Spurious correlation #2,175 · View random
A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is NCAA Men's Lacrosse Div I Championship final point differential and the second variable is Kerosene used in Czechia. The chart goes from 1993 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 NCAA Men's Lacrosse Div I Championship final point differential and the second variable is Kerosene used in Czechia. The chart goes from 1993 to 2022, and the two variables track closely in value over that time.

Download png, svg

AI explanation

As the final point differentials in the NCAA Men's Lacrosse Div I Championship increased, players' competitive spirits soared to new heights. This led to a spike in post-game celebrations, with teams igniting larger and larger victory bonfires. As the flames of success raged on, demand for kerosene in Czechia skyrocketed, fueling not only the championship fervor, but also the local economy. It seems like these lacrosse players really know how to *spark* a fiery trend, turning the sport into a flaming beacon for the kerosene industry in Czechia!

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image representing a Discovery magazine cover with a focus on the NCAA Men's Lacrosse Div I Championship final in a Czechia stadium. The winning team jubilantly celebrates as the scoreboard displays a 4-point difference. In the background, a plane takes off from a nearby airport, leaving a distinct trail of kerosene behind it. The setting should be vibrant and dynamic, showcasing the excitement of the championship game and the impressive surroundings. 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: NCAA Men's Lacrosse Div I Championship final point differential and Kerosene used in Czechia. 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 Discovery magazine cover image Concept art Concept art Cybernetic art Psychedelic
ChatGPT: A Discovery 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 NCAA Men's Lacrosse Div I Championship final point differential and Kerosene used in Czechia together. Keep the description simple.
ChatGPT: In a stadium in Czechia, the NCAA Men's Lacrosse Div I Championship final is in full swing. The scoreboard shows a final point differential of 4 as the winning team celebrates. In the distance, a plane takes off from the nearby airport, leaving a trail of kerosene behind it.

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 Discovery magazine cover image ] and depicting this scene: In a stadium in Czechia, the NCAA Men's Lacrosse Div I Championship final is in full swing. The scoreboard shows a final point differential of 4 as the winning team celebrates. In the distance, a plane takes off from the nearby airport, leaving a trail of kerosene behind it. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image representing a Discovery magazine cover with a focus on the NCAA Men's Lacrosse Div I Championship final in a Czechia stadium. The winning team jubilantly celebrates as the scoreboard displays a 4-point difference. In the background, a plane takes off from a nearby airport, leaving a distinct trail of kerosene behind it. The setting should be vibrant and dynamic, showcasing the excitement of the championship game and the impressive surroundings.

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.
^{Show prompt for explanation} Model: gpt-3.5-turbo-1106 (fine-tuned)
System prompt: You provide humorous responses in the form of plausible sounding explanations for correlations. You assume the correlation is causative for the purpose of the explanation even if it is ridiculous. You do not chat with the user, you only reply with the causal connection explanation and nothing else.
User prompt: Please make up a funny explanation for how increases in NCAA Men's Lacrosse Div I Championship final point differential positively influenced Kerosene used in Czechia. Include one good pun.

AI academic paper

(Because p < 0.01)

Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia

Journal of Sports Science and Unlikely Correlations

Jan 2024

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

^{Show prompt used to generate this paper} Quick note: This sequence is long and repetitive. That's how the prompt engineering works for this one. I manage the output in Python to format it into this PDF.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft a literature review section of an academic research paper, that starts out dry for the first few sentences but then becomes hilarious and goofy.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a literature review section of an academic research paper presenting the findings of the connection between NCAA Men's Lacrosse Div I Championship final point differential and Kerosene used in Czechia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name some cartoons and childrens' shows that you watched that are related to the topic.

Here is the title and abstract of the paper:
[[TITLE]]
Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia

[[ABSTRACT]]
In this paper, we delve into the unlikely and, some might say, absurd relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the picturesque country of Czechia. While one might initially dismiss these two variables as being entirely unrelated, our rigorous analysis has uncovered a surprising correlation that cannot be easily explained away. Utilizing data from the NCAA and the Energy Information Administration, we meticulously scrutinized the association between these seemingly disparate factors from 1993 to 2022, revealing a correlation coefficient of 0.5362108 with a statistically significant p-value of less than 0.01.

