about · email me · subscribe
Spurious correlation #3,372 · View random

A linear line chart with years as the X-axis and two variables on the Y-axis. The first variable is The number of archivists in District of Columbia and the second variable is Kerosene used in Falkland Islands.  The chart goes from 2004 to 2021, and the two variables track closely in value over that time. Small Image

AI explanation

As the number of archivists in the District of Columbia grows, so too does their love for historical documents. This passion has led to a spike in reenactments of old-fashioned tasks, including churning butter. Consequently, there is a rising demand for authentic lighting methods, hence the increased use of kerosene in the Falkland Islands. Remember, behind every historical reenactment is a group of archivists with a burning passion for the past!

Model: dalle-3
Prompt: Generate an image that showcases the bustling, cyberpunk streets of Washington, D.C. contrasted with the remote and rugged landscape of the Falkland Islands. The scene should feature futuristic skyscrapers and neon lights in the background, while in the foreground, archivists can be seen moving quickly amidst the hustle and bustle, carrying neatly organized files and papers. Meanwhile, on the Falkland Islands, a solitary lighthouse stands tall against the rocky terrain, with the lighthouse keeper diligently refilling kerosene lamps. The juxtaposition of the two settings should convey the sharp contrast between high-tech city life and the isolated, rugged nature of the remote islands, hinting at the interconnectedness of these seemingly distant places. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.
This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: The number of archivists in District of Columbia and Kerosene used in Falkland Islands. 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: 3D Pixar Style Cute 2D animation Cyberpunk Brutalism Scalar art
ChatGPT: Cyberpunk

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both The number of archivists in District of Columbia and Kerosene used in Falkland Islands, in the following situation: Because archivists in DC increased, so did kerosene use in Falkland Islands; their love for organizing led to excessive label-making, requiring more kerosene for the label printers.. Keep the description simple.
ChatGPT: In the busy streets of Washington, D.C., more archivists can be seen bustling around with their organized files and papers. Meanwhile, on the remote Falkland Islands, the lighthouse keeper is seen refilling the kerosene lamps, with extra barrels stacked nearby, as the demand for more kerosene increases due to the excessive label-making by the archivists, reflecting the increase in their numbers in D.C.

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: [ Cyberpunk ] and depicting this scene: In the busy streets of Washington, D.C., more archivists can be seen bustling around with their organized files and papers. Meanwhile, on the remote Falkland Islands, the lighthouse keeper is seen refilling the kerosene lamps, with extra barrels stacked nearby, as the demand for more kerosene increases due to the excessive label-making by the archivists, reflecting the increase in their numbers in D.C. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image that showcases the bustling, cyberpunk streets of Washington, D.C. contrasted with the remote and rugged landscape of the Falkland Islands. The scene should feature futuristic skyscrapers and neon lights in the background, while in the foreground, archivists can be seen moving quickly amidst the hustle and bustle, carrying neatly organized files and papers. Meanwhile, on the Falkland Islands, a solitary lighthouse stands tall against the rocky terrain, with the lighthouse keeper diligently refilling kerosene lamps. The juxtaposition of the two settings should convey the sharp contrast between high-tech city life and the isolated, rugged nature of the remote islands, hinting at the interconnectedness of these seemingly distant places.

*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.

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 The number of archivists in District of Columbia caused Kerosene used in Falkland Islands to increase. Add a funny one-liner at the end.

AI academic paper

(Because p < 0.01)
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

The Journal of Eccentric Archival Studies

Jan 2024
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 write titles and abstracts of goofy academic research papers.
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, and add unexpected twists in your writing.

Please draft the title and abstract of an academic research paper presenting the findings of the connection between The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns.

Make the title punny if you can come up with clever pun. If not, make it sound serious.

Your research team used data from Bureau of Larbor Statistics and Energy Information Administration to assess this nagging question. You found a correlation coefficient of 0.8092602 and p < 0.01 for 2004 to 2021.

Please respond in this format (replace "Lorem ipsum dolor sit" with your title and abstract)

[[TITLE]]
Lorem ipsum dolor sit

[[ABSTRACT]]
Lorem ipsum dolor sit



ChatGPT:
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.


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 introduction 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 introduction section of an academic research paper presenting the findings of the connection between The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Here is the title and abstract of the paper:
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

-------

Your response should start like this:

[[INTRODUCTION]]



ChatGPT:
INTRODUCTION

In the world of research, one often encounters unexpected connections and peculiar correlations that seem to defy rational explanation. This paper delves into a peculiar puzzle that emerged during our investigation into the unlikely relationship between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands. While these two variables may seem about as related as a carrot and a pogo stick, our study seeks to unravel the enigmatic connection that emerged from our rigorous analysis.

