about · email me · subscribe
Spurious correlation #5,545 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Kerosene used in Namibia and the second variable is The average number of likes on Numberphile YouTube videos.  The chart goes from 2011 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As kerosene usage in Namibia increased, more Namibians gained access to electricity, leading to a surge in interest in math and science. This newfound passion for numbers translated to an uptick in likes on Numberphile videos, proving that even the dimmest situations can spark a bright idea! Remember, when it comes to igniting a love for math, kerosene can really light up the numbers!

Model: dalle-3
Prompt: Prompt: Generate an image that conveys a cozy Namibian home illuminated by a kerosene lamp, with a family gathered around a laptop watching a Numberphile video. Show the screen of the laptop displaying the average number of likes increasing. Outside, depict the installation of a new electricity pole, symbolizing the growing access to electricity across Namibia. Capture the warm glow from the kerosene lamp and the family's excitement for math and science, creating a harmonious atmosphere full of newfound passion for numbers. 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: Kerosene used in Namibia and The average number of likes on Numberphile 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: High-tech a funny image you would see on reddit Data cyber art Art nouveau Macabre
ChatGPT: High-tech

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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos, in the following situation: As kerosene usage in Namibia increased, more Namibians gained access to electricity, leading to a surge in interest in math and science. This newfound passion for numbers translated to an uptick in likes on Numberphile videos, proving that even the dimmest situations can spark a bright idea! Remember, when it comes to igniting a love for math, kerosene can really light up the numbers!. Keep the description simple.
ChatGPT: In a cozy Namibian home illuminated by a kerosene lamp, a family sits together watching a Numberphile video on a laptop. The screen shows the average number of likes increasing as they discuss the fascinating math and science concepts. Outside, a new electricity pole is being installed, symbolizing the growing access to electricity across Namibia. The warm glow from the kerosene lamp and the excitement from the video create a harmonious atmosphere where a newfound passion for numbers begins to shine bright.

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: [ High-tech ] and depicting this scene: In a cozy Namibian home illuminated by a kerosene lamp, a family sits together watching a Numberphile video on a laptop. The screen shows the average number of likes increasing as they discuss the fascinating math and science concepts. Outside, a new electricity pole is being installed, symbolizing the growing access to electricity across Namibia. The warm glow from the kerosene lamp and the excitement from the video create a harmonious atmosphere where a newfound passion for numbers begins to shine bright. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Prompt: Generate an image that conveys a cozy Namibian home illuminated by a kerosene lamp, with a family gathered around a laptop watching a Numberphile video. Show the screen of the laptop displaying the average number of likes increasing. Outside, depict the installation of a new electricity pole, symbolizing the growing access to electricity across Namibia. Capture the warm glow from the kerosene lamp and the family's excitement for math and science, creating a harmonious atmosphere full of newfound passion for numbers.

*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 increases in Kerosene used in Namibia positively influenced The average number of likes on Numberphile YouTube videos.

AI academic paper

(Because p < 0.01)
Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos

The Journal of Combustible Consumption and Social Media Influence

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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Make the title a clever pun.

Your research team used data from Energy Information Administration and YouTube to assess this nagging question. You found a correlation coefficient of 0.9721990 and p < 0.01 for 2011 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]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.


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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Here is the title and abstract of the paper:
[[TITLE]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

The intersection of seemingly unrelated phenomena has long been a source of fascination and puzzlement for researchers across various disciplines. In the realm of energy consumption, kerosene has historically been utilized for lighting and cooking in regions where access to electricity is limited. Namibia, with its fluctuating kerosene consumption patterns, presents an intriguing case study for exploring the broader implications of energy use on environmental, economic, and social systems.

On the other side of the spectrum, the digital landscape of online content creation and consumption has spawned an era of unanticipated fame for specialized niches, including the enigmatic allure of Numberphile's YouTube channel. As a platform dedicated to unraveling the mysteries of mathematics and numbers in an engaging manner, the Numberphile community has fostered a unique culture of appreciation for numerical curiosities. The quantifiable expression of this appreciation, in the form of likes on its videos, serves as a potential window into the psyche of online audiences and their receptivity to numerical discourse.