As we unravel the enigmatic connection between the intensity of lacrosse matches and the utilization of kerosene in Czechia, we invite readers to suspend disbelief and embark on a scholarly journey filled with unexpected findings, humorously peculiar observations, and perhaps the occasional well-placed pun.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
The world of academic research often leads us down unexpected and, at times, downright bizarre paths. In this vein, our study aims to shed light on the peculiar relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the enchanting land of Czechia. While these may seem to be disparate variables as starkly different as night and day, we've plunged headfirst into the data to unravel the mysteries that lie beneath the surface.
Now, one might wonder, why on earth would anyone even think to explore the connection between a thrilling lacrosse showdown and the fuel consumption trends in a central European country? Well, dear reader, let us reassure you that this seemingly incongruous pairing is not the result of a researcher's late-night caffeine overdose but rather the product of an inquisitive mind determined to unearth the unexpected and peculiar.
As we embark on this academic escapade, it is essential to acknowledge the inherent skepticism that arises when juxtaposing such dissimilar variables. However, it is precisely in the face of skepticism that the seeds of remarkable discovery often lie. We invite you to join us on this intellectual rollercoaster, brimming with statistical analyses, data visualizations, and, dare we say, a sprinkle of statistical magic. And who knows, by the end of this paper, you might find yourself smiling at the unlikely connections that the world of research and statistics has to offer.

-------

Your response should start like this:

[[LITERATURE REVIEW]]

ChatGPT:
[[LITERATURE REVIEW]]

Our investigation into the seemingly incongruous relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in Czechia has led us to a myriad of engaging studies and literary works that offer intriguing insights into this quirky pairing. While this inquiry may appear to be an exercise in futility, we assure the reader that the pursuit of knowledge often takes us down paths less traveled, where unexpected connections and delightful surprises await.

In "The Statistical Connection Between Unlikely Variables," Smith et al. provide a comprehensive overview of the peculiar correlations that can be unearthed through rigorous data analysis. While their focus remains largely on more conventional pairings, such as ice cream consumption and crime rates, their work serves as a testament to the captivating nature of statistical exploration.

Doe and Jones, in their seminal work "Unraveling Unlikely Associations," push the boundaries of traditional research by delving into the unlikeliest of connections. Their exploration of the correlation between avocado toast consumption and polar bear populations challenges readers to embrace the whimsical side of statistical inquiry.

Realizing that even the most unexpected connections can yield valuable insights, we turned our attention to literature that might shed light on the enigmatic bond between lacrosse point differentials and kerosene usage. "The Economics of Energy Consumption in Central Europe," by Lorem, provides a compelling analysis of energy trends in the region, offering a lens through which we can begin to understand the role of kerosene in Czechia's societal tapestry.

In a departure from the traditional, we instinctively turned to the world of fiction for inspiration, uncovering narratives that, while not overtly related to our research, sparked moments of imaginative connection. "The Lacrosse Diaries" by Ipsum offers a rollicking tale of triumph and defeat on the lacrosse field, weaving a narrative that speaks to the indomitable spirit of athletic competition.

Furthermore, "Kerosene Chronicles" by Ipsum draws readers into a world where the humble fuel takes center stage, prompting us to ponder the ways in which seemingly mundane substances can hold unforeseen significance in the grand scheme of things.

Shifting gears with a touch of levity and childhood nostalgia, our journey through the annals of pop culture led us to unearth unexpected parallels in cartoons and children's shows. The animated series "Lacrosse Legends" and "Kerosene Capers" provided glimpses into the worlds of sport and energy, serving as delightful reminders that the unlikeliest of pairings can captivate our imagination and spark newfound curiosity.

As we pave the way for our study's findings, we invite readers to embrace the unconventional, to see beyond the surface and to revel in the tantalizing prospect that even the most unlikely pairings may hold truths waiting to be discovered.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the discussion section of an academic research paper presenting the findings of the connection between NCAA Men's Lacrosse Div I Championship final point differential and Kerosene used in Czechia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia

[[ABSTRACT]]
In this paper, we delve into the unlikely and, some might say, absurd relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the picturesque country of Czechia. While one might initially dismiss these two variables as being entirely unrelated, our rigorous analysis has uncovered a surprising correlation that cannot be easily explained away. Utilizing data from the NCAA and the Energy Information Administration, we meticulously scrutinized the association between these seemingly disparate factors from 1993 to 2022, revealing a correlation coefficient of 0.5362108 with a statistically significant p-value of less than 0.01.

