about · email me · subscribe
Spurious correlation #1,387 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is xkcd comics published about romance and the second variable is Kerosene used in Malawi.  The chart goes from 2007 to 2021, and the two variables track closely in value over that time. Small Image
Download png
, svg

AI explanation

As xkcd romance comics decreased, fewer people were inspired to pursue grand romantic gestures. This led to a decrease in the demand for hot air balloon rides, a popular choice for wooing in Malawi. With less need for hot air balloon fuel, the kerosene usage in Malawi naturally decreased. Who knew that matters of the heart could affect fuel consumption in such an uplifting way!

Model: dalle-3
Prompt: Generate a whimsical illustration of two stick figures standing under a starry sky, holding hands and smiling at each other. They are surrounded by small kerosene lamps that glow softly, casting a warm, romantic light on the scene. The figures are bathed in a gentle, romantic glow, with a dreamy and enchanting atmosphere. 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: xkcd comics published about romance and Kerosene used in Malawi. 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: Minimalism Woodblock painting Data cyber art Whimsical illustration Scalar art
ChatGPT: Whimsical illustration

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 xkcd comics published about romance and Kerosene used in Malawi together. Keep the description simple.
ChatGPT: In the comic, two stick figures stand under a starry sky, holding hands and smiling at each other. They are surrounded by small kerosene lamps that glow softly, casting a warm, romantic light on the scene.

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: [ Whimsical illustration ] and depicting this scene: In the comic, two stick figures stand under a starry sky, holding hands and smiling at each other. They are surrounded by small kerosene lamps that glow softly, casting a warm, romantic light on the scene. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate a whimsical illustration of two stick figures standing under a starry sky, holding hands and smiling at each other. They are surrounded by small kerosene lamps that glow softly, casting a warm, romantic light on the scene. The figures are bathed in a gentle, romantic glow, with a dreamy and enchanting atmosphere.

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

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

Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how a decrease in xkcd comics published about romance caused Kerosene used in Malawi to decrease.

AI academic paper

(Because p < 0.01)
Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi

The Journal of Offbeat Social Science 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 goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You write titles and abstracts of goofy academic research papers.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

Your research team used data from AI analysis of xkcd comics and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.9742190 and p < 0.01 for 2007 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the introduction section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the introduction section of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
[[INTRODUCTION]]

In the annals of scientific inquiry, some research endeavors may seem as peculiar as a penguin in a desert. Our study, however, ventures into uncharted territory as we endeavor to unravel the correlation between the publication of xkcd comics on romance and the consumption of kerosene in the picturesque country of Malawi. This unique juxtaposition of playful webcomics and a vital energy source makes for an unexpected pairing, much like mixing helium and uranium – HeHe.

As we embark on this unconventional academic escapade, it is important to acknowledge the initial skepticism that we confronted, akin to a researcher trying to convince a statistician to use a non-parametric test. The seemingly disparate nature of our variables, not unlike a romantic fling between a chemist and a physicist, may have raised a few eyebrows. However, as we persevered, the significance of our findings became as clear as a well-constructed punchline.

With the aid of advanced AI technology, we combed through over a decade's worth of xkcd comics, dissecting the nuances of romance as portrayed in stick-figure form like a botanist examining the petals of a rare flower. The diligent analysis of these comics revealed surprisingly nuanced insights into the themes of love, relationships, and human interactions, all cleverly illustrated by Randall Munroe's iconic stick figures.

Simultaneously, like intrepid detectives following a trail of breadcrumbs, we combed through energy consumption data provided by the Energy Information Administration. The consumption of kerosene, a primary source of lighting and cooking fuel in many Malawian households, provided a window into an entirely different aspect of human existence – one that, not unlike a tiny spark, emanates light in the darkness.

Our research, much like a carefully constructed pun, not only unearthed a statistically significant association but also afforded a glimpse into the intricate interplay between cultural artifacts and tangible energy practices. The correlation coefficient of 0.9742190 and the impressively low p-value akin to a unicorn sighting, unequivocally underscore the robustness of our findings and the significance of this unlikely relationship.

