Spurious correlation #1,069 · 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 El Salvador and the second variable is Google searches for 'attacked by a squirrel'. The chart goes from 2004 to 2021, and the two variables track closely in value over that time.

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Kerosene used in El Salvador and the second variable is Google searches for 'attacked by a squirrel'. The chart goes from 2004 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As kerosene usage decreased in El Salvador, there were fewer open flames to attract the attention of the power-hungry squirrel overlords, leading to a decrease in their organized attacks on unsuspecting individuals. Without the allure of fiery chaos, the squirrels decided to pursue more peaceful activities like acorn gathering and competitive tree climbing, leaving the people of El Salvador with a slightly lower risk of encountering vengeful, flame-loving squirrels. Remember, a squirrel's plans can be easily derailed when there are no kerosene-fueled sparks flying to ignite their bushy-tailed ambitions!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image inspired by a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s depicting a small rural village in El Salvador. Show families using kerosene lamps for lighting and a scene where the villagers switch to solar-powered lights. Illustrate how the reduction in kerosene use has led to fewer aggressive squirrels, creating a safer environment for the villagers. The visual depiction should be simple, without any words or speech bubbles. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the situation described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here is a situation: Decreased kerosene usage in El Salvador led to a decrease in attacked by a squirrel Google searches, as fewer kerosene fumes meant squirrels were less likely to get "lit" and become aggressive, leading to fewer instances of attacks on unsuspecting individuals.. Given that situation, which of the following image descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand and the tone of the explanation. Please respond with only one of the following potential descriptions: Oragami A photo-realistic image Art nouveau Whimsical illustration A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s
ChatGPT: A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated and the explanation described. Do not reference graphs or charts; describe physical objects.
User prompt: Please describe a visual scene that depicts the following situation. Keep the description simple. Decreased kerosene usage in El Salvador led to a decrease in attacked by a squirrel Google searches, as fewer kerosene fumes meant squirrels were less likely to get "lit" and become aggressive, leading to fewer instances of attacks on unsuspecting individuals.
ChatGPT: Imagine a small rural village in El Salvador, where families used to use kerosene lamps for lighting. In the past, there were frequent incidents of aggressive squirrels attacking people in the village. Now, picture a scene where the villagers have switched to solar-powered lights, reducing the use of kerosene. As a result, there are fewer squirrels behaving aggressively, and people are less likely to be attacked.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s ] and depicting this scene: Imagine a small rural village in El Salvador, where families used to use kerosene lamps for lighting. In the past, there were frequent incidents of aggressive squirrels attacking people in the village. Now, picture a scene where the villagers have switched to solar-powered lights, reducing the use of kerosene. As a result, there are fewer squirrels behaving aggressively, and people are less likely to be attacked. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image inspired by a comic-book-style illustration with muted colors and a dotted halftone pattern from the 1960s depicting a small rural village in El Salvador. Show families using kerosene lamps for lighting and a scene where the villagers switch to solar-powered lights. Illustrate how the reduction in kerosene use has led to fewer aggressive squirrels, creating a safer environment for the villagers. The visual depiction should be simple, without any words or speech bubbles.

*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.
^{Show prompt for explanation} 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 Kerosene used in El Salvador caused attacked by a squirrel (Google searches for 'attacked by a squirrel') to decrease.

AI academic paper

(Because p < 0.01)

Burning Questions: The Kerosene Connection - A Squirrely Correlation?

The Journal of Rodent-Powered Energy Research

Jan 2024

Reminder: This paper is AI-generated. Not real!

^{Show prompt used to generate this paper} 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 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 El Salvador and Google searches for 'attacked by a squirrel'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

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

Here is the title and abstract of the paper:
[[TITLE]]
"Burning Questions: The Kerosene Connection - A Squirrely Correlation?"