While these two disparate domains may seem as unrelated as a logarithm and a lighthouse, our investigation into their correlation seeks to illuminate the unexpected connections that underlie the knotty tapestry of modern human behavior and societal dynamics. The juxtaposition of kerosene consumption in Namibia and the likeability of Numberphile YouTube videos may appear as incongruous as a polyhedron in the pantry, yet our initial foray into this uncharted territory has yielded promising insights.

As we delve deeper into the enigma of this linkage, it is our hope that this scholarly pursuit will not only enrich our understanding of the intricate web of influences that shape human preferences and actions, but also inject a dose of levity into the often somber domain of academic research. After all, who would have guessed that the flickering flames of kerosene lamps could be linked to the digital thumbs-ups of mathematical enthusiasts? It is precisely these quizzical connections that infuse our investigation with intrigue and allow us to bring a spark of curiosity to the often-sterile corridors of statistical inquiry.


Model: gpt-3.5-turbo-1106
System prompt: You are a witty academic researcher. Your writing sounds like it belongs in a statistics journal.You draft 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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Perhaps you also got inspiration from some board games that are vaugely related.

Here is the title and abstract of the paper:
[[TITLE]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The intersection of seemingly unrelated phenomena has long been a source of fascination and puzzlement for researchers across various disciplines. In the realm of energy consumption, kerosene has historically been utilized for lighting and cooking in regions where access to electricity is limited. Namibia, with its fluctuating kerosene consumption patterns, presents an intriguing case study for exploring the broader implications of energy use on environmental, economic, and social systems.
On the other side of the spectrum, the digital landscape of online content creation and consumption has spawned an era of unanticipated fame for specialized niches, including the enigmatic allure of Numberphile's YouTube channel. As a platform dedicated to unraveling the mysteries of mathematics and numbers in an engaging manner, the Numberphile community has fostered a unique culture of appreciation for numerical curiosities. The quantifiable expression of this appreciation, in the form of likes on its videos, serves as a potential window into the psyche of online audiences and their receptivity to numerical discourse.
While these two disparate domains may seem as unrelated as a logarithm and a lighthouse, our investigation into their correlation seeks to illuminate the unexpected connections that underlie the knotty tapestry of modern human behavior and societal dynamics. The juxtaposition of kerosene consumption in Namibia and the likeability of Numberphile YouTube videos may appear as incongruous as a polyhedron in the pantry, yet our initial foray into this uncharted territory has yielded promising insights.
As we delve deeper into the enigma of this linkage, it is our hope that this scholarly pursuit will not only enrich our understanding of the intricate web of influences that shape human preferences and actions, but also inject a dose of levity into the often somber domain of academic research. After all, who would have guessed that the flickering flames of kerosene lamps could be linked to the digital thumbs-ups of mathematical enthusiasts? It is precisely these quizzical connections that infuse our investigation with intrigue and allow us to bring a spark of curiosity to the often-sterile corridors of statistical inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The existing literature provides some insight into the ostensibly peculiar correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Smith and Doe (2015) offer a comprehensive examination of kerosene usage patterns and their socioeconomic implications in various regions, including Namibia. Meanwhile, Jones et al. (2018) delve into the complexities of online content consumption and audience engagement, shedding light on the factors contributing to the likeability of numerical discourse in digital spaces.

Expanding beyond the confines of scholarly works, non-fiction books such as "Energy Poverty: Global Challenges and Local Solutions" by Stevens (2014) and "The Mathematics of Love: Patterns, Proofs, and the Search for the Ultimate Equation" by Fry (2015) indirectly touch on the intersecting realms of energy access and numerical fascination, albeit in divergent ways. On the other hand, fictional literature, including "The Alchemist" by Paulo Coelho and "The Illuminatus! Trilogy" by Robert Shea and Robert Anton Wilson, offers imaginative narratives that, although tangential, evoke contemplation of the mystical ties between illumination and allure.

Moreover, drawing inspiration from the world of board games, the strategic dynamics of "Illuminati: New World Order" and the illuminating allure of "Lanterns: The Harvest Festival" serve as whimsical reminders of the multifaceted manifestations of illumination and attraction, albeit in the context of playful diversions.

While these literary and ludic references may appear to veer off the immediate path of academic inquiry, they subtly underscore the enigmatic nature of the kerosene-likeability relationship, infusing our review with a lighthearted nod to the unconventional connections at the heart of our investigation. In the subsequent analysis, we shall strive to bring further illumination to this intriguing correlation and, with any luck, pave the way for a brighter understanding of these seemingly disparate yet curiously intertwined phenomena.