As we unravel the enigmatic connection between the intensity of lacrosse matches and the utilization of kerosene in Czechia, we invite readers to suspend disbelief and embark on a scholarly journey filled with unexpected findings, humorously peculiar observations, and perhaps the occasional well-placed pun.

[[LITERATURE REVIEW]]
Our investigation into the seemingly incongruous relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in Czechia has led us to a myriad of engaging studies and literary works that offer intriguing insights into this quirky pairing. While this inquiry may appear to be an exercise in futility, we assure the reader that the pursuit of knowledge often takes us down paths less traveled, where unexpected connections and delightful surprises await.
In "The Statistical Connection Between Unlikely Variables," Smith et al. provide a comprehensive overview of the peculiar correlations that can be unearthed through rigorous data analysis. While their focus remains largely on more conventional pairings, such as ice cream consumption and crime rates, their work serves as a testament to the captivating nature of statistical exploration.
Doe and Jones, in their seminal work "Unraveling Unlikely Associations," push the boundaries of traditional research by delving into the unlikeliest of connections. Their exploration of the correlation between avocado toast consumption and polar bear populations challenges readers to embrace the whimsical side of statistical inquiry.
Realizing that even the most unexpected connections can yield valuable insights, we turned our attention to literature that might shed light on the enigmatic bond between lacrosse point differentials and kerosene usage. "The Economics of Energy Consumption in Central Europe," by Lorem, provides a compelling analysis of energy trends in the region, offering a lens through which we can begin to understand the role of kerosene in Czechia's societal tapestry.
In a departure from the traditional, we instinctively turned to the world of fiction for inspiration, uncovering narratives that, while not overtly related to our research, sparked moments of imaginative connection. "The Lacrosse Diaries" by Ipsum offers a rollicking tale of triumph and defeat on the lacrosse field, weaving a narrative that speaks to the indomitable spirit of athletic competition.
Furthermore, "Kerosene Chronicles" by Ipsum draws readers into a world where the humble fuel takes center stage, prompting us to ponder the ways in which seemingly mundane substances can hold unforeseen significance in the grand scheme of things.
Shifting gears with a touch of levity and childhood nostalgia, our journey through the annals of pop culture led us to unearth unexpected parallels in cartoons and children's shows. The animated series "Lacrosse Legends" and "Kerosene Capers" provided glimpses into the worlds of sport and energy, serving as delightful reminders that the unlikeliest of pairings can captivate our imagination and spark newfound curiosity.
As we pave the way for our study's findings, we invite readers to embrace the unconventional, to see beyond the surface and to revel in the tantalizing prospect that even the most unlikely pairings may hold truths waiting to be discovered.

[[RESULTS]]
The moment of truth has arrived as we reveal the results of our investigation into the perplexing correlation between the NCAA Men's Lacrosse Division I Championship final point differentials and kerosene consumption in Czechia. After meticulously sifting through the data from 1993 to 2022, we unveiled a correlation coefficient of 0.5362108, an r-squared value of 0.2875220, and a p-value of less than 0.01. Yes, you read that right – statistically significant results that have left us both astounded and, dare we say, amused.
The relationship between the heart-racing battles on the lacrosse field and the consumption of kerosene in Czechia may seem as improbable as finding a unicorn in a statistical analysis, yet here we are, staring at a scatterplot that paints a compelling picture of this unexpected association. (*Fig. 1 sneaks in - look at that correlation!*)
Our findings not only underscore the serendipitous nature of scientific inquiry but also serve as a testament to the idea that even the most unlikely pairings can yield intriguing results. The r-squared value of 0.2875220 suggests that approximately 28.75% of the variation in kerosene consumption in Czechia can be explained by the final point differentials of the NCAA Men's Lacrosse Division I Championship. While we anticipated making progress, we weren't quite prepared to uncover such a sizable portion of the puzzle.
The statistically significant p-value further bolsters the robustness of our findings, providing confidence that the relationship we've unearthed is not merely a chance occurrence akin to finding a four-leaf clover in a statistics textbook. It's an authentic, legitimate connection that beckons for further exploration, curiosity, and yes, perhaps a bit of whimsy.
In conclusion, our results stand as a testament to the wonders and surprises that lurk within the realms of statistical analyses and academic pursuits. The correlated nature of NCAA Men's Lacrosse final point differentials and kerosene consumption in Czechia may forever remain an enigmatic enigma, but one thing is certain – this peculiar pairing has given us all a good laugh and a newfound appreciation for the idiosyncrasies of the scholarly world.

