Spurious correlation #1,460 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is Passing attempts by Drew Brees per NFL season and the second variable is Kerosene used in Equatorial Guinea. The chart goes from 2001 to 2020, 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 Passing attempts by Drew Brees per NFL season and the second variable is Kerosene used in Equatorial Guinea. The chart goes from 2001 to 2020, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As Drew Brees attempts more passes, the sheer force of his arm talent creates tiny frictional heat energy, leading to a minuscule spike in global kerosene demand. It's like he's inadvertently fueling the world one pass at a time!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image that resembles a TIME magazine cover, featuring a scene in Equatorial Guinea. In the image, Drew Brees is shown in a grassy field, tossing a football to a group of joyous young children as they eagerly attempt to catch his passes. Meanwhile, a group of workers can be seen nearby carefully refilling lanterns with kerosene, ensuring the evening festivities are well-lit. The style should be realistic, capturing the vibrant atmosphere of the scene with attention to details such as the children's excitement, the lush greenery of the field, and the warm glow of the lanterns. 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: Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea. 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: A scene from Skyrim 3D Pixar Style Glitch art Minimalism A TIME magazine cover image
ChatGPT: A TIME magazine cover image

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 Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea together. Keep the description simple.
ChatGPT: In a grassy field in Equatorial Guinea, Drew Brees can be seen tossing a football to a group of young children as they excitedly attempt to catch his passes. Meanwhile, nearby, a group of workers are carefully refilling lanterns with kerosene to ensure the evening festivities are well-lit.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ A TIME magazine cover image ] and depicting this scene: In a grassy field in Equatorial Guinea, Drew Brees can be seen tossing a football to a group of young children as they excitedly attempt to catch his passes. Meanwhile, nearby, a group of workers are carefully refilling lanterns with kerosene to ensure the evening festivities are well-lit. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that resembles a TIME magazine cover, featuring a scene in Equatorial Guinea. In the image, Drew Brees is shown in a grassy field, tossing a football to a group of joyous young children as they eagerly attempt to catch his passes. Meanwhile, a group of workers can be seen nearby carefully refilling lanterns with kerosene, ensuring the evening festivities are well-lit. The style should be realistic, capturing the vibrant atmosphere of the scene with attention to details such as the children's excitement, the lush greenery of the field, and the warm glow of the lanterns.

*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 an increase in Passing attempts by Drew Brees per NFL season caused Kerosene used in Equatorial Guinea to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)

A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

The Journal of Quirky Athlete Analyses

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 Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then cite some social media posts you read that seem to be related.

Here is the title and abstract of the paper:
[[TITLE]]
A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

[[ABSTRACT]]
The connection between NFL quarterback Drew Brees's passing attempts and the consumption of kerosene in Equatorial Guinea has been an enigma, sparking curiosity and the urge to explore this unlikely pairing. This research paper delves into the statistical relationship between these seemingly disparate entities, with an aim to shed light on this perplexing association.

Drawing upon data from the NFL and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 2001 to 2020. The results revealed a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, indicating a robust statistical connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.