Amidst this empirical journey, we found ourselves at the intersection of quantitative analysis and qualitative exploration, navigating the terrain of human emotions and energy consumption with equal parts precision and whimsy. Our results, much like a well-executed joke, are bound to elicit surprise and curiosity, paving the way for a broader discourse on the unconventional threads that weave the fabric of our world.

In traversing this uncharted territory, we invite our fellow scholars to approach this research with the levity of a well-timed jest and the gravity of a groundbreaking discovery. Our findings, much like a punchline in a stand-up routine, are sure to leave a lasting impression, encouraging a fresh perspective on the unexpected connections that shape our planet, one comic and one kerosene lamp at a time.


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

Please make up a literature review section of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the annals of scientific inquiry, some research endeavors may seem as peculiar as a penguin in a desert. Our study, however, ventures into uncharted territory as we endeavor to unravel the correlation between the publication of xkcd comics on romance and the consumption of kerosene in the picturesque country of Malawi. This unique juxtaposition of playful webcomics and a vital energy source makes for an unexpected pairing, much like mixing helium and uranium – HeHe.
As we embark on this unconventional academic escapade, it is important to acknowledge the initial skepticism that we confronted, akin to a researcher trying to convince a statistician to use a non-parametric test. The seemingly disparate nature of our variables, not unlike a romantic fling between a chemist and a physicist, may have raised a few eyebrows. However, as we persevered, the significance of our findings became as clear as a well-constructed punchline.
With the aid of advanced AI technology, we combed through over a decade's worth of xkcd comics, dissecting the nuances of romance as portrayed in stick-figure form like a botanist examining the petals of a rare flower. The diligent analysis of these comics revealed surprisingly nuanced insights into the themes of love, relationships, and human interactions, all cleverly illustrated by Randall Munroe's iconic stick figures.
Simultaneously, like intrepid detectives following a trail of breadcrumbs, we combed through energy consumption data provided by the Energy Information Administration. The consumption of kerosene, a primary source of lighting and cooking fuel in many Malawian households, provided a window into an entirely different aspect of human existence – one that, not unlike a tiny spark, emanates light in the darkness.
Our research, much like a carefully constructed pun, not only unearthed a statistically significant association but also afforded a glimpse into the intricate interplay between cultural artifacts and tangible energy practices. The correlation coefficient of 0.9742190 and the impressively low p-value akin to a unicorn sighting, unequivocally underscore the robustness of our findings and the significance of this unlikely relationship.
Amidst this empirical journey, we found ourselves at the intersection of quantitative analysis and qualitative exploration, navigating the terrain of human emotions and energy consumption with equal parts precision and whimsy. Our results, much like a well-executed joke, are bound to elicit surprise and curiosity, paving the way for a broader discourse on the unconventional threads that weave the fabric of our world.
In traversing this uncharted territory, we invite our fellow scholars to approach this research with the levity of a well-timed jest and the gravity of a groundbreaking discovery. Our findings, much like a punchline in a stand-up routine, are sure to leave a lasting impression, encouraging a fresh perspective on the unexpected connections that shape our planet, one comic and one kerosene lamp at a time.

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

The existing literature provides a foundation for our exploration of the correlation between xkcd comics centering around romance and the consumption of kerosene in Malawi. In "Love in the Time of Colic," Smith analyzes the impact of cultural representations of love on household energy consumption, offering insight into the role of popular media in shaping domestic energy practices. Similarly, Doe's work in "Energy and Emotions" delves into the emotional dimensions of energy use, illustrating the intricate interplay between emotive experiences and everyday energy consumption patterns. Conversely, Jones examines the socio-cultural implications of fuel choices in "Energizing Culture," shedding light on the multifaceted factors that influence energy usage in diverse societal contexts.

As we humorously waltz through the literature, we cannot overlook the playful insights of Munroe's "xkcd: Volume 0," which provides a compelling array of stick-figure narratives that capture the essence of human relationships. Moreover, "What If?: Serious Scientific Answers to Absurd Hypothetical Questions" by Randall Munroe fosters a spirit of intellectual curiosity and creativity, echoing the whimsical nature of our present inquiry. In a similar vein, "The Art of Loving" by Erich Fromm offers a philosophical perspective on the nature of love, serving as a poignant backdrop to our examination of romance in xkcd comics and its potential influence on kerosene consumption.

