Spurious correlation #3,341 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of soil and plant scientists in Kentucky and the second variable is Kerosene used in Sri Lanka. The chart goes from 2005 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 The number of soil and plant scientists in Kentucky and the second variable is Kerosene used in Sri Lanka. The chart goes from 2005 to 2021, and the two variables track closely in value over that time.

Download png, svg

AI explanation

Kentucky's soil and plant scientists developed a revolutionary new strain of corn, resulting in a surplus of popcorn production. This led to a boom in movie watching in Sri Lanka, increasing the demand for kerosene lamps for a cozy atmosphere during film nights.

^{Show image generation prompt} Model: dalle-3
Prompt: Create an image of a vibrant, futuristic farm setting blending the beauty of Kentucky fields and the innovation of Sri Lankan biofuel production. Show a juxtaposition of the sprawling corn fields, with a team of scientists conducting experiments among the tall stalks, and a group of workers in Sri Lanka pouring biofuel into a storage tank. Emphasize the harmony between nature and technology, with an otherworldly touch reflecting the theme of data cyber art. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

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

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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: Concept art inspired by bauhaus Data cyber art Surrealism Voxel art
ChatGPT: Data cyber art

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka, in the following situation: Because as the number of soil and plant scientists in Kentucky increases, so does the likelihood of discovering a new strain of super-efficient corn. This corn is then exported to Sri Lanka, where it's used to make biofuel, reducing the demand for kerosene and leading to a decrease in its usage.. Keep the description simple.
ChatGPT: In Kentucky, fields are buzzing with a team of soil and plant scientists surrounded by rows of tall corn stalks. As the number of scientists increases, so does the chance of discovering a new strain of super-efficient corn. Meanwhile, in Sri Lanka, a group of workers are seen pouring biofuel into a tank, replacing kerosene. The usage of kerosene decreases as biofuel made from the efficient corn is utilized.

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: [ Data cyber art ] and depicting this scene: In Kentucky, fields are buzzing with a team of soil and plant scientists surrounded by rows of tall corn stalks. As the number of scientists increases, so does the chance of discovering a new strain of super-efficient corn. Meanwhile, in Sri Lanka, a group of workers are seen pouring biofuel into a tank, replacing kerosene. The usage of kerosene decreases as biofuel made from the efficient corn is utilized. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Create an image of a vibrant, futuristic farm setting blending the beauty of Kentucky fields and the innovation of Sri Lankan biofuel production. Show a juxtaposition of the sprawling corn fields, with a team of scientists conducting experiments among the tall stalks, and a group of workers in Sri Lanka pouring biofuel into a storage tank. Emphasize the harmony between nature and technology, with an otherworldly touch reflecting the theme of data cyber art.

*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 increases in The number of soil and plant scientists in Kentucky positively influenced Kerosene used in Sri Lanka.\Make it sound serious until the end.

AI academic paper

(Because p < 0.01)

Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

Journal of Ecological Exchange

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

Please make up a literature review section of an academic research paper presenting the findings of the connection between The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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 some movies that you watched that are tangentially related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

[[ABSTRACT]]
This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
In the realm of scientific inquiry, serendipitous discoveries often spring forth from the most unexpected pairings of variables. Our investigation embarks upon the curious correlation between the number of soil and plant scientists toiling amidst the verdant stretches of Kentucky and the consumption of kerosene on the distant shores of Sri Lanka. The unearthing of this relationship stands as a testament to the curious and often whimsical nature of empirical evidence.
The juxtaposition of these seemingly disparate entities may prompt raised eyebrows and furrowed brows, but it is precisely within the unexpected that scientific revelations often reside. Thus, we find ourselves delving into the enigmatic connection between the diligent labor of Kentucky's soil and plant scientists and the glowing flame of kerosene in the households of Sri Lanka.
The present study aims to unravel the intricate tapestry of factors that intertwine these two seemingly unrelated phenomena. By drawing upon data from the Bureau of Labor Statistics and the Energy Information Administration, we quantify the relationship between these variables with a robust correlation coefficient of 0.8131174 and a statistically significant p-value of less than 0.01 across the time span of 2005 to 2021. The compelling statistical evidence impels us to embark upon a deeper understanding of the underlying forces at play.
Though the threads of causality remain elusive, this unexpected correlation beckons us to explore the unseen forces that may be at work. As we unfurl the findings of this investigation, we are poised to uncover a scientific narrative that is both intriguing and, dare we say, illuminating.
Stay tuned, dear reader, for the journey that lies ahead promises to be as captivating as it is unforeseen. For in the realm of empirical inquiry, the most captivating stories often unfold from the unlikeliest of pairings.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Smith (2008) underscores the importance of soil and plant scientists in deciphering the complex interactions within terrestrial ecosystems. Furthermore, Doe (2015) expounds upon the critical role of kerosene in the context of household energy consumption in developing countries. Closely related to this, Jones (2019) investigates the nuances of labor market dynamics in the United States.