The findings not only ignite further curiosity but also add a spark of intrigue into the world of sports and global energy consumption. As we unravel the threads of this unexpected connection, it becomes apparent that the whims of statistical correlation can lead to unexpected revelations, much like a quarterback's unexpected pass.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
As we embark on this scholarly exploration into the intersection of NFL passing prowess and the combustible world of kerosene consumption, it is essential to kindle the flames of curiosity and skepticism. For decades, researchers have been drawn to correlations that seem as improbable as a touchdown pass from the 50-yard line. The enigmatic bond between Drew Brees's passing attempts per NFL season and the utilization of kerosene in Equatorial Guinea is no exception, providing fodder for both statistical scrutiny and levity.
In the world of research, one must always keep a keen eye out for correlations that may seem to be a mere fluke, akin to a fumble recovered by a persistent running back. However, upon closer examination, these seemingly improbable connections may reveal a deeper, more profound truth. Dad joke alert: "I guess you could say we're looking to throw some light on this fiery correlation. Let's keep the puns burning, shall we?"
The burning question at the heart of this inquiry revolves around whether Drew Brees's passing attempts, a hallmark of his illustrious career, have any bearing on the consumption of kerosene in Equatorial Guinea, a nation located in the tropical climes of West Africa. The idea that an athlete's on-field performance could influence energy consumption may seem as incongruous as a quarterback wearing cleats on a basketball court, yet the data suggests otherwise.
With the statistical prowess of a seasoned defensive player, our research team has meticulously gathered and analyzed data from both the NFL and the Energy Information Administration, spanning a period of two decades. The resulting correlation coefficient of 0.8766386 and a p-value of less than 0.01 have elevated this seemingly whimsical connection to the realm of robust statistical significance. It seems that, much like a well-executed play, statistical correlation has the power to surprise even the most seasoned spectators.
The implications of these findings extend far beyond the realm of sports and energy consumption, offering a glimpse into the unpredictable nature of statistical relationships. As we unravel the threads of this unexpected correlation, it becomes evident that the world of research is rife with paradoxes and surprises, much like an onside kick in the final minutes of a game.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]
To date, the scholarly literature on the connection between NFL quarterback performance and global energy consumption has been remarkably sparse. However, a few pioneering studies have delved into similarly unexpected correlations. Smith (2015) explored the intriguing link between free-throw percentage in professional basketball and the price of avocados in Mexico, laying the groundwork for our current inquiry. Doe and Jones (2018) examined the connection between baseball stolen bases and agricultural water usage in Mongolia, emphasizing the need for further exploration of seemingly unrelated phenomena. Dad joke alert: Why did the football team go to the bank? To get their quarterback!
Beyond these seminal works, our investigation draws inspiration from various non-fiction works that provide valuable insights into statistical oddities and unconventional correlations. In "Freakonomics" by Steven D. Levitt and Stephen J. Dubner, the authors explore the hidden side of everything, including unexpected linkages between disparate aspects of society. Similarly, "The Tipping Point" by Malcolm Gladwell sheds light on the sudden and unexpected changes that can result from seemingly unrelated events or behaviors. Dad joke alert: What do you call a retired QB? A has-bean!
Turning to the literary realm, several fiction works offer a whimsical perspective on unusual connections and improbable relationships. In "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, the protagonist embarks on a journey through the cosmos, encountering bizarre coincidences and unexpected correlations along the way. "Cloud Atlas" by David Mitchell weaves together disparate storylines across time and space, reflecting the interconnectedness of seemingly unrelated events. Dad joke alert: How do football players stay cool? They stand near the fans!
Furthermore, recent social media posts have hinted at the potential link between sports performance and unexpected societal outcomes. A tweet from @SportsStatsGuru pondered whether NBA three-point shooting percentages could predict ice cream sales in Alaska, sparking lighthearted yet thought-provoking discussions. Another Reddit thread delved into the possibility of a connection between soccer goal differentials and global coffee consumption, generating playful speculation among online communities. Dad joke alert: Why are football stadiums so cool? Because they're full of fans!
In light of these diverse sources of inspiration and inquiry, our research aims to contribute to the growing body of literature exploring improbable correlations and the far-reaching implications of statistical relationships. As we unravel the connection between Drew Brees's passing attempts and kerosene consumption in Equatorial Guinea, we are reminded that the world of research is full of unexpected twists and turns, much like a well-thrown spiral.

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 Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from NFL and Energy Information Administration . You used data from 2001 to 2020

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]]
A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

[[ABSTRACT]]
The connection between NFL quarterback Drew Brees's passing attempts and the consumption of kerosene in Equatorial Guinea has been an enigma, sparking curiosity and the urge to explore this unlikely pairing. This research paper delves into the statistical relationship between these seemingly disparate entities, with an aim to shed light on this perplexing association.

Drawing upon data from the NFL and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 2001 to 2020. The results revealed a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, indicating a robust statistical connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.

The findings not only ignite further curiosity but also add a spark of intrigue into the world of sports and global energy consumption. As we unravel the threads of this unexpected connection, it becomes apparent that the whims of statistical correlation can lead to unexpected revelations, much like a quarterback's unexpected pass.

[[INTRODUCTION]]
As we embark on this scholarly exploration into the intersection of NFL passing prowess and the combustible world of kerosene consumption, it is essential to kindle the flames of curiosity and skepticism. For decades, researchers have been drawn to correlations that seem as improbable as a touchdown pass from the 50-yard line. The enigmatic bond between Drew Brees's passing attempts per NFL season and the utilization of kerosene in Equatorial Guinea is no exception, providing fodder for both statistical scrutiny and levity.
In the world of research, one must always keep a keen eye out for correlations that may seem to be a mere fluke, akin to a fumble recovered by a persistent running back. However, upon closer examination, these seemingly improbable connections may reveal a deeper, more profound truth. Dad joke alert: "I guess you could say we're looking to throw some light on this fiery correlation. Let's keep the puns burning, shall we?"
The burning question at the heart of this inquiry revolves around whether Drew Brees's passing attempts, a hallmark of his illustrious career, have any bearing on the consumption of kerosene in Equatorial Guinea, a nation located in the tropical climes of West Africa. The idea that an athlete's on-field performance could influence energy consumption may seem as incongruous as a quarterback wearing cleats on a basketball court, yet the data suggests otherwise.
With the statistical prowess of a seasoned defensive player, our research team has meticulously gathered and analyzed data from both the NFL and the Energy Information Administration, spanning a period of two decades. The resulting correlation coefficient of 0.8766386 and a p-value of less than 0.01 have elevated this seemingly whimsical connection to the realm of robust statistical significance. It seems that, much like a well-executed play, statistical correlation has the power to surprise even the most seasoned spectators.
The implications of these findings extend far beyond the realm of sports and energy consumption, offering a glimpse into the unpredictable nature of statistical relationships. As we unravel the threads of this unexpected correlation, it becomes evident that the world of research is rife with paradoxes and surprises, much like an onside kick in the final minutes of a game.

-------

Your response should start like this:

[[METHODOLOGY]]

ChatGPT:

[[METHODOLOGY]]

The methodology employed in this research endeavor sought to navigate the complex terrain of data collection and analysis, akin to a quarterback weaving through a densely packed defensive line. Drawing upon data from the National Football League (NFL) and the Energy Information Administration, our research team embarked on a multifaceted approach to illuminate the statistical relationship between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.

To begin, we scoured various online repositories and databases, much like a wide receiver scanning the field for an opening, to collect comprehensive and reliable data on Drew Brees's passing attempts across the span of 20 NFL seasons, from 2001 to 2020. With a meticulous attention to detail, we ensured that the data obtained was as accurate as a perfectly thrown spiral pass -- a feat not unlike seeking the elusive perfect PDO (Passing Data Objective) in the realm of NFL statistics.

Simultaneously, we delved into the labyrinthine troves of energy consumption data in Equatorial Guinea, seeking to capture the nuanced fluctuations in kerosene usage over the same temporal horizon. The data, akin to an astutely executed end-around play, was then meticulously organized and scrubbed to ensure its robustness and reliability in informing our statistical analyses.

Following the acquisition of these disparate yet intriguing datasets, we assembled them with the precision of a well-coached offensive line, aligning the corresponding temporal data points to discern any potential patterns or relationships between Drew Brees's passing attempts and kerosene consumption in Equatorial Guinea. The alignment process was not dissimilar to the intricate positioning of players on the field, where each move carries the potential to alter the course of the game.

Subsequently, employing advanced statistical techniques including correlation analysis, regression modeling, and time-series analysis, we meticulously scrutinized the amalgamated datasets to ascertain the presence and strength of any statistical relationship between the focal variables. The analyses, much like a carefully orchestrated playbook, were executed with an acute awareness of potential confounding variables and underlying assumptions, ensuring the robustness and validity of our findings.

Upon the completion of these multifaceted analyses, we were able to ascertain a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, underscoring the robust and statistically significant connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea. Such findings, akin to a surprising trick play that catches the defense off guard, not only demonstrate the statistical veracity of this unlikely relationship but also invite further inquiry and contemplation into the intricate interplay of seemingly disparate variables.

In conclusion, the methodological approach taken in this research endeavor, while replete with the intricacies of data collection and statistical analyses, has illuminated a compelling and unexpected correlation between Drew Brees's passing prowess and the consumption of kerosene in Equatorial Guinea, underscoring the profound and often enigmatic nature of statistical relationships.

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 Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

[[ABSTRACT]]
The connection between NFL quarterback Drew Brees's passing attempts and the consumption of kerosene in Equatorial Guinea has been an enigma, sparking curiosity and the urge to explore this unlikely pairing. This research paper delves into the statistical relationship between these seemingly disparate entities, with an aim to shed light on this perplexing association.

Drawing upon data from the NFL and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 2001 to 2020. The results revealed a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, indicating a robust statistical connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.

The findings not only ignite further curiosity but also add a spark of intrigue into the world of sports and global energy consumption. As we unravel the threads of this unexpected connection, it becomes apparent that the whims of statistical correlation can lead to unexpected revelations, much like a quarterback's unexpected pass.

[[LITERATURE REVIEW]]
To date, the scholarly literature on the connection between NFL quarterback performance and global energy consumption has been remarkably sparse. However, a few pioneering studies have delved into similarly unexpected correlations. Smith (2015) explored the intriguing link between free-throw percentage in professional basketball and the price of avocados in Mexico, laying the groundwork for our current inquiry. Doe and Jones (2018) examined the connection between baseball stolen bases and agricultural water usage in Mongolia, emphasizing the need for further exploration of seemingly unrelated phenomena. Dad joke alert: Why did the football team go to the bank? To get their quarterback!
Beyond these seminal works, our investigation draws inspiration from various non-fiction works that provide valuable insights into statistical oddities and unconventional correlations. In "Freakonomics" by Steven D. Levitt and Stephen J. Dubner, the authors explore the hidden side of everything, including unexpected linkages between disparate aspects of society. Similarly, "The Tipping Point" by Malcolm Gladwell sheds light on the sudden and unexpected changes that can result from seemingly unrelated events or behaviors. Dad joke alert: What do you call a retired QB? A has-bean!
Turning to the literary realm, several fiction works offer a whimsical perspective on unusual connections and improbable relationships. In "The Hitchhiker's Guide to the Galaxy" by Douglas Adams, the protagonist embarks on a journey through the cosmos, encountering bizarre coincidences and unexpected correlations along the way. "Cloud Atlas" by David Mitchell weaves together disparate storylines across time and space, reflecting the interconnectedness of seemingly unrelated events. Dad joke alert: How do football players stay cool? They stand near the fans!
Furthermore, recent social media posts have hinted at the potential link between sports performance and unexpected societal outcomes. A tweet from @SportsStatsGuru pondered whether NBA three-point shooting percentages could predict ice cream sales in Alaska, sparking lighthearted yet thought-provoking discussions. Another Reddit thread delved into the possibility of a connection between soccer goal differentials and global coffee consumption, generating playful speculation among online communities. Dad joke alert: Why are football stadiums so cool? Because they're full of fans!
In light of these diverse sources of inspiration and inquiry, our research aims to contribute to the growing body of literature exploring improbable correlations and the far-reaching implications of statistical relationships. As we unravel the connection between Drew Brees's passing attempts and kerosene consumption in Equatorial Guinea, we are reminded that the world of research is full of unexpected twists and turns, much like a well-thrown spiral.

[[RESULTS]]
The examination of the relationship between passing attempts by NFL quarterback Drew Brees per season and kerosene usage in Equatorial Guinea yielded a correlation coefficient of 0.8766386, indicating a strong positive association between the two variables. This robust correlation suggests that as Drew Brees's passing attempts increased, the consumption of kerosene in Equatorial Guinea also exhibited a notable rise. It seems that Brees's on-field endeavors may have set the stage for increased kerosene usage in Equatorial Guinea, igniting a fiery connection that defies conventional expectations.
Moreover, the coefficient of determination (r-squared) of 0.7684953 indicated that approximately 77% of the variability in kerosene consumption in Equatorial Guinea could be explained by the variation in Drew Brees's passing attempts per NFL season. This substantial proportion of variance explained underscores the strength of the relationship and reinforces the significance of the findings. It's as if Brees's passing attempts were shedding light on the kerosene consumption patterns in Equatorial Guinea, illuminating an unexpected nexus between sports and energy dynamics.
The p-value of less than 0.01 further solidifies the statistical significance of the observed correlation, signifying that the likelihood of the results occurring by chance is exceedingly slim. Indeed, the findings carry weight equivalent to a well-thrown pigskin, bolstering the argument for a genuine link between Drew Brees's passing prowess and the consumption of kerosene in Equatorial Guinea, a connection that continues to fuel both scholarly intrigue and quips galore.
The scatterplot (Fig. 1) visually illustrates the compelling correlation between passing attempts by Drew Brees per NFL season and kerosene usage in Equatorial Guinea, depicting a positively sloped regression line that serves as a tangible testament to the unexpected relationship unearthed by this investigation. The figure serves as a captivating visual representation of this fiery correlation, capturing the essence of an unlikely statistical connection that piques academic curiosity and draws parallels to a well-crafted touchdown pass – an unexpected and delightful play in the game of research.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The robust correlation coefficient of 0.8766386 between passing attempts by Drew Brees per NFL season and kerosene usage in Equatorial Guinea attests to the unexpected intertwining of these seemingly unrelated variables. This finding not only substantiates the pioneering work of Smith (2015) on unlikely correlations but also accentuates the need for further exploration of seemingly tangential connections in the realm of statistical relationships. As the flames of statistical analysis continue to kindle our curiosity, the connection between a quarterback's throws and Equatorial Guinea's kerosene consumption illuminates the uncharted territories of sports and global energy dynamics.

The substantial coefficient of determination (r-squared) of 0.7684953 further reinforces the strength of the relationship, elucidating that a substantial proportion of the variability in kerosene consumption in Equatorial Guinea can be elucidated by variations in Drew Brees's passing attempts per NFL season. It seems that Brees's athletic exploits not only captivate football enthusiasts but also ignite a spark in the energy dynamics of Equatorial Guinea, akin to a touchdown celebration that lights up the gridiron.

The p-value of less than 0.01 underscores the statistical significance of the observed correlation, emphasizing the unlikelihood of these results occurring by sheer happenstance. Indeed, the likelihood of this unexpected connection resulting from pure chance is as slim as a lineman's waistline in the off-season. The improbable bond between a quarterback's performance and a nation's energy consumption serves as a testament to the fascinating and often whimsical nature of statistical exploration, reminding us that, much like a well-timed field goal, research outcomes can yield unexpected and delightful surprises.

The visually compelling scatterplot (Fig. 1) elegantly encapsulates the positive correlation between passing attempts by Drew Brees per NFL season and kerosene usage in Equatorial Guinea, offering a tangible representation of this fiery statistical relationship. This vivid illustration serves as a touchdown pass of visual data, reigniting the flames of inquiry and encouraging further investigation into the uncharted territories of statistical relationships. As we delve deeper into the enigmatic connection between professional sports and global energy dynamics, we are reminded that the field of research is not merely a game of numbers but a captivating journey brimming with unexpected touchdowns and the occasional well-placed dad joke.

The unexpected nexus between Drew Brees's passing prowess and kerosene consumption in Equatorial Guinea not only adds a touch of whimsy to statistical analysis but also emphasizes the potential for serendipitous discoveries in the unlikeliest of places. As we revel in the delightful and unforeseen connection between quarterbacking and kerosene, we are reminded that the world of research is not unlike a game of football, complete with unexpected plays, captivating moments, and the occasional good-natured pun.

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 Passing attempts by Drew Brees per NFL season and Kerosene used in Equatorial Guinea. You can't resist a good dad joke. Add a relevant dad joke related to the content every couple of sentences. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

[[ABSTRACT]]
The connection between NFL quarterback Drew Brees's passing attempts and the consumption of kerosene in Equatorial Guinea has been an enigma, sparking curiosity and the urge to explore this unlikely pairing. This research paper delves into the statistical relationship between these seemingly disparate entities, with an aim to shed light on this perplexing association.

Drawing upon data from the NFL and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 2001 to 2020. The results revealed a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, indicating a robust statistical connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.

The findings not only ignite further curiosity but also add a spark of intrigue into the world of sports and global energy consumption. As we unravel the threads of this unexpected connection, it becomes apparent that the whims of statistical correlation can lead to unexpected revelations, much like a quarterback's unexpected pass.

[[INTRDUCTION]]
As we embark on this scholarly exploration into the intersection of NFL passing prowess and the combustible world of kerosene consumption, it is essential to kindle the flames of curiosity and skepticism. For decades, researchers have been drawn to correlations that seem as improbable as a touchdown pass from the 50-yard line. The enigmatic bond between Drew Brees's passing attempts per NFL season and the utilization of kerosene in Equatorial Guinea is no exception, providing fodder for both statistical scrutiny and levity.
In the world of research, one must always keep a keen eye out for correlations that may seem to be a mere fluke, akin to a fumble recovered by a persistent running back. However, upon closer examination, these seemingly improbable connections may reveal a deeper, more profound truth. Dad joke alert: "I guess you could say we're looking to throw some light on this fiery correlation. Let's keep the puns burning, shall we?"
The burning question at the heart of this inquiry revolves around whether Drew Brees's passing attempts, a hallmark of his illustrious career, have any bearing on the consumption of kerosene in Equatorial Guinea, a nation located in the tropical climes of West Africa. The idea that an athlete's on-field performance could influence energy consumption may seem as incongruous as a quarterback wearing cleats on a basketball court, yet the data suggests otherwise.
With the statistical prowess of a seasoned defensive player, our research team has meticulously gathered and analyzed data from both the NFL and the Energy Information Administration, spanning a period of two decades. The resulting correlation coefficient of 0.8766386 and a p-value of less than 0.01 have elevated this seemingly whimsical connection to the realm of robust statistical significance. It seems that, much like a well-executed play, statistical correlation has the power to surprise even the most seasoned spectators.
The implications of these findings extend far beyond the realm of sports and energy consumption, offering a glimpse into the unpredictable nature of statistical relationships. As we unravel the threads of this unexpected correlation, it becomes evident that the world of research is rife with paradoxes and surprises, much like an onside kick in the final minutes of a game.

[[RESULTS]]
The examination of the relationship between passing attempts by NFL quarterback Drew Brees per season and kerosene usage in Equatorial Guinea yielded a correlation coefficient of 0.8766386, indicating a strong positive association between the two variables. This robust correlation suggests that as Drew Brees's passing attempts increased, the consumption of kerosene in Equatorial Guinea also exhibited a notable rise. It seems that Brees's on-field endeavors may have set the stage for increased kerosene usage in Equatorial Guinea, igniting a fiery connection that defies conventional expectations.
Moreover, the coefficient of determination (r-squared) of 0.7684953 indicated that approximately 77% of the variability in kerosene consumption in Equatorial Guinea could be explained by the variation in Drew Brees's passing attempts per NFL season. This substantial proportion of variance explained underscores the strength of the relationship and reinforces the significance of the findings. It's as if Brees's passing attempts were shedding light on the kerosene consumption patterns in Equatorial Guinea, illuminating an unexpected nexus between sports and energy dynamics.
The p-value of less than 0.01 further solidifies the statistical significance of the observed correlation, signifying that the likelihood of the results occurring by chance is exceedingly slim. Indeed, the findings carry weight equivalent to a well-thrown pigskin, bolstering the argument for a genuine link between Drew Brees's passing prowess and the consumption of kerosene in Equatorial Guinea, a connection that continues to fuel both scholarly intrigue and quips galore.
The scatterplot (Fig. 1) visually illustrates the compelling correlation between passing attempts by Drew Brees per NFL season and kerosene usage in Equatorial Guinea, depicting a positively sloped regression line that serves as a tangible testament to the unexpected relationship unearthed by this investigation. The figure serves as a captivating visual representation of this fiery correlation, capturing the essence of an unlikely statistical connection that piques academic curiosity and draws parallels to a well-crafted touchdown pass – an unexpected and delightful play in the game of research.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In conclusion, our research has illuminated a fiery connection between Drew Brees's passing attempts and the kerosene quandary in Equatorial Guinea, shedding light on an unexpected and statistically robust correlation. It appears that Brees's quarterback prowess has not only impacted the NFL field but has also exerted a notable influence on the consumption of kerosene in Equatorial Guinea, igniting a relationship that defies conventional expectations and adds a spark of intrigue to the world of sports and energy dynamics.

This unexpected correlation can be likened to a well-timed touchdown pass – surprising, delightful, and certainly worthy of further exploration. As we contemplate the implications of these findings, it becomes increasingly clear that statistical relationships, much like a perfectly executed play, can defy conventional wisdom and lead to unexpected revelations. Dad joke alert: "It seems Drew Brees is not only passing footballs but also passing statistical significance tests with flying colors!"

Given the robust correlation coefficient and the substantial proportion of variance explained, this connection between Brees's passing attempts and kerosene consumption in Equatorial Guinea stands as a significant stride in unraveling the complex tapestry of statistical relationships. It's as if Drew Brees's performance on the field were casting light on the energy consumption patterns in Equatorial Guinea, illuminating a nexus that continues to fuel scholarly intrigue and pun-filled discussions.

Importantly, no more research is needed in this area. This paper can stand as the touchstone for all future enthusiasts seeking to uncover unlikely connections between the world of sports and the wider global arena.

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 A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Quirky Athlete Analyses

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 A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Esoteric Ethnophysics 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 A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea with an abstract of The connection between NFL quarterback Drew Brees's passing attempts and the consumption of kerosene in Equatorial Guinea has been an enigma, sparking curiosity and the urge to explore this unlikely pairing. This research paper delves into the statistical relationship between these seemingly disparate entities, with an aim to shed light on this perplexing association.
Drawing upon data from the NFL and the Energy Information Administration, our research team conducted a rigorous analysis spanning the years 2001 to 2020. The results revealed a striking correlation coefficient of 0.8766386 and a p-value of less than 0.01, indicating a robust statistical connection between Drew Brees's passing attempts per NFL season and the consumption of kerosene in Equatorial Guinea.
The findings not only ignite further curiosity but also add a spark of intrigue into the world of sports and global energy consumption. As we unravel the threads of this unexpected connection, it becomes apparent that the whims of statistical correlation can lead to unexpected revelations, much like a quarterback's unexpected pass.

ChatGPT:

Drew Brees passing attempts, Equatorial Guinea, kerosene consumption, statistical relationship, NFL data, Energy Information Administration, correlation coefficient, p-value, global energy consumption, statistical correlation, sports research, unexpected revelations

*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

Passing attempts by Drew Brees per NFL season
Source: NFL
See what else correlates with Passing attempts by Drew Brees per NFL season

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

Correlation r = 0.8766386 (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 = 0.7684953 (Coefficient of determination)
This means 76.8% of the change in the one variable (i.e., Kerosene used in Equatorial Guinea) is predictable based on the change in the other (i.e., Passing attempts by Drew Brees per NFL season) over the 20 years from 2001 through 2020.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.0E-7.^Show 0.0000003982528094732807000000
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 0.88 in 4.0E-5% of random cases. Said differently, if you correlated 2,510,968 random variables^Note You don't actually need 2 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 19 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 19 because we have two variables measured over a period of 20 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.

[ 0.71, 0.95 ] 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.

	2001	2002	2003	2004	2005	2006	2007	2008	2009	2010	2011	2012	2013	2014	2015	2016	2017	2018	2019	2020
Passing attempts by Drew Brees per NFL season (Pasing attempts)	27	526	356	400	500	554	652	635	514	658	657	670	650	659	627	673	536	489	378	390
Kerosene used in Equatorial Guinea (Million Barrels/Day)	0.195534	0.434521	0.391068	0.391068	0.391068	0.434521	0.434521	0.434521	0.434521	0.434521	0.434521	0.434521	0.434521	0.434521	0.434521	0.477973	0.391068	0.347616	0.260712	0.282438

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.
Y-axis doesn't start at zero: I truncated the Y-axes of the graph above. I also used a line graph, which makes the visual connection stand out more than it deserves. ^Note Nothing against line graphs. They are great at telling a story when you have linear data! But visually it is deceptive because the only data is at the points on the graph, not the lines on the graph. In between each point, the data could have been doing anything. Like going for a random walk by itself!
Mathematically what I showed is true, but it is intentionally misleading. Below is the same chart but with both Y-axes starting at zero.

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([27,526,356,400,500,554,652,635,514,658,657,670,650,659,627,673,536,489,378,390,])
array_2 = np.array([0.195534,0.434521,0.391068,0.391068,0.391068,0.434521,0.434521,0.434521,0.434521,0.434521,0.434521,0.434521,0.434521,0.434521,0.434521,0.477973,0.391068,0.347616,0.260712,0.282438,])
array_1_name = "Passing attempts by Drew Brees per NFL season"
array_2_name = "Kerosene used in Equatorial Guinea"

# 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 Passing attempts by Drew Brees per NFL season
Line chart for only Kerosene used in Equatorial Guinea
AI-generated correlation image
The spurious research paper: A Flaming Connection: Drew Brees's Passing Attempts and the Kerosene Quandary in Equatorial Guinea

View another random correlation

How fun was this correlation?

Thanks for being the explorer we needed!

Correlation ID: 1460 · Black Variable ID: 207 · Red Variable ID: 24385


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