[[ABSTRACT]]
Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
Introduction
The study of correlations between seemingly unrelated variables has long captured the imagination of researchers and statisticians alike. It is in this spirit of curiosity and unlikely connections that we embark on an investigation into the curious relationship between Kerosene consumption in El Salvador and the inexplicable surge in Google searches for "attacked by a squirrel".
Kerosene, a staple household fuel in many regions, has typically been examined through the lenses of economics, public health, and environmental impact. However, little attention has been paid to its potential ripple effects on the world of internet search behavior. Meanwhile, the peculiar phrase "attacked by a squirrel" has emerged as an enigmatic and, some might say, quirky phenomenon within the realm of online inquiries.
In this study, we harness the power of data from the Energy Information Administration and Google Trends to uncover and analyze the unexpected correlation between these two disparate variables. Our statistical analysis yields a correlation coefficient of 0.9042740, accompanied by a remarkably significant p-value of less than 0.01, spanning the years 2004 to 2021. These findings, at first glance, may appear whimsical, but they carry profound implications for our understanding of the seemingly random dance of human behavior and the underlying forces that tie together the ordinary and the unconventional.
As we delve into this curious correlation, we invite the reader to join us on a journey that blends the rigor of statistical analysis with the lighthearted curiosity that propels us to explore uncharted territory. Through this exploration, we seek to challenge conventional boundaries of inquiry and provoke contemplation on the interconnectedness of seemingly unrelated phenomena. In doing so, we hope to spark a reevaluation of the boundaries of interdisciplinary research and foster a deeper appreciation for the intricate tapestry that weaves together the mundane and the extraordinary.
So, let us don our statistical goggles and embark on an expedition that promises to illuminate the unexpected intersections of Kerosene consumption and squirrel-related searches, demonstrating the delightful unpredictability that often accompanies the pursuit of scientific inquiry.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

In the realm of energy consumption and its societal ramifications, Smith (2015) delves into the intricate web of household fuel usage in developing countries, shedding light on the socioeconomic dynamics at play. Similarly, Doe and Jones (2018) offer a comprehensive analysis of internet search patterns and the behavioral insights that can be gleaned from them, paving the way for a deeper understanding of the digital landscape.

Moving beyond the immediate domains of energy economics and online behavior, Williams and Brown (2009) present a thought-provoking examination of wildlife encounters and the psychological impacts they may impart on individuals. This exploration resonates with the unanticipated surge in searches for the phrase "attacked by a squirrel," hinting at the curious intersections of human-wildlife interactions in the digital sphere.

On a more lighthearted note, "Squirrels: A Cultural History" by Adams (2019) provides a whimsical yet informative journey into the folklore and cultural significance of these fuzzy-tailed creatures. While not a scholarly work per se, the charming anecdotes and historical tidbits woven into the narrative offer a delightful backdrop against which to consider the unexpected rise in squirrel-related internet queries.

In the realm of fiction, the works of author Acorn include "The Secret Life of Squirrels" series which, while certainly not rigorous scientific literature, captures the imagination with its playful portrayal of squirrel antics. The parallel between these fictional musings and the genuine curiosity exhibited in internet searches for squirrel-related encounters lends credence to the notion that truth can be stranger than fiction.

In the pursuit of understanding human behavior and its quirky inclinations, our researchers also turned their attention to television shows that might offer insight into the fascination with squirrel encounters. The investigative nature of "CSI: Squirrel Squad" and the comedic take on urban wildlife in "Parks and Recreation" sparked incidental curiosity, leading to a deeper contemplation of the unexpected intersections between real-world events and the pop culture narratives that color our lives.

Thus, the mosaic of literature and cultural representations surrounding our subject matter lays the groundwork for a multidimensional exploration of the unlikely correlation between Kerosene consumption in El Salvador and the surge in Google searches for "attacked by a squirrel". While playful in its underpinnings, this investigation carries significant implications for our understanding of human behavior, the digital landscape, and the complex tapestry of interconnected phenomena that shape our world.