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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from Energy Information Administration and YouTube . You used data from 2011 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]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

[[INTRODUCTION]]
The intersection of seemingly unrelated phenomena has long been a source of fascination and puzzlement for researchers across various disciplines. In the realm of energy consumption, kerosene has historically been utilized for lighting and cooking in regions where access to electricity is limited. Namibia, with its fluctuating kerosene consumption patterns, presents an intriguing case study for exploring the broader implications of energy use on environmental, economic, and social systems.
On the other side of the spectrum, the digital landscape of online content creation and consumption has spawned an era of unanticipated fame for specialized niches, including the enigmatic allure of Numberphile's YouTube channel. As a platform dedicated to unraveling the mysteries of mathematics and numbers in an engaging manner, the Numberphile community has fostered a unique culture of appreciation for numerical curiosities. The quantifiable expression of this appreciation, in the form of likes on its videos, serves as a potential window into the psyche of online audiences and their receptivity to numerical discourse.
While these two disparate domains may seem as unrelated as a logarithm and a lighthouse, our investigation into their correlation seeks to illuminate the unexpected connections that underlie the knotty tapestry of modern human behavior and societal dynamics. The juxtaposition of kerosene consumption in Namibia and the likeability of Numberphile YouTube videos may appear as incongruous as a polyhedron in the pantry, yet our initial foray into this uncharted territory has yielded promising insights.
As we delve deeper into the enigma of this linkage, it is our hope that this scholarly pursuit will not only enrich our understanding of the intricate web of influences that shape human preferences and actions, but also inject a dose of levity into the often somber domain of academic research. After all, who would have guessed that the flickering flames of kerosene lamps could be linked to the digital thumbs-ups of mathematical enthusiasts? It is precisely these quizzical connections that infuse our investigation with intrigue and allow us to bring a spark of curiosity to the often-sterile corridors of statistical inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

To unravel the mystifying connection between kerosene usage in Namibia and the likeability of Numberphile YouTube videos, we embarked on a rigorous data collection and analysis journey, guided by a curious spirit and an unyielding determination to demystify the unusual correlation we suspected. Our methodology, much like a puzzle waiting to be solved, involved a concoction of quantitative techniques and data extraction processes that could rival the complexity of a Rubik's Cube for the uninitiated.

Data on kerosene consumption in Namibia was sourced from the Energy Information Administration, providing a comprehensive overview of the country's utilization of this illuminating liquid from 2011 to 2021. This data served as the vital beacon in navigating the seas of energy consumption patterns, offering insights into the ebbs and flows of kerosene usage within the Namibian landscape. The journey to acquire this data was reminiscent of a quest in a role-playing game, with numerous internet portals and bureaucratic hurdles to overcome before arriving at the treasure trove of information.

Simultaneously, data on the average number of likes on Numberphile YouTube videos was meticulously extracted from the depths of the YouTube platform, offering a panoramic view of digital appreciation for mathematical musings. This involved traversing the digital labyrinth of metadata and engagement metrics, where each like was a tiny affirmation of numerical charisma in the vast expanse of the online realm. Gathering this data felt akin to panning for gold in a swiftly flowing river, sifting through a multitude of digital nuggets to discern the glimmering pattern of approval for numerical adventures.

Having amassed these disparate yet strangely interlinked datasets, we set sail on the choppy seas of statistical analysis, wielding the tools of correlation and regression with the precision of a compass guiding us through stormy waters. Our statistical ship was steered by the helm of software packages such as R and SPSS, harnessing their computational prowess to navigate the tumultuous waves of data points and coefficients. The analysis process was akin to charting unknown terrain, as we sought to uncover the hidden links between kerosene consumption and the virtual applause for mathematical exposition. The aim was to unveil the intriguing relationship that defied conventional wisdom and begged for elucidation.

Upon completion of our statistical voyage, we emerged with a revelation that seemed to defy the boundaries of conventional understanding. The correlation coefficient of 0.9721990 stood as a testament to the unexpected intertwining of kerosene usage and the digital appreciation of Numberphile's numerical marvels. Coupled with a p-value of less than 0.01, our findings provided robust evidence of a statistically significant relationship that defied simple explanation, leaving us with a lingering sense of bewildered fulfillment.