Turning the pages to non-fiction works, "The Hidden Half of Nature: The Microbial Roots of Life and Health" by Montgomery and Biklé (2016) sheds light on the interconnectedness of soil, microbes, and human life. Meanwhile, "The Soil Will Save Us" by Ohlson (2014) delves into the potential of soil to sequester carbon and mitigate climate change, adding another layer of complexity to the study of soil scientists.

In the realm of fiction, Michael Pollan's "The Botany of Desire: A Plant's-Eye View of the World" (2001) and Barbara Kingsolver's "Prodigal Summer" (2000) highlight the intricate relationships between humans, plants, and the natural world. Although their narratives may not directly address the connection between soil scientists and kerosene consumption, they serve as a reminder of the profound impact of ecological interdependencies in our lives.

On the cinematic front, the research team recently indulged in a viewing of "The Secret Life of Plants" and "The Kentucky Fried Movie." While the former delves into the enigmatic world of plant behavior, the latter, though unrelated to our research topic, left us with a few good laughs.

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

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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 Bureau of Larbor Statistics and Energy Information Administration . You used data from 2005 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]]
Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

[[ABSTRACT]]
This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

[[INTRODUCTION]]
In the realm of scientific inquiry, serendipitous discoveries often spring forth from the most unexpected pairings of variables. Our investigation embarks upon the curious correlation between the number of soil and plant scientists toiling amidst the verdant stretches of Kentucky and the consumption of kerosene on the distant shores of Sri Lanka. The unearthing of this relationship stands as a testament to the curious and often whimsical nature of empirical evidence.
The juxtaposition of these seemingly disparate entities may prompt raised eyebrows and furrowed brows, but it is precisely within the unexpected that scientific revelations often reside. Thus, we find ourselves delving into the enigmatic connection between the diligent labor of Kentucky's soil and plant scientists and the glowing flame of kerosene in the households of Sri Lanka.
The present study aims to unravel the intricate tapestry of factors that intertwine these two seemingly unrelated phenomena. By drawing upon data from the Bureau of Labor Statistics and the Energy Information Administration, we quantify the relationship between these variables with a robust correlation coefficient of 0.8131174 and a statistically significant p-value of less than 0.01 across the time span of 2005 to 2021. The compelling statistical evidence impels us to embark upon a deeper understanding of the underlying forces at play.
Though the threads of causality remain elusive, this unexpected correlation beckons us to explore the unseen forces that may be at work. As we unfurl the findings of this investigation, we are poised to uncover a scientific narrative that is both intriguing and, dare we say, illuminating.
Stay tuned, dear reader, for the journey that lies ahead promises to be as captivating as it is unforeseen. For in the realm of empirical inquiry, the most captivating stories often unfold from the unlikeliest of pairings.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology adopted for this study involved gathering data from reliable sources, primarily the Bureau of Labor Statistics and the Energy Information Administration, spanning the years 2005 to 2021. The categorization of soil and plant scientists in Kentucky and the measurement of kerosene consumption in Sri Lanka were deemed worthy endeavors, despite the quizzical looks and raised eyebrows that may have accompanied such an unconventional pairing.

First, the number of soil and plant scientists in Kentucky was acquired from the Bureau of Labor Statistics, utilizing the Standard Occupational Classification (SOC) system. It is worthy to note that the distinction between soil scientists and plant scientists was made with utmost botanical precision, as we would not want any root causes or leafy influences to be overlooked in our analysis. The utilization of this data allowed for the identification of temporal trends and fluctuations in the population of these dedicated practitioners of the earth sciences.

Simultaneously, the consumption of kerosene in Sri Lanka was diligently tracked through the Energy Information Administration's dataset. The quantification of kerosene usage beckoned our attention to the lively and illuminating world of energy consumption, as we endeavored to shed light on the burning question of its association with soil and plant scientists laboring in Kentucky.

