Spurious correlation #4,123 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Arson in Kentucky and the second variable is Kerosene used in Cuba. The chart goes from 1985 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 Arson in Kentucky and the second variable is Kerosene used in Cuba. The chart goes from 1985 to 2021, and the two variables track closely in value over that time.

AI explanation

As the saying goes, "When Kentucky's fires stop burning, Cuba's kerosene earnings start turning." It seems that with fewer incidents of arson in the Bluegrass State, there was a reduced demand for kerosene to fuel those fiery escapades. So, as Kentucky cooled off, Cuba's kerosene usage went up in smoke!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that looks like a scene from 'Star Wars', featuring a peaceful Kentucky town where firemen are dousing the last flickering flames of an arson incident. Meanwhile, in bustling Cuban streets, locals are lining up to purchase kerosene for their lanterns and stoves. The contrast of the extinguished fire and the glowing kerosene lamps highlights the shift in demand as Kentucky's arson incidents decrease and Cuba's need for kerosene increases. 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: Arson in Kentucky and Kerosene used in Cuba. 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: Hyper-realistic Surrealism Whimsical illustration Cute 2D animation An image that looks like it is a scene from 'Star Wars'
ChatGPT: An image that looks like it is a scene from 'Star Wars'

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 Arson in Kentucky and Kerosene used in Cuba, in the following situation: As the saying goes, "When Kentucky's fires stop burning, Cuba's kerosene earnings start turning." It seems that with fewer incidents of arson in the Bluegrass State, there was a reduced demand for kerosene to fuel those fiery escapades. So, as Kentucky cooled off, Cuba's kerosene usage went up in smoke!. Keep the description simple.
ChatGPT: In a peaceful Kentucky town, firemen douse the last flickering flames of an arson incident, while in bustling Cuban streets, locals line up to purchase kerosene for their lanterns and stoves. The contrast of the extinguished fire and the glowing kerosene lamps highlights the shift in demand as Kentucky's arson incidents decrease and Cuba's need for kerosene increases.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ An image that looks like it is a scene from 'Star Wars' ] and depicting this scene: In a peaceful Kentucky town, firemen douse the last flickering flames of an arson incident, while in bustling Cuban streets, locals line up to purchase kerosene for their lanterns and stoves. The contrast of the extinguished fire and the glowing kerosene lamps highlights the shift in demand as Kentucky's arson incidents decrease and Cuba's need for kerosene increases. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that looks like a scene from 'Star Wars', featuring a peaceful Kentucky town where firemen are dousing the last flickering flames of an arson incident. Meanwhile, in bustling Cuban streets, locals are lining up to purchase kerosene for their lanterns and stoves. The contrast of the extinguished fire and the glowing kerosene lamps highlights the shift in demand as Kentucky's arson incidents decrease and Cuba's need for kerosene increases.

*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 Arson in Kentucky caused Kerosene used in Cuba to decrease.

AI academic paper

(Because p < 0.01)

Kooky Connection: Kentucky Arson and Cuban Kerosene

The Journal of Eccentric Fire Studies

Jan 2024

^{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 Arson in Kentucky and Kerosene used in Cuba. 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]]
Kooky Connection: Kentucky Arson and Cuban Kerosene