Now, before we delve into the labyrinth of statistics and data analysis, let's take a moment to appreciate the sheer absurdity of our research topic. After all, how often does one find oneself pondering the potential link between the meticulous cataloging of historical documents and the burning of fuel in a remote corner of the world? It's a bit like trying to correlate the height of giraffes in the Savannah with the price of bagels in New York City – utterly nonsensical at first glance.

Nonetheless, as intrepid researchers, we are not ones to shy away from the bizarre and the inexplicable. Armed with an arsenal of statistical methods and a hefty dose of skepticism, we set out to explore this seemingly preposterous association. As we embarked on this intellectual escapade, we were met with raised eyebrows and quizzical stares from our esteemed colleagues. Some even dared to jest that we were venturing into the realm of academic absurdity, perhaps charting a course for the fabled land of statistical unicorns and correlation mirages.

Despite the initial aura of incredulity that surrounded our pursuit, we pressed on undeterred, armed with the firm belief that science and research often unveil the unexpected, the unconventional, and the downright bizarre. Little did we know that our foray into the archival labyrinth and the energy enigma would lead us down a path replete with unexpected twists and turns, much like a thrilling mystery novel – albeit a slightly nerdy one.

So, dear reader, fasten your seatbelts and prepare to be whisked away into the enigmatic world of statistical intrigue and improbable associations. Our journey through the peculiar landscape of archivists and kerosene consumption shall certainly be a ride to remember!


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 The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns.

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

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

Start by naming serious-sounding studies by authors like Smith, Doe, and Jones - but then quickly devolve. Name some real non-fiction books that would be related to the topic. Then name some real fiction books that sound like they could be related. Then name a couple popular internet memes that are related to one of the topics.

Here is the title and abstract of the paper:
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

-------

And here is the introduction section that led to this literature review:
[[INTRODUCTION]]
INTRODUCTION
In the world of research, one often encounters unexpected connections and peculiar correlations that seem to defy rational explanation. This paper delves into a peculiar puzzle that emerged during our investigation into the unlikely relationship between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands. While these two variables may seem about as related as a carrot and a pogo stick, our study seeks to unravel the enigmatic connection that emerged from our rigorous analysis.
Now, before we delve into the labyrinth of statistics and data analysis, let's take a moment to appreciate the sheer absurdity of our research topic. After all, how often does one find oneself pondering the potential link between the meticulous cataloging of historical documents and the burning of fuel in a remote corner of the world? It's a bit like trying to correlate the height of giraffes in the Savannah with the price of bagels in New York City – utterly nonsensical at first glance.
Nonetheless, as intrepid researchers, we are not ones to shy away from the bizarre and the inexplicable. Armed with an arsenal of statistical methods and a hefty dose of skepticism, we set out to explore this seemingly preposterous association. As we embarked on this intellectual escapade, we were met with raised eyebrows and quizzical stares from our esteemed colleagues. Some even dared to jest that we were venturing into the realm of academic absurdity, perhaps charting a course for the fabled land of statistical unicorns and correlation mirages.
Despite the initial aura of incredulity that surrounded our pursuit, we pressed on undeterred, armed with the firm belief that science and research often unveil the unexpected, the unconventional, and the downright bizarre. Little did we know that our foray into the archival labyrinth and the energy enigma would lead us down a path replete with unexpected twists and turns, much like a thrilling mystery novel – albeit a slightly nerdy one.
So, dear reader, fasten your seatbelts and prepare to be whisked away into the enigmatic world of statistical intrigue and improbable associations. Our journey through the peculiar landscape of archivists and kerosene consumption shall certainly be a ride to remember!

-------

Your response should start like this:

[[LITERATURE REVIEW]]



ChatGPT:
[[LITERATURE REVIEW]]

In the pursuit of unraveling the perplexing correlation between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands, researchers have traversed through a diverse array of studies and findings. Smith (2010) delved into the intricacies of archival management and its impact on historical preservation, while Doe (2015) examined the economic factors influencing energy consumption in remote territories. Jones (2018) explored the cultural significance of cataloging practices in different regions, shedding light on the multifaceted nature of archival work.

Turning to non-fiction literature, "The Cataloger's Handbook: A Comprehensive Guide to Modern Archival Techniques" by Maria Johnson provides a detailed insight into the meticulous processes involved in archival management, offering a glimpse into the inner workings of the archival world. In a similar vein, "The Energy Dilemma: Exploring Sustainable Solutions" by David Smithson expounds upon the various energy sources and their consumption patterns in different global locales.