-------

Your response should start like this:

[[DISCUSSION]]

ChatGPT:

[[DISCUSSION]]

The findings of our investigation have not only left us rubbing our eyes in disbelief but have also ignited a spark of curiosity that resonates with the whimsical nature of scientific exploration. The correlation coefficient of 0.5362108 and the statistically significant p-value of less than 0.01 accentuate the unexpected harmony between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in Czechia, affirming the unanticipated yet robust bond we uncovered.

Our journey through the landscape of prior research, where we encountered the statistical adventures of Smith et al. and the audacious exploration by Doe and Jones, has allowed us to appreciate the unbounded potential for delightfully peculiar correlations. Just as avocado toast consumption and polar bear populations managed to find common ground in their entangled statistical dance, the link between lacrosse fervor and kerosene consumption in the heart of Europe has emerged as a synergy that defies traditional expectations. Our results align with previous efforts that have embraced the unexpected, transcending the confines of conventional pairings to unveil captivating associations that mirror the enigmatic kinship we have brought to light.

Amidst the earnest pursuit of scientific discovery, our study has embraced the unorthodox, tracing a path that meanders through the realms of fiction, childhood whimsy, and the quirky storytelling of pop culture. The narrative tapestry of "The Lacrosse Diaries" and "Kerosene Chronicles" serves as a testament to the boundless potential for unlikely relationships to captivate our imagination, igniting sparks of wonder that transcend the conventional boundaries of scholarly inquiry.

The substantial r-squared value of 0.2875220 speaks to the meaningful extent to which lacrosse final point differentials intertwine with the consumption of kerosene in Czechia, offering a nuanced understanding of the captivating interplay between these seemingly disparate variables. While we tread on the grounds where statistical significance and scientific rigor hold sway, our foray into the unexpected serves as a poignant reminder that the charm of scholarly investigation often lies in the unanticipated, the delightful, and yes, the downright quirky.

As we unfurl the tapestry of our findings and invite fellow scholars to ponder the peculiar resonance between lacrosse triumphs and kerosene reliance, we herald the incalculable joy that can be gleaned from unearthing unexpected connections in the often sobering realm of statistical analysis and scientific inquiry. With our findings as an anchor, we beckon readers to join us in celebrating the lighthearted allure of scholarly exploration, where even the unlikeliest of pairings can breathe new life into the fabric of knowledge and elicit a chuckle or two along the way.

Model: gpt-3.5-turbo-1106
System prompt: You are a goofy academic researcher writing an academic paper. You follow the rules, but you throw out convention regularly to make jokes and funny asides.You draft the discussion section of goofy academic research papers that sounds like it belongs based on the title and abstract provided.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up a short conclusion of an academic research paper presenting the findings of the connection between NCAA Men's Lacrosse Div I Championship final point differential and Kerosene used in Czechia. Make it seem dry like academic research paper, but with lots of subtle hidden offhand remarks, jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia

[[ABSTRACT]]
In this paper, we delve into the unlikely and, some might say, absurd relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the picturesque country of Czechia. While one might initially dismiss these two variables as being entirely unrelated, our rigorous analysis has uncovered a surprising correlation that cannot be easily explained away. Utilizing data from the NCAA and the Energy Information Administration, we meticulously scrutinized the association between these seemingly disparate factors from 1993 to 2022, revealing a correlation coefficient of 0.5362108 with a statistically significant p-value of less than 0.01.

As we unravel the enigmatic connection between the intensity of lacrosse matches and the utilization of kerosene in Czechia, we invite readers to suspend disbelief and embark on a scholarly journey filled with unexpected findings, humorously peculiar observations, and perhaps the occasional well-placed pun.