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 Kerosene used in El Salvador and Google searches for 'attacked by a squirrel'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Energy Information Administration and Google Trends . You used data from 2004 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]]
"Burning Questions: The Kerosene Connection - A Squirrely Correlation?"

[[ABSTRACT]]
Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

[[INTRODUCTION]]
Introduction
The study of correlations between seemingly unrelated variables has long captured the imagination of researchers and statisticians alike. It is in this spirit of curiosity and unlikely connections that we embark on an investigation into the curious relationship between Kerosene consumption in El Salvador and the inexplicable surge in Google searches for "attacked by a squirrel".
Kerosene, a staple household fuel in many regions, has typically been examined through the lenses of economics, public health, and environmental impact. However, little attention has been paid to its potential ripple effects on the world of internet search behavior. Meanwhile, the peculiar phrase "attacked by a squirrel" has emerged as an enigmatic and, some might say, quirky phenomenon within the realm of online inquiries.
In this study, we harness the power of data from the Energy Information Administration and Google Trends to uncover and analyze the unexpected correlation between these two disparate variables. Our statistical analysis yields a correlation coefficient of 0.9042740, accompanied by a remarkably significant p-value of less than 0.01, spanning the years 2004 to 2021. These findings, at first glance, may appear whimsical, but they carry profound implications for our understanding of the seemingly random dance of human behavior and the underlying forces that tie together the ordinary and the unconventional.
As we delve into this curious correlation, we invite the reader to join us on a journey that blends the rigor of statistical analysis with the lighthearted curiosity that propels us to explore uncharted territory. Through this exploration, we seek to challenge conventional boundaries of inquiry and provoke contemplation on the interconnectedness of seemingly unrelated phenomena. In doing so, we hope to spark a reevaluation of the boundaries of interdisciplinary research and foster a deeper appreciation for the intricate tapestry that weaves together the mundane and the extraordinary.
So, let us don our statistical goggles and embark on an expedition that promises to illuminate the unexpected intersections of Kerosene consumption and squirrel-related searches, demonstrating the delightful unpredictability that often accompanies the pursuit of scientific inquiry.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To unravel the enigmatic entanglement of Kerosene consumption and the curious fascination with squirrel attacks, our research team adopted a multifaceted approach that combined quantitative analysis and a healthy dose of speculative whimsy.

Data Collection:
Our first foray into this zany expedition involved the collection of Kerosene consumption data from the Energy Information Administration, which provided a comprehensive overview of annual Kerosene usage in the vibrant and ever-surprising land of El Salvador. Meanwhile, to gauge the digital intrigue surrounding squirrel skirmishes, we ventured into the untamed wilderness of Google Trends, capturing the ebb and flow of "attacked by a squirrel" searches from the boundless expanse of the world wide web. These datasets, spanning the years 2004 to 2021, formed the bedrock of our investigative escapade.

Normalization and Standardization:
Armed with our troves of data, we set about the noble task of wrangling these disparate streams into a coherent and harmonious format. Our team skillfully normalized the Kerosene consumption figures to adjust for population growth, economic fluctuations, and the mercurial whims of consumer behavior. Simultaneously, we standardized the shadowy statistics of squirrel-inflicted search queries, ensuring that our cross-dimensional voyages would yield reliable and comparable findings.

Statistical Alchemy:
The heart of our exploration lay in the statistical cauldron, where we summoned the spectral forces of correlation analysis. With a deft flick of the wrist and a whispered incantation to the elusive spirits of p-values, we conjured forth the otherworldly metrics that would govern our journey. Employing robust statistical software, we computed the correlation coefficient to unveil the spectral ties between Kerosene consumption and the squirrel-related cyber odyssey. This unearthed correlation coefficient, a staggering 0.9042740, sent ripples of astonishment through our intrepid ranks, affirming the presence of a potent gravitational pull between these seemingly incongruous phenomena.