Venturing into the realm of fiction, our literature review takes an unexpected turn, much like a suddenly dramatic plot twist in a rom-com. "Love in the Time of Cholera" by Gabriel García Márquez evokes a rich tapestry of romantic narratives, albeit unrelated to our focus on xkcd comics and kerosene. Likewise, "The Kerosene Cowboys" by D.B. Jackson interweaves tales of adventure with Western motifs, providing a picturesque escape from our scholarly pursuits (and an unexpected juxtaposition with our research theme).

In an irreverently unconventional move for a literature review, we pored over the disparate strands of non-academic sources, including, but not limited to, the contents of assorted fortune cookies, the sprawling narratives of supermarket tabloids, and even the nuanced revelations hidden within CVS receipts. While such sources may not meet the usual standards of scholarly rigor, they undeniably contributed to our interdisciplinary understanding of the phenomenon at hand – like a surprise ingredient in an experimental recipe.

The juxtaposition of scholarly works, fictional narratives, and whimsical sources reflects our commitment to approaching research with a blend of rigour and playfulness. This diverse tapestry of references not only sets the stage for our investigation into the interconnection of xkcd comics about romance and kerosene consumption in Malawi but also underscores the unexpected tangents that can infuse academic inquiry with humor and creativity.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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 xkcd comics and Energy Information Administration . You used data from 2007 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

[[INTRODUCTION]]
In the annals of scientific inquiry, some research endeavors may seem as peculiar as a penguin in a desert. Our study, however, ventures into uncharted territory as we endeavor to unravel the correlation between the publication of xkcd comics on romance and the consumption of kerosene in the picturesque country of Malawi. This unique juxtaposition of playful webcomics and a vital energy source makes for an unexpected pairing, much like mixing helium and uranium – HeHe.
As we embark on this unconventional academic escapade, it is important to acknowledge the initial skepticism that we confronted, akin to a researcher trying to convince a statistician to use a non-parametric test. The seemingly disparate nature of our variables, not unlike a romantic fling between a chemist and a physicist, may have raised a few eyebrows. However, as we persevered, the significance of our findings became as clear as a well-constructed punchline.
With the aid of advanced AI technology, we combed through over a decade's worth of xkcd comics, dissecting the nuances of romance as portrayed in stick-figure form like a botanist examining the petals of a rare flower. The diligent analysis of these comics revealed surprisingly nuanced insights into the themes of love, relationships, and human interactions, all cleverly illustrated by Randall Munroe's iconic stick figures.
Simultaneously, like intrepid detectives following a trail of breadcrumbs, we combed through energy consumption data provided by the Energy Information Administration. The consumption of kerosene, a primary source of lighting and cooking fuel in many Malawian households, provided a window into an entirely different aspect of human existence – one that, not unlike a tiny spark, emanates light in the darkness.
Our research, much like a carefully constructed pun, not only unearthed a statistically significant association but also afforded a glimpse into the intricate interplay between cultural artifacts and tangible energy practices. The correlation coefficient of 0.9742190 and the impressively low p-value akin to a unicorn sighting, unequivocally underscore the robustness of our findings and the significance of this unlikely relationship.
Amidst this empirical journey, we found ourselves at the intersection of quantitative analysis and qualitative exploration, navigating the terrain of human emotions and energy consumption with equal parts precision and whimsy. Our results, much like a well-executed joke, are bound to elicit surprise and curiosity, paving the way for a broader discourse on the unconventional threads that weave the fabric of our world.
In traversing this uncharted territory, we invite our fellow scholars to approach this research with the levity of a well-timed jest and the gravity of a groundbreaking discovery. Our findings, much like a punchline in a stand-up routine, are sure to leave a lasting impression, encouraging a fresh perspective on the unexpected connections that shape our planet, one comic and one kerosene lamp at a time.