By employing the unparalleled power of statistical analysis, the relationship between these seemingly unrelated variables was teased out, yielding a robust correlation coefficient of 0.8131174 and a p-value of less than 0.01. The statistical significance of this correlation prompted further exploration into the potential confounding factors lurking beneath the surface.

In order to ascertain the reliability and validity of the findings, an extensive sensitivity analysis was conducted, ensuring that the results were not susceptible to the capricious whims of outliers or confounding covariates. The thoroughness of this analysis was akin to sifting through soil for the most fertile data points, aiming to unearth the underlying truth from amidst the statistical underbrush.

While the precision of our methodology does not preclude the possibility of unmeasured variables or confounding effects, the rigorous and diligent approach undertaken in this study offers a compelling insight into the captivating correlation between the soil and plant scientists of Kentucky and the kerosene consumption in Sri Lanka. The findings of this research, much like the interplay between the earth and the luminous flame, promise to shed light on a connection that is as unexpected as it is illuminating.

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

Please make up the results section of an academic research paper presenting the findings of the connection between The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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 Bureau of Larbor Statistics and Energy Information Administration .

For the time period 2005 to 2021, you found a correlation 0.8131174, r-squared of 0.6611599, 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]]
Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

[[ABSTRACT]]
This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
In the realm of scientific inquiry, serendipitous discoveries often spring forth from the most unexpected pairings of variables. Our investigation embarks upon the curious correlation between the number of soil and plant scientists toiling amidst the verdant stretches of Kentucky and the consumption of kerosene on the distant shores of Sri Lanka. The unearthing of this relationship stands as a testament to the curious and often whimsical nature of empirical evidence.
The juxtaposition of these seemingly disparate entities may prompt raised eyebrows and furrowed brows, but it is precisely within the unexpected that scientific revelations often reside. Thus, we find ourselves delving into the enigmatic connection between the diligent labor of Kentucky's soil and plant scientists and the glowing flame of kerosene in the households of Sri Lanka.
The present study aims to unravel the intricate tapestry of factors that intertwine these two seemingly unrelated phenomena. By drawing upon data from the Bureau of Labor Statistics and the Energy Information Administration, we quantify the relationship between these variables with a robust correlation coefficient of 0.8131174 and a statistically significant p-value of less than 0.01 across the time span of 2005 to 2021. The compelling statistical evidence impels us to embark upon a deeper understanding of the underlying forces at play.
Though the threads of causality remain elusive, this unexpected correlation beckons us to explore the unseen forces that may be at work. As we unfurl the findings of this investigation, we are poised to uncover a scientific narrative that is both intriguing and, dare we say, illuminating.
Stay tuned, dear reader, for the journey that lies ahead promises to be as captivating as it is unforeseen. For in the realm of empirical inquiry, the most captivating stories often unfold from the unlikeliest of pairings.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis of the data revealed a remarkable correlation coefficient of 0.8131174 between the number of soil and plant scientists in Kentucky and kerosene consumption in Sri Lanka for the period spanning 2005 to 2021. The interpretation of this coefficient implies a strong positive linear relationship between the two variables, indicating that as the population of soil and plant scientists in Kentucky increased, there was a corresponding surge in kerosene consumption in Sri Lanka. The coefficient of determination (r-squared) of 0.6611599 suggests that approximately 66.12% of the variation in kerosene use in Sri Lanka can be explained by the variation in the number of soil and plant scientists in Kentucky.

Moreover, the p-value of less than 0.01 indicates that the observed correlation is statistically significant, rejecting the null hypothesis that there is no relationship between the two variables. This implies that the likelihood of obtaining such a strong correlation coefficient purely by chance is less than 1%, providing compelling evidence for a genuine association between the variables.

A visual representation of the observed relationship is depicted in Figure 1, where the scatterplot exhibits a conspicuous clustering of data points, affirming the robust correlation between the number of soil and plant scientists in Kentucky and kerosene usage in Sri Lanka. The figure visually encapsulates the surprising synchronization of these seemingly disparate phenomena, inviting further contemplation on the intricate dance of variables at play.

These findings, although unexpected and perhaps even eyebrow-raising, open the door to a deeper exploration of the underlying mechanisms that underpin the connection between the diligent work of soil and plant scientists in Kentucky and the utilization of kerosene in Sri Lanka. This unusual correlation prompts considerable curiosity within the scientific community and offers an enticing opportunity for additional in-depth investigation into the forces that may be at the root of this intriguing association.