Significance Testing:
No arcane exploration would be complete without subjecting our findings to the unforgiving gauntlet of significance testing. Thus, we administered the sacred rites of hypothesis testing, unleashing the fierce and unyielding p-value to render judgment upon our correlation coefficient. The resulting p-value, commanding submission at values less than 0.01, stood as a resolute testament to the undeniable significance of the unearthed link.

Ethical Considerations:
Amidst the fervor of our statistical exploits, we remained steadfast in our dedication to scientific integrity and ethical rigor. Our data manipulations adhered to the virtuous principles of transparency and reproducibility, and our statistical sorcery was conducted with utmost respect for the sanctity of empirical inquiry.

In summary, our exhaustive methodological pilgrimage traversed the realms of data gathering, normalization, statistical conjuring, and ethical fortitude, culminating in the appending of our academic seal to the remarkable findings that beckon us into the boundless frontier of interdisciplinary exploration.

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 Kerosene used in El Salvador and Google searches for 'attacked by a squirrel'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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 Energy Information Administration and Google Trends .

For the time period 2004 to 2021, you found a correlation 0.9042740, r-squared of 0.8177115, 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]]
"Burning Questions: The Kerosene Connection - A Squirrely Correlation?"

[[ABSTRACT]]
Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
Introduction
The study of correlations between seemingly unrelated variables has long captured the imagination of researchers and statisticians alike. It is in this spirit of curiosity and unlikely connections that we embark on an investigation into the curious relationship between Kerosene consumption in El Salvador and the inexplicable surge in Google searches for "attacked by a squirrel".
Kerosene, a staple household fuel in many regions, has typically been examined through the lenses of economics, public health, and environmental impact. However, little attention has been paid to its potential ripple effects on the world of internet search behavior. Meanwhile, the peculiar phrase "attacked by a squirrel" has emerged as an enigmatic and, some might say, quirky phenomenon within the realm of online inquiries.
In this study, we harness the power of data from the Energy Information Administration and Google Trends to uncover and analyze the unexpected correlation between these two disparate variables. Our statistical analysis yields a correlation coefficient of 0.9042740, accompanied by a remarkably significant p-value of less than 0.01, spanning the years 2004 to 2021. These findings, at first glance, may appear whimsical, but they carry profound implications for our understanding of the seemingly random dance of human behavior and the underlying forces that tie together the ordinary and the unconventional.
As we delve into this curious correlation, we invite the reader to join us on a journey that blends the rigor of statistical analysis with the lighthearted curiosity that propels us to explore uncharted territory. Through this exploration, we seek to challenge conventional boundaries of inquiry and provoke contemplation on the interconnectedness of seemingly unrelated phenomena. In doing so, we hope to spark a reevaluation of the boundaries of interdisciplinary research and foster a deeper appreciation for the intricate tapestry that weaves together the mundane and the extraordinary.
So, let us don our statistical goggles and embark on an expedition that promises to illuminate the unexpected intersections of Kerosene consumption and squirrel-related searches, demonstrating the delightful unpredictability that often accompanies the pursuit of scientific inquiry.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The statistical analysis of the relationship between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel" yielded a remarkably strong correlation. Our findings revealed a correlation coefficient of 0.9042740, indicating a robust positive association between these seemingly unrelated variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.8177115, suggesting that approximately 81.77% of the variability in "attacked by a squirrel" searches can be explained by variations in Kerosene consumption. Furthermore, the p-value was found to be less than 0.01, signifying a statistically significant relationship between the two variables.

Figure 1 portrays a scatterplot depicting the striking correlation between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel". The data points form a clear, upward-sloping trend, affirming the strength of the positive association between these unusual phenomena.

The unexpected connection uncovered in this analysis challenges traditional perspectives and underscores the intricate interplay between apparently disparate domains. The findings prompt contemplation on the intricate web of causation and the peculiar pathways through which human behavior and societal influences manifest themselves. While the initial premise of this investigation may appear whimsical, the outcomes serve as a reminder of the intriguing and often unpredictable nature of statistical inquiry.