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

In this study, the methodology employed to unravel the curious relationship between xkcd comics featuring romance and kerosene consumption in Malawi was as meticulously crafted as a well-structured pun. The research team harnessed a combination of advanced AI analysis of xkcd comics and rigorously obtained data from the Energy Information Administration. This approach, much like serving up a biology joke to a group of chemists, aimed to blend humor with precision to shed light on this unconventional correlation.

To initiate the investigative process, an extensive dataset of xkcd comics dating from 2007 to 2021 was procured, cataloged, and meticulously analyzed. Advanced AI algorithms, reminiscent of a stand-up comedian honing their craft, were employed to detect and categorize the themes and instances of romance, love, and relationships within the corpus of webcomics. This process, akin to separating the knock-knock jokes from the punchlines, ensured a nuanced understanding of the portrayal of romance in Randall Munroe's iconic stick-figure art.

Simultaneously, the research team embarked on a quest to gather comprehensive data on kerosene consumption in Malawi during the same period. The Energy Information Administration, akin to an encyclopedia of energy statistics, was tapped into to acquire detailed information on the consumption patterns and trends of kerosene, a primary source of lighting and cooking fuel in Malawian households. This data, much like a trusty sidekick, accompanied the comic analysis to form the basis for uncovering the unexpected connections between cultural artifacts and real-world energy usage.

With the comedic diligence of a comedy writer testing out a new joke, statistical analyses were then conducted to quantify the observed relationship between the themes of romance in xkcd comics and the consumption of kerosene in Malawi. Through the application of robust correlation analyses and regression models, the team aimed to decipher the strength and direction of this peculiar association, emphasizing the importance of rigorous scientific inquiry even in the face of unconventional research subjects.

Furthermore, the qualitative aspects of the relationship between xkcd comics and kerosene consumption were explored through thematic analysis and contextual interpretation. The team engaged in an interpretive dance with the data, examining the nuanced storytelling within the comics and the socio-cultural implications of kerosene use in Malawi. This qualitative investigation, much like a cleverly placed double entendre, added depth and insight to our understanding of the intertwined narratives of comic romance and real-world energy practices.

Throughout this methodological journey, the research team maintained a balanced blend of scientific rigor and playful exploration, likening our approach to a well-crafted joke that combines wit with precision. The confluence of AI-driven comic analysis, comprehensive energy data collection, and robust statistical and qualitative methodologies formed the bedrock of our investigation, ensuring a thorough and multi-faceted examination of the unexpected correlation between xkcd romance and kerosene consumption in Malawi.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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 xkcd comics and Energy Information Administration .

For the time period 2007 to 2021, you found a correlation 0.9742190, r-squared of 0.9491026, 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the annals of scientific inquiry, some research endeavors may seem as peculiar as a penguin in a desert. Our study, however, ventures into uncharted territory as we endeavor to unravel the correlation between the publication of xkcd comics on romance and the consumption of kerosene in the picturesque country of Malawi. This unique juxtaposition of playful webcomics and a vital energy source makes for an unexpected pairing, much like mixing helium and uranium – HeHe.
As we embark on this unconventional academic escapade, it is important to acknowledge the initial skepticism that we confronted, akin to a researcher trying to convince a statistician to use a non-parametric test. The seemingly disparate nature of our variables, not unlike a romantic fling between a chemist and a physicist, may have raised a few eyebrows. However, as we persevered, the significance of our findings became as clear as a well-constructed punchline.
With the aid of advanced AI technology, we combed through over a decade's worth of xkcd comics, dissecting the nuances of romance as portrayed in stick-figure form like a botanist examining the petals of a rare flower. The diligent analysis of these comics revealed surprisingly nuanced insights into the themes of love, relationships, and human interactions, all cleverly illustrated by Randall Munroe's iconic stick figures.
Simultaneously, like intrepid detectives following a trail of breadcrumbs, we combed through energy consumption data provided by the Energy Information Administration. The consumption of kerosene, a primary source of lighting and cooking fuel in many Malawian households, provided a window into an entirely different aspect of human existence – one that, not unlike a tiny spark, emanates light in the darkness.
Our research, much like a carefully constructed pun, not only unearthed a statistically significant association but also afforded a glimpse into the intricate interplay between cultural artifacts and tangible energy practices. The correlation coefficient of 0.9742190 and the impressively low p-value akin to a unicorn sighting, unequivocally underscore the robustness of our findings and the significance of this unlikely relationship.
Amidst this empirical journey, we found ourselves at the intersection of quantitative analysis and qualitative exploration, navigating the terrain of human emotions and energy consumption with equal parts precision and whimsy. Our results, much like a well-executed joke, are bound to elicit surprise and curiosity, paving the way for a broader discourse on the unconventional threads that weave the fabric of our world.
In traversing this uncharted territory, we invite our fellow scholars to approach this research with the levity of a well-timed jest and the gravity of a groundbreaking discovery. Our findings, much like a punchline in a stand-up routine, are sure to leave a lasting impression, encouraging a fresh perspective on the unexpected connections that shape our planet, one comic and one kerosene lamp at a time.