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

Please make up the discussion section of an academic research paper presenting the findings of the connection between The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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]]
Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

[[ABSTRACT]]
This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

[[LITERATURE REVIEW]]
Smith (2008) underscores the importance of soil and plant scientists in deciphering the complex interactions within terrestrial ecosystems. Furthermore, Doe (2015) expounds upon the critical role of kerosene in the context of household energy consumption in developing countries. Closely related to this, Jones (2019) investigates the nuances of labor market dynamics in the United States.
Turning the pages to non-fiction works, "The Hidden Half of Nature: The Microbial Roots of Life and Health" by Montgomery and Biklé (2016) sheds light on the interconnectedness of soil, microbes, and human life. Meanwhile, "The Soil Will Save Us" by Ohlson (2014) delves into the potential of soil to sequester carbon and mitigate climate change, adding another layer of complexity to the study of soil scientists.
In the realm of fiction, Michael Pollan's "The Botany of Desire: A Plant's-Eye View of the World" (2001) and Barbara Kingsolver's "Prodigal Summer" (2000) highlight the intricate relationships between humans, plants, and the natural world. Although their narratives may not directly address the connection between soil scientists and kerosene consumption, they serve as a reminder of the profound impact of ecological interdependencies in our lives.
On the cinematic front, the research team recently indulged in a viewing of "The Secret Life of Plants" and "The Kentucky Fried Movie." While the former delves into the enigmatic world of plant behavior, the latter, though unrelated to our research topic, left us with a few good laughs.

[[RESULTS]]
The analysis of the data revealed a remarkable correlation coefficient of 0.8131174 between the number of soil and plant scientists in Kentucky and kerosene consumption in Sri Lanka for the period spanning 2005 to 2021. The interpretation of this coefficient implies a strong positive linear relationship between the two variables, indicating that as the population of soil and plant scientists in Kentucky increased, there was a corresponding surge in kerosene consumption in Sri Lanka. The coefficient of determination (r-squared) of 0.6611599 suggests that approximately 66.12% of the variation in kerosene use in Sri Lanka can be explained by the variation in the number of soil and plant scientists in Kentucky.
Moreover, the p-value of less than 0.01 indicates that the observed correlation is statistically significant, rejecting the null hypothesis that there is no relationship between the two variables. This implies that the likelihood of obtaining such a strong correlation coefficient purely by chance is less than 1%, providing compelling evidence for a genuine association between the variables.
A visual representation of the observed relationship is depicted in Figure 1, where the scatterplot exhibits a conspicuous clustering of data points, affirming the robust correlation between the number of soil and plant scientists in Kentucky and kerosene usage in Sri Lanka. The figure visually encapsulates the surprising synchronization of these seemingly disparate phenomena, inviting further contemplation on the intricate dance of variables at play.
These findings, although unexpected and perhaps even eyebrow-raising, open the door to a deeper exploration of the underlying mechanisms that underpin the connection between the diligent work of soil and plant scientists in Kentucky and the utilization of kerosene in Sri Lanka. This unusual correlation prompts considerable curiosity within the scientific community and offers an enticing opportunity for additional in-depth investigation into the forces that may be at the root of this intriguing association.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of this study lend credence to earlier research that has hinted at the cryptic links between soil and plant scientists in Kentucky and kerosene consumption in Sri Lanka. As Smith (2008) and Doe (2015) have suggested, the critical role of soil and plant scientists in uncovering the intricate web of interactions within terrestrial ecosystems may indeed have repercussions that extend far beyond the borders of the United States. Furthermore, the unexpected synchronization between the diligent work of soil and plant scientists in Kentucky and the utilization of kerosene in Sri Lanka evokes contemplation on the interplay of variables in our global ecosystem.

The substantial correlation coefficient and statistically significant p-value serve as testament to the robustness of the observed relationship, providing supporting evidence for the unanticipated connection. Our results affirm the assertion of Montgomery and Biklé (2016) regarding the interconnectivity of soil, microbes, and human life, as well as the potential of soil to sequester carbon, resonating with the complex tapestry of factors influencing kerosene consumption in Sri Lanka. The unexpected correlation calls to mind the intricate dance of variables emphasized by Ohlson (2014) and highlights the need for a holistic understanding of ecological interactions on a global scale.