This unexpected linkage between Kerosene consumption and "attacked by a squirrel" searches invites further exploration into the underlying mechanisms that bridge the gap between everyday fuel usage and internet search behavior. The findings of this study accentuate the serendipitous discoveries that can emerge from the unearthing of peculiar correlations, reinforcing the importance of embracing the unexpected in scientific exploration.

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 Kerosene used in El Salvador and Google searches for 'attacked by a squirrel'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
"Burning Questions: The Kerosene Connection - A Squirrely Correlation?"

[[ABSTRACT]]
Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

[[LITERATURE REVIEW]]
In the realm of energy consumption and its societal ramifications, Smith (2015) delves into the intricate web of household fuel usage in developing countries, shedding light on the socioeconomic dynamics at play. Similarly, Doe and Jones (2018) offer a comprehensive analysis of internet search patterns and the behavioral insights that can be gleaned from them, paving the way for a deeper understanding of the digital landscape.
Moving beyond the immediate domains of energy economics and online behavior, Williams and Brown (2009) present a thought-provoking examination of wildlife encounters and the psychological impacts they may impart on individuals. This exploration resonates with the unanticipated surge in searches for the phrase "attacked by a squirrel," hinting at the curious intersections of human-wildlife interactions in the digital sphere.
On a more lighthearted note, "Squirrels: A Cultural History" by Adams (2019) provides a whimsical yet informative journey into the folklore and cultural significance of these fuzzy-tailed creatures. While not a scholarly work per se, the charming anecdotes and historical tidbits woven into the narrative offer a delightful backdrop against which to consider the unexpected rise in squirrel-related internet queries.
In the realm of fiction, the works of author Acorn include "The Secret Life of Squirrels" series which, while certainly not rigorous scientific literature, captures the imagination with its playful portrayal of squirrel antics. The parallel between these fictional musings and the genuine curiosity exhibited in internet searches for squirrel-related encounters lends credence to the notion that truth can be stranger than fiction.
In the pursuit of understanding human behavior and its quirky inclinations, our researchers also turned their attention to television shows that might offer insight into the fascination with squirrel encounters. The investigative nature of "CSI: Squirrel Squad" and the comedic take on urban wildlife in "Parks and Recreation" sparked incidental curiosity, leading to a deeper contemplation of the unexpected intersections between real-world events and the pop culture narratives that color our lives.
Thus, the mosaic of literature and cultural representations surrounding our subject matter lays the groundwork for a multidimensional exploration of the unlikely correlation between Kerosene consumption in El Salvador and the surge in Google searches for "attacked by a squirrel". While playful in its underpinnings, this investigation carries significant implications for our understanding of human behavior, the digital landscape, and the complex tapestry of interconnected phenomena that shape our world.

[[RESULTS]]
The statistical analysis of the relationship between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel" yielded a remarkably strong correlation. Our findings revealed a correlation coefficient of 0.9042740, indicating a robust positive association between these seemingly unrelated variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.8177115, suggesting that approximately 81.77% of the variability in "attacked by a squirrel" searches can be explained by variations in Kerosene consumption. Furthermore, the p-value was found to be less than 0.01, signifying a statistically significant relationship between the two variables.
Figure 1 portrays a scatterplot depicting the striking correlation between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel". The data points form a clear, upward-sloping trend, affirming the strength of the positive association between these unusual phenomena.
The unexpected connection uncovered in this analysis challenges traditional perspectives and underscores the intricate interplay between apparently disparate domains. The findings prompt contemplation on the intricate web of causation and the peculiar pathways through which human behavior and societal influences manifest themselves. While the initial premise of this investigation may appear whimsical, the outcomes serve as a reminder of the intriguing and often unpredictable nature of statistical inquiry.
This unexpected linkage between Kerosene consumption and "attacked by a squirrel" searches invites further exploration into the underlying mechanisms that bridge the gap between everyday fuel usage and internet search behavior. The findings of this study accentuate the serendipitous discoveries that can emerge from the unearthing of peculiar correlations, reinforcing the importance of embracing the unexpected in scientific exploration.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The astounding correlation between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel" undeniably defies traditional expectations, challenging researchers to navigate the peculiar twists and turns of statistical inquiry. Our findings not only substantiate earlier research on the interconnectedness of seemingly distinct phenomena but also beckon forth a cascade of unexpected realizations akin to a squirrel leaping from branch to branch.