In conclusion, our methodology blended the fervor of exploration with the precision of statistical analysis, offering a unique lens through which to examine the enigmatic bond between kerosene and kudos. This unconventional journey reminded us that beneath the seemingly mundane and disparate elements of our world, there exist threads of connection that await discovery, much like the unexplored pathways of a mathematical labyrinth.


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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 2011 to 2021, you found a correlation 0.9721990, r-squared of 0.9451710, 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]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The intersection of seemingly unrelated phenomena has long been a source of fascination and puzzlement for researchers across various disciplines. In the realm of energy consumption, kerosene has historically been utilized for lighting and cooking in regions where access to electricity is limited. Namibia, with its fluctuating kerosene consumption patterns, presents an intriguing case study for exploring the broader implications of energy use on environmental, economic, and social systems.
On the other side of the spectrum, the digital landscape of online content creation and consumption has spawned an era of unanticipated fame for specialized niches, including the enigmatic allure of Numberphile's YouTube channel. As a platform dedicated to unraveling the mysteries of mathematics and numbers in an engaging manner, the Numberphile community has fostered a unique culture of appreciation for numerical curiosities. The quantifiable expression of this appreciation, in the form of likes on its videos, serves as a potential window into the psyche of online audiences and their receptivity to numerical discourse.
While these two disparate domains may seem as unrelated as a logarithm and a lighthouse, our investigation into their correlation seeks to illuminate the unexpected connections that underlie the knotty tapestry of modern human behavior and societal dynamics. The juxtaposition of kerosene consumption in Namibia and the likeability of Numberphile YouTube videos may appear as incongruous as a polyhedron in the pantry, yet our initial foray into this uncharted territory has yielded promising insights.
As we delve deeper into the enigma of this linkage, it is our hope that this scholarly pursuit will not only enrich our understanding of the intricate web of influences that shape human preferences and actions, but also inject a dose of levity into the often somber domain of academic research. After all, who would have guessed that the flickering flames of kerosene lamps could be linked to the digital thumbs-ups of mathematical enthusiasts? It is precisely these quizzical connections that infuse our investigation with intrigue and allow us to bring a spark of curiosity to the often-sterile corridors of statistical inquiry.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our analysis reveal a remarkably strong correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9721990, an r-squared of 0.9451710, and a p-value of less than 0.01, indicating a highly significant relationship. These findings suggest that there is a substantial association between the utilization of kerosene in Namibia and the propensity of online viewers to express their appreciation for numerical content.

Figure 1 provides a visual representation of the relationship between kerosene consumption and the average number of likes on Numberphile YouTube videos, demonstrating a clear and compelling trend. The scatterplot showcases the data points aligning themselves with almost mathematical precision, reinforcing the robustness of the correlation we have uncovered.

Our investigation into this unexpected linkage between kerosene usage and digital appreciation underscores the intricate and often unforeseen interplay between seemingly unrelated domains. These findings not only challenge conventional wisdom but also add a touch of whimsy to the typically staid world of statistical inquiry. The unexpected nature of this correlation serves as a potent reminder that the world of data analysis can yield surprising discoveries, akin to stumbling upon a hidden treasure in a seemingly mundane dataset.

The implications of these results extend beyond the mere statistical relationship; they beckon us to venture into uncharted territories of inquiry and provoke contemplation on the tantalizing mysteries of human behavior and societal dynamics. The convergence of kerosene consumption and digital engagement serves as a poignant reminder that in the vast landscape of research, unexpected connections can illuminate hitherto unseen patterns and provoke thoughtful reflection.

In conclusion, our study has brought to light a remarkable correlation between kerosene consumption in Namibia and the likeability of Numberphile YouTube videos. These findings prompt further exploration into the underlying mechanisms driving this peculiar relationship, paving the way for future investigations into the curious interplay between energy usage and online appreciation.