[[ABSTRACT]]
This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The connection between seemingly disparate events and phenomena has long fascinated and confounded researchers across various disciplines. In the realm of criminology and energy studies, the paradoxical correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba is a puzzle that has eluded explanation. What could possibly link the deliberate act of setting fires in the Bluegrass State and the use of kerosene for lighting and heating in the Caribbean island nation?
Despite the initial skepticism such a correlation may evoke, the statistical analysis from this study yielded a correlation coefficient of 0.7882704 and a significance level of p < 0.01. This robust statistical evidence compels attention, inviting us to explore the potential interconnectedness of these seemingly unrelated occurrences. Although the physical distance and contextual dissimilarity between Kentucky and Cuba may appear to obfuscate any conceivable connection, our findings suggest otherwise.
The perplexing nature of this correlation prompts one to imagine scenarios where arsonists in Kentucky receive shipments of Cuban kerosene, or where the consumption of kerosene in Cuba somehow sparks a ripple effect that ignites fires across the ocean. Of course, these whimsical conjectures merely serve as a reminder of the enigmatic nature of the relationship under investigation.
This unexpected correlation not only poses intriguing questions for fire safety and energy policy but also hints at the complexity of human behavior transcending geographical boundaries. The unexpected link between arson in Kentucky and kerosene consumption in Cuba, which we have affectionately deemed the "Kooky Connection," unveils the potential for unanticipated interconnections across seemingly unrelated realms. As we navigate through the uncharted territory of this peculiar relationship, we stand poised to unveil the sparks of insight that may fuel further scholarly inquiry and illuminate the hidden ties that bind our world.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The authors find that the connection between instances of arson in Kentucky and the consumption of kerosene in Cuba has perplexed and intrigued researchers across various disciplines. In "Smith et al. (2015)," the authors delve into the intricate relationship between arson and fuel sources, shedding light on the complex motivations underlying deliberate fire setting. Similarly, Doe and Jones (2018) examine the socioeconomic factors influencing energy consumption patterns in Caribbean island nations, offering valuable insight into the cultural and environmental dynamics at play.

Moving beyond the realm of academic studies, works such as "The Arsonist's Dilemma: A Sociopsychological Analysis" and "Kerosene Chronicles: A Historical Perspective" provide further context and depth to the nuanced interplay between fire-related behavior and fuel usage. The former offers a thought-provoking exploration of the mindsets of arsonists, while the latter traces the historical trajectory of kerosene as a crucial energy source in various global contexts.

Beyond the confines of non-fiction literature, the fictional world offers intriguing narratives that tangentially touch upon the themes of fire, fuel, and unexpected connections. Novels such as "Burning Bridges" and "The Kerosene Conundrum" weave captivating tales that, while not explicitly addressing the Kentucky-Cuba correlation, offer thematic reverberations that resonate with the enigmatic nature of our research inquiry.

In a different medium, cinematic productions such as "Burn After Reading" and "The Cuban Kerosene Caper" provide fictionalized portrayals of intrigue, mystery, and unexpected twists – elements that, in a lighthearted manner, parallel the unexpected nature of our research findings. While these movies may not directly address the specific correlation under study, they offer a playful reminder of the whimsical possibilities and unexpected connections that our research seeks to unravel.

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 Arson in Kentucky and Kerosene used in Cuba. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Your research team collected data from all across the internet, but mostly just used information from FBI Criminal Justice Information Services and Energy Information Administration . You used data from 1985 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]]
Kooky Connection: Kentucky Arson and Cuban Kerosene

[[ABSTRACT]]
This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

[[INTRODUCTION]]
The connection between seemingly disparate events and phenomena has long fascinated and confounded researchers across various disciplines. In the realm of criminology and energy studies, the paradoxical correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba is a puzzle that has eluded explanation. What could possibly link the deliberate act of setting fires in the Bluegrass State and the use of kerosene for lighting and heating in the Caribbean island nation?
Despite the initial skepticism such a correlation may evoke, the statistical analysis from this study yielded a correlation coefficient of 0.7882704 and a significance level of p < 0.01. This robust statistical evidence compels attention, inviting us to explore the potential interconnectedness of these seemingly unrelated occurrences. Although the physical distance and contextual dissimilarity between Kentucky and Cuba may appear to obfuscate any conceivable connection, our findings suggest otherwise.
The perplexing nature of this correlation prompts one to imagine scenarios where arsonists in Kentucky receive shipments of Cuban kerosene, or where the consumption of kerosene in Cuba somehow sparks a ripple effect that ignites fires across the ocean. Of course, these whimsical conjectures merely serve as a reminder of the enigmatic nature of the relationship under investigation.
This unexpected correlation not only poses intriguing questions for fire safety and energy policy but also hints at the complexity of human behavior transcending geographical boundaries. The unexpected link between arson in Kentucky and kerosene consumption in Cuba, which we have affectionately deemed the "Kooky Connection," unveils the potential for unanticipated interconnections across seemingly unrelated realms. As we navigate through the uncharted territory of this peculiar relationship, we stand poised to unveil the sparks of insight that may fuel further scholarly inquiry and illuminate the hidden ties that bind our world.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this study involved a multi-faceted approach that combined quantitative analysis with a touch of whimsy. The research team aggregated data from the FBI Criminal Justice Information Services and the Energy Information Administration, utilizing information spanning the years 1985 to 2021.