The literature review, while tailored to scholarly pursuits, uncovers uncharted territories that whisper their secrets to those with a keen eye. As we revisit the whimsical interludes of "Squirrels: A Cultural History" by Adams, the notion of squirrels as more than just fuzzy-tailed creatures gains traction, paralleling the unforeseen surge in internet searches for squirrel-related encounters. Like squirrels scurrying through the foliage, the scholarly and fictional sources surrounding our subject matter converge to form a multidimensional canopy of insight, allowing our team to unapologetically embrace the enigmatic allure of unexpected correlations.

Our results bolster the previously alluded scholarly works, affirming the intricate web of causation and the cryptic pathways that intertwine human behavior and societal influences. The robust positive association between Kerosene consumption and "attacked by a squirrel" searches, boasting a correlation coefficient of 0.9042740 and a coefficient of determination of 0.8177115, serves as a testament to the fortuitous discoveries that lurk within the annals of statistical adventuring.

As scientific voyagers charting unexplored territories, we must not shy away from the unconventional, for it is in the interstitial spaces of unpredictability that hidden gems often lay nestled. This study, though birthed from seemingly whimsical premises, encapsulates the essence of scientific inquiry as a vessel bound toward the unanticipated, compelling scholars to dance with the unexpected and brave the tempestuous currents of statistical caprice.

In conclusion, the compelling correlation between Kerosene usage and "attacked by a squirrel" searches illuminates the captivating and sometimes bewildering tapestry of integrated phenomena. These findings prod the scientific community to cultivate a spirit of audacious exploration, beckoning forth the unanticipated and unveiling the extraordinary amidst the seemingly mundane.

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 Kerosene used in El Salvador and Google searches for 'attacked by a squirrel'. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. 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]]
"Burning Questions: The Kerosene Connection - A Squirrely Correlation?"

[[ABSTRACT]]
Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

[[INTRDUCTION]]
Introduction
The study of correlations between seemingly unrelated variables has long captured the imagination of researchers and statisticians alike. It is in this spirit of curiosity and unlikely connections that we embark on an investigation into the curious relationship between Kerosene consumption in El Salvador and the inexplicable surge in Google searches for "attacked by a squirrel".
Kerosene, a staple household fuel in many regions, has typically been examined through the lenses of economics, public health, and environmental impact. However, little attention has been paid to its potential ripple effects on the world of internet search behavior. Meanwhile, the peculiar phrase "attacked by a squirrel" has emerged as an enigmatic and, some might say, quirky phenomenon within the realm of online inquiries.
In this study, we harness the power of data from the Energy Information Administration and Google Trends to uncover and analyze the unexpected correlation between these two disparate variables. Our statistical analysis yields a correlation coefficient of 0.9042740, accompanied by a remarkably significant p-value of less than 0.01, spanning the years 2004 to 2021. These findings, at first glance, may appear whimsical, but they carry profound implications for our understanding of the seemingly random dance of human behavior and the underlying forces that tie together the ordinary and the unconventional.
As we delve into this curious correlation, we invite the reader to join us on a journey that blends the rigor of statistical analysis with the lighthearted curiosity that propels us to explore uncharted territory. Through this exploration, we seek to challenge conventional boundaries of inquiry and provoke contemplation on the interconnectedness of seemingly unrelated phenomena. In doing so, we hope to spark a reevaluation of the boundaries of interdisciplinary research and foster a deeper appreciation for the intricate tapestry that weaves together the mundane and the extraordinary.
So, let us don our statistical goggles and embark on an expedition that promises to illuminate the unexpected intersections of Kerosene consumption and squirrel-related searches, demonstrating the delightful unpredictability that often accompanies the pursuit of scientific inquiry.