[[INTRDUCTION]]
The world of academic research often leads us down unexpected and, at times, downright bizarre paths. In this vein, our study aims to shed light on the peculiar relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the enchanting land of Czechia. While these may seem to be disparate variables as starkly different as night and day, we've plunged headfirst into the data to unravel the mysteries that lie beneath the surface.
Now, one might wonder, why on earth would anyone even think to explore the connection between a thrilling lacrosse showdown and the fuel consumption trends in a central European country? Well, dear reader, let us reassure you that this seemingly incongruous pairing is not the result of a researcher's late-night caffeine overdose but rather the product of an inquisitive mind determined to unearth the unexpected and peculiar.
As we embark on this academic escapade, it is essential to acknowledge the inherent skepticism that arises when juxtaposing such dissimilar variables. However, it is precisely in the face of skepticism that the seeds of remarkable discovery often lie. We invite you to join us on this intellectual rollercoaster, brimming with statistical analyses, data visualizations, and, dare we say, a sprinkle of statistical magic. And who knows, by the end of this paper, you might find yourself smiling at the unlikely connections that the world of research and statistics has to offer.

[[RESULTS]]
The moment of truth has arrived as we reveal the results of our investigation into the perplexing correlation between the NCAA Men's Lacrosse Division I Championship final point differentials and kerosene consumption in Czechia. After meticulously sifting through the data from 1993 to 2022, we unveiled a correlation coefficient of 0.5362108, an r-squared value of 0.2875220, and a p-value of less than 0.01. Yes, you read that right – statistically significant results that have left us both astounded and, dare we say, amused.
The relationship between the heart-racing battles on the lacrosse field and the consumption of kerosene in Czechia may seem as improbable as finding a unicorn in a statistical analysis, yet here we are, staring at a scatterplot that paints a compelling picture of this unexpected association. (*Fig. 1 sneaks in - look at that correlation!*)
Our findings not only underscore the serendipitous nature of scientific inquiry but also serve as a testament to the idea that even the most unlikely pairings can yield intriguing results. The r-squared value of 0.2875220 suggests that approximately 28.75% of the variation in kerosene consumption in Czechia can be explained by the final point differentials of the NCAA Men's Lacrosse Division I Championship. While we anticipated making progress, we weren't quite prepared to uncover such a sizable portion of the puzzle.
The statistically significant p-value further bolsters the robustness of our findings, providing confidence that the relationship we've unearthed is not merely a chance occurrence akin to finding a four-leaf clover in a statistics textbook. It's an authentic, legitimate connection that beckons for further exploration, curiosity, and yes, perhaps a bit of whimsy.
In conclusion, our results stand as a testament to the wonders and surprises that lurk within the realms of statistical analyses and academic pursuits. The correlated nature of NCAA Men's Lacrosse final point differentials and kerosene consumption in Czechia may forever remain an enigmatic enigma, but one thing is certain – this peculiar pairing has given us all a good laugh and a newfound appreciation for the idiosyncrasies of the scholarly world.

-------

Your response should start like this:

[[CONCLUSION]]

ChatGPT:

[[CONCLUSION]]

In investigating the uncanny correlation between the NCAA Men's Lacrosse Division I Championship final point differentials and kerosene consumption in Czechia, our research has delved into an unexpected realm where statistical analyses and sports collide. As we wrap up this scholarly endeavor, it's safe to say that we've uncovered a correlation that is as surprising as finding a needle in a haystack – or in our case, finding the correlation coefficient of 0.5362108 amidst the data haystack.

Our findings have left us both fascinated and amused, akin to stumbling upon a statistical Easter egg, if you will. The r-squared value of 0.2875220, while not quite reaching the heights of a perfect correlation, still represents a substantial portion of the mystery unraveled. It's like finding the missing piece of a complicated statistical jigsaw puzzle and realizing it's been right under your nose, much like those elusive car keys we all spend countless minutes searching for.

The statistically significant p-value of less than 0.01 adds an air of credibility to our discovery, emphasizing that this connection is no statistical mirage. It's as real as the data points on our scatterplot, standing as a testament to the unexpected and the delightful quirks of scientific inquiry.

As we bid adieu to this odyssey of statistical exploration and lacrosse-related pondering, we acknowledge that while our findings may leave some scratching their heads, it's precisely these unexpected connections that remind us of the whimsical nature of research. So, grab that statistical wand and wave it in celebration of the enigmatic bond between the intensity of lacrosse and the allure of kerosene consumption in Czechia.

In closing, we assert that further research in this area is as unnecessary as a third nostril – for, my dear colleagues, when it comes to the fantastical marriage of lacrosse finals and kerosene consumption, we've already uncovered more than enough statistical magic. Cheers to the unexpected, the perplexing, and the downright amusing nature of academic discovery!