As we delve deeper into this enigmatic association, it becomes evident that the parallel worlds of archival studies and energy consumption converge in the realm of fiction as well. "The Cataloging Caper" by E. A. Poe, a work of literary intrigue set in the mysterious world of archival mysteries, draws readers into a tangled web of cataloging conundrums and peculiar coincidences. Furthermore, "The Kerosene Chronicles" by Agatha Christie meanders through the remote corners of the world where the flickering flames of kerosene lamps illuminate dark secrets and unexpected connections.

Venturing into the realm of internet memes, the infamous "Distracted Archivist" meme captures the essence of meticulous focus amid chaos, resonating with the painstaking organization that characterizes archival work. Meanwhile, the "Kerosene Kitten" meme, a play on words with a feline twist, humorously illustrates the unexpected allure of kerosene in popular culture.

In navigating the landscape of scholarly inquiry and imaginative exploration, it is essential to embrace the unexpected and entertain the eccentric. With a nod to the seriousness of academic pursuits and a wink to the whimsicality of the human spirit, this literature review sets the stage for a journey through the unexpected correlations and peculiar connections that characterize our research endeavors.


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 methodology section of an academic research paper.
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the methodology section of an academic research paper presenting the findings of the connection between The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration . You used data from 2004 to 2021

Make up the research methods you don't know. Make them a bit goofy and convoluted.

Here is the title, abstract, and introduction of the paper:
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

[[INTRODUCTION]]
INTRODUCTION
In the world of research, one often encounters unexpected connections and peculiar correlations that seem to defy rational explanation. This paper delves into a peculiar puzzle that emerged during our investigation into the unlikely relationship between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands. While these two variables may seem about as related as a carrot and a pogo stick, our study seeks to unravel the enigmatic connection that emerged from our rigorous analysis.
Now, before we delve into the labyrinth of statistics and data analysis, let's take a moment to appreciate the sheer absurdity of our research topic. After all, how often does one find oneself pondering the potential link between the meticulous cataloging of historical documents and the burning of fuel in a remote corner of the world? It's a bit like trying to correlate the height of giraffes in the Savannah with the price of bagels in New York City – utterly nonsensical at first glance.
Nonetheless, as intrepid researchers, we are not ones to shy away from the bizarre and the inexplicable. Armed with an arsenal of statistical methods and a hefty dose of skepticism, we set out to explore this seemingly preposterous association. As we embarked on this intellectual escapade, we were met with raised eyebrows and quizzical stares from our esteemed colleagues. Some even dared to jest that we were venturing into the realm of academic absurdity, perhaps charting a course for the fabled land of statistical unicorns and correlation mirages.
Despite the initial aura of incredulity that surrounded our pursuit, we pressed on undeterred, armed with the firm belief that science and research often unveil the unexpected, the unconventional, and the downright bizarre. Little did we know that our foray into the archival labyrinth and the energy enigma would lead us down a path replete with unexpected twists and turns, much like a thrilling mystery novel – albeit a slightly nerdy one.
So, dear reader, fasten your seatbelts and prepare to be whisked away into the enigmatic world of statistical intrigue and improbable associations. Our journey through the peculiar landscape of archivists and kerosene consumption shall certainly be a ride to remember!

-------

Your response should start like this:

[[METHODOLOGY]]



ChatGPT:

[[METHODOLOGY]]

As we embarked on our quest to unearth the unlikely connection between the number of archivists in the District of Columbia and the kerosene consumption in the Falkland Islands, we immediately realized that traditional research methods wouldn't quite cut the mustard. After all, we were treading into uncharted territory, where the rules of causation and correlation seemed to dance to the beat of their own drum, much like a cactus trying to salsa.

Data Collection:
Our research team scoured the vast expanse of the internet for data on the number of archivists employed in the District of Columbia and the kerosene consumption in the Falkland Islands. We primarily relied on the Bureau of Labor Statistics for information on archivists and the Energy Information Administration for data on kerosene consumption. However, we also shamelessly utilized data from assorted governmental and non-governmental sources, all in the name of scientific exploration and the pursuit of statistical enlightenment. The time frame for our data collection spanned from 2004 to 2021, allowing us to capture the ebb and flow of archivists' careers and kerosene use over the years.

Data Interpretation:
Once we had amassed a veritable trove of data, we set sail on the tumultuous seas of statistical analysis. Our trusty statistical software became our compass, guiding us through the treacherous waters of regression analysis, correlation coefficients, and p-values. We calculated the Pearson correlation coefficient to discern the strength and direction of the relationship between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. Additionally, we performed a simple linear regression analysis to uncover any potential predictive power of archivists on kerosene use, much like attempting to predict the next episode of a soap opera based on the dramatic pauses and meaningful glances.

Reliability and Validity:
In our pursuit of scientific rigor, we meticulously examined the reliability and validity of the data sources. We scrutinized the Bureau of Labor Statistics and the Energy Information Administration with a keen eye for anomalies, ensuring that our data upheld the standards of accuracy and dependability. We also performed sensitivity analyses to test the robustness of our findings, much like poking a particularly suspect pudding to see if it jiggles more than it should.

Ethical Considerations:
In adherence to the highest ethical standards of research, we ensured the confidentiality and anonymity of the data sources, shielding the identity of each archivist and each barrel of kerosene from prying eyes. We operated with the utmost integrity, recognizing that the guardians of historical records and the bearers of kerosene deserved the same respect and privacy as any other research subjects.

Limitations:
While we navigated the choppy waters of statistical analysis with the bravado of intrepid explorers, we acknowledge that our study is not without limitations. The ecological nature of our data poses challenges in establishing causality, much like trying to decipher whether a chicken crossed the road due to free will or a compelling invitation to the other side. Furthermore, the generalizability of our findings may be constrained by the specific contexts of the District of Columbia and the Falkland Islands, akin to scrutinizing the dietary preferences of penguins to draw conclusions about all flightless birds.

Despite these constraints, we stand by the conviction that our research has shed light on a truly peculiar correlation, showcasing the delightful unpredictability of the world of statistics and the enigmatic allure of academic inquiry.


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 results section of an academic research paper. You speak in the past tense (you found...).
User prompt:
Pretend you are an academic researcher. Your writing sounds like it belongs in a medical or economics journal. However, you frequently crack jokes, make puns, or add unexpected twists in your writing.

Please make up the results section of an academic research paper presenting the findings of the connection between The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Your research team collected data from all across the internet, but mostly just used information from Bureau of Larbor Statistics and Energy Information Administration .

For the time period 2004 to 2021, you found a correlation 0.8092602, r-squared of 0.6549021, and p < 0.01.

One figure will be included. The figure (Fig. 1) is a scatterplot showing the strong correlation between the two variables. You don't need to specify where; I will add the figure.

Here is the title and abstract of the paper:
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

-------

And here is the methodology section that led to this result:
[[METHODOLOGY]]
INTRODUCTION
In the world of research, one often encounters unexpected connections and peculiar correlations that seem to defy rational explanation. This paper delves into a peculiar puzzle that emerged during our investigation into the unlikely relationship between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands. While these two variables may seem about as related as a carrot and a pogo stick, our study seeks to unravel the enigmatic connection that emerged from our rigorous analysis.
Now, before we delve into the labyrinth of statistics and data analysis, let's take a moment to appreciate the sheer absurdity of our research topic. After all, how often does one find oneself pondering the potential link between the meticulous cataloging of historical documents and the burning of fuel in a remote corner of the world? It's a bit like trying to correlate the height of giraffes in the Savannah with the price of bagels in New York City – utterly nonsensical at first glance.
Nonetheless, as intrepid researchers, we are not ones to shy away from the bizarre and the inexplicable. Armed with an arsenal of statistical methods and a hefty dose of skepticism, we set out to explore this seemingly preposterous association. As we embarked on this intellectual escapade, we were met with raised eyebrows and quizzical stares from our esteemed colleagues. Some even dared to jest that we were venturing into the realm of academic absurdity, perhaps charting a course for the fabled land of statistical unicorns and correlation mirages.
Despite the initial aura of incredulity that surrounded our pursuit, we pressed on undeterred, armed with the firm belief that science and research often unveil the unexpected, the unconventional, and the downright bizarre. Little did we know that our foray into the archival labyrinth and the energy enigma would lead us down a path replete with unexpected twists and turns, much like a thrilling mystery novel – albeit a slightly nerdy one.
So, dear reader, fasten your seatbelts and prepare to be whisked away into the enigmatic world of statistical intrigue and improbable associations. Our journey through the peculiar landscape of archivists and kerosene consumption shall certainly be a ride to remember!

-------

Your response should start like this:

[[RESULTS]]



ChatGPT:

[[RESULTS]]

The results of our investigation revealed an unexpected and robust correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. Over the time period of 2004 to 2021, we found a striking correlation coefficient of 0.8092602, indicating a strong positive relationship between the two variables. This correlation was further supported by an r-squared value of 0.6549021, signifying that approximately 65.49% of the variability in kerosene consumption could be explained by the number of archivists in the District of Columbia.

In the world of statistical analysis, a p-value of less than 0.01 is often celebrated like a rare gemstone in the rough terrain of research. And in our case, the p-value served as the glittering confirmation of our findings, indicating that the observed correlation was highly unlikely to have occurred by mere chance. It seems that our peculiar pursuit of unraveling the archival-energy conundrum has indeed borne fruit, albeit of the statistically significant variety.

Now, while these results may seem as surprising as finding a unicorn in a field of standardized regression slopes, we must resist the temptation to jump to hasty conclusions. Correlation, as we know, does not imply causation, and we are acutely aware of the need for caution in interpreting our findings. Despite the strong statistical association we observed, it is critical to approach this peculiar correlation with a healthy dose of skepticism and scholarly rigor. After all, the connection between archivists and kerosene may be an unexpected statistical fluke, much like discovering an obscure correlation between the number of pirates and global temperatures – a classic example of the perils of assuming causation based on correlation.

To visually capture the essence of our findings, we present Figure 1, a scatterplot illustrating the remarkably strong correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. This plot serves as a testament to the improbable link that our research has uncovered, reminding us that in the labyrinth of statistical inquiry, truth can indeed be stranger than fiction.

In summary, our results shine a spotlight on the unexpected interconnectedness that pervades the world of research, illuminating an unforeseen relationship that challenges conventional wisdom and delights in the sheer quirkiness of statistical exploration. As we stand on the precipice of yet another improbable analytical journey, we are reminded once again that in the realm of research, the line between the bizarre and the enlightening is often as thin as a statistical error bar.


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 The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

Limit your response to 500 tokens.

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

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

[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

[[LITERATURE REVIEW]]
In the pursuit of unraveling the perplexing correlation between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands, researchers have traversed through a diverse array of studies and findings. Smith (2010) delved into the intricacies of archival management and its impact on historical preservation, while Doe (2015) examined the economic factors influencing energy consumption in remote territories. Jones (2018) explored the cultural significance of cataloging practices in different regions, shedding light on the multifaceted nature of archival work.
Turning to non-fiction literature, "The Cataloger's Handbook: A Comprehensive Guide to Modern Archival Techniques" by Maria Johnson provides a detailed insight into the meticulous processes involved in archival management, offering a glimpse into the inner workings of the archival world. In a similar vein, "The Energy Dilemma: Exploring Sustainable Solutions" by David Smithson expounds upon the various energy sources and their consumption patterns in different global locales.
As we delve deeper into this enigmatic association, it becomes evident that the parallel worlds of archival studies and energy consumption converge in the realm of fiction as well. "The Cataloging Caper" by E. A. Poe, a work of literary intrigue set in the mysterious world of archival mysteries, draws readers into a tangled web of cataloging conundrums and peculiar coincidences. Furthermore, "The Kerosene Chronicles" by Agatha Christie meanders through the remote corners of the world where the flickering flames of kerosene lamps illuminate dark secrets and unexpected connections.
Venturing into the realm of internet memes, the infamous "Distracted Archivist" meme captures the essence of meticulous focus amid chaos, resonating with the painstaking organization that characterizes archival work. Meanwhile, the "Kerosene Kitten" meme, a play on words with a feline twist, humorously illustrates the unexpected allure of kerosene in popular culture.
In navigating the landscape of scholarly inquiry and imaginative exploration, it is essential to embrace the unexpected and entertain the eccentric. With a nod to the seriousness of academic pursuits and a wink to the whimsicality of the human spirit, this literature review sets the stage for a journey through the unexpected correlations and peculiar connections that characterize our research endeavors.

[[RESULTS]]
The results of our investigation revealed an unexpected and robust correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. Over the time period of 2004 to 2021, we found a striking correlation coefficient of 0.8092602, indicating a strong positive relationship between the two variables. This correlation was further supported by an r-squared value of 0.6549021, signifying that approximately 65.49% of the variability in kerosene consumption could be explained by the number of archivists in the District of Columbia.
In the world of statistical analysis, a p-value of less than 0.01 is often celebrated like a rare gemstone in the rough terrain of research. And in our case, the p-value served as the glittering confirmation of our findings, indicating that the observed correlation was highly unlikely to have occurred by mere chance. It seems that our peculiar pursuit of unraveling the archival-energy conundrum has indeed borne fruit, albeit of the statistically significant variety.
Now, while these results may seem as surprising as finding a unicorn in a field of standardized regression slopes, we must resist the temptation to jump to hasty conclusions. Correlation, as we know, does not imply causation, and we are acutely aware of the need for caution in interpreting our findings. Despite the strong statistical association we observed, it is critical to approach this peculiar correlation with a healthy dose of skepticism and scholarly rigor. After all, the connection between archivists and kerosene may be an unexpected statistical fluke, much like discovering an obscure correlation between the number of pirates and global temperatures – a classic example of the perils of assuming causation based on correlation.
To visually capture the essence of our findings, we present Figure 1, a scatterplot illustrating the remarkably strong correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. This plot serves as a testament to the improbable link that our research has uncovered, reminding us that in the labyrinth of statistical inquiry, truth can indeed be stranger than fiction.
In summary, our results shine a spotlight on the unexpected interconnectedness that pervades the world of research, illuminating an unforeseen relationship that challenges conventional wisdom and delights in the sheer quirkiness of statistical exploration. As we stand on the precipice of yet another improbable analytical journey, we are reminded once again that in the realm of research, the line between the bizarre and the enlightening is often as thin as a statistical error bar.

-------

Your response should start like this:

[[DISCUSSION]]



ChatGPT:

[[DISCUSSION]]

The remarkable correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands piques our curiosity like a suspenseful plot twist in a thriller novel. Our findings not only support prior research but also unravel a tapestry of unexpected connections that challenge traditional disciplinary boundaries, much like solving a mystery that leads us down a rabbit hole of archival intrigue and energy enigma.

It's as if our research has uncovered a real-life "Cataloging Caper," reminiscent of E. A. Poe's fictional work, where perplexing coincidences and peculiar correlations abound. The statistical significance of our results, with a p-value less than 0.01, serves as the metaphorical smoking gun in this enigmatic saga, reinforcing the validity of our uncovered correlation and adding to the drama of our scholarly pursuit. We can almost envision a thrilling screenplay adaptation – "The Kerosene Chronicles: Unraveling the Archival Enigma."

The extensive literature review not only set the stage for our anomalous findings but also hinted at the interdisciplinary nature of our discovery, akin to the compelling crossover of genres in Agatha Christie's "The Kerosene Chronicles." Just as Christie brought together improbable characters in her novels, our research has brought together two seemingly disparate variables, creating a fusion that challenges the boundaries of traditional academic inquiry.

Our results not only validate the unexpected connection between archivists and kerosene consumption but also send a cheeky nod to the statistical perils of assuming causation based on correlation. The cautionary tale of the number of pirates and global temperatures serves as a humorous reminder of the need for scholarly diligence and critical thinking in interpreting statistical relationships, as understanding statistics requires the same level of scrutiny as deciphering a cryptic message in an old archival document.

As we navigate these uncharted waters of interdisciplinary discovery, our findings prompt us to embrace the whimsicality of research. Just as the "Distracted Archivist" meme captures the meticulous focus amidst chaos, our research shines a light on the meticulous unraveling of an unexpected correlation within the chaos of statistical exploration. The unexpected, after all, may hold the key to unlocking new paths of inquiry.

In essence, our research uncovers the exhilarating unpredictability that lurks within the world of statistics and academic inquiry, reminding us that, much like a mystery novel, the twists and turns of research can lead us to astonishing revelations – even if they involve archivists and kerosene consumption.


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 The number of archivists in District of Columbia and Kerosene used in Falkland Islands. Make lots of jokes, goofy observations, and puns. Sneak in some jokes and clever puns about science, research, statistics, and the variables.

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

Here are the title, abstract, introduction, and results sections.
[[TITLE]]
The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands

[[ABSTRACT]]
The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

[[INTRDUCTION]]
INTRODUCTION
In the world of research, one often encounters unexpected connections and peculiar correlations that seem to defy rational explanation. This paper delves into a peculiar puzzle that emerged during our investigation into the unlikely relationship between the number of archivists in the District of Columbia and the consumption of kerosene in the Falkland Islands. While these two variables may seem about as related as a carrot and a pogo stick, our study seeks to unravel the enigmatic connection that emerged from our rigorous analysis.
Now, before we delve into the labyrinth of statistics and data analysis, let's take a moment to appreciate the sheer absurdity of our research topic. After all, how often does one find oneself pondering the potential link between the meticulous cataloging of historical documents and the burning of fuel in a remote corner of the world? It's a bit like trying to correlate the height of giraffes in the Savannah with the price of bagels in New York City – utterly nonsensical at first glance.
Nonetheless, as intrepid researchers, we are not ones to shy away from the bizarre and the inexplicable. Armed with an arsenal of statistical methods and a hefty dose of skepticism, we set out to explore this seemingly preposterous association. As we embarked on this intellectual escapade, we were met with raised eyebrows and quizzical stares from our esteemed colleagues. Some even dared to jest that we were venturing into the realm of academic absurdity, perhaps charting a course for the fabled land of statistical unicorns and correlation mirages.
Despite the initial aura of incredulity that surrounded our pursuit, we pressed on undeterred, armed with the firm belief that science and research often unveil the unexpected, the unconventional, and the downright bizarre. Little did we know that our foray into the archival labyrinth and the energy enigma would lead us down a path replete with unexpected twists and turns, much like a thrilling mystery novel – albeit a slightly nerdy one.
So, dear reader, fasten your seatbelts and prepare to be whisked away into the enigmatic world of statistical intrigue and improbable associations. Our journey through the peculiar landscape of archivists and kerosene consumption shall certainly be a ride to remember!

[[RESULTS]]
The results of our investigation revealed an unexpected and robust correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. Over the time period of 2004 to 2021, we found a striking correlation coefficient of 0.8092602, indicating a strong positive relationship between the two variables. This correlation was further supported by an r-squared value of 0.6549021, signifying that approximately 65.49% of the variability in kerosene consumption could be explained by the number of archivists in the District of Columbia.
In the world of statistical analysis, a p-value of less than 0.01 is often celebrated like a rare gemstone in the rough terrain of research. And in our case, the p-value served as the glittering confirmation of our findings, indicating that the observed correlation was highly unlikely to have occurred by mere chance. It seems that our peculiar pursuit of unraveling the archival-energy conundrum has indeed borne fruit, albeit of the statistically significant variety.
Now, while these results may seem as surprising as finding a unicorn in a field of standardized regression slopes, we must resist the temptation to jump to hasty conclusions. Correlation, as we know, does not imply causation, and we are acutely aware of the need for caution in interpreting our findings. Despite the strong statistical association we observed, it is critical to approach this peculiar correlation with a healthy dose of skepticism and scholarly rigor. After all, the connection between archivists and kerosene may be an unexpected statistical fluke, much like discovering an obscure correlation between the number of pirates and global temperatures – a classic example of the perils of assuming causation based on correlation.
To visually capture the essence of our findings, we present Figure 1, a scatterplot illustrating the remarkably strong correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands. This plot serves as a testament to the improbable link that our research has uncovered, reminding us that in the labyrinth of statistical inquiry, truth can indeed be stranger than fiction.
In summary, our results shine a spotlight on the unexpected interconnectedness that pervades the world of research, illuminating an unforeseen relationship that challenges conventional wisdom and delights in the sheer quirkiness of statistical exploration. As we stand on the precipice of yet another improbable analytical journey, we are reminded once again that in the realm of research, the line between the bizarre and the enlightening is often as thin as a statistical error bar.

-------

Your response should start like this:

[[CONCLUSION]]



ChatGPT:

[[CONCLUSION]]

In conclusion, our research has led us down a rabbit hole of statistical strangeness and intellectual intrigue, unveiling a correlation between the number of archivists in the District of Columbia and kerosene consumption in the Falkland Islands that is as unexpected as finding a penguin in the Sahara. Our findings, with a correlation coefficient resembling a strong, unbreakable bond between two unlikely companions, have left us pondering the quirky dance of variables in the great statistical waltz of life.

As we wrap up this odyssey into the world of peculiar correlations, we can't help but marvel at the peculiarities of the academic pursuit. The pursuit of knowledge has brought us face to face with enigmatic entanglements that defy rational explanation, reminding us that the world of research is often as full of surprises as a magician's hat.

While our results may seem as outlandish as discovering a statistician at a salsa dance competition, we must exercise caution in drawing definitive conclusions. Correlation, that fickle friend of statisticians, does not imply causation, and we must approach this perplexing relationship with the same caution one would use when encountering a statistical black hole – proceed with care and a healthy dose of skepticism.

In the grand scheme of scholarly inquiry, our research throws a spotlight on the unexpected and the inexplicable, reminding us that the pursuit of knowledge is a journey that often leads through the whimsical, the improbable, and the entirely bewildering. Perhaps, in the world of research, truth is indeed stranger than fiction, and statistical exploration is akin to navigating a maze filled with delightful surprises and confounding conundrums.

In conclusion, we assert that no further research is needed in this area. Instead, we encourage fellow researchers to embrace the absurdity of statistical exploration and to revel in the peculiarities that make the pursuit of knowledge a delightfully quirky endeavor. After all, as we bid adieu to this improbable correlation, we are reminded that the journey of discovery often meanders through the most unexpected of paths, much like navigating through a statistical funhouse – thrilling, occasionally perplexing, and always ripe for a good laugh.


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 The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands. Respond only with the name of a fictional academic journal.

ChatGPT:

The Journal of Eccentric Archival Studies


Model: gpt-3.5-turbo-1106
System prompt: You provide fictional names of nonprofit research organizations and associations. You say nothing else, and you do not chat with the user.
User prompt: Please provide the name of a funny but plausible sounding nonprofit, academic, or scientific association or organization that would sponsor research that resulted in a paper entited The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands. Respond only with the name of a fictional organization.

ChatGPT:

The Society for Transcontinental Archival Research and Preservation


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 The Cataloging Conundrum: Unearthing the Unlikely Link Between Archivists in the District of Columbia and Kerosene Consumption in the Falkland Islands with an abstract of The seemingly unrelated realms of archival studies and energy consumption have been the subject of rigorous investigation in this study. Utilizing data from the Bureau of Labor Statistics and the Energy Information Administration, we sought to decipher the mysterious connection between the number of archivists in the District of Columbia and the use of kerosene in the Falkland Islands. Despite initial skepticism and raised eyebrows from our colleagues, our findings revealed a surprising correlation coefficient of 0.8092602 and a p-value less than 0.01 for the years 2004 to 2021. Our research delves into a world of archival intrigue and energy enigma, shedding light on an unexpected relationship that defies conventional wisdom. This paper demonstrates that, indeed, the world of research can be filled with unexpected twists and turns, much like a thrilling mystery novel.

ChatGPT:

archival studies, energy consumption, Bureau of Labor Statistics, Energy Information Administration, archivists, District of Columbia, kerosene consumption, Falkland Islands, correlation coefficient, p-value, research, unexpected relationships, unconventional wisdom, mystery novel

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



Random correlation

Discover a new correlation

View all correlations

View all research papers

Report an error


Data details

The number of archivists in District of Columbia
Detailed data title: BLS estimate of archivists in District of Columbia
Source: Bureau of Larbor Statistics
See what else correlates with The number of archivists in District of Columbia

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

Correlation r = 0.8092602 (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 = 0.6549021 (Coefficient of determination)
This means 65.5% of the change in the one variable (i.e., Kerosene used in Falkland Islands) is predictable based on the change in the other (i.e., The number of archivists in District of Columbia) over the 18 years from 2004 through 2021.

p < 0.01, which is statistically significant(Null hypothesis significance test)
The p-value is 4.7E-5. 0.0000474866225560091240000000
The p-value is a measure of how probable it is that we would randomly find a result this extreme. More specifically the p-value is a measure of how probable it is that we would randomly find a result this extreme if we had only tested one pair of variables one time.

But I am a p-villain. I absolutely did not test only one pair of variables one time. I correlated hundreds of millions of pairs of variables. I threw boatloads of data into an industrial-sized blender to find this correlation.

Who is going to stop me? p-value reporting doesn't require me to report how many calculations I had to go through in order to find a low p-value!
On average, you will find a correaltion as strong as 0.81 in 0.0047% of random cases. Said differently, if you correlated 21,059 random variables You don't actually need 21 thousand variables to find a correlation like this one. 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.

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 17 degrees of freedom, Degrees of freedom is a measure of how many free components we are testing. In this case it is 17 because we have two variables measured over a period of 18 years. It's just the number of years minus ( the number of variables minus one ), which in this case simplifies to the number of years minus one.
you would randomly expect to find a correlation as strong as this one.

[ 0.55, 0.93 ] 95% correlation confidence interval (using the Fisher z-transformation)
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: 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.
200420052006200720082009201020112012201320142015201620172018201920202021
The number of archivists in District of Columbia (Archivists)4040160210200110110120110140150170180200220170130170
Kerosene used in Falkland Islands (Million Barrels/Day)0.06336070.06353420.08471230.08471230.08448090.08471230.07835890.08047670.08448090.08471230.08471230.0953010.1056010.1001630.105890.105890.08918570.094922




Why this works

  1. 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.
  2. Lack of causal connection: There is probably 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.
  3. 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 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.
  4. 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. 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. 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([40,40,160,210,200,110,110,120,110,140,150,170,180,200,220,170,130,170,])
array_2 = np.array([0.0633607,0.0635342,0.0847123,0.0847123,0.0844809,0.0847123,0.0783589,0.0804767,0.0844809,0.0847123,0.0847123,0.095301,0.105601,0.100163,0.10589,0.10589,0.0891857,0.094922,])
array_1_name = "The number of archivists in District of Columbia"
array_2_name = "Kerosene used in Falkland Islands"

# 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. 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:


View another random correlation

How fun was this correlation?

Your rating skills are top-notch!


Correlation ID: 3372 · Black Variable ID: 16955 · Red Variable ID: 24408
about · subscribe · emailme@tylervigen.com · twitter

CC BY 4.0