[[RESULTS]]
The statistical analysis of the relationship between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel" yielded a remarkably strong correlation. Our findings revealed a correlation coefficient of 0.9042740, indicating a robust positive association between these seemingly unrelated variables. Additionally, the coefficient of determination (r-squared) was calculated to be 0.8177115, suggesting that approximately 81.77% of the variability in "attacked by a squirrel" searches can be explained by variations in Kerosene consumption. Furthermore, the p-value was found to be less than 0.01, signifying a statistically significant relationship between the two variables.
Figure 1 portrays a scatterplot depicting the striking correlation between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel". The data points form a clear, upward-sloping trend, affirming the strength of the positive association between these unusual phenomena.
The unexpected connection uncovered in this analysis challenges traditional perspectives and underscores the intricate interplay between apparently disparate domains. The findings prompt contemplation on the intricate web of causation and the peculiar pathways through which human behavior and societal influences manifest themselves. While the initial premise of this investigation may appear whimsical, the outcomes serve as a reminder of the intriguing and often unpredictable nature of statistical inquiry.
This unexpected linkage between Kerosene consumption and "attacked by a squirrel" searches invites further exploration into the underlying mechanisms that bridge the gap between everyday fuel usage and internet search behavior. The findings of this study accentuate the serendipitous discoveries that can emerge from the unearthing of peculiar correlations, reinforcing the importance of embracing the unexpected in scientific exploration.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our study has shed light on the unexpected correlation between Kerosene consumption in El Salvador and Google searches for "attacked by a squirrel". The remarkably strong correlation coefficient of 0.9042740 and the statistically significant p-value of less than 0.01 have led us to ponder the delightful peculiarity of human behavior and the interconnectedness of seemingly unrelated variables. The scatterplot in Figure 1 serves as a visual testament to the surprising synchrony between these disparate phenomena, leaving us marveling at the unpredictable dance of statistical inquiry.

While the notion of Kerosene fuel sparking an uptick in squirrel-related searches may seem whimsical at first glance, the robust statistical evidence suggests a substantive linkage. The resilience of the correlation prompts contemplation on the intricate tapestry of societal influences and the idiosyncratic pathways through which seemingly disjointed events intersect. This study serves as a pleasing reminder of the unpredictability that often accompanies the pursuit of scientific inquiry, revealing the unexpected treasures that lie in the vast landscape of statistical exploration.

As we contemplate the implications of our findings, we must resist the temptation to squirrel away these results without further examination. However, the peculiar correlation uncovered may have reached the acorn of its insights, and it seems unlikely that further research in this area will yield substantial walnuts – I mean, results. Therefore, we assert, with a twinge of disappointment, that no more research is needed in this particular area of Kerosene and squirrel-related search behavior. After all, it's time to nut up or shut up when it comes to statistical investigations.

And with that, we bid adieu to the curious tale of Kerosene and squirrel searches, leaving behind a trail of statistical breadcrumbs for future explorers to follow.

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 Burning Questions: The Kerosene Connection - A Squirrely Correlation?. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Rodent-Powered Energy 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 Burning Questions: The Kerosene Connection - A Squirrely Correlation?. Respond only with the name of a fictional organization.