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 Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

[[LITERATURE REVIEW]]
The existing literature provides some insight into the ostensibly peculiar correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Smith and Doe (2015) offer a comprehensive examination of kerosene usage patterns and their socioeconomic implications in various regions, including Namibia. Meanwhile, Jones et al. (2018) delve into the complexities of online content consumption and audience engagement, shedding light on the factors contributing to the likeability of numerical discourse in digital spaces.
Expanding beyond the confines of scholarly works, non-fiction books such as "Energy Poverty: Global Challenges and Local Solutions" by Stevens (2014) and "The Mathematics of Love: Patterns, Proofs, and the Search for the Ultimate Equation" by Fry (2015) indirectly touch on the intersecting realms of energy access and numerical fascination, albeit in divergent ways. On the other hand, fictional literature, including "The Alchemist" by Paulo Coelho and "The Illuminatus! Trilogy" by Robert Shea and Robert Anton Wilson, offers imaginative narratives that, although tangential, evoke contemplation of the mystical ties between illumination and allure.
Moreover, drawing inspiration from the world of board games, the strategic dynamics of "Illuminati: New World Order" and the illuminating allure of "Lanterns: The Harvest Festival" serve as whimsical reminders of the multifaceted manifestations of illumination and attraction, albeit in the context of playful diversions.
While these literary and ludic references may appear to veer off the immediate path of academic inquiry, they subtly underscore the enigmatic nature of the kerosene-likeability relationship, infusing our review with a lighthearted nod to the unconventional connections at the heart of our investigation. In the subsequent analysis, we shall strive to bring further illumination to this intriguing correlation and, with any luck, pave the way for a brighter understanding of these seemingly disparate yet curiously intertwined phenomena.

[[RESULTS]]
The results of our analysis reveal a remarkably strong correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9721990, an r-squared of 0.9451710, and a p-value of less than 0.01, indicating a highly significant relationship. These findings suggest that there is a substantial association between the utilization of kerosene in Namibia and the propensity of online viewers to express their appreciation for numerical content.
Figure 1 provides a visual representation of the relationship between kerosene consumption and the average number of likes on Numberphile YouTube videos, demonstrating a clear and compelling trend. The scatterplot showcases the data points aligning themselves with almost mathematical precision, reinforcing the robustness of the correlation we have uncovered.
Our investigation into this unexpected linkage between kerosene usage and digital appreciation underscores the intricate and often unforeseen interplay between seemingly unrelated domains. These findings not only challenge conventional wisdom but also add a touch of whimsy to the typically staid world of statistical inquiry. The unexpected nature of this correlation serves as a potent reminder that the world of data analysis can yield surprising discoveries, akin to stumbling upon a hidden treasure in a seemingly mundane dataset.
The implications of these results extend beyond the mere statistical relationship; they beckon us to venture into uncharted territories of inquiry and provoke contemplation on the tantalizing mysteries of human behavior and societal dynamics. The convergence of kerosene consumption and digital engagement serves as a poignant reminder that in the vast landscape of research, unexpected connections can illuminate hitherto unseen patterns and provoke thoughtful reflection.
In conclusion, our study has brought to light a remarkable correlation between kerosene consumption in Namibia and the likeability of Numberphile YouTube videos. These findings prompt further exploration into the underlying mechanisms driving this peculiar relationship, paving the way for future investigations into the curious interplay between energy usage and online appreciation.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The results of our study confirmed the unexpectedly strong correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos, lending support to the prior research and opening up a realm of intriguing possibilities. The thorough analysis revealed a correlation coefficient of 0.9721990, solidifying the robust statistical relationship between these seemingly disparate phenomena.

Harking back to our lighthearted literary review, we cannot overlook the whimsical references to "The Illuminatus! Trilogy" and "Lanterns: The Harvest Festival," which, while seemingly eccentric, subtly hinted at the underlying mystical ties between illumination and allure. Our findings serve to underscore the enigmatic nature of this relationship, shedding light on the unexpected interconnectedness of the realms of illumination, energy, and online appreciation.

In a similar vein, the scholarly works of Smith and Doe (2015) and Jones et al. (2018) provided valuable insights into the socioeconomic implications of kerosene usage and the complexities of online audience engagement, respectively. The support from these prior studies fortifies the foundation of our investigation and invites further inquiry into the underlying mechanisms driving this unusual correlation.

The strong statistical relationship unearthed in our study not only challenges conventional wisdom but also injects a dash of whimsy into the traditionally serious domain of statistical inquiry. It serves as a reminder of the boundless potential for unexpected discoveries within the realm of data analysis, akin to an illuminating realization in the midst of seemingly routine statistical exploration.

Additionally, the interaction between kerosene consumption and digital engagement prompts contemplation on the mysterious allure of human behavior and societal dynamics. This unexpected correlation beckons further exploration into the uncharted territories of inquiry, inviting researchers to delve into the captivating mysteries of energy usage and online appreciation.

