light on the covert impacts of digital content on everyday decisions, evoking musings reminiscent of a choose-your-own-adventure book where every turn leads to unexpected discoveries. In this vein, our study aims to inject a sense of levity into the usually somber realm of statistical analysis, much like a well-timed dad joke can turn a mundane conversation into a memorable one.

In summary, our findings provide ample fodder for further scholarly exploration of the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices. The statistical analysis not only illuminated this unexpected relationship but also set off a flame of light-hearted inquiry, reminding us that in the world of research, even the most unexpected correlations can elicit hearty laughter.

In reflecting on the unexpected coupling presented by our study, it's clear that statistics itself has pulled off the ultimate dad joke, leaving us pondering the punchline long after the laughter has subsided. The correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, but as our results and prior research suggest, it holds substantial empirical support – leaving us with a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between How fun Computerphile YouTube video titles are and Kerosene used in Mali. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali

[[ABSTRACT]]
This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.

In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.

Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.

In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

[[INTRDUCTION]]
Oftentimes in the realm of academic research, we find ourselves stumbling upon whimsical correlations that seem too absurd to be true, like the connection between the delightful absurdity of Computerphile video titles and the use of kerosene in Mali. One might ponder, "What do viral videos about computer science have to do with household fuel choices in a West African country?" But as researchers, we are bound by duty to investigate even the most seemingly nonsensical linkages, much like your dad is bound by duty to make puns at every opportunity.
As we delve into this delightfully unexpected correlation, one can't help but recall the wise words of our favorite statistician: "Correlation does not imply causation, but it sure does waggle its eyebrows suggestively and gesture furtively while mouthing 'look over there.’" So, with a healthy dose of skepticism and a sprinkle of humor, we set out to explore this peculiar relationship between digital amusement and the consumption of kerosene. It's like trying to balance an equation with a pun - unexpected and yet strangely satisfying.
Leaping headfirst into the rabbit hole of statistical analysis, we were met with an eyebrow-raising correlation coefficient of 0.8296455 and a gleamingly significant p-value (p < 0.01), validating the unexpected association between the fun factor of Computerphile video titles and the adoption of kerosene as a household energy source in Mali. It's as if the stats were saying, "Now isn't this a gas?"
Our research seeks to not only illuminate this surprising connection but also to prompt a shift in perspective, challenging the conventional boundaries of what influences consumer behavior. After all, who would have thought that a cleverly titled video on algorithms could influence the way people light their homes? It's like finding a hidden message in a string of ASCII art – cryptic, yet undeniably intriguing.

[[RESULTS]]
The analysis of data collected from 2013 to 2021 revealed a remarkably strong correlation between the whimsicality of Computerphile video titles and kerosene consumption in Mali (r = 0.8296455, r-squared = 0.6883117, p < 0.01). It appears that the puns and witty wordplay in the video titles were not the only things lighting up the screen – they were also igniting a spark in the energy choices of households in Mali.
Fig. 1 showcases the scatterplot depicting this unexpected relationship between the fun factor of Computerphile video titles and kerosene usage. It's as if the statistical analysis itself couldn't resist making a visual pun, portraying the correlation in a way that is sure to draw a chuckle from even the most stoic researcher.
In scrutinizing this peculiar linkage, we unearthed a connection that is undeniably puzzling but remarkable in its statistical robustness. It’s like finding the punchline to a statistical joke buried within the data – unexpected, yet undeniably satisfying.
The findings not only present a fascinating conundrum but also suggest an unconventional insight into the potential influence of digital content on everyday choices. It's akin to stumbling upon a hidden algorithm in a string of data – surprising, yet thought-provoking.
Moreover, the correlation coefficient of 0.8296455 indicates a strong positive association between the delightful absurdity of Computerphile video titles and the use of kerosene, inviting one to wonder if the anxiously anticipated punchline was, in fact, the statistical correlation all along.
This unexpected coupling raises new questions and offers a playful twist to our understanding of consumer behavior. It’s as if statistics pulled off the ultimate dad joke, leaving us pondering the punchline long after the laughter has subsided.
In summary, the results of our study unveil a captivating correlation between the amusement derived from Computerphile video titles and the consumption of kerosene in Mali, sparking both curiosity and a shared chuckle among scholars. The statistical analysis not only illuminated this unexpected relationship but also kindled a flame of light-hearted inquiry, reminding us that in the world of research, even the most unexpected correlations can elicit a hearty laugh.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In wrapping up our investigation into the intriguing intertwining of the whimsical world of Computerphile video titles and the fiery realm of kerosene consumption in Mali, it's clear that this correlation is not just a mere statistical fluke – it's statistically hilarious. As we reflect on our findings, one cannot help but appreciate the unexpected punchlines that emerged from our data analysis, proving that correlations can indeed be a gas – in more ways than one.

Our research has not only ignited a flame of curiosity but also shed light on the enchanting influence of digital amusement on everyday choices, demonstrating that statistics can be both illuminating and a source of entertainment. Much like a lighthearted dad joke, this correlation between Computerphile video titles and kerosene usage in Mali has left us with a warm glow of amusement and a deep appreciation for the delightful mysteries that statistical analysis can unveil.

While we could continue to fan the flames of inquiry in this area, it seems that our study has provided a hearty serving of statistical humor and insight, leaving us with the undeniable conclusion that no further research is needed in this captivating, yet wholly unexpected, realm of inquiry. After all, as every good academic researcher knows, sometimes a correlation is simply too good to question further.


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 Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Science and Unconventional Research


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 Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali. Respond only with the name of a fictional organization.

ChatGPT:

The Society for the Advancement of Quirky Technological Research


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 Ignite the Delight: The Spite of Computerphile Video Titles and Kerosene in Mali with an abstract of This research presents a quirky yet illuminating exploration of the correlation between the whimsicality of Computerphile YouTube video titles and kerosene consumption in Mali. Leveraging an intersection of artificial intelligence (AI) analysis of YouTube video titles and data from the Energy Information Administration, our study unveils a surprisingly robust link between the entertainment value of Computerphile video titles and the consumption of kerosene in Mali from 2013 to 2021.
In scrutinizing the dataset, we established a correlation coefficient of 0.8296455 and a significant p-value (p < 0.01), substantiating the association between the amusement derived from Computerphile video titles and the usage of kerosene. As the analysis kindled our curiosity, we embarked on an investigative journey to unravel the underlying mechanisms governing this unexpected relationship between digital levity and household fuel choices.
Our findings shed light on the potential inadvertently comedic influence of Computerphile videos on energy preferences, causing one to ponder: "Are these puns about computer science sparking a fire in the hearts of kerosene consumers in Mali?" This study not only adds a whimsical twist to the scholarly understanding of energy dynamics but also underscores the need for further exploration of the covert impacts of digital content on everyday choices.
In summarizing our research, we conclude that while the correlation between the delightfulness of Computerphile video titles and kerosene usage in Mali may seem like a flammable joke at first, it holds substantial empirical support. This study leaves us with fuel for thought and a reminder that in the world of statistical analysis, unexpected connections can certainly light up a room.

ChatGPT:

Computerphile, YouTube, video titles, kerosene consumption, Mali, artificial intelligence, AI analysis, Energy Information Administration, correlation coefficient, p-value, entertainment value, digital content, energy dynamics, statistical analysis, humorous influence, household fuel choices

*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

How fun Computerphile YouTube video titles are
Detailed data title: How fun Computerphile YouTube video titles are, as rated by an AI.
Source: AI analysis of YouTube video titles
Additional Info: I asked a large language model, 'On a scale of 1-10, how _______ do you think this YouTube video title is?' for every video.

See what else correlates with How fun Computerphile YouTube video titles are

Kerosene used in Mali
Detailed data title: Volume of kerosene used consumed in Mali in millions of barrels per day
Source: Energy Information Administration
See what else correlates with Kerosene used in Mali

Correlation r = 0.8296455 (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 = 0.6883117 (Coefficient of determination)
This means 68.8% of the change in the one variable (i.e., Kerosene used in Mali) is predictable based on the change in the other (i.e., How fun Computerphile YouTube video titles are) over the 9 years from 2013 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0057. 0.0056632501638261980000000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.83 in 0.57% of random cases. Said differently, if you correlated 177 random variables Which I absolutely did.
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.

[ 0.37, 0.96 ] 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.
201320142015201620172018201920202021
How fun Computerphile YouTube video titles are (Fun score (out of 10))6.31756.52226.65636.47926.63046.47786.57476.35596.7021
Kerosene used in Mali (Million Barrels/Day)0.6776990.6988770.6988760.6969670.6988770.6988770.6988770.6673370.704154




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. 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.




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([6.3175,6.5222,6.6563,6.4792,6.6304,6.4778,6.5747,6.3559,6.7021,])
array_2 = np.array([0.677699,0.698877,0.698876,0.696967,0.698877,0.698877,0.698877,0.667337,0.704154,])
array_1_name = "How fun Computerphile YouTube video titles are"
array_2_name = "Kerosene used in Mali"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)



Reuseable content

You may re-use the images on this page for any purpose, even commercial purposes, without asking for permission. The only requirement is that you attribute Tyler Vigen. Attribution can take many different forms. If you leave the "tylervigen.com" link in the image, that satisfies it just fine. If you remove it and move it to a footnote, that's fine too. You can also just write "Charts courtesy of Tyler Vigen" at the bottom of an article.

You do not need to attribute "the spurious correlations website," and you don't even need to link here if you don't want to. I don't gain anything from pageviews. There are no ads on this site, there is nothing for sale, and I am not for hire.

For the record, I am just one person. Tyler Vigen, he/him/his. I do have degrees, but they should not go after my name unless you want to annoy my wife. If that is your goal, then go ahead and cite me as "Tyler Vigen, A.A. A.A.S. B.A. J.D." Otherwise it is just "Tyler Vigen."

When spoken, my last name is pronounced "vegan," like I don't eat meat.

Full license details.
For more on re-use permissions, or to get a signed release form, see tylervigen.com/permission.

Download images for these variables:


View another random correlation

How fun was this correlation?

Hats off to you for rating!


Correlation ID: 5414 · Black Variable ID: 25916 · Red Variable ID: 24674
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0