To establish the connection between arson in Kentucky and kerosene consumption in Cuba, a series of convoluted computational algorithms were applied. The team employed a state-of-the-art statistical software adorned with a bow tie, to ensure a sophisticated and dapper analysis of the datasets.

The data underwent rigorous scrutiny, akin to separating the flammable from the non-flammable, before being subjected to a series of statistical tests. A delicate dance of regression analysis and time series modeling was performed, akin to a duet between an arsonist and the flickering flame from a kerosene lamp.

The correlation between the number of arson incidents in Kentucky and the volume of kerosene consumed in Cuba was measured using a variety of statistical techniques, most of which involved carefully avoiding any potential source of combustion during the analysis.

The research team also conducted an extensive literature review, sifting through the academic landscape for any evidence of a flame-fueled bond between these phenomena. Additionally, the team engaged in spirited debates and discussions, often fueled by copious amounts of coffee and the occasional flash of inspiration akin to a sudden spark of insight.

In summary, the methodology of this study combined the precision of statistical analysis with the creative flair of academic inquiry to unravel the mysterious connection between Kentucky arson and Cuban kerosene consumption.

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 Arson in Kentucky and Kerosene used in Cuba. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

For the time period 1985 to 2021, you found a correlation 0.7882704, r-squared of 0.6213703, 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]]
Kooky Connection: Kentucky Arson and Cuban Kerosene

[[ABSTRACT]]
This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
The connection between seemingly disparate events and phenomena has long fascinated and confounded researchers across various disciplines. In the realm of criminology and energy studies, the paradoxical correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba is a puzzle that has eluded explanation. What could possibly link the deliberate act of setting fires in the Bluegrass State and the use of kerosene for lighting and heating in the Caribbean island nation?
Despite the initial skepticism such a correlation may evoke, the statistical analysis from this study yielded a correlation coefficient of 0.7882704 and a significance level of p < 0.01. This robust statistical evidence compels attention, inviting us to explore the potential interconnectedness of these seemingly unrelated occurrences. Although the physical distance and contextual dissimilarity between Kentucky and Cuba may appear to obfuscate any conceivable connection, our findings suggest otherwise.
The perplexing nature of this correlation prompts one to imagine scenarios where arsonists in Kentucky receive shipments of Cuban kerosene, or where the consumption of kerosene in Cuba somehow sparks a ripple effect that ignites fires across the ocean. Of course, these whimsical conjectures merely serve as a reminder of the enigmatic nature of the relationship under investigation.
This unexpected correlation not only poses intriguing questions for fire safety and energy policy but also hints at the complexity of human behavior transcending geographical boundaries. The unexpected link between arson in Kentucky and kerosene consumption in Cuba, which we have affectionately deemed the "Kooky Connection," unveils the potential for unanticipated interconnections across seemingly unrelated realms. As we navigate through the uncharted territory of this peculiar relationship, we stand poised to unveil the sparks of insight that may fuel further scholarly inquiry and illuminate the hidden ties that bind our world.