ChatGPT:

The Association for Silly Science 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 Burning Questions: The Kerosene Connection - A Squirrely Correlation? with an abstract of Kerosene, a commonly used household fuel in El Salvador, has long been a subject of interest in its economic and environmental implications. However, the extent of its impact on seemingly unrelated phenomena such as internet search behavior has been overlooked. In this study, we dive deep into the unlikely association between Kerosene consumption in El Salvador and Google searches for the peculiar string "attacked by a squirrel". Leveraging data from the Energy Information Administration and Google Trends, we uncover a surprising correlation that challenges conventional wisdom. Our analysis reveals a striking correlation coefficient of 0.9042740 and a statistically significant p-value of less than 0.01, covering the years 2004 to 2021. The implications of this unexpected linkage prompt critical reflections on the interconnectedness of seemingly disparate events and underscore the need for further nuanced investigation in interdisciplinary research. Despite the seemingly whimsical nature of the inquiry, these findings shed light on the intricate interconnectedness of human behavior and seemingly unrelated variables, prompting a deeper consideration of the underlying mechanisms that unite the mundane and the extraordinary.

ChatGPT:

kerosene consumption, El Salvador, household fuel, economic implications, environmental implications, internet search behavior, Google searches, "attacked by a squirrel", correlation coefficient, statistical significance, Energy Information Administration, Google Trends, interdisciplinary research, human behavior, interconnectedness, variables, underlying mechanisms

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

Google searches for 'attacked by a squirrel'
Detailed data title: Relative volume of Google searches for 'attacked by a squirrel' (Worldwide, without quotes)
Source: Google Trends
Additional Info: ^{See full details} Relative search volume (not absolute numbers)

See what else correlates with Google searches for 'attacked by a squirrel'

Correlation r = 0.9042740 (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 = 0.8177115 (Coefficient of determination)
This means 81.8% of the change in the one variable (i.e., Google searches for 'attacked by a squirrel') is predictable based on the change in the other (i.e., Kerosene used in El Salvador) over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 2.6E-7.^Show 0.0000002615977757533122000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme.^Note 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 0.9 in 2.6E-5% of random cases. Said differently, if you correlated 3,822,662 random variables^Note You don't actually need 3 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 17 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 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.

[ 0.76, 0.96 ] 95% correlation confidence interval (using the Fisher z-transformation)
^{Read more about the confidence interval} 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: ^Note 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.

	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Kerosene used in El Salvador (Million Barrels/Day)	0.654727	0.677699	0.677699	0.296493	0.0633607	0.0635342	0.0635342	0.0635342	0	0	0.0211781	0.021178	0.021726	0.021726	0.021726	0.0869041	0.0731802	0.077887
Google searches for 'attacked by a squirrel' (Rel. search volume)	12.25	12	11.75	2.41667	0	3.33333	4.75	2.5	4.33333	3.91667	2	0.916667	2.58333	0.75	0.416667	1.16667	1.41667	3.58333

Why this works

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.
Lack of causal connection: There is probably^Note 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.
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^Note 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. ^{Show the steps to do this.} 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([0.654727,0.677699,0.677699,0.296493,0.0633607,0.0635342,0.0635342,0.0635342,0,0,0.0211781,0.021178,0.021726,0.021726,0.021726,0.0869041,0.0731802,0.077887,])
array_2 = np.array([12.25,12,11.75,2.41667,0,3.33333,4.75,2.5,4.33333,3.91667,2,0.916667,2.58333,0.75,0.416667,1.16667,1.41667,3.58333,])
array_1_name = "Kerosene used in El Salvador"
array_2_name = "Google searches for 'attacked by a squirrel'"

# 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. ^Note 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:

High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.

If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.

Alternatively you can use a tool like Inkscape.
High resolution line chart, optimized for mobile
Alternative high resolution line chart
Scatterplot
Portable line chart (png)
Portable line chart (png), optimized for mobile
Line chart for only Kerosene used in El Salvador
Line chart for only Google searches for 'attacked by a squirrel'
The spurious research paper: Burning Questions: The Kerosene Connection - A Squirrely Correlation?

View another random correlation

How fun was this correlation?

I'm grateful for your review!

Correlation ID: 1069 · Black Variable ID: 24380 · Red Variable ID: 1354


Problem variable:
Issue:
Additional details: Optional
Confirm you are a human: