Spurious correlation #3,791 · 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 Arizona and the second variable is Kerosene used in Turkiye. The chart goes from 1985 to 2022, 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 Arizona and the second variable is Kerosene used in Turkiye. The chart goes from 1985 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the number of arson incidents in Arizona dropped, there was a subsequent decline in the demand for kerosene as a potential accelerant. This led to a surplus of kerosene, causing exports to countries like Turkiye to decrease as they found themselves with ample supply, and ultimately resulting in a nationwide shortage of kerosene in Turkiye. It seems like even the kerosene market couldn't handle the heat of the Arizona arsons fizzling out!

^{Show image generation prompt} Model: dalle-3
Prompt: [ Cute cartoon ] Create an image of a charming Arizona desert scene with a small fire flickering on the horizon as the sun sets. A group of adorable cartoon firefighters in colorful uniforms, emblazoned with the letters "AZFD", is seen quickly extinguishing the flames. Additionally, depict a bustling cartoon representation of the streets of Turkiye, where a crowd marvels at a team of cute, skilled firefighters containing a small kerosene-related fire. The locals cheer and applaud these lovable heroes as they proudly stand, showcasing their expertise and helping reduce kerosene usage in the community. 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 Arizona and Kerosene used in Turkiye. 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: Symbolism Cute cartoon Cyber folk a funny image you would see on reddit Cute cartoon
ChatGPT: Cute cartoon

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 Arizona and Kerosene used in Turkiye, in the following situation: Because the decrease in arson in Arizona reduced the demand for emergency responders, which in turn led to a surplus of firefighters. This surplus of firefighters then found profitable opportunities overseas in Turkiye, leading to a decrease in kerosene usage due to their expertise in preventing fires.. Keep the description simple.
ChatGPT: In a dusty Arizona desert, a small fire flickers on the horizon as the sun sets. A group of firefighters, their uniforms emblazoned with the letters "AZFD," quickly extinguishes the flames. As they pack up their equipment, a surplus of firefighters gathers by their trucks, chatting and laughing. Meanwhile, in the bustling streets of Turkiye, a crowd watches in amazement as a team of skilled firefighters swiftly contain a small kerosene-related fire, preventing a disaster. The locals cheer and applaud as the firefighters stand proudly, their expertise evident as they help reduce kerosene usage in the community.

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: [ Cute cartoon ] and depicting this scene: In a dusty Arizona desert, a small fire flickers on the horizon as the sun sets. A group of firefighters, their uniforms emblazoned with the letters "AZFD," quickly extinguishes the flames. As they pack up their equipment, a surplus of firefighters gathers by their trucks, chatting and laughing. Meanwhile, in the bustling streets of Turkiye, a crowd watches in amazement as a team of skilled firefighters swiftly contain a small kerosene-related fire, preventing a disaster. The locals cheer and applaud as the firefighters stand proudly, their expertise evident as they help reduce kerosene usage in the community. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: [ Cute cartoon ] Create an image of a charming Arizona desert scene with a small fire flickering on the horizon as the sun sets. A group of adorable cartoon firefighters in colorful uniforms, emblazoned with the letters "AZFD", is seen quickly extinguishing the flames. Additionally, depict a bustling cartoon representation of the streets of Turkiye, where a crowd marvels at a team of cute, skilled firefighters containing a small kerosene-related fire. The locals cheer and applaud these lovable heroes as they proudly stand, showcasing their expertise and helping reduce kerosene usage in the community.

*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 Arizona caused Kerosene used in Turkiye to decrease. Make it feel plausible.

AI academic paper

(Because p < 0.01)

Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

Journal of Pyrostatistics and Combustion Dynamics

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 Arson in Arizona and Kerosene used in Turkiye. Make lots of 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 devolve ever further, and mention something completely ridiculous, like you conducted literature review by reading CVS receipts.

Here is the title and abstract of the paper:
[[TITLE]]
Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

[[ABSTRACT]]
This study seeks to ignite curiosity by examining the tantalizing correlation between arson rates in Arizona and kerosene consumption in Turkiye. Using data from FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a thorough investigation spanning from 1985 to 2022. Surprisingly, the correlation coefficient of 0.8498352 and p < 0.01 suggested a strong positive relationship between these seemingly unrelated phenomena. We delve into the potential implications of this fiery connection and shed light on the sparks flying between arson in the desert state and kerosene use across the globe.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The flickering flames of curiosity have long danced around the enigmatic relationship between seemingly unrelated phenomena. This study seeks to illuminate the fiery connection between arson rates in Arizona and the consumption of kerosene in Turkiye, igniting a spark of interest in the scientific community. As we delve into this incendiary investigation, the aim is to shed light on the smoldering correlation between these two variables, and to explore the potential implications of this unexpected pairing.
Venturing beyond the traditional realms of research, we are kindling a fire under the conventional understanding of cause and effect. The association between arson and kerosene consumption may seem to be fueled by coincidence, but as we carefully analyze the data, it becomes clear that there's more to this fiery tale than mere happenstance.
With a correlation coefficient of 0.8498352 and a scorching p-value < 0.01, the statistical analysis has revealed a robust positive relationship between the two variables. To put it in layman's terms, these findings are hotter than a freshly ignited bonfire on a chilly evening. But, as any seasoned researcher knows, correlation does not necessarily imply causation – a principle that we'll keep in mind as we traverse this treacherous terrain of data analysis.
Join us as we embark on this scorching exploration, where the heat is on and the findings are smokin'. Prepare to be mesmerized by the sizzling science of unexpected correlations, as we aim to fan the flames of understanding and illuminate the blazing bond between arson in the desert state and the consumption of kerosene across the seas.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

The tantalizing correlation between arson rates in Arizona and the consumption of kerosene in Turkiye has sparked the interest of researchers and enthusiasts alike. Our investigation into this fiery connection has led us to scrutinize a range of literature spanning various disciplines.

In "Firestarter: The Arsonist's Toolkit," Smith and Doe explore the psychology behind arson perpetration and its impact on society. While their work primarily focuses on individual motives and criminal behavior, it inadvertently sets ablaze the imagination with the intriguing possibility of a cross-continental kerosene connection.

Turning to energy consumption, Jones and Smith's study, "Fueling the Future: A Global Perspective on Kerosene Usage," provides a comprehensive analysis of kerosene consumption patterns across regions. Although their work does not explicitly delve into the incidence of arson, it kindles the flames of curiosity regarding potential associations between this fuel and fire-related activities.

Expanding our purview, "The Tinder Chronicles" by John Blaze peeks into the world of combustible materials and their mesmerizing, if not incendiary, qualities. While not a scholarly work by traditional standards, the book's vivid descriptions of ignition and combustion foster a newfound appreciation for the mesmerizing allure of fire-related phenomena.

Venturing further into speculative fiction, Ray Bradbury's "Fahrenheit 451" captivates readers with its dystopian portrayal of a society where books are burned to ashes. While the narrative primarily revolves around censorship and intellectual freedom, it fuels our imagination with alternate possibilities of fuel-related enigmas.

As we wade deeper into the burning embers of academic inquiry, it is essential to acknowledge the non-traditional sources that have unwittingly stoked the flames of our intellectual pursuit. The authors acknowledge that, in a quest to uncover unconventional connections, they have perused an eclectic assortment of materials, including but not limited to ancient scrolls, cave drawings, and even meticulously analyzed CVS receipts to identify potential patterns, all in the pursuit of shedding light on this fiery correlation.

In the grand scheme of scholarly inquiry, the authors maintain a healthy appreciation for the humor and creativity that can infuse the often rigorous pursuit of knowledge. After all, what is a scholarly pursuit if it cannot light a spark of joy and wonder in the hearts of those who embark on the smoldering journey of 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 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 Arizona and Kerosene used in Turkiye. Make lots of 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 FBI Criminal Justice Information Services and Energy Information Administration . You used data from 1985 to 2022

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]]
Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

[[ABSTRACT]]
This study seeks to ignite curiosity by examining the tantalizing correlation between arson rates in Arizona and kerosene consumption in Turkiye. Using data from FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a thorough investigation spanning from 1985 to 2022. Surprisingly, the correlation coefficient of 0.8498352 and p < 0.01 suggested a strong positive relationship between these seemingly unrelated phenomena. We delve into the potential implications of this fiery connection and shed light on the sparks flying between arson in the desert state and kerosene use across the globe.

[[INTRODUCTION]]
The flickering flames of curiosity have long danced around the enigmatic relationship between seemingly unrelated phenomena. This study seeks to illuminate the fiery connection between arson rates in Arizona and the consumption of kerosene in Turkiye, igniting a spark of interest in the scientific community. As we delve into this incendiary investigation, the aim is to shed light on the smoldering correlation between these two variables, and to explore the potential implications of this unexpected pairing.
Venturing beyond the traditional realms of research, we are kindling a fire under the conventional understanding of cause and effect. The association between arson and kerosene consumption may seem to be fueled by coincidence, but as we carefully analyze the data, it becomes clear that there's more to this fiery tale than mere happenstance.
With a correlation coefficient of 0.8498352 and a scorching p-value < 0.01, the statistical analysis has revealed a robust positive relationship between the two variables. To put it in layman's terms, these findings are hotter than a freshly ignited bonfire on a chilly evening. But, as any seasoned researcher knows, correlation does not necessarily imply causation – a principle that we'll keep in mind as we traverse this treacherous terrain of data analysis.
Join us as we embark on this scorching exploration, where the heat is on and the findings are smokin'. Prepare to be mesmerized by the sizzling science of unexpected correlations, as we aim to fan the flames of understanding and illuminate the blazing bond between arson in the desert state and the consumption of kerosene across the seas.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

To extinguish any doubts about the validity of our findings, our research team embarked on a scorching journey through the vast expanse of data collection and analysis. The data for arson rates in Arizona was collected from the FBI Criminal Justice Information Services, while the kerosene consumption data in Turkiye was sourced from the Energy Information Administration. The study period spanned from 1985 to 2022, ensuring a comprehensive exploration of the fiery relationship between these variables.

Our first step in scoping out this inferno of a study was to meticulously gather the relevant data. With a fine-tooth comb, we combed through years of arson statistics and kerosene consumption figures, ensuring that no ember of information was left unturned. After navigating the maze of online databases and statistical archives, we emerged triumphant, clutching a trove of sizzling data to fuel our analysis.

The next stage of our scorching methodology involved a rigorous examination of the collected data. Armed with the formidable tool of statistical software, we set the data ablaze with complex analyses. Our team engaged in a hypnotic dance of correlation coefficients, regression models, and significance tests, all to unearth the potential sparks flying between arson in Arizona and kerosene consumption in Turkiye.

To avoid getting burnt by spurious findings, we conducted sensitivity analyses and robustness checks, ensuring that the correlation we observed was not merely a flash in the pan. After subjecting the data to intense scrutiny, we emerged with a scorching correlation coefficient of 0.8498352 and a sizzling p-value < 0.01, signaling a robust positive relationship between these seemingly disparate variables.

Taking utmost care to avoid drawing hasty conclusions from our findings, we exercised caution in interpreting the scorching statistical results. While the fiery bond between arson and kerosene consumption may appear to be a match made in statistical heaven, we remained mindful of the age-old adage that correlation does not imply causation, cooling the flames of overenthusiastic interpretation.

In summary, the methodology of this study involved a thorough gathering of data, a heat-intensive statistical analysis, and a cautious interpretation of the scorching findings. As we move forward into the inferno of discussion and conclusion, the flames of scientific curiosity will continue to flicker, illuminating the unexpected fiery connection between arson in Arizona and kerosene consumption in Turkiye.

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 Arizona and Kerosene used in Turkiye. Make lots of 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]]
Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

[[ABSTRACT]]
This study seeks to ignite curiosity by examining the tantalizing correlation between arson rates in Arizona and kerosene consumption in Turkiye. Using data from FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a thorough investigation spanning from 1985 to 2022. Surprisingly, the correlation coefficient of 0.8498352 and p < 0.01 suggested a strong positive relationship between these seemingly unrelated phenomena. We delve into the potential implications of this fiery connection and shed light on the sparks flying between arson in the desert state and kerosene use across the globe.

[[LITERATURE REVIEW]]
The tantalizing correlation between arson rates in Arizona and the consumption of kerosene in Turkiye has sparked the interest of researchers and enthusiasts alike. Our investigation into this fiery connection has led us to scrutinize a range of literature spanning various disciplines.
In "Firestarter: The Arsonist's Toolkit," Smith and Doe explore the psychology behind arson perpetration and its impact on society. While their work primarily focuses on individual motives and criminal behavior, it inadvertently sets ablaze the imagination with the intriguing possibility of a cross-continental kerosene connection.
Turning to energy consumption, Jones and Smith's study, "Fueling the Future: A Global Perspective on Kerosene Usage," provides a comprehensive analysis of kerosene consumption patterns across regions. Although their work does not explicitly delve into the incidence of arson, it kindles the flames of curiosity regarding potential associations between this fuel and fire-related activities.
Expanding our purview, "The Tinder Chronicles" by John Blaze peeks into the world of combustible materials and their mesmerizing, if not incendiary, qualities. While not a scholarly work by traditional standards, the book's vivid descriptions of ignition and combustion foster a newfound appreciation for the mesmerizing allure of fire-related phenomena.
Venturing further into speculative fiction, Ray Bradbury's "Fahrenheit 451" captivates readers with its dystopian portrayal of a society where books are burned to ashes. While the narrative primarily revolves around censorship and intellectual freedom, it fuels our imagination with alternate possibilities of fuel-related enigmas.
As we wade deeper into the burning embers of academic inquiry, it is essential to acknowledge the non-traditional sources that have unwittingly stoked the flames of our intellectual pursuit. The authors acknowledge that, in a quest to uncover unconventional connections, they have perused an eclectic assortment of materials, including but not limited to ancient scrolls, cave drawings, and even meticulously analyzed CVS receipts to identify potential patterns, all in the pursuit of shedding light on this fiery correlation.
In the grand scheme of scholarly inquiry, the authors maintain a healthy appreciation for the humor and creativity that can infuse the often rigorous pursuit of knowledge. After all, what is a scholarly pursuit if it cannot light a spark of joy and wonder in the hearts of those who embark on the smoldering journey of discovery?

[[RESULTS]]
The scorching analysis of the data revealed a remarkable correlation coefficient of 0.8498352 and an r-squared value of 0.7222198, indicating a strong positive relationship between arson rates in Arizona and kerosene consumption in Turkiye. This finding is hotter than a Bunsen burner in a chemistry lab!
Fig. 1 displays a scorching scatterplot that visually encapsulates the red-hot relationship between these two variables. It's as if the data points are fueled by the burning desire to show how closely these phenomena are intertwined.
The statistical significance, with a p-value of < 0.01, is more striking than a firework lighting up the night sky. These results are statistically significant enough to make any statistical analyst start sweating - no need for a bonfire here, the statistical heat is more than enough!
However, it must be emphasized that correlation does not imply causation, just as finding a matchstick in one's pocket doesn't imply starting a forest fire. This important reminder keeps our feet firmly grounded in the realm of scientific inquiry, even as we're surrounded by sparks of statistical excitement.
In conclusion, these results are more electric than static electricity on a dry day! The fiery connection between arson in Arizona and kerosene consumption in Turkiye has set the academic world ablaze with curiosity, and the research team is fired up about further investigating the implications and potential factors underlying this unexpected correlation.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The scorching results of our study have breathed life into the smoldering embers of the literature review. Much like a skilled arsonist, our findings have added fuel to the fire of existing research on this intriguing connection between arson in Arizona and kerosene consumption in Turkiye.

First and foremost, our results align with the existing literature that has hinted at the potential linkage between arson perpetration and the usage of kerosene. Just as Jones and Smith's work kindled the flames of curiosity regarding the association between kerosene fuel and fire-related activities, our study fans the flames of empirical evidence to support this fiery connection. The correlation coefficient of 0.8498352 has set the scientific community ablaze with excitement, validating our initial hypotheses and kindling the sparks of further inquiry.

Moreover, our findings shed light on the stark statistical significance, emphasizing the robustness of the observed relationship. The p-value of < 0.01 is more notable than a flaming meteor shower, illuminating the significance of the association between arson rates in Arizona and kerosene consumption in Turkiye. These statistical results sizzle with significance and serve as a beacon for future research endeavors in this scorching field.

When considering the broader implications of our study, it is crucial to acknowledge the multifaceted nature of the fiery connection between arson and kerosene consumption. While our research does not unveil the underlying causative mechanisms, the robust correlation uncovered serves as the glowing ember that ignites further investigations into the potential factors driving this association. Just as a careful examination of a crime scene reveals telltale signs of arson, our study provides a tantalizing starting point for unraveling the enigmatic ties between these seemingly unrelated phenomena.

In conclusion, our study ignites the torch of scientific inquiry, illuminating the captivating correlation between arson in Arizona and kerosene consumption in Turkiye. As we stoke the flames of curiosity and continue to fan the embers of knowledge, the fiery connection between these variables remains a dazzling conundrum worthy of continued investigation. After all, what is research if it does not ignite the flames of wonder and illuminate the path for future explorations?

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 Arizona and Kerosene used in Turkiye. Make lots of 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]]
Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

[[ABSTRACT]]
This study seeks to ignite curiosity by examining the tantalizing correlation between arson rates in Arizona and kerosene consumption in Turkiye. Using data from FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a thorough investigation spanning from 1985 to 2022. Surprisingly, the correlation coefficient of 0.8498352 and p < 0.01 suggested a strong positive relationship between these seemingly unrelated phenomena. We delve into the potential implications of this fiery connection and shed light on the sparks flying between arson in the desert state and kerosene use across the globe.

[[INTRDUCTION]]
The flickering flames of curiosity have long danced around the enigmatic relationship between seemingly unrelated phenomena. This study seeks to illuminate the fiery connection between arson rates in Arizona and the consumption of kerosene in Turkiye, igniting a spark of interest in the scientific community. As we delve into this incendiary investigation, the aim is to shed light on the smoldering correlation between these two variables, and to explore the potential implications of this unexpected pairing.
Venturing beyond the traditional realms of research, we are kindling a fire under the conventional understanding of cause and effect. The association between arson and kerosene consumption may seem to be fueled by coincidence, but as we carefully analyze the data, it becomes clear that there's more to this fiery tale than mere happenstance.
With a correlation coefficient of 0.8498352 and a scorching p-value < 0.01, the statistical analysis has revealed a robust positive relationship between the two variables. To put it in layman's terms, these findings are hotter than a freshly ignited bonfire on a chilly evening. But, as any seasoned researcher knows, correlation does not necessarily imply causation – a principle that we'll keep in mind as we traverse this treacherous terrain of data analysis.
Join us as we embark on this scorching exploration, where the heat is on and the findings are smokin'. Prepare to be mesmerized by the sizzling science of unexpected correlations, as we aim to fan the flames of understanding and illuminate the blazing bond between arson in the desert state and the consumption of kerosene across the seas.

[[RESULTS]]
The scorching analysis of the data revealed a remarkable correlation coefficient of 0.8498352 and an r-squared value of 0.7222198, indicating a strong positive relationship between arson rates in Arizona and kerosene consumption in Turkiye. This finding is hotter than a Bunsen burner in a chemistry lab!
Fig. 1 displays a scorching scatterplot that visually encapsulates the red-hot relationship between these two variables. It's as if the data points are fueled by the burning desire to show how closely these phenomena are intertwined.
The statistical significance, with a p-value of < 0.01, is more striking than a firework lighting up the night sky. These results are statistically significant enough to make any statistical analyst start sweating - no need for a bonfire here, the statistical heat is more than enough!
However, it must be emphasized that correlation does not imply causation, just as finding a matchstick in one's pocket doesn't imply starting a forest fire. This important reminder keeps our feet firmly grounded in the realm of scientific inquiry, even as we're surrounded by sparks of statistical excitement.
In conclusion, these results are more electric than static electricity on a dry day! The fiery connection between arson in Arizona and kerosene consumption in Turkiye has set the academic world ablaze with curiosity, and the research team is fired up about further investigating the implications and potential factors underlying this unexpected correlation.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In closing, the scorching findings of this research kindle a fiery fascination with the unexpected link between arson in Arizona and kerosene consumption in Turkiye. The robust correlation coefficient, akin to a blazing bonfire, ignites curiosity about the potential intertwined nature of these two seemingly distinct phenomena. It seems these variables are as inseparable as a match and a fuse!

While the statistically significant relationship seems to glow as bright as the Northern Lights, it's crucial to remember that correlation doesn't imply causation, just as finding a pirate's treasure map doesn't guarantee a chest full of gold doubloons. We must tread carefully as we navigate this landscape, ensuring we don't get burned by drawing premature conclusions.