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The analysis of the data revealed a remarkably strong correlation between the number of xkcd comics featuring romance and the consumption of kerosene in Malawi. With a correlation coefficient of 0.9742190, our findings indicate a robust relationship between these seemingly unrelated variables, much like the intricate dance of protons and electrons in a chemical reaction – they may seem distant, but they're undeniably connected.

The r-squared value of 0.9491026 further solidifies the strength of this association, highlighting the extent to which changes in the publication of romance-themed xkcd comics can be predictive of variations in kerosene consumption in Malawi. It's almost as if the comics are casting a spell on the kerosene consumption data, weaving an enchanting tale of correlation.

Our findings were bolstered by the statistical significance of the relationship, with a p-value of less than 0.01. This level of significance is as clear-cut as a good dad joke – there's no room for ambiguity here. It's statistically sound, just like a nerdy pun at a science convention.

Furthermore, the analysis culminates in the presentation of a visually compelling scatterplot (Fig. 1), serving as a testament to the strength of the correlation uncovered in our research. This figure encapsulates the interconnectedness of xkcd romance comics and kerosene consumption in Malawi, akin to the fusion of hydrogen nuclei in the heart of a star – a dazzling display of harmony between two disparate elements.


Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

[[LITERATURE REVIEW]]
The existing literature provides a foundation for our exploration of the correlation between xkcd comics centering around romance and the consumption of kerosene in Malawi. In "Love in the Time of Colic," Smith analyzes the impact of cultural representations of love on household energy consumption, offering insight into the role of popular media in shaping domestic energy practices. Similarly, Doe's work in "Energy and Emotions" delves into the emotional dimensions of energy use, illustrating the intricate interplay between emotive experiences and everyday energy consumption patterns. Conversely, Jones examines the socio-cultural implications of fuel choices in "Energizing Culture," shedding light on the multifaceted factors that influence energy usage in diverse societal contexts.
As we humorously waltz through the literature, we cannot overlook the playful insights of Munroe's "xkcd: Volume 0," which provides a compelling array of stick-figure narratives that capture the essence of human relationships. Moreover, "What If?: Serious Scientific Answers to Absurd Hypothetical Questions" by Randall Munroe fosters a spirit of intellectual curiosity and creativity, echoing the whimsical nature of our present inquiry. In a similar vein, "The Art of Loving" by Erich Fromm offers a philosophical perspective on the nature of love, serving as a poignant backdrop to our examination of romance in xkcd comics and its potential influence on kerosene consumption.
Venturing into the realm of fiction, our literature review takes an unexpected turn, much like a suddenly dramatic plot twist in a rom-com. "Love in the Time of Cholera" by Gabriel García Márquez evokes a rich tapestry of romantic narratives, albeit unrelated to our focus on xkcd comics and kerosene. Likewise, "The Kerosene Cowboys" by D.B. Jackson interweaves tales of adventure with Western motifs, providing a picturesque escape from our scholarly pursuits (and an unexpected juxtaposition with our research theme).
In an irreverently unconventional move for a literature review, we pored over the disparate strands of non-academic sources, including, but not limited to, the contents of assorted fortune cookies, the sprawling narratives of supermarket tabloids, and even the nuanced revelations hidden within CVS receipts. While such sources may not meet the usual standards of scholarly rigor, they undeniably contributed to our interdisciplinary understanding of the phenomenon at hand – like a surprise ingredient in an experimental recipe.
The juxtaposition of scholarly works, fictional narratives, and whimsical sources reflects our commitment to approaching research with a blend of rigour and playfulness. This diverse tapestry of references not only sets the stage for our investigation into the interconnection of xkcd comics about romance and kerosene consumption in Malawi but also underscores the unexpected tangents that can infuse academic inquiry with humor and creativity.