-------

Your response should start like this:

[[RESULTS]]

ChatGPT:

[[RESULTS]]

The analysis revealed a striking correlation coefficient of 0.7882704 between instances of arson in Kentucky and the consumption of kerosene in Cuba. This correlation indicates a strong positive relationship between the two variables. Furthermore, the coefficient of determination (r-squared) was found to be 0.6213703, suggesting that approximately 62.1% of the variance in Kentucky arson can be explained by the consumption of kerosene in Cuba. The p-value of less than 0.01 indicates that the likelihood of observing such a strong correlation by random chance is exceedingly low, further bolstering the validity of the relationship.

The scatterplot (see Fig. 1) visually depicts the robust positive correlation between Kentucky arson and Cuban kerosene consumption. Each data point on the plot represents a specific time period within the years 1985 to 2021, providing a clear illustration of the covariation between the two variables.

These findings have unearthed a truly peculiar link between two seemingly unrelated phenomena. Despite the geographical, cultural, and contextual disparities between Kentucky and Cuba, the statistical evidence points to an improbable connection that defies conventional explanations. The unexpected nature of this correlation beckons further exploration and contemplation, prompting researchers to delve deeper into the underpinnings of this enigmatic relationship.

The unexpected association between Kentucky arson and Cuban kerosene consumption, often referred to by our research team as the "Kooky Connection," offers a rich tapestry of possibilities for future investigations. The sparks of insight gained from this study not only illuminate the interplay between these divergent domains but also serve as a catalyst for unraveling the hidden threads that weave through the fabric of our interconnected world.

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 Arson in Kentucky and Kerosene used in Cuba. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Kooky Connection: Kentucky Arson and Cuban Kerosene

[[ABSTRACT]]
This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

[[LITERATURE REVIEW]]
The authors find that the connection between instances of arson in Kentucky and the consumption of kerosene in Cuba has perplexed and intrigued researchers across various disciplines. In "Smith et al. (2015)," the authors delve into the intricate relationship between arson and fuel sources, shedding light on the complex motivations underlying deliberate fire setting. Similarly, Doe and Jones (2018) examine the socioeconomic factors influencing energy consumption patterns in Caribbean island nations, offering valuable insight into the cultural and environmental dynamics at play.
Moving beyond the realm of academic studies, works such as "The Arsonist's Dilemma: A Sociopsychological Analysis" and "Kerosene Chronicles: A Historical Perspective" provide further context and depth to the nuanced interplay between fire-related behavior and fuel usage. The former offers a thought-provoking exploration of the mindsets of arsonists, while the latter traces the historical trajectory of kerosene as a crucial energy source in various global contexts.
Beyond the confines of non-fiction literature, the fictional world offers intriguing narratives that tangentially touch upon the themes of fire, fuel, and unexpected connections. Novels such as "Burning Bridges" and "The Kerosene Conundrum" weave captivating tales that, while not explicitly addressing the Kentucky-Cuba correlation, offer thematic reverberations that resonate with the enigmatic nature of our research inquiry.
In a different medium, cinematic productions such as "Burn After Reading" and "The Cuban Kerosene Caper" provide fictionalized portrayals of intrigue, mystery, and unexpected twists – elements that, in a lighthearted manner, parallel the unexpected nature of our research findings. While these movies may not directly address the specific correlation under study, they offer a playful reminder of the whimsical possibilities and unexpected connections that our research seeks to unravel.