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 Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia. Respond only with the name of a fictional academic journal.

ChatGPT:

Journal of Sports Science and Unlikely Correlations

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 Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia. Respond only with the name of a fictional organization.

ChatGPT:

The Institute for Interdisciplinary Kerosene Studies

Model: gpt-3.5-turbo-1106
System prompt: You provide potential search keywords separated by commas. You say nothing else, and you do not chat with the user.
User prompt: Please provide potential search keywords for a paper titled Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia with an abstract of In this paper, we delve into the unlikely and, some might say, absurd relationship between the final point differentials of the NCAA Men's Lacrosse Division I Championship and the consumption of kerosene in the picturesque country of Czechia. While one might initially dismiss these two variables as being entirely unrelated, our rigorous analysis has uncovered a surprising correlation that cannot be easily explained away. Utilizing data from the NCAA and the Energy Information Administration, we meticulously scrutinized the association between these seemingly disparate factors from 1993 to 2022, revealing a correlation coefficient of 0.5362108 with a statistically significant p-value of less than 0.01.
As we unravel the enigmatic connection between the intensity of lacrosse matches and the utilization of kerosene in Czechia, we invite readers to suspend disbelief and embark on a scholarly journey filled with unexpected findings, humorously peculiar observations, and perhaps the occasional well-placed pun.

ChatGPT:

NCAA Men's Lacrosse, Division I Championship, point differential, kerosene consumption, Czechia, correlation, statistical analysis, unusual relationship, NCAA data, Energy Information Administration, lacrosse match intensity

*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

NCAA Men's Lacrosse Div I Championship final point differential
Source: NCAA
See what else correlates with NCAA Men's Lacrosse Div I Championship final point differential

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

Correlation r = 0.5362108 (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 = 0.2875220 (Coefficient of determination)
This means 28.8% of the change in the one variable (i.e., Kerosene used in Czechia) is predictable based on the change in the other (i.e., NCAA Men's Lacrosse Div I Championship final point differential) over the 30 years from 1993 through 2022.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 0.0023.^Show 0.0022555675282903047000000000
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 0.54 in 0.23% of random cases. Said differently, if you correlated 443 random variables^Note Which I absolutely did.
with the same 29 degrees of freedom, ^Note Degrees of freedom is a measure of how many free components we are testing. In this case it is 29 because we have two variables measured over a period of 30 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.

[ 0.22, 0.75 ] 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.

	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
NCAA Men's Lacrosse Div I Championship final point differential (Points)	1	1	4	1	12	10	2	6	1	1	2	1	1	8	1	3	1	1	2	6	6	2	5	1	3	2	4	0	1	2
Kerosene used in Czechia (Million Barrels/Day)	0.09863	0.09863	0.032877	0.262295	0.591781	0.723288	0.265403	0.120219	0.311688	0.266667	0.266667	0.263736	0.258065	0.264901	0.264901	0.263158	0.076712	0.258065	0.269663	0.263736	0.262295	0.266667	0.076712	0.262295	0.262295	0.262295	0.262295	0.262295	0.258065	0.258065

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([1,1,4,1,12,10,2,6,1,1,2,1,1,8,1,3,1,1,2,6,6,2,5,1,3,2,4,0,1,2,])
array_2 = np.array([0.09863,0.09863,0.032877,0.262295,0.591781,0.723288,0.265403,0.120219,0.311688,0.266667,0.266667,0.263736,0.258065,0.264901,0.264901,0.263158,0.076712,0.258065,0.269663,0.263736,0.262295,0.266667,0.076712,0.262295,0.262295,0.262295,0.262295,0.262295,0.258065,0.258065,])
array_1_name = "NCAA Men's Lacrosse Div I Championship final point differential"
array_2_name = "Kerosene used in Czechia"

# 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 NCAA Men's Lacrosse Div I Championship final point differential
Line chart for only Kerosene used in Czechia
AI-generated correlation image
The spurious research paper: Kerosene Kouzelný: Connecting NCAA Men's Lacrosse Div I Championship Final Point Differential and Kerosene Consumption in Czechia

View another random correlation

How fun was this correlation?

Your rating is pure awesomeness!

Correlation ID: 2175 · Black Variable ID: 129 · Red Variable ID: 24346


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