[[RESULTS]]
The analysis of the data revealed a remarkably strong correlation between the number of xkcd comics featuring romance and the consumption of kerosene in Malawi. With a correlation coefficient of 0.9742190, our findings indicate a robust relationship between these seemingly unrelated variables, much like the intricate dance of protons and electrons in a chemical reaction – they may seem distant, but they're undeniably connected.
The r-squared value of 0.9491026 further solidifies the strength of this association, highlighting the extent to which changes in the publication of romance-themed xkcd comics can be predictive of variations in kerosene consumption in Malawi. It's almost as if the comics are casting a spell on the kerosene consumption data, weaving an enchanting tale of correlation.
Our findings were bolstered by the statistical significance of the relationship, with a p-value of less than 0.01. This level of significance is as clear-cut as a good dad joke – there's no room for ambiguity here. It's statistically sound, just like a nerdy pun at a science convention.
Furthermore, the analysis culminates in the presentation of a visually compelling scatterplot (Fig. 1), serving as a testament to the strength of the correlation uncovered in our research. This figure encapsulates the interconnectedness of xkcd romance comics and kerosene consumption in Malawi, akin to the fusion of hydrogen nuclei in the heart of a star – a dazzling display of harmony between two disparate elements.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The significant correlation between the publication of xkcd comics featuring romance and the consumption of kerosene in Malawi evokes a reflection not only on the unexpected synchronicities in our world but also on the potential societal and cultural factors underpinning such an association. Our findings lend credence to the role of popular culture in influencing real-world behaviors and resource utilization, like a good dad joke making its way into a serious discussion.

Building on the literature review, which humorously meandered through diverse realms, including the philosophical musings of Erich Fromm and the unexpected tangents of non-academic sources, our research supported the notion that cultural representations of love and relationships can indeed impact energy consumption patterns. The parallels drawn by Smith between cultural depictions of love and household energy consumption find resonance in our uncovering of a tangible link between romance-themed xkcd comics and kerosene usage. It's as if our findings emerged from the punchline of a cosmic joke, tying together seemingly incongruous elements.

Similar to the spirited curiosity fostered by Randall Munroe's works, our research invites a lighthearted yet substantial exploration of interconnected phenomena. While we approached the analysis with the precision of a lab scientist, we couldn't resist infusing our work with the whimsy found in Munroe's stick-figure narratives. This interplay of rigor and levity epitomizes the fusion of scholarly inquiry and creative thinking, much like a good quip in the midst of a data discussion.

Furthermore, our findings echo the themes of unexpected connections and intertwined fates that underpin Munroe's style. The robust correlation coefficient and r-squared value underscore the depth of the relationship identified, akin to the coherence of a well-constructed scientific argument or a clever play on words. The statistical significance, with a p-value of less than 0.01, cements the validity of our results, much like a well-timed punchline in a comedic routine – it's undeniably impactful.

In essence, our research not only unravels a surprising correlation but also illuminates the interplay of seemingly unrelated elements in a manner that sparks intrigue and invites further interdisciplinary investigations. As we peer through the lens of xkcd comics and kerosene consumption in Malawi, we find ourselves in a terrain where science and humor intersect, much like the meeting point of two opposing magnetic poles – it's both electrifying and amusing.


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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between xkcd comics published about romance and Kerosene used in Malawi. 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]]
"Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi"

[[ABSTRACT]]
The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.

As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.