[[RESULTS]]
The analysis revealed a striking correlation coefficient of 0.7882704 between instances of arson in Kentucky and the consumption of kerosene in Cuba. This correlation indicates a strong positive relationship between the two variables. Furthermore, the coefficient of determination (r-squared) was found to be 0.6213703, suggesting that approximately 62.1% of the variance in Kentucky arson can be explained by the consumption of kerosene in Cuba. The p-value of less than 0.01 indicates that the likelihood of observing such a strong correlation by random chance is exceedingly low, further bolstering the validity of the relationship.
The scatterplot (see Fig. 1) visually depicts the robust positive correlation between Kentucky arson and Cuban kerosene consumption. Each data point on the plot represents a specific time period within the years 1985 to 2021, providing a clear illustration of the covariation between the two variables.
These findings have unearthed a truly peculiar link between two seemingly unrelated phenomena. Despite the geographical, cultural, and contextual disparities between Kentucky and Cuba, the statistical evidence points to an improbable connection that defies conventional explanations. The unexpected nature of this correlation beckons further exploration and contemplation, prompting researchers to delve deeper into the underpinnings of this enigmatic relationship.
The unexpected association between Kentucky arson and Cuban kerosene consumption, often referred to by our research team as the "Kooky Connection," offers a rich tapestry of possibilities for future investigations. The sparks of insight gained from this study not only illuminate the interplay between these divergent domains but also serve as a catalyst for unraveling the hidden threads that weave through the fabric of our interconnected world.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The results of our study provide empirical support for the unexpected and unprecedented correlation between instances of arson in Kentucky and the consumption of kerosene in Cuba. These findings are in line with prior research that has attempted to unravel the enigmatic connection between seemingly isolated phenomena. The kooky coincidence of Kentucky arson and Cuban kerosene consumption, often dismissed as a whimsical notion, has now been substantiated by robust statistical evidence.

The literature review hinted at the complex motivations underlying deliberate fire setting and shed light on the socioeconomic factors influencing energy consumption patterns in diverse cultural contexts. These insights resonate with our findings, suggesting that the interplay between human behavior and energy usage transcends geographical and contextual boundaries. The quirky motifs and thematic reverberations from literature and cinema, while not directly addressing the specific correlation at hand, offer a lighthearted nod to the unexpected twists that our research has uncovered.

By establishing a strong positive relationship between Kentucky arson and Cuban kerosene consumption, our study challenges conventional explanations and prompts contemplation of the hidden threads that intertwine diverse domains. The statistical evidence, with a correlation coefficient exceeding 0.7 and a p-value of less than 0.01, firmly supports the existence of this improbable connection. The implications of this linkage, playfully termed the "Kooky Connection," extend beyond the realms of fire safety and energy policy, opening new avenues for interdisciplinary inquiries into the multifaceted interconnections of our world.

In sum, the statistical revelations from our study afford a fresh perspective on the interconnectedness of seemingly disparate phenomena. The sparks of insight ignited by this research kindle the flames of curiosity, beckoning scholars to untangle the web of improbable correlations and hidden relationships that permeate our global tapestry. The "Kooky Connection" stands as a testament to the unexpected complexities that underpin human behavior and societal dynamics, fueling further scholarly inquiry and perpetuating the enduring allure of intellectual discovery.

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 Arson in Kentucky and Kerosene used in Cuba. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Kooky Connection: Kentucky Arson and Cuban Kerosene

[[ABSTRACT]]
This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

[[INTRDUCTION]]
The connection between seemingly disparate events and phenomena has long fascinated and confounded researchers across various disciplines. In the realm of criminology and energy studies, the paradoxical correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba is a puzzle that has eluded explanation. What could possibly link the deliberate act of setting fires in the Bluegrass State and the use of kerosene for lighting and heating in the Caribbean island nation?
Despite the initial skepticism such a correlation may evoke, the statistical analysis from this study yielded a correlation coefficient of 0.7882704 and a significance level of p < 0.01. This robust statistical evidence compels attention, inviting us to explore the potential interconnectedness of these seemingly unrelated occurrences. Although the physical distance and contextual dissimilarity between Kentucky and Cuba may appear to obfuscate any conceivable connection, our findings suggest otherwise.
The perplexing nature of this correlation prompts one to imagine scenarios where arsonists in Kentucky receive shipments of Cuban kerosene, or where the consumption of kerosene in Cuba somehow sparks a ripple effect that ignites fires across the ocean. Of course, these whimsical conjectures merely serve as a reminder of the enigmatic nature of the relationship under investigation.
This unexpected correlation not only poses intriguing questions for fire safety and energy policy but also hints at the complexity of human behavior transcending geographical boundaries. The unexpected link between arson in Kentucky and kerosene consumption in Cuba, which we have affectionately deemed the "Kooky Connection," unveils the potential for unanticipated interconnections across seemingly unrelated realms. As we navigate through the uncharted territory of this peculiar relationship, we stand poised to unveil the sparks of insight that may fuel further scholarly inquiry and illuminate the hidden ties that bind our world.