The strong positive linear relationship uncovered in this study may indeed be the tip of the iceberg, as our understanding of the underlying mechanisms governing this association remains nascent. While Michael Pollan's "The Botany of Desire" and Barbara Kingsolver's "Prodigal Summer" may not have explicitly addressed the connection between soil scientists and kerosene consumption, their narratives serve as a lens through which to view the profound impact of ecological interdependencies, reminding us of the intricate ways in which seemingly disparate elements of our natural world may be entwined.

In light of our results, the enigmatic relationship between soil scientists in Kentucky and kerosene use in Sri Lanka beckons for further exploration. This unexpected correlation has ignited considerable curiosity within the scientific community and presents an alluring opportunity for additional in-depth investigation into the forces that may be at the root of this intriguing association. The study not only sheds light on the unanticipated interconnectedness of seemingly unrelated phenomena but also calls for a more nuanced understanding of the global interplay of ecological variables.

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

Please make up a short conclusion of an academic research paper presenting the findings of the connection between The number of soil and plant scientists in Kentucky and Kerosene used in Sri Lanka. 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]]
Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

[[ABSTRACT]]
This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

[[INTRDUCTION]]
In the realm of scientific inquiry, serendipitous discoveries often spring forth from the most unexpected pairings of variables. Our investigation embarks upon the curious correlation between the number of soil and plant scientists toiling amidst the verdant stretches of Kentucky and the consumption of kerosene on the distant shores of Sri Lanka. The unearthing of this relationship stands as a testament to the curious and often whimsical nature of empirical evidence.
The juxtaposition of these seemingly disparate entities may prompt raised eyebrows and furrowed brows, but it is precisely within the unexpected that scientific revelations often reside. Thus, we find ourselves delving into the enigmatic connection between the diligent labor of Kentucky's soil and plant scientists and the glowing flame of kerosene in the households of Sri Lanka.
The present study aims to unravel the intricate tapestry of factors that intertwine these two seemingly unrelated phenomena. By drawing upon data from the Bureau of Labor Statistics and the Energy Information Administration, we quantify the relationship between these variables with a robust correlation coefficient of 0.8131174 and a statistically significant p-value of less than 0.01 across the time span of 2005 to 2021. The compelling statistical evidence impels us to embark upon a deeper understanding of the underlying forces at play.
Though the threads of causality remain elusive, this unexpected correlation beckons us to explore the unseen forces that may be at work. As we unfurl the findings of this investigation, we are poised to uncover a scientific narrative that is both intriguing and, dare we say, illuminating.
Stay tuned, dear reader, for the journey that lies ahead promises to be as captivating as it is unforeseen. For in the realm of empirical inquiry, the most captivating stories often unfold from the unlikeliest of pairings.

[[RESULTS]]
The analysis of the data revealed a remarkable correlation coefficient of 0.8131174 between the number of soil and plant scientists in Kentucky and kerosene consumption in Sri Lanka for the period spanning 2005 to 2021. The interpretation of this coefficient implies a strong positive linear relationship between the two variables, indicating that as the population of soil and plant scientists in Kentucky increased, there was a corresponding surge in kerosene consumption in Sri Lanka. The coefficient of determination (r-squared) of 0.6611599 suggests that approximately 66.12% of the variation in kerosene use in Sri Lanka can be explained by the variation in the number of soil and plant scientists in Kentucky.
Moreover, the p-value of less than 0.01 indicates that the observed correlation is statistically significant, rejecting the null hypothesis that there is no relationship between the two variables. This implies that the likelihood of obtaining such a strong correlation coefficient purely by chance is less than 1%, providing compelling evidence for a genuine association between the variables.
A visual representation of the observed relationship is depicted in Figure 1, where the scatterplot exhibits a conspicuous clustering of data points, affirming the robust correlation between the number of soil and plant scientists in Kentucky and kerosene usage in Sri Lanka. The figure visually encapsulates the surprising synchronization of these seemingly disparate phenomena, inviting further contemplation on the intricate dance of variables at play.
These findings, although unexpected and perhaps even eyebrow-raising, open the door to a deeper exploration of the underlying mechanisms that underpin the connection between the diligent work of soil and plant scientists in Kentucky and the utilization of kerosene in Sri Lanka. This unusual correlation prompts considerable curiosity within the scientific community and offers an enticing opportunity for additional in-depth investigation into the forces that may be at the root of this intriguing association.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the investigation into the relationship between the number of soil and plant scientists in Kentucky and kerosene consumption in Sri Lanka has yielded compelling and, dare I say, illuminating findings. The robust correlation coefficient and statistically significant p-value unearthed in this study indeed beckon us to peel back the layers of this unexpected connection and delve into the fertile soil of inquiry.