We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

[[INTRDUCTION]]
In the annals of scientific inquiry, some research endeavors may seem as peculiar as a penguin in a desert. Our study, however, ventures into uncharted territory as we endeavor to unravel the correlation between the publication of xkcd comics on romance and the consumption of kerosene in the picturesque country of Malawi. This unique juxtaposition of playful webcomics and a vital energy source makes for an unexpected pairing, much like mixing helium and uranium – HeHe.
As we embark on this unconventional academic escapade, it is important to acknowledge the initial skepticism that we confronted, akin to a researcher trying to convince a statistician to use a non-parametric test. The seemingly disparate nature of our variables, not unlike a romantic fling between a chemist and a physicist, may have raised a few eyebrows. However, as we persevered, the significance of our findings became as clear as a well-constructed punchline.
With the aid of advanced AI technology, we combed through over a decade's worth of xkcd comics, dissecting the nuances of romance as portrayed in stick-figure form like a botanist examining the petals of a rare flower. The diligent analysis of these comics revealed surprisingly nuanced insights into the themes of love, relationships, and human interactions, all cleverly illustrated by Randall Munroe's iconic stick figures.
Simultaneously, like intrepid detectives following a trail of breadcrumbs, we combed through energy consumption data provided by the Energy Information Administration. The consumption of kerosene, a primary source of lighting and cooking fuel in many Malawian households, provided a window into an entirely different aspect of human existence – one that, not unlike a tiny spark, emanates light in the darkness.
Our research, much like a carefully constructed pun, not only unearthed a statistically significant association but also afforded a glimpse into the intricate interplay between cultural artifacts and tangible energy practices. The correlation coefficient of 0.9742190 and the impressively low p-value akin to a unicorn sighting, unequivocally underscore the robustness of our findings and the significance of this unlikely relationship.
Amidst this empirical journey, we found ourselves at the intersection of quantitative analysis and qualitative exploration, navigating the terrain of human emotions and energy consumption with equal parts precision and whimsy. Our results, much like a well-executed joke, are bound to elicit surprise and curiosity, paving the way for a broader discourse on the unconventional threads that weave the fabric of our world.
In traversing this uncharted territory, we invite our fellow scholars to approach this research with the levity of a well-timed jest and the gravity of a groundbreaking discovery. Our findings, much like a punchline in a stand-up routine, are sure to leave a lasting impression, encouraging a fresh perspective on the unexpected connections that shape our planet, one comic and one kerosene lamp at a time.

[[RESULTS]]
The analysis of the data revealed a remarkably strong correlation between the number of xkcd comics featuring romance and the consumption of kerosene in Malawi. With a correlation coefficient of 0.9742190, our findings indicate a robust relationship between these seemingly unrelated variables, much like the intricate dance of protons and electrons in a chemical reaction – they may seem distant, but they're undeniably connected.
The r-squared value of 0.9491026 further solidifies the strength of this association, highlighting the extent to which changes in the publication of romance-themed xkcd comics can be predictive of variations in kerosene consumption in Malawi. It's almost as if the comics are casting a spell on the kerosene consumption data, weaving an enchanting tale of correlation.
Our findings were bolstered by the statistical significance of the relationship, with a p-value of less than 0.01. This level of significance is as clear-cut as a good dad joke – there's no room for ambiguity here. It's statistically sound, just like a nerdy pun at a science convention.
Furthermore, the analysis culminates in the presentation of a visually compelling scatterplot (Fig. 1), serving as a testament to the strength of the correlation uncovered in our research. This figure encapsulates the interconnectedness of xkcd romance comics and kerosene consumption in Malawi, akin to the fusion of hydrogen nuclei in the heart of a star – a dazzling display of harmony between two disparate elements.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a fascinating connection between the publication of xkcd comics on romance and the consumption of kerosene in Malawi. It's as surprising as finding out that statistical outliers have their own social club. The robust correlation coefficient of 0.9742190 and the rock-solid r-squared value of 0.9491026 paint a vivid picture of the intertwined nature of these variables, much like a beautifully entangled pair of particles in quantum physics.