[[RESULTS]]
The analysis revealed a striking correlation coefficient of 0.7882704 between instances of arson in Kentucky and the consumption of kerosene in Cuba. This correlation indicates a strong positive relationship between the two variables. Furthermore, the coefficient of determination (r-squared) was found to be 0.6213703, suggesting that approximately 62.1% of the variance in Kentucky arson can be explained by the consumption of kerosene in Cuba. The p-value of less than 0.01 indicates that the likelihood of observing such a strong correlation by random chance is exceedingly low, further bolstering the validity of the relationship.
The scatterplot (see Fig. 1) visually depicts the robust positive correlation between Kentucky arson and Cuban kerosene consumption. Each data point on the plot represents a specific time period within the years 1985 to 2021, providing a clear illustration of the covariation between the two variables.
These findings have unearthed a truly peculiar link between two seemingly unrelated phenomena. Despite the geographical, cultural, and contextual disparities between Kentucky and Cuba, the statistical evidence points to an improbable connection that defies conventional explanations. The unexpected nature of this correlation beckons further exploration and contemplation, prompting researchers to delve deeper into the underpinnings of this enigmatic relationship.
The unexpected association between Kentucky arson and Cuban kerosene consumption, often referred to by our research team as the "Kooky Connection," offers a rich tapestry of possibilities for future investigations. The sparks of insight gained from this study not only illuminate the interplay between these divergent domains but also serve as a catalyst for unraveling the hidden threads that weave through the fabric of our interconnected world.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, the unearthing of the "Kooky Connection" between arson in Kentucky and kerosene consumption in Cuba has undoubtedly ignited a newfound curiosity within the academic community. The statistical analyses have illuminated a startling correlation that transcends geographic, cultural, and contextual disparities, leaving researchers both bemused and intrigued. While the exact mechanisms underlying this peculiar relationship elude our understanding, the robust correlation coefficient and significance level cannot be ignored, suggesting an inexplicable interconnection that challenges conventional wisdom.

As we ponder the implications of this improbable linkage, one cannot help but mull over the whimsical scenarios that might give rise to such a connection. Could it be that Kentucky arsonists harbor a penchant for Cuban kerosene, or that the illumination of kerosene lamps in Cuba inadvertently triggers a cross-continental pyromania? Indeed, the mind boggles at the possible narratives that could weave the fabric of this unlikely association.

The sparks of insight gleaned from this study not only shed light on the enigmatic intersection of fire-related behavior and energy consumption but also kindle a sense of wonder at the hidden ties that bind our world. We cannot help but anticipate the flames of curiosity that may ignite future inquiries, although we do assert that no more research in this inexplicable area is needed.

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 Kooky Connection: Kentucky Arson and Cuban Kerosene. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eccentric Fire Studies

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 Kooky Connection: Kentucky Arson and Cuban Kerosene. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Quirky Fire Research

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Kooky Connection: Kentucky Arson and Cuban Kerosene with an abstract of This study investigates the curious correlation between instances of arson in the state of Kentucky and the consumption of kerosene in Cuba. Using data from the FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 1985 to 2021. With a correlation coefficient of 0.7882704 and p < 0.01, the statistical connection between these seemingly disparate phenomena cannot be denied. Despite the physical distance and contextual dissimilarity, the evidence suggests a peculiar relationship that warrants further investigation. This unexpected linkage may hold implications not only for fire safety and energy policy, but also for the intertwined nature of human behavior across borders. The sparks of insight from this study shed light on the intersection of seemingly unrelated realms, illuminating the potential for hidden connections to fuel further scholarly inquiry.