The strong positive linear relationship between these seemingly disparate variables may prompt raised eyebrows and furrowed brows among the scholarly folk. The correlation coefficient of 0.8131174 serves as a compass, guiding us through the enigmatic underbrush of empirical evidence. The coefficient of determination, with its whimsical name "r-squared," sheds light on the intricate dance of variables, explaining approximately 66.12% of the variation in kerosene use in Sri Lanka. Oh, the joy of quantifying the mysterious underpinnings of this phenomenon!

The visual representation in Figure 1, akin to a delightful painting in a gallery of statistical findings, captures the captivating interplay between the diligent soil and plant scientists of Kentucky and the glowing warmth of kerosene in Sri Lankan households. It is indeed a tableau vivant of empirical revelation, inviting further contemplation and, why not, a hearty chuckle at the unexpected absurdity of scholarly inquiry.

However, as every good story must come to an end, we posit that no further research is needed in this particular domain, for the findings of this investigation stand as a testament to the delightful unpredictability of empirical exploration. The illumination of this peculiar connection between soil scientists and kerosene usage in Sri Lanka beckons us to embrace the whimsical nature of scientific inquiry and revel in the unexpected connections that lie beneath the surface of statistical analysis.

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 Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Ecological Exchange

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 Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka. Respond only with the name of a fictional organization.

ChatGPT:

The Center for Global Soil Sustainability

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 Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka with an abstract of This study delves into the curious connection between the quantity of soil and plant scientists laboring in the bluegrass state of Kentucky and the consumption of kerosene in the tropical isle of Sri Lanka. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, a robust correlation coefficient of 0.8131174 and p < 0.01 were unearthed for the span of 2005 to 2021. It was found that as the population of soil and plant scientists in Kentucky increased, there was a concurrent surge in kerosene use in Sri Lanka. This intriguing discovery prompts further investigation into the underlying factors that may be sowing the seeds of this unexpected correlation. While the nature of the relationship remains enigmatic, it is clear that there is more to explore than meets the eye.

ChatGPT:

soil scientists, plant scientists, Kentucky, kerosene consumption, Sri Lanka, correlation coefficient, Bureau of Labor Statistics, Energy Information Administration

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

Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error

Data details

The number of soil and plant scientists in Kentucky
Detailed data title: BLS estimate of soil and plant scientists in Kentucky
Source: Bureau of Larbor Statistics
See what else correlates with The number of soil and plant scientists in Kentucky

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

Correlation r = 0.8131174 (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 = 0.6611599 (Coefficient of determination)
This means 66.1% of the change in the one variable (i.e., Kerosene used in Sri Lanka) is predictable based on the change in the other (i.e., The number of soil and plant scientists in Kentucky) over the 17 years from 2005 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.2E-5.^Show 0.0000723020598795336200000000
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 0.81 in 0.0072% of random cases. Said differently, if you correlated 13,831 random variables^Note Which I absolutely did.
with the same 16 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 16 because we have two variables measured over a period of 17 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.

[ 0.55, 0.93 ] 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.

	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
The number of soil and plant scientists in Kentucky (Laborers)	170	160	190	140	180	160	150	120	120	130	150	160	70	60	50	160	160
Kerosene used in Sri Lanka (Million Barrels/Day)	3.7697	4.53211	3.5791	3.18915	3.19789	3.49438	3.5791	3.84388	2.64726	2.58373	3	3	1.30356	0.760411	0.825589	2.47677	2.47677

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([170,160,190,140,180,160,150,120,120,130,150,160,70,60,50,160,160,])
array_2 = np.array([3.7697,4.53211,3.5791,3.18915,3.19789,3.49438,3.5791,3.84388,2.64726,2.58373,3,3,1.30356,0.760411,0.825589,2.47677,2.47677,])
array_1_name = "The number of soil and plant scientists in Kentucky"
array_2_name = "Kerosene used in Sri Lanka"

# 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 The number of soil and plant scientists in Kentucky
Line chart for only Kerosene used in Sri Lanka
AI-generated correlation image
The spurious research paper: Going Green: The Scene Between Soil Scientists in Kentucky and Kerosene Consumption in Sri Lanka

View another random correlation

How fun was this correlation?

Your rating is much appreciated!

Correlation ID: 3341 · Black Variable ID: 17580 · Red Variable ID: 24942


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