Our results, with a p-value of less than 0.01, stand as firm as a dad's insistence that his puns are funny – statistically significant and impossible to ignore. We've shed light on an unconventional relationship that's as unexpected as a sudden plot twist in a telenovela. This finding raises the question – are the xkcd romance comics igniting sparks of inspiration that lead to increased kerosene consumption, or is there something more profound at play here, much like a Shakespearean sonnet disguised as a knock-knock joke?

This research opens doors to a new realm of interdisciplinary exploration, much like a secret passage in a medieval castle – full of unexpected connections and hidden gems waiting to be unearthed. Let's flip the switch on further investigation and bask in the glow of this illuminating discovery. With that being said, it's clear that no more research is needed in this area. We've cracked the code and sparked the conversation. It's time to let this quirky duo of xkcd comics and kerosene shine on their own.


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 Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Offbeat Social Science 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 Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Quirky Research Advancement and Investigation (SQRAI)


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 Sparks Flying: Exploring the Correlation Between xkcd Comics on Romance and Kerosene Consumption in Malawi with an abstract of The study investigates the surprising yet intriguing relationship between xkcd comics featuring romance and the consumption of kerosene in Malawi. By leveraging advanced AI analysis of xkcd comics and obtaining data from the Energy Information Administration, our research team delved into this unconventional link. While our findings are sure to light a spark in the academic community, they also shed light on the importance and implications of seemingly unrelated phenomena converging in unforeseen ways.
As we navigated through the data like a miner in a pun mine, we uncovered a correlation coefficient of 0.9742190 and a statistically significant p-value of less than 0.01 for the period spanning from 2007 to 2021. This association, like a well-crafted dad joke, is not to be overlooked. Our research, much like a romantic comedy, provides a delightful twist, showcasing the unexpected interconnectedness between seemingly disparate elements of popular culture and real-world energy consumption.
We present not only quantitative evidence but also delve into the qualitative aspects with a good dose of humor, much like a romantic date with a stand-up comedian. This research, albeit unconventional, opens new avenues for interdisciplinary exploration and underscores the value of approaching empirical analysis with an open mind.

ChatGPT:

xkcd comics, romance, kerosene consumption, Malawi, correlation, AI analysis, Energy Information Administration, correlation coefficient, p-value, popular culture, real-world energy consumption, interdisciplinary exploration, empirical analysis

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

xkcd comics published about romance
Detailed data title: The number of xkcd comics published each year about romance
Source: AI analysis of xkcd comics
Additional Info: I designed a Python workflow to perform OCR on every xkcd comic, feed that text into a large language model, and ask the model whether this comic was about the category named in the title.

See what else correlates with xkcd comics published about romance

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

Correlation r = 0.9742190 (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 = 0.9491026 (Coefficient of determination)
This means 94.9% of the change in the one variable (i.e., Kerosene used in Malawi) is predictable based on the change in the other (i.e., xkcd comics published about romance) over the 15 years from 2007 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 8.71E-10. 0.0000000008708627934047282000
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 8.71E-8% of random cases. Said differently, if you correlated 1,148,286,513 random variables You don't actually need 1 billion 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 14 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 14 because we have two variables measured over a period of 15 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.

[ 0.92, 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.
200720082009201020112012201320142015201620172018201920202021
xkcd comics published about romance (xkcd comics)383521281118343231156
Kerosene used in Malawi (Million Barrels/Day)0.3120970.3078250.2160670.1972050.1166080.09576770.02743730.02743730.0086830.0145720.01108030.008299340.008690410.008307090.00876539




Why this works

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




Try it yourself

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

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

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

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

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

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

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

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

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


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

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

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

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

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([38,35,21,28,11,18,3,4,3,2,3,1,1,5,6,])
array_2 = np.array([0.312097,0.307825,0.216067,0.197205,0.116608,0.0957677,0.0274373,0.0274373,0.008683,0.014572,0.0110803,0.00829934,0.00869041,0.00830709,0.00876539,])
array_1_name = "xkcd comics published about romance"
array_2_name = "Kerosene used in Malawi"

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

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



Reuseable content

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

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

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

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

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

Download images for these variables:


View another random correlation

How fun was this correlation?

Your rating skills are top-notch!


Correlation ID: 1387 · Black Variable ID: 20013 · Red Variable ID: 24660
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0