ChatGPT:

Kentucky arson, Cuban kerosene, arson statistics, Kentucky fire incidents, Cuban kerosene consumption, FBI Criminal Justice Information Services, Energy Information Administration, correlation analysis, fire safety implications, energy policy implications, human behavior across borders

*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

Arson in Kentucky
Detailed data title: The arson rate per 100,000 residents in Kentucky
Source: FBI Criminal Justice Information Services
See what else correlates with Arson in Kentucky

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

Correlation r = 0.7882704 (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 = 0.6213703 (Coefficient of determination)
This means 62.1% of the change in the one variable (i.e., Kerosene used in Cuba) is predictable based on the change in the other (i.e., Arson in Kentucky) over the 37 years from 1985 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 7.0E-9.^Show 0.0000000069501159077246610000
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 0.79 in 7.0E-7% of random cases. Said differently, if you correlated 143,882,493 random variables^Note You don't actually need 143 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 36 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 36 because we have two variables measured over a period of 37 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.

[ 0.62, 0.89 ] 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.

	1985	1986	1987	1988	1989	1990	1991	1992	1993	1994	1995	1996	1997	1998	1999	2000	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020	2021
Arson in Kentucky (Arson rate)	32.7	39.4	35	10.3	26.5	27.5	33.7	28.6	28.7	32.4	37.3	13.7	11.7	10.5	10.8	9.6	10.1	8.4	7	3	19	11.3	8.2	7.2	18.1	15.9	15.5	16.1	14.4	12	8.3	13.2	11.4	10	10.2	10.8	9.6
Kerosene used in Cuba (Million Barrels/Day)	14.6292	15	14	13	14	13	12	12	12	13	12	12	4.6	3.2	3	4.70981	3.66381	2.49901	4.04501	7.5188	5.61219	2.83786	1.99074	1.75298	1.65189	1.67307	1.67307	1.67307	1.67307	1.27068	2	2	1.71636	1.6729	1.586	1.39047	1.39047

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.
Outlandish outliers: There are "outliers" in this data.^Note In concept, "outlier" just means "way different than the rest of your dataset." When calculating a correlation like this, they are particularly impactful because a single outlier can substantially increase your correlation.

For the purposes of this project, I counted a point as an outlier if it the residual was two standard deviations from the mean.

(This bullet point only shows up in the details page on charts that do, in fact, have outliers.)
They stand out on the scatterplot above: notice the dots that are far away from any other dots. I intentionally mishandeled outliers, which makes the correlation look extra strong.

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([32.7,39.4,35,10.3,26.5,27.5,33.7,28.6,28.7,32.4,37.3,13.7,11.7,10.5,10.8,9.6,10.1,8.4,7,3,19,11.3,8.2,7.2,18.1,15.9,15.5,16.1,14.4,12,8.3,13.2,11.4,10,10.2,10.8,9.6,])
array_2 = np.array([14.6292,15,14,13,14,13,12,12,12,13,12,12,4.6,3.2,3,4.70981,3.66381,2.49901,4.04501,7.5188,5.61219,2.83786,1.99074,1.75298,1.65189,1.67307,1.67307,1.67307,1.67307,1.27068,2,2,1.71636,1.6729,1.586,1.39047,1.39047,])
array_1_name = "Arson in Kentucky"
array_2_name = "Kerosene used in Cuba"

# 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 Arson in Kentucky
Line chart for only Kerosene used in Cuba
AI-generated correlation image
The spurious research paper: Kooky Connection: Kentucky Arson and Cuban Kerosene

View another random correlation

How fun was this correlation?

You're the rating guru we've been waiting for!

Correlation ID: 4123 · Black Variable ID: 20044 · Red Variable ID: 24336


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