Our study serves as a shining example of the unpredictable and oftentimes peculiar connections that can emerge from rigorous statistical analyses, simultaneously illuminating hitherto unseen patterns and provoking thoughtful reflection. The robustness of the correlation between kerosene consumption in Namibia and the likeability of Numberphile YouTube videos suggests a compelling avenue for future investigations, unveiling the tantalizing potential for further revelations in the captivating realm of statistical inquiry.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between Kerosene used in Namibia and The average number of likes on Numberphile YouTube videos. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
"Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos"

[[ABSTRACT]]
In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

[[INTRDUCTION]]
The intersection of seemingly unrelated phenomena has long been a source of fascination and puzzlement for researchers across various disciplines. In the realm of energy consumption, kerosene has historically been utilized for lighting and cooking in regions where access to electricity is limited. Namibia, with its fluctuating kerosene consumption patterns, presents an intriguing case study for exploring the broader implications of energy use on environmental, economic, and social systems.
On the other side of the spectrum, the digital landscape of online content creation and consumption has spawned an era of unanticipated fame for specialized niches, including the enigmatic allure of Numberphile's YouTube channel. As a platform dedicated to unraveling the mysteries of mathematics and numbers in an engaging manner, the Numberphile community has fostered a unique culture of appreciation for numerical curiosities. The quantifiable expression of this appreciation, in the form of likes on its videos, serves as a potential window into the psyche of online audiences and their receptivity to numerical discourse.
While these two disparate domains may seem as unrelated as a logarithm and a lighthouse, our investigation into their correlation seeks to illuminate the unexpected connections that underlie the knotty tapestry of modern human behavior and societal dynamics. The juxtaposition of kerosene consumption in Namibia and the likeability of Numberphile YouTube videos may appear as incongruous as a polyhedron in the pantry, yet our initial foray into this uncharted territory has yielded promising insights.
As we delve deeper into the enigma of this linkage, it is our hope that this scholarly pursuit will not only enrich our understanding of the intricate web of influences that shape human preferences and actions, but also inject a dose of levity into the often somber domain of academic research. After all, who would have guessed that the flickering flames of kerosene lamps could be linked to the digital thumbs-ups of mathematical enthusiasts? It is precisely these quizzical connections that infuse our investigation with intrigue and allow us to bring a spark of curiosity to the often-sterile corridors of statistical inquiry.

[[RESULTS]]
The results of our analysis reveal a remarkably strong correlation between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Over the period of 2011 to 2021, we found a correlation coefficient of 0.9721990, an r-squared of 0.9451710, and a p-value of less than 0.01, indicating a highly significant relationship. These findings suggest that there is a substantial association between the utilization of kerosene in Namibia and the propensity of online viewers to express their appreciation for numerical content.
Figure 1 provides a visual representation of the relationship between kerosene consumption and the average number of likes on Numberphile YouTube videos, demonstrating a clear and compelling trend. The scatterplot showcases the data points aligning themselves with almost mathematical precision, reinforcing the robustness of the correlation we have uncovered.
Our investigation into this unexpected linkage between kerosene usage and digital appreciation underscores the intricate and often unforeseen interplay between seemingly unrelated domains. These findings not only challenge conventional wisdom but also add a touch of whimsy to the typically staid world of statistical inquiry. The unexpected nature of this correlation serves as a potent reminder that the world of data analysis can yield surprising discoveries, akin to stumbling upon a hidden treasure in a seemingly mundane dataset.
The implications of these results extend beyond the mere statistical relationship; they beckon us to venture into uncharted territories of inquiry and provoke contemplation on the tantalizing mysteries of human behavior and societal dynamics. The convergence of kerosene consumption and digital engagement serves as a poignant reminder that in the vast landscape of research, unexpected connections can illuminate hitherto unseen patterns and provoke thoughtful reflection.
In conclusion, our study has brought to light a remarkable correlation between kerosene consumption in Namibia and the likeability of Numberphile YouTube videos. These findings prompt further exploration into the underlying mechanisms driving this peculiar relationship, paving the way for future investigations into the curious interplay between energy usage and online appreciation.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, the findings of our research have brought an unexpected luminosity to the correlation between kerosene consumption in Namibia and the likeability of Numberphile YouTube videos. The substantial correlation coefficient of 0.9721990 and the convincingly low p-value point to an illuminating connection between these seemingly disparate entities. This eyebrow-raising linkage not only challenges conventional wisdom but also adds a dash of whimsy to the typically sober terrain of statistical inquiry.

It appears that the flickering flames of kerosene lamps in Namibia may indeed cast a glow on the digital thumbs-ups of mathematical enthusiasts. As our investigation delved into this uncharted territory, it not only shed light on this unexpected relationship but also kindled a sense of curiosity and amusement in the often sterile corridors of rigorous research. The visual representation in Figure 1 further illuminates the captivating trend, aligning data points with almost mathematical precision, as if the underlying pattern were following a formula of its own.

The discovery of this unlikely correlation serves as a gentle nudge to remember that even in the rigorous realms of statistical analysis, the element of surprise can be as prevalent as in any suspenseful plot. The unexpected combination of kerosene usage and online engagement beckons us to seek out hidden patterns and embrace the delightful mysteries that data can unfold.

In light of these findings, we assert that no further research is needed in this area. The compelling correlation we have uncovered encourages us to embrace the quirky connections that lurk within datasets and reminds us that in the colorful landscape of statistical inquiry, the most unexpected results can often yield the brightest insights.


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 Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Combustible Consumption and Social Media Influence


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 Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Comparative Combustion Studies


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 Kerosene and Kudos: Illuminating the Correlation Between Kerosene Consumption in Namibia and Likeability of Numberphile YouTube Videos with an abstract of In this paper, we investigate the surprising link between kerosene consumption in Namibia and the average number of likes on Numberphile YouTube videos. Utilizing data from the Energy Information Administration and YouTube, we conducted a rigorous analysis covering the years 2011 to 2021. Our findings reveal a remarkable correlation coefficient of 0.9721990 and a p-value of less than 0.01, indicating a strong statistical relationship. These unexpected results shed light on the potential influence of kerosene usage on online appreciation of numerical phenomena. Our study provides evidence of a peculiar connection between these seemingly disparate elements and prompts further inquiry into the underlying mechanisms at play.

ChatGPT:

Kerosene consumption Namibia, likeability Numberphile YouTube videos, correlation kerosene consumption and YouTube likes, Energy Information Administration Namibia, YouTube video likes analysis, kerosene usage online appreciation, statistical relationship kerosene consumption and YouTube likes, numerical phenomena online influence

*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

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

The average number of likes on Numberphile YouTube videos
Detailed data title: The average number of likes on Numberphile YouTube videos.
Source: Numberphile YouTube
See what else correlates with The average number of likes on Numberphile YouTube videos

Correlation r = 0.9721990 (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 = 0.9451710 (Coefficient of determination)
This means 94.5% of the change in the one variable (i.e., The average number of likes on Numberphile YouTube videos) is predictable based on the change in the other (i.e., Kerosene used in Namibia) over the 11 years from 2011 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 5.6E-7. 0.0000005601518590935621000000
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 0.97 in 5.6E-5% of random cases. Said differently, if you correlated 1,785,230 random variables You don't actually need 1 million variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

In this particular case, the values are so extreme as to be meaningless. That's why no one reports p-values with specificity after they drop below 0.01.

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 10 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 10 because we have two variables measured over a period of 11 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.

[ 0.89, 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.
20112012201320142015201620172018201920202021
Kerosene used in Namibia (Million Barrels/Day)0.04235620.06336070.04235620.04235620.0423560.042240.04235620.04235620.04345210.04153550.043827
The average number of likes on Numberphile YouTube videos (Average likes)17750.45815120879.81951921294.123676.22103717035.51843016989.716385.9




Why this works

  1. Data dredging: I have 25,237 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 636,906,169 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
  2. Lack of causal connection: There is probably Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
    no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
  3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
    p-value calculation does not take this into account, so mathematically it appears less probable than it really is.
  4. Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
    Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([0.0423562,0.0633607,0.0423562,0.0423562,0.042356,0.04224,0.0423562,0.0423562,0.0434521,0.0415355,0.043827,])
array_2 = np.array([17750.4,58151,20879.8,19519,21294.1,23676.2,21037,17035.5,18430,16989.7,16385.9,])
array_1_name = "Kerosene used in Namibia"
array_2_name = "The average number of likes on Numberphile 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?

Big thanks for reviewing!


Correlation ID: 5545 · Black Variable ID: 24725 · Red Variable ID: 25472
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0