As we extinguish the flames of this discussion, it seems that further research in this area is as unnecessary as bringing a flashlight to a sunlit beach. The findings of this investigation provide ample fuel for thought and no further kindling of fiery curiosity is warranted. Let this smoldering study be a cautionary tale: sometimes in science, as in life, correlations may seem hotter than they really are.

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 Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Pyrostatistics and Combustion Dynamics

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 Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye. Respond only with the name of a fictional organization.

ChatGPT:

The Global Institute for Fire Dynamics and Fuels 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 Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye with an abstract of This study seeks to ignite curiosity by examining the tantalizing correlation between arson rates in Arizona and kerosene consumption in Turkiye. Using data from FBI Criminal Justice Information Services and the Energy Information Administration, our research team conducted a thorough investigation spanning from 1985 to 2022. Surprisingly, the correlation coefficient of 0.8498352 and p < 0.01 suggested a strong positive relationship between these seemingly unrelated phenomena. We delve into the potential implications of this fiery connection and shed light on the sparks flying between arson in the desert state and kerosene use across the globe.

ChatGPT:

arson rates, Arizona, kerosene consumption, Turkiye, correlation, FBI Criminal Justice Information Services, Energy Information Administration, positive relationship, implications, sparks flying

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

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

Correlation r = 0.8498352 (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 = 0.7222198 (Coefficient of determination)
This means 72.2% of the change in the one variable (i.e., Kerosene used in Turkiye) is predictable based on the change in the other (i.e., Arson in Arizona) over the 38 years from 1985 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 1.5E-11.^Show 0.0000000000149198941724717840
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 0.85 in 1.5E-9% of random cases. Said differently, if you correlated 67,024,604,092 random variables^Note You don't actually need 67 billion variables to find a correlation like this one. I don't have that many variables in my database. You can also correlate variables that are not independent. I do this a lot.

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

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

Just to be clear: I'm being completely transparent about the calculations. There is no math trickery. This is just how statistics shakes out when you calculate hundreds of millions of random correlations.
with the same 37 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 37 because we have two variables measured over a period of 38 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.

[ 0.73, 0.92 ] 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	2022
Arson in Arizona (Arson rate)	58.4	63.4	52.6	51.1	58.9	43	39.2	31.3	29.6	32.6	36.1	30.2	28.2	26.5	26.9	27.4	29	32.5	28	26.6	27.9	38.2	34.9	38.8	32.5	28.5	27	29.9	26.3	26.2	17.5	16.6	16.9	23.9	12.8	17.4	6.1	11.6
Kerosene used in Turkiye (Million Barrels/Day)	5.42466	5.26849	6.21644	5.5847	4.75069	3.92329	3.65206	3.03552	3.30137	2.35068	2.2274	2.00273	1.59726	1.68493	1.15522	0.806011	0.694611	0.567123	1.53425	0.79235	0.613699	0.526027	0.912329	1.12295	0.79726	1.1726	1.40274	1.03279	1.20822	0.881967	1.03881	0.556075	0.56338	0.301887	0.39779	0.199405	0.047904	0.047904

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([58.4,63.4,52.6,51.1,58.9,43,39.2,31.3,29.6,32.6,36.1,30.2,28.2,26.5,26.9,27.4,29,32.5,28,26.6,27.9,38.2,34.9,38.8,32.5,28.5,27,29.9,26.3,26.2,17.5,16.6,16.9,23.9,12.8,17.4,6.1,11.6,])
array_2 = np.array([5.42466,5.26849,6.21644,5.5847,4.75069,3.92329,3.65206,3.03552,3.30137,2.35068,2.2274,2.00273,1.59726,1.68493,1.15522,0.806011,0.694611,0.567123,1.53425,0.79235,0.613699,0.526027,0.912329,1.12295,0.79726,1.1726,1.40274,1.03279,1.20822,0.881967,1.03881,0.556075,0.56338,0.301887,0.39779,0.199405,0.047904,0.047904,])
array_1_name = "Arson in Arizona"
array_2_name = "Kerosene used in Turkiye"

# 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 Arizona
Line chart for only Kerosene used in Turkiye
AI-generated correlation image
The spurious research paper: Burnin' Love: A Fiery Connection Between Arson in Arizona and Kerosene Consumption in Turkiye

View another random correlation

How fun was this correlation?

Bravo! Your evaluation rocks!

Correlation ID: 3791 · Black Variable ID: 20049 · Red Variable ID: 25016


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